Merge pull request #1555 from open-webui/dev

0.1.119

.dockerignore

@@ -7,7 +7,6 @@ node_modules
 /package
 .env
 .env.*
-!.env.example
 vite.config.js.timestamp-*
 vite.config.ts.timestamp-*
 __pycache__

.env.example

@@ -1,6 +1,6 @@
 # Ollama URL for the backend to connect
-# The path '/ollama/api' will be redirected to the specified backend URL
-OLLAMA_API_BASE_URL='http://localhost:11434/api'
+# The path '/ollama' will be redirected to the specified backend URL
+OLLAMA_BASE_URL='http://localhost:11434'
 
 OPENAI_API_BASE_URL=''
 OPENAI_API_KEY=''
@@ -9,4 +9,8 @@ OPENAI_API_KEY=''
 
 # DO NOT TRACK
 SCARF_NO_ANALYTICS=true
-DO_NOT_TRACK=true
+DO_NOT_TRACK=true
+
+# Use locally bundled version of the LiteLLM cost map json
+# to avoid repetitive startup connections
+LITELLM_LOCAL_MODEL_COST_MAP="True"

.github/ISSUE_TEMPLATE/bug_report.md

@@ -32,7 +32,7 @@ assignees: ''
 **Confirmation:**
 
 - [ ] I have read and followed all the instructions provided in the README.md.
-- [ ] I have reviewed the troubleshooting.md document.
+- [ ] I am on the latest version of both Open WebUI and Ollama.
 - [ ] I have included the browser console logs.
 - [ ] I have included the Docker container logs.
 

.github/workflows/build-release.yml

@@ -19,24 +19,34 @@ jobs:
           echo "No changes to package.json"
           exit 1
         }
-
+    
     - name: Get version number from package.json
       id: get_version
       run: |
         VERSION=$(jq -r '.version' package.json)
         echo "::set-output name=version::$VERSION"
 
+    - name: Extract latest CHANGELOG entry
+      id: changelog
+      run: |
+        CHANGELOG_CONTENT=$(awk 'BEGIN {print_section=0;} /^## \[/ {if (print_section == 0) {print_section=1;} else {exit;}} print_section {print;}' CHANGELOG.md)
+        CHANGELOG_ESCAPED=$(echo "$CHANGELOG_CONTENT" | sed ':a;N;$!ba;s/\n/%0A/g')
+        echo "Extracted latest release notes from CHANGELOG.md:" 
+        echo -e "$CHANGELOG_CONTENT" 
+        echo "::set-output name=content::$CHANGELOG_ESCAPED"
+
     - name: Create GitHub release
       uses: actions/github-script@v5
       with:
         github-token: ${{ secrets.GITHUB_TOKEN }}
         script: |
+          const changelog = `${{ steps.changelog.outputs.content }}`;
           const release = await github.rest.repos.createRelease({
             owner: context.repo.owner,
             repo: context.repo.repo,
             tag_name: `v${{ steps.get_version.outputs.version }}`,
             name: `v${{ steps.get_version.outputs.version }}`,
-            body: 'Automatically created new release',
+            body: changelog,
           })
           console.log(`Created release ${release.data.html_url}`)
 
@@ -47,3 +57,14 @@ jobs:
         path: .
       env:
         GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+
+    - name: Trigger Docker build workflow
+      uses: actions/github-script@v7
+      with:
+        script: |
+          github.rest.actions.createWorkflowDispatch({
+            owner: context.repo.owner,
+            repo: context.repo.repo,
+            workflow_id: 'docker-build.yaml',
+            ref: 'v${{ steps.get_version.outputs.version }}',
+          })

.github/workflows/docker-build.yaml

@@ -1,8 +1,7 @@
-#
-name: Create and publish a Docker image
+name: Create and publish Docker images with specific build args
 
-# Configures this workflow to run every time a change is pushed to the branch called `release`.
 on:
+  workflow_dispatch:
   push:
     branches:
       - main
@@ -10,30 +9,39 @@ on:
     tags:
       - v*
 
-# Defines two custom environment variables for the workflow. These are used for the Container registry domain, and a name for the Docker image that this workflow builds.
 env:
   REGISTRY: ghcr.io
   IMAGE_NAME: ${{ github.repository }}
+  FULL_IMAGE_NAME: ghcr.io/${{ github.repository }}
 
-# There is a single job in this workflow. It's configured to run on the latest available version of Ubuntu.
 jobs:
-  build-and-push-image:
+  build-main-image:
     runs-on: ubuntu-latest
-    # Sets the permissions granted to the `GITHUB_TOKEN` for the actions in this job.
     permissions:
       contents: read
       packages: write
-      #
+    strategy:
+      fail-fast: false
+      matrix:
+        platform:
+          - linux/amd64
+          - linux/arm64
+
     steps:
+      - name: Prepare
+        run: |
+          platform=${{ matrix.platform }}
+          echo "PLATFORM_PAIR=${platform//\//-}" >> $GITHUB_ENV
+
       - name: Checkout repository
         uses: actions/checkout@v4
-      # Required for multi architecture build
+
       - name: Set up QEMU
         uses: docker/setup-qemu-action@v3
-      # Required for multi architecture build
+
       - name: Set up Docker Buildx
         uses: docker/setup-buildx-action@v3
-      # Uses the `docker/login-action` action to log in to the Container registry registry using the account and password that will publish the packages. Once published, the packages are scoped to the account defined here.
+
       - name: Log in to the Container registry
         uses: docker/login-action@v3
         with:
@@ -41,25 +49,336 @@ jobs:
           username: ${{ github.actor }}
           password: ${{ secrets.GITHUB_TOKEN }}
 
-      - name: Extract metadata for Docker images
+      - name: Extract metadata for Docker images (default latest tag)
         id: meta
         uses: docker/metadata-action@v5
         with:
-          images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
-          # This configuration dynamically generates tags based on the branch, tag, commit, and custom suffix for lite version.
+          images: ${{ env.FULL_IMAGE_NAME }}
           tags: |
             type=ref,event=branch
             type=ref,event=tag
             type=sha,prefix=git-
             type=semver,pattern={{version}}
+            type=semver,pattern={{major}}.{{minor}}
           flavor: |
             latest=${{ github.ref == 'refs/heads/main' }}
 
-      - name: Build and push Docker image
+      - name: Build Docker image (latest)
         uses: docker/build-push-action@v5
+        id: build
         with:
           context: .
           push: true
-          platforms: linux/amd64,linux/arm64
-          tags: ${{ steps.meta.outputs.tags }}
+          platforms: ${{ matrix.platform }}
           labels: ${{ steps.meta.outputs.labels }}
+          outputs: type=image,name=${{ env.FULL_IMAGE_NAME }},push-by-digest=true,name-canonical=true,push=true
+          cache-from: type=gha
+          cache-to: type=gha,mode=max
+
+      - name: Export digest
+        run: |
+          mkdir -p /tmp/digests
+          digest="${{ steps.build.outputs.digest }}"
+          touch "/tmp/digests/${digest#sha256:}"
+
+      - name: Upload digest
+        uses: actions/upload-artifact@v4
+        with:
+          name: digests-main-${{ env.PLATFORM_PAIR }}
+          path: /tmp/digests/*
+          if-no-files-found: error
+          retention-days: 1
+
+  build-cuda-image:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      packages: write
+    strategy:
+      fail-fast: false
+      matrix:
+        platform:
+          - linux/amd64
+          - linux/arm64
+
+    steps:
+      - name: Prepare
+        run: |
+          platform=${{ matrix.platform }}
+          echo "PLATFORM_PAIR=${platform//\//-}" >> $GITHUB_ENV
+
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v3
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Log in to the Container registry
+        uses: docker/login-action@v3
+        with:
+          registry: ${{ env.REGISTRY }}
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Extract metadata for Docker images (default latest tag)
+        id: meta
+        uses: docker/metadata-action@v5
+        with:
+          images: ${{ env.FULL_IMAGE_NAME }}
+          tags: |
+            type=ref,event=branch
+            type=ref,event=tag
+            type=sha,prefix=git-
+            type=semver,pattern={{version}}
+            type=semver,pattern={{major}}.{{minor}}
+            type=raw,enable=${{ github.ref == 'refs/heads/main' }},prefix=,suffix=,value=cuda
+          flavor: |
+            latest=${{ github.ref == 'refs/heads/main' }}
+            suffix=-cuda,onlatest=true
+
+      - name: Build Docker image (cuda)
+        uses: docker/build-push-action@v5
+        id: build
+        with:
+          context: .
+          push: true
+          platforms: ${{ matrix.platform }}
+          labels: ${{ steps.meta.outputs.labels }}
+          outputs: type=image,name=${{ env.FULL_IMAGE_NAME }},push-by-digest=true,name-canonical=true,push=true
+          cache-from: type=gha
+          cache-to: type=gha,mode=max
+          build-args: USE_CUDA=true
+
+      - name: Export digest
+        run: |
+          mkdir -p /tmp/digests
+          digest="${{ steps.build.outputs.digest }}"
+          touch "/tmp/digests/${digest#sha256:}"
+
+      - name: Upload digest
+        uses: actions/upload-artifact@v4
+        with:
+          name: digests-cuda-${{ env.PLATFORM_PAIR }}
+          path: /tmp/digests/*
+          if-no-files-found: error
+          retention-days: 1
+
+  build-ollama-image:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      packages: write
+    strategy:
+      fail-fast: false
+      matrix:
+        platform:
+          - linux/amd64
+          - linux/arm64
+
+    steps:
+      - name: Prepare
+        run: |
+          platform=${{ matrix.platform }}
+          echo "PLATFORM_PAIR=${platform//\//-}" >> $GITHUB_ENV
+
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v3
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Log in to the Container registry
+        uses: docker/login-action@v3
+        with:
+          registry: ${{ env.REGISTRY }}
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Extract metadata for Docker images (ollama tag)
+        id: meta
+        uses: docker/metadata-action@v5
+        with:
+          images: ${{ env.FULL_IMAGE_NAME }}
+          tags: |
+            type=ref,event=branch
+            type=ref,event=tag
+            type=sha,prefix=git-
+            type=semver,pattern={{version}}
+            type=semver,pattern={{major}}.{{minor}}
+            type=raw,enable=${{ github.ref == 'refs/heads/main' }},prefix=,suffix=,value=ollama
+          flavor: |
+            latest=${{ github.ref == 'refs/heads/main' }}
+            suffix=-ollama,onlatest=true
+
+      - name: Build Docker image (ollama)
+        uses: docker/build-push-action@v5
+        id: build
+        with:
+          context: .
+          push: true
+          platforms: ${{ matrix.platform }}
+          labels: ${{ steps.meta.outputs.labels }}
+          outputs: type=image,name=${{ env.FULL_IMAGE_NAME }},push-by-digest=true,name-canonical=true,push=true
+          cache-from: type=gha
+          cache-to: type=gha,mode=max
+          build-args: USE_OLLAMA=true
+
+      - name: Export digest
+        run: |
+          mkdir -p /tmp/digests
+          digest="${{ steps.build.outputs.digest }}"
+          touch "/tmp/digests/${digest#sha256:}"
+
+      - name: Upload digest
+        uses: actions/upload-artifact@v4
+        with:
+          name: digests-ollama-${{ env.PLATFORM_PAIR }}
+          path: /tmp/digests/*
+          if-no-files-found: error
+          retention-days: 1
+
+  merge-main-images:
+    runs-on: ubuntu-latest
+    needs: [ build-main-image ]
+    steps:
+      - name: Download digests
+        uses: actions/download-artifact@v4
+        with:
+          pattern: digests-main-*
+          path: /tmp/digests
+          merge-multiple: true
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Log in to the Container registry
+        uses: docker/login-action@v3
+        with:
+          registry: ${{ env.REGISTRY }}
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Extract metadata for Docker images (default latest tag)
+        id: meta
+        uses: docker/metadata-action@v5
+        with:
+          images: ${{ env.FULL_IMAGE_NAME }}
+          tags: |
+            type=ref,event=branch
+            type=ref,event=tag
+            type=sha,prefix=git-
+            type=semver,pattern={{version}}
+            type=semver,pattern={{major}}.{{minor}}
+          flavor: |
+            latest=${{ github.ref == 'refs/heads/main' }}
+
+      - name: Create manifest list and push
+        working-directory: /tmp/digests
+        run: |
+          docker buildx imagetools create $(jq -cr '.tags | map("-t " + .) | join(" ")' <<< "$DOCKER_METADATA_OUTPUT_JSON") \
+            $(printf '${{ env.FULL_IMAGE_NAME }}@sha256:%s ' *)
+
+      - name: Inspect image
+        run: |
+          docker buildx imagetools inspect ${{ env.FULL_IMAGE_NAME }}:${{ steps.meta.outputs.version }}
+
+
+  merge-cuda-images:
+    runs-on: ubuntu-latest
+    needs: [ build-cuda-image ]
+    steps:
+      - name: Download digests
+        uses: actions/download-artifact@v4
+        with:
+          pattern: digests-cuda-*
+          path: /tmp/digests
+          merge-multiple: true
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Log in to the Container registry
+        uses: docker/login-action@v3
+        with:
+          registry: ${{ env.REGISTRY }}
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Extract metadata for Docker images (default latest tag)
+        id: meta
+        uses: docker/metadata-action@v5
+        with:
+          images: ${{ env.FULL_IMAGE_NAME }}
+          tags: |
+            type=ref,event=branch
+            type=ref,event=tag
+            type=sha,prefix=git-
+            type=semver,pattern={{version}}
+            type=semver,pattern={{major}}.{{minor}}
+            type=raw,enable=${{ github.ref == 'refs/heads/main' }},prefix=,suffix=,value=cuda
+          flavor: |
+            latest=${{ github.ref == 'refs/heads/main' }}
+            suffix=-cuda,onlatest=true
+
+      - name: Create manifest list and push
+        working-directory: /tmp/digests
+        run: |
+          docker buildx imagetools create $(jq -cr '.tags | map("-t " + .) | join(" ")' <<< "$DOCKER_METADATA_OUTPUT_JSON") \
+            $(printf '${{ env.FULL_IMAGE_NAME }}@sha256:%s ' *)
+
+      - name: Inspect image
+        run: |
+          docker buildx imagetools inspect ${{ env.FULL_IMAGE_NAME }}:${{ steps.meta.outputs.version }}
+
+  merge-ollama-images:
+    runs-on: ubuntu-latest
+    needs: [ build-ollama-image ]
+    steps:
+      - name: Download digests
+        uses: actions/download-artifact@v4
+        with:
+          pattern: digests-ollama-*
+          path: /tmp/digests
+          merge-multiple: true
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Log in to the Container registry
+        uses: docker/login-action@v3
+        with:
+          registry: ${{ env.REGISTRY }}
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Extract metadata for Docker images (default ollama tag)
+        id: meta
+        uses: docker/metadata-action@v5
+        with:
+          images: ${{ env.FULL_IMAGE_NAME }}
+          tags: |
+            type=ref,event=branch
+            type=ref,event=tag
+            type=sha,prefix=git-
+            type=semver,pattern={{version}}
+            type=semver,pattern={{major}}.{{minor}}
+            type=raw,enable=${{ github.ref == 'refs/heads/main' }},prefix=,suffix=,value=ollama
+          flavor: |
+            latest=${{ github.ref == 'refs/heads/main' }}
+            suffix=-ollama,onlatest=true
+
+      - name: Create manifest list and push
+        working-directory: /tmp/digests
+        run: |
+          docker buildx imagetools create $(jq -cr '.tags | map("-t " + .) | join(" ")' <<< "$DOCKER_METADATA_OUTPUT_JSON") \
+            $(printf '${{ env.FULL_IMAGE_NAME }}@sha256:%s ' *)
+
+      - name: Inspect image
+        run: |
+          docker buildx imagetools inspect ${{ env.FULL_IMAGE_NAME }}:${{ steps.meta.outputs.version }}

.github/workflows/format-backend.yaml

@@ -1,27 +1,39 @@
 name: Python CI
+
 on:
   push:
-    branches: ['main']
+    branches:
+      - main
+      - dev
   pull_request:
+    branches:
+      - main
+      - dev
+
 jobs:
   build:
     name: 'Format Backend'
-    env:
-      PUBLIC_API_BASE_URL: ''
     runs-on: ubuntu-latest
+
     strategy:
       matrix:
-        node-version:
-          - latest
+        python-version: [3.11]
+
     steps:
       - uses: actions/checkout@v4
-      - name: Use Python
-        uses: actions/setup-python@v4
-      - name: Use Bun
-        uses: oven-sh/setup-bun@v1
+
+      - name: Set up Python
+        uses: actions/setup-python@v2
+        with:
+          python-version: ${{ matrix.python-version }}
+
       - name: Install dependencies
         run: |
           python -m pip install --upgrade pip
-          pip install yapf
+          pip install black
+
       - name: Format backend
-        run: bun run format:backend
+        run: npm run format:backend
+
+      - name: Check for changes after format
+        run: git diff --exit-code

.github/workflows/format-build-frontend.yaml

@@ -1,22 +1,36 @@
-name: Bun CI
+name: Frontend Build
+
 on:
   push:
-    branches: ['main']
+    branches:
+      - main
+      - dev
   pull_request:
+    branches:
+      - main
+      - dev
+
 jobs:
   build:
     name: 'Format & Build Frontend'
-    env:
-      PUBLIC_API_BASE_URL: ''
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v4
-      - name: Use Bun
-        uses: oven-sh/setup-bun@v1
-      - run: bun --version
-      - name: Install frontend dependencies
-        run: bun install
-      - name: Format frontend
-        run: bun run format
-      - name: Build frontend
-        run: bun run build
+      - name: Checkout Repository
+        uses: actions/checkout@v4
+
+      - name: Setup Node.js
+        uses: actions/setup-node@v3
+        with:
+          node-version: '20' # Or specify any other version you want to use
+
+      - name: Install Dependencies
+        run: npm install
+
+      - name: Format Frontend
+        run: npm run format
+
+      - name: Check for Changes After Format
+        run: git diff --exit-code
+
+      - name: Build Frontend
+        run: npm run build

.gitignore

@@ -166,7 +166,7 @@ cython_debug/
 #  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
 #  and can be added to the global gitignore or merged into this file.  For a more nuclear
 #  option (not recommended) you can uncomment the following to ignore the entire idea folder.
-#.idea/
+.idea/
 
 # Logs
 logs

CHANGELOG.md

@@ -5,6 +5,264 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [0.1.119] - 2024-04-16
+
+### Added
+
+- **🌟 Enhanced RAG Embedding Support**: Ollama, and OpenAI models can now be used for RAG embedding model.
+- **🔄 Seamless Integration**: Copy 'ollama run <model name>' directly from Ollama page to easily select and pull models.
+- **🏷️ Tagging Feature**: Add tags to chats directly via the sidebar chat menu.
+- **📱 Mobile Accessibility**: Swipe left and right on mobile to effortlessly open and close the sidebar.
+- **🔍 Improved Navigation**: Admin panel now supports pagination for user list.
+- **🌍 Additional Language Support**: Added Polish language support.
+
+### Fixed
+
+- **🌍 Language Enhancements**: Vietnamese and Spanish translations have been improved.
+- **🔧 Helm Fixes**: Resolved issues with Helm trailing slash and manifest.json.
+
+### Changed
+
+- **🐳 Docker Optimization**: Updated docker image build process to utilize 'uv' for significantly faster builds compared to 'pip3'.
+
+## [0.1.118] - 2024-04-10
+
+### Added
+
+- **🦙 Ollama and CUDA Images**: Added support for ':ollama' and ':cuda' tagged images.
+- **👍 Enhanced Response Rating**: Now you can annotate your ratings for better feedback.
+- **👤 User Initials Profile Photo**: User initials are now the default profile photo.
+- **🔍 Update RAG Embedding Model**: Customize RAG embedding model directly in document settings.
+- **🌍 Additional Language Support**: Added Turkish language support.
+
+### Fixed
+
+- **🔒 Share Chat Permission**: Resolved issue with chat sharing permissions.
+- **🛠 Modal Close**: Modals can now be closed using the Esc key.
+
+### Changed
+
+- **🎨 Admin Panel Styling**: Refreshed styling for the admin panel.
+- **🐳 Docker Image Build**: Updated docker image build process for improved efficiency.
+
+## [0.1.117] - 2024-04-03
+
+### Added
+
+- 🗨️ **Local Chat Sharing**: Share chat links seamlessly between users.
+- 🔑 **API Key Generation Support**: Generate secret keys to leverage Open WebUI with OpenAI libraries.
+- 📄 **Chat Download as PDF**: Easily download chats in PDF format.
+- 📝 **Improved Logging**: Enhancements to logging functionality.
+- 📧 **Trusted Email Authentication**: Authenticate using a trusted email header.
+
+### Fixed
+
+- 🌷 **Enhanced Dutch Translation**: Improved translation for Dutch users.
+- ⚪ **White Theme Styling**: Resolved styling issue with the white theme.
+- 📜 **LaTeX Chat Screen Overflow**: Fixed screen overflow issue with LaTeX rendering.
+- 🔒 **Security Patches**: Applied necessary security patches.
+
+## [0.1.116] - 2024-03-31
+
+### Added
+
+- **🔄 Enhanced UI**: Model selector now conveniently located in the navbar, enabling seamless switching between multiple models during conversations.
+- **🔍 Improved Model Selector**: Directly pull a model from the selector/Models now display detailed information for better understanding.
+- **💬 Webhook Support**: Now compatible with Google Chat and Microsoft Teams.
+- **🌐 Localization**: Korean translation (I18n) now available.
+- **🌑 Dark Theme**: OLED dark theme introduced for reduced strain during prolonged usage.
+- **🏷️ Tag Autocomplete**: Dropdown feature added for effortless chat tagging.
+
+### Fixed
+
+- **🔽 Auto-Scrolling**: Addressed OpenAI auto-scrolling issue.
+- **🏷️ Tag Validation**: Implemented tag validation to prevent empty string tags.
+- **🚫 Model Whitelisting**: Resolved LiteLLM model whitelisting issue.
+- **✅ Spelling**: Corrected various spelling issues for improved readability.
+
+## [0.1.115] - 2024-03-24
+
+### Added
+
+- **🔍 Custom Model Selector**: Easily find and select custom models with the new search filter feature.
+- **🛑 Cancel Model Download**: Added the ability to cancel model downloads.
+- **🎨 Image Generation ComfyUI**: Image generation now supports ComfyUI.
+- **🌟 Updated Light Theme**: Updated the light theme for a fresh look.
+- **🌍 Additional Language Support**: Now supporting Bulgarian, Italian, Portuguese, Japanese, and Dutch.
+
+### Fixed
+
+- **🔧 Fixed Broken Experimental GGUF Upload**: Resolved issues with experimental GGUF upload functionality.
+
+### Changed
+
+- **🔄 Vector Storage Reset Button**: Moved the reset vector storage button to document settings.
+
+## [0.1.114] - 2024-03-20
+
+### Added
+
+- **🔗 Webhook Integration**: Now you can subscribe to new user sign-up events via webhook. Simply navigate to the admin panel > admin settings > webhook URL.
+- **🛡️ Enhanced Model Filtering**: Alongside Ollama, OpenAI proxy model whitelisting, we've added model filtering functionality for LiteLLM proxy.
+- **🌍 Expanded Language Support**: Spanish, Catalan, and Vietnamese languages are now available, with improvements made to others.
+
+### Fixed
+
+- **🔧 Input Field Spelling**: Resolved issue with spelling mistakes in input fields.
+- **🖊️ Light Mode Styling**: Fixed styling issue with light mode in document adding.
+
+### Changed
+
+- **🔄 Language Sorting**: Languages are now sorted alphabetically by their code for improved organization.
+
+## [0.1.113] - 2024-03-18
+
+### Added
+
+- 🌍 **Localization**: You can now change the UI language in Settings > General. We support Ukrainian, German, Farsi (Persian), Traditional and Simplified Chinese and French translations. You can help us to translate the UI into your language! More info in our [CONTRIBUTION.md](https://github.com/open-webui/open-webui/blob/main/docs/CONTRIBUTING.md#-translations-and-internationalization).
+- 🎨 **System-wide Theme**: Introducing a new system-wide theme for enhanced visual experience.
+
+### Fixed
+
+- 🌑 **Dark Background on Select Fields**: Improved readability by adding a dark background to select fields, addressing issues on certain browsers/devices.
+- **Multiple OPENAI_API_BASE_URLS Issue**: Resolved issue where multiple base URLs caused conflicts when one wasn't functioning.
+- **RAG Encoding Issue**: Fixed encoding problem in RAG.
+- **npm Audit Fix**: Addressed npm audit findings.
+- **Reduced Scroll Threshold**: Improved auto-scroll experience by reducing the scroll threshold from 50px to 5px.
+
+### Changed
+
+- 🔄 **Sidebar UI Update**: Updated sidebar UI to feature a chat menu dropdown, replacing two icons for improved navigation.
+
+## [0.1.112] - 2024-03-15
+
+### Fixed
+
+- 🗨️ Resolved chat malfunction after image generation.
+- 🎨 Fixed various RAG issues.
+- 🧪 Rectified experimental broken GGUF upload logic.
+
+## [0.1.111] - 2024-03-10
+
+### Added
+
+- 🛡️ **Model Whitelisting**: Admins now have the ability to whitelist models for users with the 'user' role.
+- 🔄 **Update All Models**: Added a convenient button to update all models at once.
+- 📄 **Toggle PDF OCR**: Users can now toggle PDF OCR option for improved parsing performance.
+- 🎨 **DALL-E Integration**: Introduced DALL-E integration for image generation alongside automatic1111.
+- 🛠️ **RAG API Refactoring**: Refactored RAG logic and exposed its API, with additional documentation to follow.
+
+### Fixed
+
+- 🔒 **Max Token Settings**: Added max token settings for anthropic/claude-3-sonnet-20240229 (Issue #1094).
+- 🔧 **Misalignment Issue**: Corrected misalignment of Edit and Delete Icons when Chat Title is Empty (Issue #1104).
+- 🔄 **Context Loss Fix**: Resolved RAG losing context on model response regeneration with Groq models via API key (Issue #1105).
+- 📁 **File Handling Bug**: Addressed File Not Found Notification when Dropping a Conversation Element (Issue #1098).
+- 🖱️ **Dragged File Styling**: Fixed dragged file layover styling issue.
+
+## [0.1.110] - 2024-03-06
+
+### Added
+
+- **🌐 Multiple OpenAI Servers Support**: Enjoy seamless integration with multiple OpenAI-compatible APIs, now supported natively.
+
+### Fixed
+
+- **🔍 OCR Issue**: Resolved PDF parsing issue caused by OCR malfunction.
+- **🚫 RAG Issue**: Fixed the RAG functionality, ensuring it operates smoothly.
+- **📄 "Add Docs" Model Button**: Addressed the non-functional behavior of the "Add Docs" model button.
+
+## [0.1.109] - 2024-03-06
+
+### Added
+
+- **🔄 Multiple Ollama Servers Support**: Enjoy enhanced scalability and performance with support for multiple Ollama servers in a single WebUI. Load balancing features are now available, providing improved efficiency (#788, #278).
+- **🔧 Support for Claude 3 and Gemini**: Responding to user requests, we've expanded our toolset to include Claude 3 and Gemini, offering a wider range of functionalities within our platform (#1064).
+- **🔍 OCR Functionality for PDF Loader**: We've augmented our PDF loader with Optical Character Recognition (OCR) capabilities. Now, extract text from scanned documents and images within PDFs, broadening the scope of content processing (#1050).
+
+### Fixed
+
+- **🛠️ RAG Collection**: Implemented a dynamic mechanism to recreate RAG collections, ensuring users have up-to-date and accurate data (#1031).
+- **📝 User Agent Headers**: Fixed issue of RAG web requests being sent with empty user_agent headers, reducing rejections from certain websites. Realistic headers are now utilized for these requests (#1024).
+- **⏹️ Playground Cancel Functionality**: Introducing a new "Cancel" option for stopping Ollama generation in the Playground, enhancing user control and usability (#1006).
+- **🔤 Typographical Error in 'ASSISTANT' Field**: Corrected a typographical error in the 'ASSISTANT' field within the GGUF model upload template for accuracy and consistency (#1061).
+
+### Changed
+
+- **🔄 Refactored Message Deletion Logic**: Streamlined message deletion process for improved efficiency and user experience, simplifying interactions within the platform (#1004).
+- **⚠️ Deprecation of `OLLAMA_API_BASE_URL`**: Deprecated `OLLAMA_API_BASE_URL` environment variable; recommend using `OLLAMA_BASE_URL` instead. Refer to our documentation for further details.
+
+## [0.1.108] - 2024-03-02
+
+### Added
+
+- **🎮 Playground Feature (Beta)**: Explore the full potential of the raw API through an intuitive UI with our new playground feature, accessible to admins. Simply click on the bottom name area of the sidebar to access it. The playground feature offers two modes text completion (notebook) and chat completion. As it's in beta, please report any issues you encounter.
+- **🛠️ Direct Database Download for Admins**: Admins can now download the database directly from the WebUI via the admin settings.
+- **🎨 Additional RAG Settings**: Customize your RAG process with the ability to edit the TOP K value. Navigate to Documents > Settings > General to make changes.
+- **🖥️ UI Improvements**: Tooltips now available in the input area and sidebar handle. More tooltips will be added across other parts of the UI.
+
+### Fixed
+
+- Resolved input autofocus issue on mobile when the sidebar is open, making it easier to use.
+- Corrected numbered list display issue in Safari (#963).
+- Restricted user ability to delete chats without proper permissions (#993).
+
+### Changed
+
+- **Simplified Ollama Settings**: Ollama settings now don't require the `/api` suffix. You can now utilize the Ollama base URL directly, e.g., `http://localhost:11434`. Also, an `OLLAMA_BASE_URL` environment variable has been added.
+- **Database Renaming**: Starting from this release, `ollama.db` will be automatically renamed to `webui.db`.
+
+## [0.1.107] - 2024-03-01
+
+### Added
+
+- **🚀 Makefile and LLM Update Script**: Included Makefile and a script for LLM updates in the repository.
+
+### Fixed
+
+- Corrected issue where links in the settings modal didn't appear clickable (#960).
+- Fixed problem with web UI port not taking effect due to incorrect environment variable name in run-compose.sh (#996).
+- Enhanced user experience by displaying chat in browser title and enabling automatic scrolling to the bottom (#992).
+
+### Changed
+
+- Upgraded toast library from `svelte-french-toast` to `svelte-sonner` for a more polished UI.
+- Enhanced accessibility with the addition of dark mode on the authentication page.
+
+## [0.1.106] - 2024-02-27
+
+### Added
+
+- **🎯 Auto-focus Feature**: The input area now automatically focuses when initiating or opening a chat conversation.
+
+### Fixed
+
+- Corrected typo from "HuggingFace" to "Hugging Face" (Issue #924).
+- Resolved bug causing errors in chat completion API calls to OpenAI due to missing "num_ctx" parameter (Issue #927).
+- Fixed issues preventing text editing, selection, and cursor retention in the input field (Issue #940).
+- Fixed a bug where defining an OpenAI-compatible API server using 'OPENAI_API_BASE_URL' containing 'openai' string resulted in hiding models not containing 'gpt' string from the model menu. (Issue #930)
+
+## [0.1.105] - 2024-02-25
+
+### Added
+
+- **📄 Document Selection**: Now you can select and delete multiple documents at once for easier management.
+
+### Changed
+
+- **🏷️ Document Pre-tagging**: Simply click the "+" button at the top, enter tag names in the popup window, or select from a list of existing tags. Then, upload files with the added tags for streamlined organization.
+
+## [0.1.104] - 2024-02-25
+
+### Added
+
+- **🔄 Check for Updates**: Keep your system current by checking for updates conveniently located in Settings > About.
+- **🗑️ Automatic Tag Deletion**: Unused tags on the sidebar will now be deleted automatically with just a click.
+
+### Changed
+
+- **🎨 Modernized Styling**: Enjoy a refreshed look with updated styling for a more contemporary experience.
+
 ## [0.1.103] - 2024-02-25
 
 ### Added

Dockerfile

@@ -1,75 +1,117 @@
 # syntax=docker/dockerfile:1
+# Initialize device type args
+# use build args in the docker build commmand with --build-arg="BUILDARG=true"
+ARG USE_CUDA=false
+ARG USE_OLLAMA=false
+# Tested with cu117 for CUDA 11 and cu121 for CUDA 12 (default)
+ARG USE_CUDA_VER=cu121
+# any sentence transformer model; models to use can be found at https://huggingface.co/models?library=sentence-transformers
+# Leaderboard: https://huggingface.co/spaces/mteb/leaderboard 
+# for better performance and multilangauge support use "intfloat/multilingual-e5-large" (~2.5GB) or "intfloat/multilingual-e5-base" (~1.5GB)
+# IMPORTANT: If you change the default model (all-MiniLM-L6-v2) and vice versa, you aren't able to use RAG Chat with your previous documents loaded in the WebUI! You need to re-embed them.
+ARG USE_EMBEDDING_MODEL=all-MiniLM-L6-v2
 
-FROM node:alpine as build
+######## WebUI frontend ########
+FROM --platform=$BUILDPLATFORM node:21-alpine3.19 as build
 
 WORKDIR /app
 
-# wget embedding model weight from alpine (does not exist from slim-buster)
-RUN wget "https://chroma-onnx-models.s3.amazonaws.com/all-MiniLM-L6-v2/onnx.tar.gz" -O - | \
-    tar -xzf - -C /app
-
 COPY package.json package-lock.json ./
 RUN npm ci
 
 COPY . .
 RUN npm run build
 
-
+######## WebUI backend ########
 FROM python:3.11-slim-bookworm as base
 
-ENV ENV=prod
-ENV PORT ""
+# Use args
+ARG USE_CUDA
+ARG USE_OLLAMA
+ARG USE_CUDA_VER
+ARG USE_EMBEDDING_MODEL
 
-ENV OLLAMA_API_BASE_URL "/ollama/api"
+## Basis ##
+ENV ENV=prod \
+    PORT=8080 \
+    # pass build args to the build
+    USE_OLLAMA_DOCKER=${USE_OLLAMA} \
+    USE_CUDA_DOCKER=${USE_CUDA} \
+    USE_CUDA_DOCKER_VER=${USE_CUDA_VER} \
+    USE_EMBEDDING_MODEL_DOCKER=${USE_EMBEDDING_MODEL}
 
-ENV OPENAI_API_BASE_URL ""
-ENV OPENAI_API_KEY ""
+## Basis URL Config ##
+ENV OLLAMA_BASE_URL="/ollama" \
+    OPENAI_API_BASE_URL=""
 
-ENV WEBUI_SECRET_KEY ""
+## API Key and Security Config ##
+ENV OPENAI_API_KEY="" \
+    WEBUI_SECRET_KEY="" \
+    SCARF_NO_ANALYTICS=true \
+    DO_NOT_TRACK=true
 
-ENV SCARF_NO_ANALYTICS true
-ENV DO_NOT_TRACK true
+# Use locally bundled version of the LiteLLM cost map json
+# to avoid repetitive startup connections
+ENV LITELLM_LOCAL_MODEL_COST_MAP="True"
 
-######## Preloaded models ########
-# whisper TTS Settings
-ENV WHISPER_MODEL="base"
-ENV WHISPER_MODEL_DIR="/app/backend/data/cache/whisper/models"
 
-# RAG Embedding Model Settings
-# any sentence transformer model; models to use can be found at https://huggingface.co/models?library=sentence-transformers
-# Leaderboard: https://huggingface.co/spaces/mteb/leaderboard 
-# for better persormance and multilangauge support use "intfloat/multilingual-e5-large" (~2.5GB) or "intfloat/multilingual-e5-base" (~1.5GB)
-# IMPORTANT: If you change the default model (all-MiniLM-L6-v2) and vice versa, you aren't able to use RAG Chat with your previous documents loaded in the WebUI! You need to re-embed them.
-ENV RAG_EMBEDDING_MODEL="all-MiniLM-L6-v2"
-# device type for whisper tts and ebbeding models - "cpu" (default), "cuda" (nvidia gpu and CUDA required) or "mps" (apple silicon) - choosing this right can lead to better performance
-ENV RAG_EMBEDDING_MODEL_DEVICE_TYPE="cpu"
-ENV RAG_EMBEDDING_MODEL_DIR="/app/backend/data/cache/embedding/models"
-ENV SENTENCE_TRANSFORMERS_HOME $RAG_EMBEDDING_MODEL_DIR
+#### Other models #########################################################
+## whisper TTS model settings ##
+ENV WHISPER_MODEL="base" \
+    WHISPER_MODEL_DIR="/app/backend/data/cache/whisper/models"
 
-######## Preloaded models ########
+## RAG Embedding model settings ##
+ENV RAG_EMBEDDING_MODEL="$USE_EMBEDDING_MODEL_DOCKER" \
+    RAG_EMBEDDING_MODEL_DIR="/app/backend/data/cache/embedding/models" \
+    SENTENCE_TRANSFORMERS_HOME="/app/backend/data/cache/embedding/models"
+#### Other models ##########################################################
 
 WORKDIR /app/backend
 
+RUN if [ "$USE_OLLAMA" = "true" ]; then \
+        apt-get update && \
+        # Install pandoc and netcat
+        apt-get install -y --no-install-recommends pandoc netcat-openbsd && \
+        # for RAG OCR
+        apt-get install -y --no-install-recommends ffmpeg libsm6 libxext6 && \
+        # install helper tools
+        apt-get install -y --no-install-recommends curl && \
+        # install ollama
+        curl -fsSL https://ollama.com/install.sh | sh && \
+        # cleanup
+        rm -rf /var/lib/apt/lists/*; \
+    else \
+        apt-get update && \
+        # Install pandoc and netcat
+        apt-get install -y --no-install-recommends pandoc netcat-openbsd && \
+        # for RAG OCR
+        apt-get install -y --no-install-recommends ffmpeg libsm6 libxext6 && \
+        # cleanup
+        rm -rf /var/lib/apt/lists/*; \
+    fi
+
 # install python dependencies
 COPY ./backend/requirements.txt ./requirements.txt
 
-RUN pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu --no-cache-dir
-RUN pip3 install -r requirements.txt --no-cache-dir
+RUN pip3 install uv && \
+    if [ "$USE_CUDA" = "true" ]; then \
+        # If you use CUDA the whisper and embedding model will be downloaded on first use
+        pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/$USE_CUDA_DOCKER_VER --no-cache-dir && \
+        uv pip install --system -r requirements.txt --no-cache-dir && \
+        python -c "import os; from faster_whisper import WhisperModel; WhisperModel(os.environ['WHISPER_MODEL'], device='cpu', compute_type='int8', download_root=os.environ['WHISPER_MODEL_DIR'])" && \
+        python -c "import os; from chromadb.utils import embedding_functions; sentence_transformer_ef = embedding_functions.SentenceTransformerEmbeddingFunction(model_name=os.environ['RAG_EMBEDDING_MODEL'], device='cpu')"; \
+    else \
+        pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu --no-cache-dir && \
+        uv pip install --system -r requirements.txt --no-cache-dir && \
+        python -c "import os; from faster_whisper import WhisperModel; WhisperModel(os.environ['WHISPER_MODEL'], device='cpu', compute_type='int8', download_root=os.environ['WHISPER_MODEL_DIR'])" && \
+        python -c "import os; from chromadb.utils import embedding_functions; sentence_transformer_ef = embedding_functions.SentenceTransformerEmbeddingFunction(model_name=os.environ['RAG_EMBEDDING_MODEL'], device='cpu')"; \
+    fi
 
-# Install pandoc and netcat
-# RUN python -c "import pypandoc; pypandoc.download_pandoc()"
-RUN apt-get update \
-    && apt-get install -y pandoc netcat-openbsd \
-    && rm -rf /var/lib/apt/lists/*
 
-# preload embedding model
-RUN python -c "import os; from chromadb.utils import embedding_functions; sentence_transformer_ef = embedding_functions.SentenceTransformerEmbeddingFunction(model_name=os.environ['RAG_EMBEDDING_MODEL'], device=os.environ['RAG_EMBEDDING_MODEL_DEVICE_TYPE'])"
-# preload tts model
-RUN python -c "import os; from faster_whisper import WhisperModel; WhisperModel(os.environ['WHISPER_MODEL'], device='auto', compute_type='int8', download_root=os.environ['WHISPER_MODEL_DIR'])"
 
 # copy embedding weight from build
-RUN mkdir -p /root/.cache/chroma/onnx_models/all-MiniLM-L6-v2
-COPY --from=build /app/onnx /root/.cache/chroma/onnx_models/all-MiniLM-L6-v2/onnx
+# RUN mkdir -p /root/.cache/chroma/onnx_models/all-MiniLM-L6-v2
+# COPY --from=build /app/onnx /root/.cache/chroma/onnx_models/all-MiniLM-L6-v2/onnx
 
 # copy built frontend files
 COPY --from=build /app/build /app/build
@@ -79,4 +121,6 @@ COPY --from=build /app/package.json /app/package.json
 # copy backend files
 COPY ./backend .
 
+EXPOSE 8080
+
 CMD [ "bash", "start.sh"]

Makefile

@@ -0,0 +1,27 @@
+install:
+	@docker-compose up -d
+
+remove:
+	@chmod +x confirm_remove.sh
+	@./confirm_remove.sh
+
+
+start:
+	@docker-compose start
+startAndBuild: 
+	docker-compose up -d --build
+
+stop:
+	@docker-compose stop
+
+update:
+	# Calls the LLM update script
+	chmod +x update_ollama_models.sh
+	@./update_ollama_models.sh
+	@git pull
+	@docker-compose down
+	# Make sure the ollama-webui container is stopped before rebuilding
+	@docker stop open-webui || true
+	@docker-compose up --build -d
+	@docker-compose start
+

README.md

@@ -11,7 +11,7 @@
 [![Discord](https://img.shields.io/badge/Discord-Open_WebUI-blue?logo=discord&logoColor=white)](https://discord.gg/5rJgQTnV4s)
 [![](https://img.shields.io/static/v1?label=Sponsor&message=%E2%9D%A4&logo=GitHub&color=%23fe8e86)](https://github.com/sponsors/tjbck)
 
-User-friendly WebUI for LLMs, supported LLM runners include Ollama and OpenAI-compatible APIs. For more information, be sure to check out our [Open WebUI Documentation](https://docs.openwebui.com/).
+Open WebUI is an extensible, feature-rich, and user-friendly self-hosted WebUI designed to operate entirely offline. It supports various LLM runners, including Ollama and OpenAI-compatible APIs. For more information, be sure to check out our [Open WebUI Documentation](https://docs.openwebui.com/).
 
 ![Open WebUI Demo](./demo.gif)
 
@@ -53,8 +53,6 @@ User-friendly WebUI for LLMs, supported LLM runners include Ollama and OpenAI-co
 
 - 💬 **Collaborative Chat**: Harness the collective intelligence of multiple models by seamlessly orchestrating group conversations. Use the `@` command to specify the model, enabling dynamic and diverse dialogues within your chat interface. Immerse yourself in the collective intelligence woven into your chat environment.
 
-- 🤝 **OpenAI API Integration**: Effortlessly integrate OpenAI-compatible API for versatile conversations alongside Ollama models. Customize the API Base URL to link with **LMStudio, Mistral, OpenRouter, and more**.
-
 - 🔄 **Regeneration History Access**: Easily revisit and explore your entire regeneration history.
 
 - 📜 **Chat History**: Effortlessly access and manage your conversation history.
@@ -65,12 +63,24 @@ User-friendly WebUI for LLMs, supported LLM runners include Ollama and OpenAI-co
 
 - ⚙️ **Fine-Tuned Control with Advanced Parameters**: Gain a deeper level of control by adjusting parameters such as temperature and defining your system prompts to tailor the conversation to your specific preferences and needs.
 
+- 🎨🤖 **Image Generation Integration**: Seamlessly incorporate image generation capabilities using AUTOMATIC1111 API (local) and DALL-E, enriching your chat experience with dynamic visual content.
+
+- 🤝 **OpenAI API Integration**: Effortlessly integrate OpenAI-compatible API for versatile conversations alongside Ollama models. Customize the API Base URL to link with **LMStudio, Mistral, OpenRouter, and more**.
+
+- ✨ **Multiple OpenAI-Compatible API Support**: Seamlessly integrate and customize various OpenAI-compatible APIs, enhancing the versatility of your chat interactions.
+
 - 🔗 **External Ollama Server Connection**: Seamlessly link to an external Ollama server hosted on a different address by configuring the environment variable.
 
+- 🔀 **Multiple Ollama Instance Load Balancing**: Effortlessly distribute chat requests across multiple Ollama instances for enhanced performance and reliability.
+
+- 👥 **Multi-User Management**: Easily oversee and administer users via our intuitive admin panel, streamlining user management processes.
+
 - 🔐 **Role-Based Access Control (RBAC)**: Ensure secure access with restricted permissions; only authorized individuals can access your Ollama, and exclusive model creation/pulling rights are reserved for administrators.
 
 - 🔒 **Backend Reverse Proxy Support**: Bolster security through direct communication between Open WebUI backend and Ollama. This key feature eliminates the need to expose Ollama over LAN. Requests made to the '/ollama/api' route from the web UI are seamlessly redirected to Ollama from the backend, enhancing overall system security.
 
+- 🌐🌍 **Multilingual Support**: Experience Open WebUI in your preferred language with our internationalization (i18n) support. Join us in expanding our supported languages! We're actively seeking contributors!
+
 - 🌟 **Continuous Updates**: We are committed to improving Open WebUI with regular updates and new features.
 
 ## 🔗 Also Check Out Open WebUI Community!
@@ -84,24 +94,27 @@ Don't forget to explore our sibling project, [Open WebUI Community](https://open
 
 ### Quick Start with Docker 🐳
 
-> [!IMPORTANT]
+> [!WARNING]
 > When using Docker to install Open WebUI, make sure to include the `-v open-webui:/app/backend/data` in your Docker command. This step is crucial as it ensures your database is properly mounted and prevents any loss of data.
 
-- **If Ollama is on your computer**, use this command:
+> [!TIP]  
+> If you wish to utilize Open WebUI with Ollama included or CUDA acceleration, we recommend utilizing our official images tagged with either `:cuda` or `:ollama`. To enable CUDA, you must install the [Nvidia CUDA container toolkit](https://docs.nvidia.com/dgx/nvidia-container-runtime-upgrade/) on your Linux/WSL system.
 
-  ```bash
-  docker run -d -p 3000:8080 --add-host=host.docker.internal:host-gateway -v open-webui:/app/backend/data --name open-webui --restart always ghcr.io/open-webui/open-webui:main
-  ```
+**If Ollama is on your computer**, use this command:
 
-- **If Ollama is on a Different Server**, use this command:
+```bash
+docker run -d -p 3000:8080 --add-host=host.docker.internal:host-gateway -v open-webui:/app/backend/data --name open-webui --restart always ghcr.io/open-webui/open-webui:main
+```
 
-- To connect to Ollama on another server, change the `OLLAMA_API_BASE_URL` to the server's URL:
+**If Ollama is on a Different Server**, use this command:
 
-  ```bash
-  docker run -d -p 3000:8080 -e OLLAMA_API_BASE_URL=https://example.com/api -v open-webui:/app/backend/data --name open-webui --restart always ghcr.io/open-webui/open-webui:main
-  ```
+To connect to Ollama on another server, change the `OLLAMA_BASE_URL` to the server's URL:
 
-- After installation, you can access Open WebUI at [http://localhost:3000](http://localhost:3000). Enjoy! 😄
+```bash
+docker run -d -p 3000:8080 -e OLLAMA_BASE_URL=https://example.com -v open-webui:/app/backend/data --name open-webui --restart always ghcr.io/open-webui/open-webui:main
+```
+
+After installation, you can access Open WebUI at [http://localhost:3000](http://localhost:3000). Enjoy! 😄
 
 #### Open WebUI: Server Connection Error
 
@@ -110,7 +123,7 @@ If you're experiencing connection issues, it’s often due to the WebUI docker c
 **Example Docker Command**:
 
 ```bash
-docker run -d --network=host -v open-webui:/app/backend/data -e OLLAMA_API_BASE_URL=http://127.0.0.1:11434/api --name open-webui --restart always ghcr.io/open-webui/open-webui:main
+docker run -d --network=host -v open-webui:/app/backend/data -e OLLAMA_BASE_URL=http://127.0.0.1:11434 --name open-webui --restart always ghcr.io/open-webui/open-webui:main
 ```
 
 ### Other Installation Methods
@@ -160,6 +173,16 @@ This project is licensed under the [MIT License](LICENSE) - see the [LICENSE](LI
 If you have any questions, suggestions, or need assistance, please open an issue or join our
 [Open WebUI Discord community](https://discord.gg/5rJgQTnV4s) to connect with us! 🤝
 
+## Star History
+
+<a href="https://star-history.com/#open-webui/open-webui&Date">
+  <picture>
+    <source media="(prefers-color-scheme: dark)" srcset="https://api.star-history.com/svg?repos=open-webui/open-webui&type=Date&theme=dark" />
+    <source media="(prefers-color-scheme: light)" srcset="https://api.star-history.com/svg?repos=open-webui/open-webui&type=Date" />
+    <img alt="Star History Chart" src="https://api.star-history.com/svg?repos=open-webui/open-webui&type=Date" />
+  </picture>
+</a>
+
 ---
 
 Created by [Timothy J. Baek](https://github.com/tjbck) - Let's make Open Web UI even more amazing together! 💪

TROUBLESHOOTING.md

@@ -4,7 +4,7 @@
 
 The Open WebUI system is designed to streamline interactions between the client (your browser) and the Ollama API. At the heart of this design is a backend reverse proxy, enhancing security and resolving CORS issues.
 
-- **How it Works**: The Open WebUI is designed to interact with the Ollama API through a specific route. When a request is made from the WebUI to Ollama, it is not directly sent to the Ollama API. Initially, the request is sent to the Open WebUI backend via `/ollama/api` route. From there, the backend is responsible for forwarding the request to the Ollama API. This forwarding is accomplished by using the route specified in the `OLLAMA_API_BASE_URL` environment variable. Therefore, a request made to `/ollama/api` in the WebUI is effectively the same as making a request to `OLLAMA_API_BASE_URL` in the backend. For instance, a request to `/ollama/api/tags` in the WebUI is equivalent to `OLLAMA_API_BASE_URL/tags` in the backend.
+- **How it Works**: The Open WebUI is designed to interact with the Ollama API through a specific route. When a request is made from the WebUI to Ollama, it is not directly sent to the Ollama API. Initially, the request is sent to the Open WebUI backend via `/ollama` route. From there, the backend is responsible for forwarding the request to the Ollama API. This forwarding is accomplished by using the route specified in the `OLLAMA_BASE_URL` environment variable. Therefore, a request made to `/ollama` in the WebUI is effectively the same as making a request to `OLLAMA_BASE_URL` in the backend. For instance, a request to `/ollama/api/tags` in the WebUI is equivalent to `OLLAMA_BASE_URL/api/tags` in the backend.
 
 - **Security Benefits**: This design prevents direct exposure of the Ollama API to the frontend, safeguarding against potential CORS (Cross-Origin Resource Sharing) issues and unauthorized access. Requiring authentication to access the Ollama API further enhances this security layer.
 
@@ -15,7 +15,7 @@ If you're experiencing connection issues, it’s often due to the WebUI docker c
 **Example Docker Command**:
 
 ```bash
-docker run -d --network=host -v open-webui:/app/backend/data -e OLLAMA_API_BASE_URL=http://127.0.0.1:11434/api --name open-webui --restart always ghcr.io/open-webui/open-webui:main
+docker run -d --network=host -v open-webui:/app/backend/data -e OLLAMA_BASE_URL=http://127.0.0.1:11434 --name open-webui --restart always ghcr.io/open-webui/open-webui:main
 ```
 
 ### General Connection Errors
@@ -25,8 +25,8 @@ docker run -d --network=host -v open-webui:/app/backend/data -e OLLAMA_API_BASE_
 **Troubleshooting Steps**:
 
 1. **Verify Ollama URL Format**:
-   - When running the Web UI container, ensure the `OLLAMA_API_BASE_URL` is correctly set, including the `/api` suffix. (e.g., `http://192.168.1.1:11434/api` for different host setups).
+   - When running the Web UI container, ensure the `OLLAMA_BASE_URL` is correctly set. (e.g., `http://192.168.1.1:11434` for different host setups).
    - In the Open WebUI, navigate to "Settings" > "General".
-   - Confirm that the Ollama Server URL is correctly set to `[OLLAMA URL]/api` (e.g., `http://localhost:11434/api`), including the `/api` suffix.
+   - Confirm that the Ollama Server URL is correctly set to `[OLLAMA URL]` (e.g., `http://localhost:11434`).
 
 By following these enhanced troubleshooting steps, connection issues should be effectively resolved. For further assistance or queries, feel free to reach out to us on our community Discord.

backend/apps/audio/main.py

@@ -1,4 +1,5 @@
 import os
+import logging
 from fastapi import (
     FastAPI,
     Request,
@@ -21,7 +22,18 @@ from utils.utils import (
 )
 from utils.misc import calculate_sha256
 
-from config import CACHE_DIR, UPLOAD_DIR, WHISPER_MODEL, WHISPER_MODEL_DIR
+from config import (
+    SRC_LOG_LEVELS,
+    CACHE_DIR,
+    UPLOAD_DIR,
+    WHISPER_MODEL,
+    WHISPER_MODEL_DIR,
+    WHISPER_MODEL_AUTO_UPDATE,
+    DEVICE_TYPE,
+)
+
+log = logging.getLogger(__name__)
+log.setLevel(SRC_LOG_LEVELS["AUDIO"])
 
 app = FastAPI()
 app.add_middleware(
@@ -32,13 +44,17 @@ app.add_middleware(
     allow_headers=["*"],
 )
 
+# setting device type for whisper model
+whisper_device_type = DEVICE_TYPE if DEVICE_TYPE and DEVICE_TYPE == "cuda" else "cpu"
+log.info(f"whisper_device_type: {whisper_device_type}")
+
 
 @app.post("/transcribe")
 def transcribe(
     file: UploadFile = File(...),
     user=Depends(get_current_user),
 ):
-    print(file.content_type)
+    log.info(f"file.content_type: {file.content_type}")
 
     if file.content_type not in ["audio/mpeg", "audio/wav"]:
         raise HTTPException(
@@ -54,15 +70,27 @@ def transcribe(
             f.write(contents)
             f.close()
 
-        model = WhisperModel(
-            WHISPER_MODEL,
-            device="auto",
-            compute_type="int8",
-            download_root=WHISPER_MODEL_DIR,
-        )
+        whisper_kwargs = {
+            "model_size_or_path": WHISPER_MODEL,
+            "device": whisper_device_type,
+            "compute_type": "int8",
+            "download_root": WHISPER_MODEL_DIR,
+            "local_files_only": not WHISPER_MODEL_AUTO_UPDATE,
+        }
+
+        log.debug(f"whisper_kwargs: {whisper_kwargs}")
+
+        try:
+            model = WhisperModel(**whisper_kwargs)
+        except:
+            log.warning(
+                "WhisperModel initialization failed, attempting download with local_files_only=False"
+            )
+            whisper_kwargs["local_files_only"] = False
+            model = WhisperModel(**whisper_kwargs)
 
         segments, info = model.transcribe(file_path, beam_size=5)
-        print(
+        log.info(
             "Detected language '%s' with probability %f"
             % (info.language, info.language_probability)
         )
@@ -72,7 +100,7 @@ def transcribe(
         return {"text": transcript.strip()}
 
     except Exception as e:
-        print(e)
+        log.exception(e)
 
         raise HTTPException(
             status_code=status.HTTP_400_BAD_REQUEST,

backend/apps/images/main.py

@@ -18,10 +18,31 @@ from utils.utils import (
     get_current_user,
     get_admin_user,
 )
+
+from apps.images.utils.comfyui import ImageGenerationPayload, comfyui_generate_image
 from utils.misc import calculate_sha256
 from typing import Optional
 from pydantic import BaseModel
-from config import AUTOMATIC1111_BASE_URL
+from pathlib import Path
+import uuid
+import base64
+import json
+import logging
+
+from config import (
+    SRC_LOG_LEVELS,
+    CACHE_DIR,
+    ENABLE_IMAGE_GENERATION,
+    AUTOMATIC1111_BASE_URL,
+    COMFYUI_BASE_URL,
+)
+
+
+log = logging.getLogger(__name__)
+log.setLevel(SRC_LOG_LEVELS["IMAGES"])
+
+IMAGE_CACHE_DIR = Path(CACHE_DIR).joinpath("./image/generations/")
+IMAGE_CACHE_DIR.mkdir(parents=True, exist_ok=True)
 
 app = FastAPI()
 app.add_middleware(
@@ -32,46 +53,104 @@ app.add_middleware(
     allow_headers=["*"],
 )
 
+app.state.ENGINE = ""
+app.state.ENABLED = ENABLE_IMAGE_GENERATION
+
+app.state.OPENAI_API_KEY = ""
+app.state.MODEL = ""
+
+
 app.state.AUTOMATIC1111_BASE_URL = AUTOMATIC1111_BASE_URL
-app.state.ENABLED = app.state.AUTOMATIC1111_BASE_URL != ""
+app.state.COMFYUI_BASE_URL = COMFYUI_BASE_URL
+
+
 app.state.IMAGE_SIZE = "512x512"
 app.state.IMAGE_STEPS = 50
 
 
-@app.get("/enabled", response_model=bool)
-async def get_enable_status(request: Request, user=Depends(get_admin_user)):
-    return app.state.ENABLED
+@app.get("/config")
+async def get_config(request: Request, user=Depends(get_admin_user)):
+    return {"engine": app.state.ENGINE, "enabled": app.state.ENABLED}
 
 
-@app.get("/enabled/toggle", response_model=bool)
-async def toggle_enabled(request: Request, user=Depends(get_admin_user)):
-    try:
-        r = requests.head(app.state.AUTOMATIC1111_BASE_URL)
-        app.state.ENABLED = not app.state.ENABLED
-        return app.state.ENABLED
-    except Exception as e:
-        raise HTTPException(status_code=400, detail=ERROR_MESSAGES.DEFAULT(e))
+class ConfigUpdateForm(BaseModel):
+    engine: str
+    enabled: bool
 
 
-class UrlUpdateForm(BaseModel):
-    url: str
+@app.post("/config/update")
+async def update_config(form_data: ConfigUpdateForm, user=Depends(get_admin_user)):
+    app.state.ENGINE = form_data.engine
+    app.state.ENABLED = form_data.enabled
+    return {"engine": app.state.ENGINE, "enabled": app.state.ENABLED}
+
+
+class EngineUrlUpdateForm(BaseModel):
+    AUTOMATIC1111_BASE_URL: Optional[str] = None
+    COMFYUI_BASE_URL: Optional[str] = None
 
 
 @app.get("/url")
-async def get_openai_url(user=Depends(get_admin_user)):
-    return {"AUTOMATIC1111_BASE_URL": app.state.AUTOMATIC1111_BASE_URL}
+async def get_engine_url(user=Depends(get_admin_user)):
+    return {
+        "AUTOMATIC1111_BASE_URL": app.state.AUTOMATIC1111_BASE_URL,
+        "COMFYUI_BASE_URL": app.state.COMFYUI_BASE_URL,
+    }
 
 
 @app.post("/url/update")
-async def update_openai_url(form_data: UrlUpdateForm, user=Depends(get_admin_user)):
+async def update_engine_url(
+    form_data: EngineUrlUpdateForm, user=Depends(get_admin_user)
+):
 
-    if form_data.url == "":
+    if form_data.AUTOMATIC1111_BASE_URL == None:
         app.state.AUTOMATIC1111_BASE_URL = AUTOMATIC1111_BASE_URL
     else:
-        app.state.AUTOMATIC1111_BASE_URL = form_data.url.strip("/")
+        url = form_data.AUTOMATIC1111_BASE_URL.strip("/")
+        try:
+            r = requests.head(url)
+            app.state.AUTOMATIC1111_BASE_URL = url
+        except Exception as e:
+            raise HTTPException(status_code=400, detail=ERROR_MESSAGES.DEFAULT(e))
+
+    if form_data.COMFYUI_BASE_URL == None:
+        app.state.COMFYUI_BASE_URL = COMFYUI_BASE_URL
+    else:
+        url = form_data.COMFYUI_BASE_URL.strip("/")
+
+        try:
+            r = requests.head(url)
+            app.state.COMFYUI_BASE_URL = url
+        except Exception as e:
+            raise HTTPException(status_code=400, detail=ERROR_MESSAGES.DEFAULT(e))
 
     return {
         "AUTOMATIC1111_BASE_URL": app.state.AUTOMATIC1111_BASE_URL,
+        "COMFYUI_BASE_URL": app.state.COMFYUI_BASE_URL,
+        "status": True,
+    }
+
+
+class OpenAIKeyUpdateForm(BaseModel):
+    key: str
+
+
+@app.get("/key")
+async def get_openai_key(user=Depends(get_admin_user)):
+    return {"OPENAI_API_KEY": app.state.OPENAI_API_KEY}
+
+
+@app.post("/key/update")
+async def update_openai_key(
+    form_data: OpenAIKeyUpdateForm, user=Depends(get_admin_user)
+):
+
+    if form_data.key == "":
+        raise HTTPException(status_code=400, detail=ERROR_MESSAGES.API_KEY_NOT_FOUND)
+
+    app.state.OPENAI_API_KEY = form_data.key
+    return {
+        "OPENAI_API_KEY": app.state.OPENAI_API_KEY,
         "status": True,
     }
 
@@ -132,9 +211,34 @@ async def update_image_size(
 @app.get("/models")
 def get_models(user=Depends(get_current_user)):
     try:
-        r = requests.get(url=f"{app.state.AUTOMATIC1111_BASE_URL}/sdapi/v1/sd-models")
-        models = r.json()
-        return models
+        if app.state.ENGINE == "openai":
+            return [
+                {"id": "dall-e-2", "name": "DALL·E 2"},
+                {"id": "dall-e-3", "name": "DALL·E 3"},
+            ]
+        elif app.state.ENGINE == "comfyui":
+
+            r = requests.get(url=f"{app.state.COMFYUI_BASE_URL}/object_info")
+            info = r.json()
+
+            return list(
+                map(
+                    lambda model: {"id": model, "name": model},
+                    info["CheckpointLoaderSimple"]["input"]["required"]["ckpt_name"][0],
+                )
+            )
+
+        else:
+            r = requests.get(
+                url=f"{app.state.AUTOMATIC1111_BASE_URL}/sdapi/v1/sd-models"
+            )
+            models = r.json()
+            return list(
+                map(
+                    lambda model: {"id": model["title"], "name": model["model_name"]},
+                    models,
+                )
+            )
     except Exception as e:
         app.state.ENABLED = False
         raise HTTPException(status_code=400, detail=ERROR_MESSAGES.DEFAULT(e))
@@ -143,10 +247,14 @@ def get_models(user=Depends(get_current_user)):
 @app.get("/models/default")
 async def get_default_model(user=Depends(get_admin_user)):
     try:
-        r = requests.get(url=f"{app.state.AUTOMATIC1111_BASE_URL}/sdapi/v1/options")
-        options = r.json()
-
-        return {"model": options["sd_model_checkpoint"]}
+        if app.state.ENGINE == "openai":
+            return {"model": app.state.MODEL if app.state.MODEL else "dall-e-2"}
+        elif app.state.ENGINE == "comfyui":
+            return {"model": app.state.MODEL if app.state.MODEL else ""}
+        else:
+            r = requests.get(url=f"{app.state.AUTOMATIC1111_BASE_URL}/sdapi/v1/options")
+            options = r.json()
+            return {"model": options["sd_model_checkpoint"]}
     except Exception as e:
         app.state.ENABLED = False
         raise HTTPException(status_code=400, detail=ERROR_MESSAGES.DEFAULT(e))
@@ -157,16 +265,23 @@ class UpdateModelForm(BaseModel):
 
 
 def set_model_handler(model: str):
-    r = requests.get(url=f"{app.state.AUTOMATIC1111_BASE_URL}/sdapi/v1/options")
-    options = r.json()
+    if app.state.ENGINE == "openai":
+        app.state.MODEL = model
+        return app.state.MODEL
+    if app.state.ENGINE == "comfyui":
+        app.state.MODEL = model
+        return app.state.MODEL
+    else:
+        r = requests.get(url=f"{app.state.AUTOMATIC1111_BASE_URL}/sdapi/v1/options")
+        options = r.json()
 
-    if model != options["sd_model_checkpoint"]:
-        options["sd_model_checkpoint"] = model
-        r = requests.post(
-            url=f"{app.state.AUTOMATIC1111_BASE_URL}/sdapi/v1/options", json=options
-        )
+        if model != options["sd_model_checkpoint"]:
+            options["sd_model_checkpoint"] = model
+            r = requests.post(
+                url=f"{app.state.AUTOMATIC1111_BASE_URL}/sdapi/v1/options", json=options
+            )
 
-    return options
+        return options
 
 
 @app.post("/models/default/update")
@@ -181,45 +296,170 @@ class GenerateImageForm(BaseModel):
     model: Optional[str] = None
     prompt: str
     n: int = 1
-    size: str = "512x512"
+    size: Optional[str] = None
     negative_prompt: Optional[str] = None
 
 
+def save_b64_image(b64_str):
+    image_id = str(uuid.uuid4())
+    file_path = IMAGE_CACHE_DIR.joinpath(f"{image_id}.png")
+
+    try:
+        # Split the base64 string to get the actual image data
+        img_data = base64.b64decode(b64_str)
+
+        # Write the image data to a file
+        with open(file_path, "wb") as f:
+            f.write(img_data)
+
+        return image_id
+    except Exception as e:
+        log.error(f"Error saving image: {e}")
+        return None
+
+
+def save_url_image(url):
+    image_id = str(uuid.uuid4())
+    file_path = IMAGE_CACHE_DIR.joinpath(f"{image_id}.png")
+
+    try:
+        r = requests.get(url)
+        r.raise_for_status()
+
+        with open(file_path, "wb") as image_file:
+            image_file.write(r.content)
+
+        return image_id
+    except Exception as e:
+        log.exception(f"Error saving image: {e}")
+        return None
+
+
 @app.post("/generations")
 def generate_image(
     form_data: GenerateImageForm,
     user=Depends(get_current_user),
 ):
 
-    print(form_data)
+    width, height = tuple(map(int, app.state.IMAGE_SIZE.split("x")))
 
+    r = None
     try:
-        if form_data.model:
-            set_model_handler(form_data.model)
+        if app.state.ENGINE == "openai":
 
-        width, height = tuple(map(int, app.state.IMAGE_SIZE.split("x")))
+            headers = {}
+            headers["Authorization"] = f"Bearer {app.state.OPENAI_API_KEY}"
+            headers["Content-Type"] = "application/json"
 
-        data = {
-            "prompt": form_data.prompt,
-            "batch_size": form_data.n,
-            "width": width,
-            "height": height,
-        }
+            data = {
+                "model": app.state.MODEL if app.state.MODEL != "" else "dall-e-2",
+                "prompt": form_data.prompt,
+                "n": form_data.n,
+                "size": form_data.size if form_data.size else app.state.IMAGE_SIZE,
+                "response_format": "b64_json",
+            }
 
-        if app.state.IMAGE_STEPS != None:
-            data["steps"] = app.state.IMAGE_STEPS
+            r = requests.post(
+                url=f"https://api.openai.com/v1/images/generations",
+                json=data,
+                headers=headers,
+            )
 
-        if form_data.negative_prompt != None:
-            data["negative_prompt"] = form_data.negative_prompt
+            r.raise_for_status()
+            res = r.json()
 
-        print(data)
+            images = []
 
-        r = requests.post(
-            url=f"{app.state.AUTOMATIC1111_BASE_URL}/sdapi/v1/txt2img",
-            json=data,
-        )
+            for image in res["data"]:
+                image_id = save_b64_image(image["b64_json"])
+                images.append({"url": f"/cache/image/generations/{image_id}.png"})
+                file_body_path = IMAGE_CACHE_DIR.joinpath(f"{image_id}.json")
+
+                with open(file_body_path, "w") as f:
+                    json.dump(data, f)
+
+            return images
+
+        elif app.state.ENGINE == "comfyui":
+
+            data = {
+                "prompt": form_data.prompt,
+                "width": width,
+                "height": height,
+                "n": form_data.n,
+            }
+
+            if app.state.IMAGE_STEPS != None:
+                data["steps"] = app.state.IMAGE_STEPS
+
+            if form_data.negative_prompt != None:
+                data["negative_prompt"] = form_data.negative_prompt
+
+            data = ImageGenerationPayload(**data)
+
+            res = comfyui_generate_image(
+                app.state.MODEL,
+                data,
+                user.id,
+                app.state.COMFYUI_BASE_URL,
+            )
+            log.debug(f"res: {res}")
+
+            images = []
+
+            for image in res["data"]:
+                image_id = save_url_image(image["url"])
+                images.append({"url": f"/cache/image/generations/{image_id}.png"})
+                file_body_path = IMAGE_CACHE_DIR.joinpath(f"{image_id}.json")
+
+                with open(file_body_path, "w") as f:
+                    json.dump(data.model_dump(exclude_none=True), f)
+
+            log.debug(f"images: {images}")
+            return images
+        else:
+            if form_data.model:
+                set_model_handler(form_data.model)
+
+            data = {
+                "prompt": form_data.prompt,
+                "batch_size": form_data.n,
+                "width": width,
+                "height": height,
+            }
+
+            if app.state.IMAGE_STEPS != None:
+                data["steps"] = app.state.IMAGE_STEPS
+
+            if form_data.negative_prompt != None:
+                data["negative_prompt"] = form_data.negative_prompt
+
+            r = requests.post(
+                url=f"{app.state.AUTOMATIC1111_BASE_URL}/sdapi/v1/txt2img",
+                json=data,
+            )
+
+            res = r.json()
+
+            log.debug(f"res: {res}")
+
+            images = []
+
+            for image in res["images"]:
+                image_id = save_b64_image(image)
+                images.append({"url": f"/cache/image/generations/{image_id}.png"})
+                file_body_path = IMAGE_CACHE_DIR.joinpath(f"{image_id}.json")
+
+                with open(file_body_path, "w") as f:
+                    json.dump({**data, "info": res["info"]}, f)
+
+            return images
 
-        return r.json()
     except Exception as e:
-        print(e)
-        raise HTTPException(status_code=400, detail=ERROR_MESSAGES.DEFAULT(e))
+        error = e
+
+        if r != None:
+            data = r.json()
+            if "error" in data:
+                error = data["error"]["message"]
+        raise HTTPException(status_code=400, detail=ERROR_MESSAGES.DEFAULT(error))

backend/apps/images/utils/comfyui.py

@@ -0,0 +1,234 @@
+import websocket  # NOTE: websocket-client (https://github.com/websocket-client/websocket-client)
+import uuid
+import json
+import urllib.request
+import urllib.parse
+import random
+import logging
+
+from config import SRC_LOG_LEVELS
+
+log = logging.getLogger(__name__)
+log.setLevel(SRC_LOG_LEVELS["COMFYUI"])
+
+from pydantic import BaseModel
+
+from typing import Optional
+
+COMFYUI_DEFAULT_PROMPT = """
+{
+  "3": {
+    "inputs": {
+      "seed": 0,
+      "steps": 20,
+      "cfg": 8,
+      "sampler_name": "euler",
+      "scheduler": "normal",
+      "denoise": 1,
+      "model": [
+        "4",
+        0
+      ],
+      "positive": [
+        "6",
+        0
+      ],
+      "negative": [
+        "7",
+        0
+      ],
+      "latent_image": [
+        "5",
+        0
+      ]
+    },
+    "class_type": "KSampler",
+    "_meta": {
+      "title": "KSampler"
+    }
+  },
+  "4": {
+    "inputs": {
+      "ckpt_name": "model.safetensors"
+    },
+    "class_type": "CheckpointLoaderSimple",
+    "_meta": {
+      "title": "Load Checkpoint"
+    }
+  },
+  "5": {
+    "inputs": {
+      "width": 512,
+      "height": 512,
+      "batch_size": 1
+    },
+    "class_type": "EmptyLatentImage",
+    "_meta": {
+      "title": "Empty Latent Image"
+    }
+  },
+  "6": {
+    "inputs": {
+      "text": "Prompt",
+      "clip": [
+        "4",
+        1
+      ]
+    },
+    "class_type": "CLIPTextEncode",
+    "_meta": {
+      "title": "CLIP Text Encode (Prompt)"
+    }
+  },
+  "7": {
+    "inputs": {
+      "text": "Negative Prompt",
+      "clip": [
+        "4",
+        1
+      ]
+    },
+    "class_type": "CLIPTextEncode",
+    "_meta": {
+      "title": "CLIP Text Encode (Prompt)"
+    }
+  },
+  "8": {
+    "inputs": {
+      "samples": [
+        "3",
+        0
+      ],
+      "vae": [
+        "4",
+        2
+      ]
+    },
+    "class_type": "VAEDecode",
+    "_meta": {
+      "title": "VAE Decode"
+    }
+  },
+  "9": {
+    "inputs": {
+      "filename_prefix": "ComfyUI",
+      "images": [
+        "8",
+        0
+      ]
+    },
+    "class_type": "SaveImage",
+    "_meta": {
+      "title": "Save Image"
+    }
+  }
+}
+"""
+
+
+def queue_prompt(prompt, client_id, base_url):
+    log.info("queue_prompt")
+    p = {"prompt": prompt, "client_id": client_id}
+    data = json.dumps(p).encode("utf-8")
+    req = urllib.request.Request(f"{base_url}/prompt", data=data)
+    return json.loads(urllib.request.urlopen(req).read())
+
+
+def get_image(filename, subfolder, folder_type, base_url):
+    log.info("get_image")
+    data = {"filename": filename, "subfolder": subfolder, "type": folder_type}
+    url_values = urllib.parse.urlencode(data)
+    with urllib.request.urlopen(f"{base_url}/view?{url_values}") as response:
+        return response.read()
+
+
+def get_image_url(filename, subfolder, folder_type, base_url):
+    log.info("get_image")
+    data = {"filename": filename, "subfolder": subfolder, "type": folder_type}
+    url_values = urllib.parse.urlencode(data)
+    return f"{base_url}/view?{url_values}"
+
+
+def get_history(prompt_id, base_url):
+    log.info("get_history")
+    with urllib.request.urlopen(f"{base_url}/history/{prompt_id}") as response:
+        return json.loads(response.read())
+
+
+def get_images(ws, prompt, client_id, base_url):
+    prompt_id = queue_prompt(prompt, client_id, base_url)["prompt_id"]
+    output_images = []
+    while True:
+        out = ws.recv()
+        if isinstance(out, str):
+            message = json.loads(out)
+            if message["type"] == "executing":
+                data = message["data"]
+                if data["node"] is None and data["prompt_id"] == prompt_id:
+                    break  # Execution is done
+        else:
+            continue  # previews are binary data
+
+    history = get_history(prompt_id, base_url)[prompt_id]
+    for o in history["outputs"]:
+        for node_id in history["outputs"]:
+            node_output = history["outputs"][node_id]
+            if "images" in node_output:
+                for image in node_output["images"]:
+                    url = get_image_url(
+                        image["filename"], image["subfolder"], image["type"], base_url
+                    )
+                    output_images.append({"url": url})
+    return {"data": output_images}
+
+
+class ImageGenerationPayload(BaseModel):
+    prompt: str
+    negative_prompt: Optional[str] = ""
+    steps: Optional[int] = None
+    seed: Optional[int] = None
+    width: int
+    height: int
+    n: int = 1
+
+
+def comfyui_generate_image(
+    model: str, payload: ImageGenerationPayload, client_id, base_url
+):
+    host = base_url.replace("http://", "").replace("https://", "")
+
+    comfyui_prompt = json.loads(COMFYUI_DEFAULT_PROMPT)
+
+    comfyui_prompt["4"]["inputs"]["ckpt_name"] = model
+    comfyui_prompt["5"]["inputs"]["batch_size"] = payload.n
+    comfyui_prompt["5"]["inputs"]["width"] = payload.width
+    comfyui_prompt["5"]["inputs"]["height"] = payload.height
+
+    # set the text prompt for our positive CLIPTextEncode
+    comfyui_prompt["6"]["inputs"]["text"] = payload.prompt
+    comfyui_prompt["7"]["inputs"]["text"] = payload.negative_prompt
+
+    if payload.steps:
+        comfyui_prompt["3"]["inputs"]["steps"] = payload.steps
+
+    comfyui_prompt["3"]["inputs"]["seed"] = (
+        payload.seed if payload.seed else random.randint(0, 18446744073709551614)
+    )
+
+    try:
+        ws = websocket.WebSocket()
+        ws.connect(f"ws://{host}/ws?clientId={client_id}")
+        log.info("WebSocket connection established.")
+    except Exception as e:
+        log.exception(f"Failed to connect to WebSocket server: {e}")
+        return None
+
+    try:
+        images = get_images(ws, comfyui_prompt, client_id, base_url)
+    except Exception as e:
+        log.exception(f"Error while receiving images: {e}")
+        images = None
+
+    ws.close()
+
+    return images

backend/apps/litellm/main.py

@@ -0,0 +1,100 @@
+import logging
+
+from litellm.proxy.proxy_server import ProxyConfig, initialize
+from litellm.proxy.proxy_server import app
+
+from fastapi import FastAPI, Request, Depends, status, Response
+from fastapi.responses import JSONResponse
+
+from starlette.middleware.base import BaseHTTPMiddleware, RequestResponseEndpoint
+from starlette.responses import StreamingResponse
+import json
+
+from utils.utils import get_http_authorization_cred, get_current_user
+from config import SRC_LOG_LEVELS, ENV
+
+log = logging.getLogger(__name__)
+log.setLevel(SRC_LOG_LEVELS["LITELLM"])
+
+
+from config import (
+    MODEL_FILTER_ENABLED,
+    MODEL_FILTER_LIST,
+)
+
+
+proxy_config = ProxyConfig()
+
+
+async def config():
+    router, model_list, general_settings = await proxy_config.load_config(
+        router=None, config_file_path="./data/litellm/config.yaml"
+    )
+
+    await initialize(config="./data/litellm/config.yaml", telemetry=False)
+
+
+async def startup():
+    await config()
+
+
+@app.on_event("startup")
+async def on_startup():
+    await startup()
+
+
+app.state.MODEL_FILTER_ENABLED = MODEL_FILTER_ENABLED
+app.state.MODEL_FILTER_LIST = MODEL_FILTER_LIST
+
+
+@app.middleware("http")
+async def auth_middleware(request: Request, call_next):
+    auth_header = request.headers.get("Authorization", "")
+    request.state.user = None
+
+    try:
+        user = get_current_user(get_http_authorization_cred(auth_header))
+        log.debug(f"user: {user}")
+        request.state.user = user
+    except Exception as e:
+        return JSONResponse(status_code=400, content={"detail": str(e)})
+
+    response = await call_next(request)
+    return response
+
+
+class ModifyModelsResponseMiddleware(BaseHTTPMiddleware):
+    async def dispatch(
+        self, request: Request, call_next: RequestResponseEndpoint
+    ) -> Response:
+
+        response = await call_next(request)
+        user = request.state.user
+
+        if "/models" in request.url.path:
+            if isinstance(response, StreamingResponse):
+                # Read the content of the streaming response
+                body = b""
+                async for chunk in response.body_iterator:
+                    body += chunk
+
+                data = json.loads(body.decode("utf-8"))
+
+                if app.state.MODEL_FILTER_ENABLED:
+                    if user and user.role == "user":
+                        data["data"] = list(
+                            filter(
+                                lambda model: model["id"]
+                                in app.state.MODEL_FILTER_LIST,
+                                data["data"],
+                            )
+                        )
+
+                # Modified Flag
+                data["modified"] = True
+                return JSONResponse(content=data)
+
+        return response
+
+
+app.add_middleware(ModifyModelsResponseMiddleware)

backend/apps/ollama/old_main.py

@@ -1,127 +0,0 @@
-from fastapi import FastAPI, Request, Response, HTTPException, Depends
-from fastapi.middleware.cors import CORSMiddleware
-from fastapi.responses import StreamingResponse
-
-import requests
-import json
-from pydantic import BaseModel
-
-from apps.web.models.users import Users
-from constants import ERROR_MESSAGES
-from utils.utils import decode_token, get_current_user
-from config import OLLAMA_API_BASE_URL, WEBUI_AUTH
-
-import aiohttp
-
-app = FastAPI()
-app.add_middleware(
-    CORSMiddleware,
-    allow_origins=["*"],
-    allow_credentials=True,
-    allow_methods=["*"],
-    allow_headers=["*"],
-)
-
-app.state.OLLAMA_API_BASE_URL = OLLAMA_API_BASE_URL
-
-# TARGET_SERVER_URL = OLLAMA_API_BASE_URL
-
-
-@app.get("/url")
-async def get_ollama_api_url(user=Depends(get_current_user)):
-    if user and user.role == "admin":
-        return {"OLLAMA_API_BASE_URL": app.state.OLLAMA_API_BASE_URL}
-    else:
-        raise HTTPException(status_code=401, detail=ERROR_MESSAGES.ACCESS_PROHIBITED)
-
-
-class UrlUpdateForm(BaseModel):
-    url: str
-
-
-@app.post("/url/update")
-async def update_ollama_api_url(
-    form_data: UrlUpdateForm, user=Depends(get_current_user)
-):
-    if user and user.role == "admin":
-        app.state.OLLAMA_API_BASE_URL = form_data.url
-        return {"OLLAMA_API_BASE_URL": app.state.OLLAMA_API_BASE_URL}
-    else:
-        raise HTTPException(status_code=401, detail=ERROR_MESSAGES.ACCESS_PROHIBITED)
-
-
-# async def fetch_sse(method, target_url, body, headers):
-#     async with aiohttp.ClientSession() as session:
-#         try:
-#             async with session.request(
-#                 method, target_url, data=body, headers=headers
-#             ) as response:
-#                 print(response.status)
-#                 async for line in response.content:
-#                     yield line
-#         except Exception as e:
-#             print(e)
-#             error_detail = "Open WebUI: Server Connection Error"
-#             yield json.dumps({"error": error_detail, "message": str(e)}).encode()
-
-
-@app.api_route("/{path:path}", methods=["GET", "POST", "PUT", "DELETE"])
-async def proxy(path: str, request: Request, user=Depends(get_current_user)):
-    target_url = f"{app.state.OLLAMA_API_BASE_URL}/{path}"
-    print(target_url)
-
-    body = await request.body()
-    headers = dict(request.headers)
-
-    if user.role in ["user", "admin"]:
-        if path in ["pull", "delete", "push", "copy", "create"]:
-            if user.role != "admin":
-                raise HTTPException(
-                    status_code=401, detail=ERROR_MESSAGES.ACCESS_PROHIBITED
-                )
-    else:
-        raise HTTPException(status_code=401, detail=ERROR_MESSAGES.ACCESS_PROHIBITED)
-
-    headers.pop("Host", None)
-    headers.pop("Authorization", None)
-    headers.pop("Origin", None)
-    headers.pop("Referer", None)
-
-    session = aiohttp.ClientSession()
-    response = None
-    try:
-        response = await session.request(
-            request.method, target_url, data=body, headers=headers
-        )
-
-        print(response)
-        if not response.ok:
-            data = await response.json()
-            print(data)
-            response.raise_for_status()
-
-        async def generate():
-            async for line in response.content:
-                print(line)
-                yield line
-            await session.close()
-
-        return StreamingResponse(generate(), response.status)
-
-    except Exception as e:
-        print(e)
-        error_detail = "Open WebUI: Server Connection Error"
-
-        if response is not None:
-            try:
-                res = await response.json()
-                if "error" in res:
-                    error_detail = f"Ollama: {res['error']}"
-            except:
-                error_detail = f"Ollama: {e}"
-
-        await session.close()
-        raise HTTPException(
-            status_code=response.status if response else 500,
-            detail=error_detail,
-        )

backend/apps/openai/main.py

@@ -3,7 +3,11 @@ from fastapi.middleware.cors import CORSMiddleware
 from fastapi.responses import StreamingResponse, JSONResponse, FileResponse
 
 import requests
+import aiohttp
+import asyncio
 import json
+import logging
+
 from pydantic import BaseModel
 
 
@@ -15,11 +19,23 @@ from utils.utils import (
     get_verified_user,
     get_admin_user,
 )
-from config import OPENAI_API_BASE_URL, OPENAI_API_KEY, CACHE_DIR
+from config import (
+    SRC_LOG_LEVELS,
+    OPENAI_API_BASE_URLS,
+    OPENAI_API_KEYS,
+    CACHE_DIR,
+    MODEL_FILTER_ENABLED,
+    MODEL_FILTER_LIST,
+)
+from typing import List, Optional
+
 
 import hashlib
 from pathlib import Path
 
+log = logging.getLogger(__name__)
+log.setLevel(SRC_LOG_LEVELS["OPENAI"])
+
 app = FastAPI()
 app.add_middleware(
     CORSMiddleware,
@@ -29,132 +45,274 @@ app.add_middleware(
     allow_headers=["*"],
 )
 
-app.state.OPENAI_API_BASE_URL = OPENAI_API_BASE_URL
-app.state.OPENAI_API_KEY = OPENAI_API_KEY
+app.state.MODEL_FILTER_ENABLED = MODEL_FILTER_ENABLED
+app.state.MODEL_FILTER_LIST = MODEL_FILTER_LIST
+
+app.state.OPENAI_API_BASE_URLS = OPENAI_API_BASE_URLS
+app.state.OPENAI_API_KEYS = OPENAI_API_KEYS
+
+app.state.MODELS = {}
 
 
-class UrlUpdateForm(BaseModel):
-    url: str
+@app.middleware("http")
+async def check_url(request: Request, call_next):
+    if len(app.state.MODELS) == 0:
+        await get_all_models()
+    else:
+        pass
+
+    response = await call_next(request)
+    return response
 
 
-class KeyUpdateForm(BaseModel):
-    key: str
+class UrlsUpdateForm(BaseModel):
+    urls: List[str]
 
 
-@app.get("/url")
-async def get_openai_url(user=Depends(get_admin_user)):
-    return {"OPENAI_API_BASE_URL": app.state.OPENAI_API_BASE_URL}
+class KeysUpdateForm(BaseModel):
+    keys: List[str]
 
 
-@app.post("/url/update")
-async def update_openai_url(form_data: UrlUpdateForm, user=Depends(get_admin_user)):
-    app.state.OPENAI_API_BASE_URL = form_data.url
-    return {"OPENAI_API_BASE_URL": app.state.OPENAI_API_BASE_URL}
+@app.get("/urls")
+async def get_openai_urls(user=Depends(get_admin_user)):
+    return {"OPENAI_API_BASE_URLS": app.state.OPENAI_API_BASE_URLS}
 
 
-@app.get("/key")
-async def get_openai_key(user=Depends(get_admin_user)):
-    return {"OPENAI_API_KEY": app.state.OPENAI_API_KEY}
+@app.post("/urls/update")
+async def update_openai_urls(form_data: UrlsUpdateForm, user=Depends(get_admin_user)):
+    app.state.OPENAI_API_BASE_URLS = form_data.urls
+    return {"OPENAI_API_BASE_URLS": app.state.OPENAI_API_BASE_URLS}
 
 
-@app.post("/key/update")
-async def update_openai_key(form_data: KeyUpdateForm, user=Depends(get_admin_user)):
-    app.state.OPENAI_API_KEY = form_data.key
-    return {"OPENAI_API_KEY": app.state.OPENAI_API_KEY}
+@app.get("/keys")
+async def get_openai_keys(user=Depends(get_admin_user)):
+    return {"OPENAI_API_KEYS": app.state.OPENAI_API_KEYS}
+
+
+@app.post("/keys/update")
+async def update_openai_key(form_data: KeysUpdateForm, user=Depends(get_admin_user)):
+    app.state.OPENAI_API_KEYS = form_data.keys
+    return {"OPENAI_API_KEYS": app.state.OPENAI_API_KEYS}
 
 
 @app.post("/audio/speech")
 async def speech(request: Request, user=Depends(get_verified_user)):
-    target_url = f"{app.state.OPENAI_API_BASE_URL}/audio/speech"
-
-    if app.state.OPENAI_API_KEY == "":
-        raise HTTPException(status_code=401, detail=ERROR_MESSAGES.API_KEY_NOT_FOUND)
-
-    body = await request.body()
-
-    name = hashlib.sha256(body).hexdigest()
-
-    SPEECH_CACHE_DIR = Path(CACHE_DIR).joinpath("./audio/speech/")
-    SPEECH_CACHE_DIR.mkdir(parents=True, exist_ok=True)
-    file_path = SPEECH_CACHE_DIR.joinpath(f"{name}.mp3")
-    file_body_path = SPEECH_CACHE_DIR.joinpath(f"{name}.json")
-
-    # Check if the file already exists in the cache
-    if file_path.is_file():
-        return FileResponse(file_path)
-
-    headers = {}
-    headers["Authorization"] = f"Bearer {app.state.OPENAI_API_KEY}"
-    headers["Content-Type"] = "application/json"
-
+    idx = None
     try:
-        print("openai")
-        r = requests.post(
-            url=target_url,
-            data=body,
-            headers=headers,
-            stream=True,
-        )
+        idx = app.state.OPENAI_API_BASE_URLS.index("https://api.openai.com/v1")
+        body = await request.body()
+        name = hashlib.sha256(body).hexdigest()
 
-        r.raise_for_status()
+        SPEECH_CACHE_DIR = Path(CACHE_DIR).joinpath("./audio/speech/")
+        SPEECH_CACHE_DIR.mkdir(parents=True, exist_ok=True)
+        file_path = SPEECH_CACHE_DIR.joinpath(f"{name}.mp3")
+        file_body_path = SPEECH_CACHE_DIR.joinpath(f"{name}.json")
 
-        # Save the streaming content to a file
-        with open(file_path, "wb") as f:
-            for chunk in r.iter_content(chunk_size=8192):
-                f.write(chunk)
+        # Check if the file already exists in the cache
+        if file_path.is_file():
+            return FileResponse(file_path)
 
-        with open(file_body_path, "w") as f:
-            json.dump(json.loads(body.decode("utf-8")), f)
+        headers = {}
+        headers["Authorization"] = f"Bearer {app.state.OPENAI_API_KEYS[idx]}"
+        headers["Content-Type"] = "application/json"
 
-        # Return the saved file
-        return FileResponse(file_path)
+        r = None
+        try:
+            r = requests.post(
+                url=f"{app.state.OPENAI_API_BASE_URLS[idx]}/audio/speech",
+                data=body,
+                headers=headers,
+                stream=True,
+            )
 
+            r.raise_for_status()
+
+            # Save the streaming content to a file
+            with open(file_path, "wb") as f:
+                for chunk in r.iter_content(chunk_size=8192):
+                    f.write(chunk)
+
+            with open(file_body_path, "w") as f:
+                json.dump(json.loads(body.decode("utf-8")), f)
+
+            # Return the saved file
+            return FileResponse(file_path)
+
+        except Exception as e:
+            log.exception(e)
+            error_detail = "Open WebUI: Server Connection Error"
+            if r is not None:
+                try:
+                    res = r.json()
+                    if "error" in res:
+                        error_detail = f"External: {res['error']}"
+                except:
+                    error_detail = f"External: {e}"
+
+            raise HTTPException(
+                status_code=r.status_code if r else 500, detail=error_detail
+            )
+
+    except ValueError:
+        raise HTTPException(status_code=401, detail=ERROR_MESSAGES.OPENAI_NOT_FOUND)
+
+
+async def fetch_url(url, key):
+    try:
+        headers = {"Authorization": f"Bearer {key}"}
+        async with aiohttp.ClientSession() as session:
+            async with session.get(url, headers=headers) as response:
+                return await response.json()
     except Exception as e:
-        print(e)
-        error_detail = "Open WebUI: Server Connection Error"
-        if r is not None:
-            try:
-                res = r.json()
-                if "error" in res:
-                    error_detail = f"External: {res['error']}"
-            except:
-                error_detail = f"External: {e}"
+        # Handle connection error here
+        log.error(f"Connection error: {e}")
+        return None
 
-        raise HTTPException(status_code=r.status_code, detail=error_detail)
+
+def merge_models_lists(model_lists):
+    merged_list = []
+
+    for idx, models in enumerate(model_lists):
+        if models is not None and "error" not in models:
+            merged_list.extend(
+                [
+                    {**model, "urlIdx": idx}
+                    for model in models
+                    if "api.openai.com" not in app.state.OPENAI_API_BASE_URLS[idx]
+                    or "gpt" in model["id"]
+                ]
+            )
+
+    return merged_list
+
+
+async def get_all_models():
+    log.info("get_all_models()")
+
+    if len(app.state.OPENAI_API_KEYS) == 1 and app.state.OPENAI_API_KEYS[0] == "":
+        models = {"data": []}
+    else:
+        tasks = [
+            fetch_url(f"{url}/models", app.state.OPENAI_API_KEYS[idx])
+            for idx, url in enumerate(app.state.OPENAI_API_BASE_URLS)
+        ]
+
+        responses = await asyncio.gather(*tasks)
+        models = {
+            "data": merge_models_lists(
+                list(
+                    map(
+                        lambda response: (
+                            response["data"]
+                            if response and "data" in response
+                            else None
+                        ),
+                        responses,
+                    )
+                )
+            )
+        }
+
+        log.info(f"models: {models}")
+        app.state.MODELS = {model["id"]: model for model in models["data"]}
+
+        return models
+
+
+@app.get("/models")
+@app.get("/models/{url_idx}")
+async def get_models(url_idx: Optional[int] = None, user=Depends(get_current_user)):
+    if url_idx == None:
+        models = await get_all_models()
+        if app.state.MODEL_FILTER_ENABLED:
+            if user.role == "user":
+                models["data"] = list(
+                    filter(
+                        lambda model: model["id"] in app.state.MODEL_FILTER_LIST,
+                        models["data"],
+                    )
+                )
+                return models
+        return models
+    else:
+        url = app.state.OPENAI_API_BASE_URLS[url_idx]
+
+        r = None
+
+        try:
+            r = requests.request(method="GET", url=f"{url}/models")
+            r.raise_for_status()
+
+            response_data = r.json()
+            if "api.openai.com" in url:
+                response_data["data"] = list(
+                    filter(lambda model: "gpt" in model["id"], response_data["data"])
+                )
+
+            return response_data
+        except Exception as e:
+            log.exception(e)
+            error_detail = "Open WebUI: Server Connection Error"
+            if r is not None:
+                try:
+                    res = r.json()
+                    if "error" in res:
+                        error_detail = f"External: {res['error']}"
+                except:
+                    error_detail = f"External: {e}"
+
+            raise HTTPException(
+                status_code=r.status_code if r else 500,
+                detail=error_detail,
+            )
 
 
 @app.api_route("/{path:path}", methods=["GET", "POST", "PUT", "DELETE"])
 async def proxy(path: str, request: Request, user=Depends(get_verified_user)):
-    target_url = f"{app.state.OPENAI_API_BASE_URL}/{path}"
-    print(target_url, app.state.OPENAI_API_KEY)
-
-    if app.state.OPENAI_API_KEY == "":
-        raise HTTPException(status_code=401, detail=ERROR_MESSAGES.API_KEY_NOT_FOUND)
+    idx = 0
 
     body = await request.body()
-
     # TODO: Remove below after gpt-4-vision fix from Open AI
     # Try to decode the body of the request from bytes to a UTF-8 string (Require add max_token to fix gpt-4-vision)
     try:
         body = body.decode("utf-8")
         body = json.loads(body)
 
+        idx = app.state.MODELS[body.get("model")]["urlIdx"]
+
         # Check if the model is "gpt-4-vision-preview" and set "max_tokens" to 4000
         # This is a workaround until OpenAI fixes the issue with this model
         if body.get("model") == "gpt-4-vision-preview":
             if "max_tokens" not in body:
                 body["max_tokens"] = 4000
-            print("Modified body_dict:", body)
+            log.debug("Modified body_dict:", body)
+
+        # Fix for ChatGPT calls failing because the num_ctx key is in body
+        if "num_ctx" in body:
+            # If 'num_ctx' is in the dictionary, delete it
+            # Leaving it there generates an error with the
+            # OpenAI API (Feb 2024)
+            del body["num_ctx"]
 
         # Convert the modified body back to JSON
         body = json.dumps(body)
     except json.JSONDecodeError as e:
-        print("Error loading request body into a dictionary:", e)
+        log.error("Error loading request body into a dictionary:", e)
+
+    url = app.state.OPENAI_API_BASE_URLS[idx]
+    key = app.state.OPENAI_API_KEYS[idx]
+
+    target_url = f"{url}/{path}"
+
+    if key == "":
+        raise HTTPException(status_code=401, detail=ERROR_MESSAGES.API_KEY_NOT_FOUND)
 
     headers = {}
-    headers["Authorization"] = f"Bearer {app.state.OPENAI_API_KEY}"
+    headers["Authorization"] = f"Bearer {key}"
     headers["Content-Type"] = "application/json"
 
+    r = None
+
     try:
         r = requests.request(
             method=request.method,
@@ -174,24 +332,10 @@ async def proxy(path: str, request: Request, user=Depends(get_verified_user)):
                 headers=dict(r.headers),
             )
         else:
-            # For non-SSE, read the response and return it
-            # response_data = (
-            #     r.json()
-            #     if r.headers.get("Content-Type", "")
-            #     == "application/json"
-            #     else r.text
-            # )
-
             response_data = r.json()
-
-            if "openai" in app.state.OPENAI_API_BASE_URL and path == "models":
-                response_data["data"] = list(
-                    filter(lambda model: "gpt" in model["id"], response_data["data"])
-                )
-
             return response_data
     except Exception as e:
-        print(e)
+        log.exception(e)
         error_detail = "Open WebUI: Server Connection Error"
         if r is not None:
             try:
@@ -201,4 +345,6 @@ async def proxy(path: str, request: Request, user=Depends(get_verified_user)):
             except:
                 error_detail = f"External: {e}"
 
-        raise HTTPException(status_code=r.status_code, detail=error_detail)
+        raise HTTPException(
+            status_code=r.status_code if r else 500, detail=error_detail
+        )

backend/apps/rag/main.py

@@ -8,19 +8,20 @@ from fastapi import (
     Form,
 )
 from fastapi.middleware.cors import CORSMiddleware
-import os, shutil
+import os, shutil, logging, re
 
 from pathlib import Path
 from typing import List
 
-from sentence_transformers import SentenceTransformer
 from chromadb.utils import embedding_functions
+from chromadb.utils.batch_utils import create_batches
 
 from langchain_community.document_loaders import (
     WebBaseLoader,
     TextLoader,
     PyPDFLoader,
     CSVLoader,
+    BSHTMLLoader,
     Docx2txtLoader,
     UnstructuredEPubLoader,
     UnstructuredWordDocumentLoader,
@@ -38,12 +39,23 @@ import uuid
 import json
 
 
+from apps.ollama.main import generate_ollama_embeddings, GenerateEmbeddingsForm
+
 from apps.web.models.documents import (
     Documents,
     DocumentForm,
     DocumentResponse,
 )
 
+from apps.rag.utils import (
+    query_doc,
+    query_embeddings_doc,
+    query_collection,
+    query_embeddings_collection,
+    get_embedding_model_path,
+    generate_openai_embeddings,
+)
+
 from utils.misc import (
     calculate_sha256,
     calculate_sha256_string,
@@ -52,10 +64,13 @@ from utils.misc import (
 )
 from utils.utils import get_current_user, get_admin_user
 from config import (
+    SRC_LOG_LEVELS,
     UPLOAD_DIR,
     DOCS_DIR,
+    RAG_EMBEDDING_ENGINE,
     RAG_EMBEDDING_MODEL,
-    RAG_EMBEDDING_MODEL_DEVICE_TYPE,
+    RAG_EMBEDDING_MODEL_AUTO_UPDATE,
+    DEVICE_TYPE,
     CHROMA_CLIENT,
     CHUNK_SIZE,
     CHUNK_OVERLAP,
@@ -64,25 +79,33 @@ from config import (
 
 from constants import ERROR_MESSAGES
 
-#
-# if RAG_EMBEDDING_MODEL:
-#    sentence_transformer_ef = SentenceTransformer(
-#        model_name_or_path=RAG_EMBEDDING_MODEL,
-#        cache_folder=RAG_EMBEDDING_MODEL_DIR,
-#        device=RAG_EMBEDDING_MODEL_DEVICE_TYPE,
-#    )
-
+log = logging.getLogger(__name__)
+log.setLevel(SRC_LOG_LEVELS["RAG"])
 
 app = FastAPI()
 
+
+app.state.TOP_K = 4
 app.state.CHUNK_SIZE = CHUNK_SIZE
 app.state.CHUNK_OVERLAP = CHUNK_OVERLAP
-app.state.RAG_TEMPLATE = RAG_TEMPLATE
+
+
+app.state.RAG_EMBEDDING_ENGINE = RAG_EMBEDDING_ENGINE
 app.state.RAG_EMBEDDING_MODEL = RAG_EMBEDDING_MODEL
+app.state.RAG_TEMPLATE = RAG_TEMPLATE
+
+app.state.RAG_OPENAI_API_BASE_URL = "https://api.openai.com"
+app.state.RAG_OPENAI_API_KEY = ""
+
+app.state.PDF_EXTRACT_IMAGES = False
+
+
 app.state.sentence_transformer_ef = (
     embedding_functions.SentenceTransformerEmbeddingFunction(
-        model_name=app.state.RAG_EMBEDDING_MODEL,
-        device=RAG_EMBEDDING_MODEL_DEVICE_TYPE,
+        model_name=get_embedding_model_path(
+            app.state.RAG_EMBEDDING_MODEL, RAG_EMBEDDING_MODEL_AUTO_UPDATE
+        ),
+        device=DEVICE_TYPE,
     )
 )
 
@@ -106,33 +129,6 @@ class StoreWebForm(CollectionNameForm):
     url: str
 
 
-def store_data_in_vector_db(data, collection_name) -> bool:
-    text_splitter = RecursiveCharacterTextSplitter(
-        chunk_size=app.state.CHUNK_SIZE, chunk_overlap=app.state.CHUNK_OVERLAP
-    )
-    docs = text_splitter.split_documents(data)
-
-    texts = [doc.page_content for doc in docs]
-    metadatas = [doc.metadata for doc in docs]
-
-    try:
-        collection = CHROMA_CLIENT.create_collection(
-            name=collection_name,
-            embedding_function=app.state.sentence_transformer_ef,
-        )
-
-        collection.add(
-            documents=texts, metadatas=metadatas, ids=[str(uuid.uuid1()) for _ in texts]
-        )
-        return True
-    except Exception as e:
-        print(e)
-        if e.__class__.__name__ == "UniqueConstraintError":
-            return True
-
-        return False
-
-
 @app.get("/")
 async def get_status():
     return {
@@ -140,46 +136,91 @@ async def get_status():
         "chunk_size": app.state.CHUNK_SIZE,
         "chunk_overlap": app.state.CHUNK_OVERLAP,
         "template": app.state.RAG_TEMPLATE,
+        "embedding_engine": app.state.RAG_EMBEDDING_ENGINE,
         "embedding_model": app.state.RAG_EMBEDDING_MODEL,
     }
 
 
-@app.get("/embedding/model")
-async def get_embedding_model(user=Depends(get_admin_user)):
+@app.get("/embedding")
+async def get_embedding_config(user=Depends(get_admin_user)):
     return {
         "status": True,
+        "embedding_engine": app.state.RAG_EMBEDDING_ENGINE,
         "embedding_model": app.state.RAG_EMBEDDING_MODEL,
+        "openai_config": {
+            "url": app.state.RAG_OPENAI_API_BASE_URL,
+            "key": app.state.RAG_OPENAI_API_KEY,
+        },
     }
 
 
+class OpenAIConfigForm(BaseModel):
+    url: str
+    key: str
+
+
 class EmbeddingModelUpdateForm(BaseModel):
+    openai_config: Optional[OpenAIConfigForm] = None
+    embedding_engine: str
     embedding_model: str
 
 
-@app.post("/embedding/model/update")
-async def update_embedding_model(
+@app.post("/embedding/update")
+async def update_embedding_config(
     form_data: EmbeddingModelUpdateForm, user=Depends(get_admin_user)
 ):
-    app.state.RAG_EMBEDDING_MODEL = form_data.embedding_model
-    app.state.sentence_transformer_ef = (
-        embedding_functions.SentenceTransformerEmbeddingFunction(
-            model_name=app.state.RAG_EMBEDDING_MODEL,
-            device=RAG_EMBEDDING_MODEL_DEVICE_TYPE,
-        )
+    log.info(
+        f"Updating embedding model: {app.state.RAG_EMBEDDING_MODEL} to {form_data.embedding_model}"
     )
+    try:
+        app.state.RAG_EMBEDDING_ENGINE = form_data.embedding_engine
 
+        if app.state.RAG_EMBEDDING_ENGINE in ["ollama", "openai"]:
+            app.state.RAG_EMBEDDING_MODEL = form_data.embedding_model
+            app.state.sentence_transformer_ef = None
+
+            if form_data.openai_config != None:
+                app.state.RAG_OPENAI_API_BASE_URL = form_data.openai_config.url
+                app.state.RAG_OPENAI_API_KEY = form_data.openai_config.key
+        else:
+            sentence_transformer_ef = (
+                embedding_functions.SentenceTransformerEmbeddingFunction(
+                    model_name=get_embedding_model_path(
+                        form_data.embedding_model, True
+                    ),
+                    device=DEVICE_TYPE,
+                )
+            )
+            app.state.RAG_EMBEDDING_MODEL = form_data.embedding_model
+            app.state.sentence_transformer_ef = sentence_transformer_ef
+
+        return {
+            "status": True,
+            "embedding_engine": app.state.RAG_EMBEDDING_ENGINE,
+            "embedding_model": app.state.RAG_EMBEDDING_MODEL,
+            "openai_config": {
+                "url": app.state.RAG_OPENAI_API_BASE_URL,
+                "key": app.state.RAG_OPENAI_API_KEY,
+            },
+        }
+
+    except Exception as e:
+        log.exception(f"Problem updating embedding model: {e}")
+        raise HTTPException(
+            status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
+            detail=ERROR_MESSAGES.DEFAULT(e),
+        )
+
+
+@app.get("/config")
+async def get_rag_config(user=Depends(get_admin_user)):
     return {
         "status": True,
-        "embedding_model": app.state.RAG_EMBEDDING_MODEL,
-    }
-
-
-@app.get("/chunk")
-async def get_chunk_params(user=Depends(get_admin_user)):
-    return {
-        "status": True,
-        "chunk_size": app.state.CHUNK_SIZE,
-        "chunk_overlap": app.state.CHUNK_OVERLAP,
+        "pdf_extract_images": app.state.PDF_EXTRACT_IMAGES,
+        "chunk": {
+            "chunk_size": app.state.CHUNK_SIZE,
+            "chunk_overlap": app.state.CHUNK_OVERLAP,
+        },
     }
 
 
@@ -188,17 +229,24 @@ class ChunkParamUpdateForm(BaseModel):
     chunk_overlap: int
 
 
-@app.post("/chunk/update")
-async def update_chunk_params(
-    form_data: ChunkParamUpdateForm, user=Depends(get_admin_user)
-):
-    app.state.CHUNK_SIZE = form_data.chunk_size
-    app.state.CHUNK_OVERLAP = form_data.chunk_overlap
+class ConfigUpdateForm(BaseModel):
+    pdf_extract_images: bool
+    chunk: ChunkParamUpdateForm
+
+
+@app.post("/config/update")
+async def update_rag_config(form_data: ConfigUpdateForm, user=Depends(get_admin_user)):
+    app.state.PDF_EXTRACT_IMAGES = form_data.pdf_extract_images
+    app.state.CHUNK_SIZE = form_data.chunk.chunk_size
+    app.state.CHUNK_OVERLAP = form_data.chunk.chunk_overlap
 
     return {
         "status": True,
-        "chunk_size": app.state.CHUNK_SIZE,
-        "chunk_overlap": app.state.CHUNK_OVERLAP,
+        "pdf_extract_images": app.state.PDF_EXTRACT_IMAGES,
+        "chunk": {
+            "chunk_size": app.state.CHUNK_SIZE,
+            "chunk_overlap": app.state.CHUNK_OVERLAP,
+        },
     }
 
 
@@ -210,40 +258,75 @@ async def get_rag_template(user=Depends(get_current_user)):
     }
 
 
-class RAGTemplateForm(BaseModel):
-    template: str
+@app.get("/query/settings")
+async def get_query_settings(user=Depends(get_admin_user)):
+    return {
+        "status": True,
+        "template": app.state.RAG_TEMPLATE,
+        "k": app.state.TOP_K,
+    }
 
 
-@app.post("/template/update")
-async def update_rag_template(form_data: RAGTemplateForm, user=Depends(get_admin_user)):
-    # TODO: check template requirements
-    app.state.RAG_TEMPLATE = (
-        form_data.template if form_data.template != "" else RAG_TEMPLATE
-    )
+class QuerySettingsForm(BaseModel):
+    k: Optional[int] = None
+    template: Optional[str] = None
+
+
+@app.post("/query/settings/update")
+async def update_query_settings(
+    form_data: QuerySettingsForm, user=Depends(get_admin_user)
+):
+    app.state.RAG_TEMPLATE = form_data.template if form_data.template else RAG_TEMPLATE
+    app.state.TOP_K = form_data.k if form_data.k else 4
     return {"status": True, "template": app.state.RAG_TEMPLATE}
 
 
 class QueryDocForm(BaseModel):
     collection_name: str
     query: str
-    k: Optional[int] = 4
+    k: Optional[int] = None
 
 
 @app.post("/query/doc")
-def query_doc(
+def query_doc_handler(
     form_data: QueryDocForm,
     user=Depends(get_current_user),
 ):
+
     try:
-        # if you use docker use the model from the environment variable
-        collection = CHROMA_CLIENT.get_collection(
-            name=form_data.collection_name,
-            embedding_function=app.state.sentence_transformer_ef,
-        )
-        result = collection.query(query_texts=[form_data.query], n_results=form_data.k)
-        return result
+        if app.state.RAG_EMBEDDING_ENGINE == "":
+            return query_doc(
+                collection_name=form_data.collection_name,
+                query=form_data.query,
+                k=form_data.k if form_data.k else app.state.TOP_K,
+                embedding_function=app.state.sentence_transformer_ef,
+            )
+        else:
+            if app.state.RAG_EMBEDDING_ENGINE == "ollama":
+                query_embeddings = generate_ollama_embeddings(
+                    GenerateEmbeddingsForm(
+                        **{
+                            "model": app.state.RAG_EMBEDDING_MODEL,
+                            "prompt": form_data.query,
+                        }
+                    )
+                )
+            elif app.state.RAG_EMBEDDING_ENGINE == "openai":
+                query_embeddings = generate_openai_embeddings(
+                    model=app.state.RAG_EMBEDDING_MODEL,
+                    text=form_data.query,
+                    key=app.state.RAG_OPENAI_API_KEY,
+                    url=app.state.RAG_OPENAI_API_BASE_URL,
+                )
+
+            return query_embeddings_doc(
+                collection_name=form_data.collection_name,
+                query_embeddings=query_embeddings,
+                k=form_data.k if form_data.k else app.state.TOP_K,
+            )
+
     except Exception as e:
-        print(e)
+        log.exception(e)
         raise HTTPException(
             status_code=status.HTTP_400_BAD_REQUEST,
             detail=ERROR_MESSAGES.DEFAULT(e),
@@ -253,77 +336,53 @@ def query_doc(
 class QueryCollectionsForm(BaseModel):
     collection_names: List[str]
     query: str
-    k: Optional[int] = 4
-
-
-def merge_and_sort_query_results(query_results, k):
-    # Initialize lists to store combined data
-    combined_ids = []
-    combined_distances = []
-    combined_metadatas = []
-    combined_documents = []
-
-    # Combine data from each dictionary
-    for data in query_results:
-        combined_ids.extend(data["ids"][0])
-        combined_distances.extend(data["distances"][0])
-        combined_metadatas.extend(data["metadatas"][0])
-        combined_documents.extend(data["documents"][0])
-
-    # Create a list of tuples (distance, id, metadata, document)
-    combined = list(
-        zip(combined_distances, combined_ids, combined_metadatas, combined_documents)
-    )
-
-    # Sort the list based on distances
-    combined.sort(key=lambda x: x[0])
-
-    # Unzip the sorted list
-    sorted_distances, sorted_ids, sorted_metadatas, sorted_documents = zip(*combined)
-
-    # Slicing the lists to include only k elements
-    sorted_distances = list(sorted_distances)[:k]
-    sorted_ids = list(sorted_ids)[:k]
-    sorted_metadatas = list(sorted_metadatas)[:k]
-    sorted_documents = list(sorted_documents)[:k]
-
-    # Create the output dictionary
-    merged_query_results = {
-        "ids": [sorted_ids],
-        "distances": [sorted_distances],
-        "metadatas": [sorted_metadatas],
-        "documents": [sorted_documents],
-        "embeddings": None,
-        "uris": None,
-        "data": None,
-    }
-
-    return merged_query_results
+    k: Optional[int] = None
 
 
 @app.post("/query/collection")
-def query_collection(
+def query_collection_handler(
     form_data: QueryCollectionsForm,
     user=Depends(get_current_user),
 ):
-    results = []
-
-    for collection_name in form_data.collection_names:
-        try:
-            # if you use docker use the model from the environment variable
-            collection = CHROMA_CLIENT.get_collection(
-                name=collection_name,
+    try:
+        if app.state.RAG_EMBEDDING_ENGINE == "":
+            return query_collection(
+                collection_names=form_data.collection_names,
+                query=form_data.query,
+                k=form_data.k if form_data.k else app.state.TOP_K,
                 embedding_function=app.state.sentence_transformer_ef,
             )
+        else:
 
-            result = collection.query(
-                query_texts=[form_data.query], n_results=form_data.k
+            if app.state.RAG_EMBEDDING_ENGINE == "ollama":
+                query_embeddings = generate_ollama_embeddings(
+                    GenerateEmbeddingsForm(
+                        **{
+                            "model": app.state.RAG_EMBEDDING_MODEL,
+                            "prompt": form_data.query,
+                        }
+                    )
+                )
+            elif app.state.RAG_EMBEDDING_ENGINE == "openai":
+                query_embeddings = generate_openai_embeddings(
+                    model=app.state.RAG_EMBEDDING_MODEL,
+                    text=form_data.query,
+                    key=app.state.RAG_OPENAI_API_KEY,
+                    url=app.state.RAG_OPENAI_API_BASE_URL,
+                )
+
+            return query_embeddings_collection(
+                collection_names=form_data.collection_names,
+                query_embeddings=query_embeddings,
+                k=form_data.k if form_data.k else app.state.TOP_K,
             )
-            results.append(result)
-        except:
-            pass
 
-    return merge_and_sort_query_results(results, form_data.k)
+    except Exception as e:
+        log.exception(e)
+        raise HTTPException(
+            status_code=status.HTTP_400_BAD_REQUEST,
+            detail=ERROR_MESSAGES.DEFAULT(e),
+        )
 
 
 @app.post("/web")
@@ -337,20 +396,118 @@ def store_web(form_data: StoreWebForm, user=Depends(get_current_user)):
         if collection_name == "":
             collection_name = calculate_sha256_string(form_data.url)[:63]
 
-        store_data_in_vector_db(data, collection_name)
+        store_data_in_vector_db(data, collection_name, overwrite=True)
         return {
             "status": True,
             "collection_name": collection_name,
             "filename": form_data.url,
         }
     except Exception as e:
-        print(e)
+        log.exception(e)
         raise HTTPException(
             status_code=status.HTTP_400_BAD_REQUEST,
             detail=ERROR_MESSAGES.DEFAULT(e),
         )
 
 
+def store_data_in_vector_db(data, collection_name, overwrite: bool = False) -> bool:
+
+    text_splitter = RecursiveCharacterTextSplitter(
+        chunk_size=app.state.CHUNK_SIZE,
+        chunk_overlap=app.state.CHUNK_OVERLAP,
+        add_start_index=True,
+    )
+
+    docs = text_splitter.split_documents(data)
+
+    if len(docs) > 0:
+        log.info(f"store_data_in_vector_db {docs}")
+        return store_docs_in_vector_db(docs, collection_name, overwrite), None
+    else:
+        raise ValueError(ERROR_MESSAGES.EMPTY_CONTENT)
+
+
+def store_text_in_vector_db(
+    text, metadata, collection_name, overwrite: bool = False
+) -> bool:
+    text_splitter = RecursiveCharacterTextSplitter(
+        chunk_size=app.state.CHUNK_SIZE,
+        chunk_overlap=app.state.CHUNK_OVERLAP,
+        add_start_index=True,
+    )
+    docs = text_splitter.create_documents([text], metadatas=[metadata])
+    return store_docs_in_vector_db(docs, collection_name, overwrite)
+
+
+def store_docs_in_vector_db(docs, collection_name, overwrite: bool = False) -> bool:
+    log.info(f"store_docs_in_vector_db {docs} {collection_name}")
+
+    texts = [doc.page_content for doc in docs]
+    metadatas = [doc.metadata for doc in docs]
+
+    try:
+        if overwrite:
+            for collection in CHROMA_CLIENT.list_collections():
+                if collection_name == collection.name:
+                    log.info(f"deleting existing collection {collection_name}")
+                    CHROMA_CLIENT.delete_collection(name=collection_name)
+
+        if app.state.RAG_EMBEDDING_ENGINE == "":
+
+            collection = CHROMA_CLIENT.create_collection(
+                name=collection_name,
+                embedding_function=app.state.sentence_transformer_ef,
+            )
+
+            for batch in create_batches(
+                api=CHROMA_CLIENT,
+                ids=[str(uuid.uuid1()) for _ in texts],
+                metadatas=metadatas,
+                documents=texts,
+            ):
+                collection.add(*batch)
+
+        else:
+            collection = CHROMA_CLIENT.create_collection(name=collection_name)
+
+            if app.state.RAG_EMBEDDING_ENGINE == "ollama":
+                embeddings = [
+                    generate_ollama_embeddings(
+                        GenerateEmbeddingsForm(
+                            **{"model": app.state.RAG_EMBEDDING_MODEL, "prompt": text}
+                        )
+                    )
+                    for text in texts
+                ]
+            elif app.state.RAG_EMBEDDING_ENGINE == "openai":
+                embeddings = [
+                    generate_openai_embeddings(
+                        model=app.state.RAG_EMBEDDING_MODEL,
+                        text=text,
+                        key=app.state.RAG_OPENAI_API_KEY,
+                        url=app.state.RAG_OPENAI_API_BASE_URL,
+                    )
+                    for text in texts
+                ]
+
+            for batch in create_batches(
+                api=CHROMA_CLIENT,
+                ids=[str(uuid.uuid1()) for _ in texts],
+                metadatas=metadatas,
+                embeddings=embeddings,
+                documents=texts,
+            ):
+                collection.add(*batch)
+
+        return True
+    except Exception as e:
+        log.exception(e)
+        if e.__class__.__name__ == "UniqueConstraintError":
+            return True
+
+        return False
+
+
 def get_loader(filename: str, file_content_type: str, file_path: str):
     file_ext = filename.split(".")[-1].lower()
     known_type = True
@@ -401,13 +558,15 @@ def get_loader(filename: str, file_content_type: str, file_path: str):
     ]
 
     if file_ext == "pdf":
-        loader = PyPDFLoader(file_path)
+        loader = PyPDFLoader(file_path, extract_images=app.state.PDF_EXTRACT_IMAGES)
     elif file_ext == "csv":
         loader = CSVLoader(file_path)
     elif file_ext == "rst":
         loader = UnstructuredRSTLoader(file_path, mode="elements")
     elif file_ext == "xml":
         loader = UnstructuredXMLLoader(file_path)
+    elif file_ext in ["htm", "html"]:
+        loader = BSHTMLLoader(file_path, open_encoding="unicode_escape")
     elif file_ext == "md":
         loader = UnstructuredMarkdownLoader(file_path)
     elif file_content_type == "application/epub+zip":
@@ -423,10 +582,12 @@ def get_loader(filename: str, file_content_type: str, file_path: str):
         "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
     ] or file_ext in ["xls", "xlsx"]:
         loader = UnstructuredExcelLoader(file_path)
-    elif file_ext in known_source_ext or (file_content_type and file_content_type.find("text/") >= 0):
-        loader = TextLoader(file_path)
+    elif file_ext in known_source_ext or (
+        file_content_type and file_content_type.find("text/") >= 0
+    ):
+        loader = TextLoader(file_path, autodetect_encoding=True)
     else:
-        loader = TextLoader(file_path)
+        loader = TextLoader(file_path, autodetect_encoding=True)
         known_type = False
 
     return loader, known_type
@@ -440,10 +601,13 @@ def store_doc(
 ):
     # "https://www.gutenberg.org/files/1727/1727-h/1727-h.htm"
 
-    print(file.content_type)
+    log.info(f"file.content_type: {file.content_type}")
     try:
-        filename = file.filename
+        unsanitized_filename = file.filename
+        filename = os.path.basename(unsanitized_filename)
+
         file_path = f"{UPLOAD_DIR}/{filename}"
+
         contents = file.file.read()
         with open(file_path, "wb") as f:
             f.write(contents)
@@ -454,24 +618,26 @@ def store_doc(
             collection_name = calculate_sha256(f)[:63]
         f.close()
 
-        loader, known_type = get_loader(file.filename, file.content_type, file_path)
+        loader, known_type = get_loader(filename, file.content_type, file_path)
         data = loader.load()
-        result = store_data_in_vector_db(data, collection_name)
 
-        if result:
-            return {
-                "status": True,
-                "collection_name": collection_name,
-                "filename": filename,
-                "known_type": known_type,
-            }
-        else:
+        try:
+            result = store_data_in_vector_db(data, collection_name)
+
+            if result:
+                return {
+                    "status": True,
+                    "collection_name": collection_name,
+                    "filename": filename,
+                    "known_type": known_type,
+                }
+        except Exception as e:
             raise HTTPException(
                 status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
-                detail=ERROR_MESSAGES.DEFAULT(),
+                detail=e,
             )
     except Exception as e:
-        print(e)
+        log.exception(e)
         if "No pandoc was found" in str(e):
             raise HTTPException(
                 status_code=status.HTTP_400_BAD_REQUEST,
@@ -484,6 +650,37 @@ def store_doc(
             )
 
 
+class TextRAGForm(BaseModel):
+    name: str
+    content: str
+    collection_name: Optional[str] = None
+
+
+@app.post("/text")
+def store_text(
+    form_data: TextRAGForm,
+    user=Depends(get_current_user),
+):
+
+    collection_name = form_data.collection_name
+    if collection_name == None:
+        collection_name = calculate_sha256_string(form_data.content)
+
+    result = store_text_in_vector_db(
+        form_data.content,
+        metadata={"name": form_data.name, "created_by": user.id},
+        collection_name=collection_name,
+    )
+
+    if result:
+        return {"status": True, "collection_name": collection_name}
+    else:
+        raise HTTPException(
+            status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
+            detail=ERROR_MESSAGES.DEFAULT(),
+        )
+
+
 @app.get("/scan")
 def scan_docs_dir(user=Depends(get_admin_user)):
     for path in Path(DOCS_DIR).rglob("./**/*"):
@@ -502,41 +699,45 @@ def scan_docs_dir(user=Depends(get_admin_user)):
                 )
                 data = loader.load()
 
-                result = store_data_in_vector_db(data, collection_name)
+                try:
+                    result = store_data_in_vector_db(data, collection_name)
 
-                if result:
-                    sanitized_filename = sanitize_filename(filename)
-                    doc = Documents.get_doc_by_name(sanitized_filename)
+                    if result:
+                        sanitized_filename = sanitize_filename(filename)
+                        doc = Documents.get_doc_by_name(sanitized_filename)
 
-                    if doc == None:
-                        doc = Documents.insert_new_doc(
-                            user.id,
-                            DocumentForm(
-                                **{
-                                    "name": sanitized_filename,
-                                    "title": filename,
-                                    "collection_name": collection_name,
-                                    "filename": filename,
-                                    "content": (
-                                        json.dumps(
-                                            {
-                                                "tags": list(
-                                                    map(
-                                                        lambda name: {"name": name},
-                                                        tags,
+                        if doc == None:
+                            doc = Documents.insert_new_doc(
+                                user.id,
+                                DocumentForm(
+                                    **{
+                                        "name": sanitized_filename,
+                                        "title": filename,
+                                        "collection_name": collection_name,
+                                        "filename": filename,
+                                        "content": (
+                                            json.dumps(
+                                                {
+                                                    "tags": list(
+                                                        map(
+                                                            lambda name: {"name": name},
+                                                            tags,
+                                                        )
                                                     )
-                                                )
-                                            }
-                                        )
-                                        if len(tags)
-                                        else "{}"
-                                    ),
-                                }
-                            ),
-                        )
+                                                }
+                                            )
+                                            if len(tags)
+                                            else "{}"
+                                        ),
+                                    }
+                                ),
+                            )
+                except Exception as e:
+                    log.exception(e)
+                    pass
 
         except Exception as e:
-            print(e)
+            log.exception(e)
 
     return True
 
@@ -557,11 +758,11 @@ def reset(user=Depends(get_admin_user)) -> bool:
             elif os.path.isdir(file_path):
                 shutil.rmtree(file_path)
         except Exception as e:
-            print("Failed to delete %s. Reason: %s" % (file_path, e))
+            log.error("Failed to delete %s. Reason: %s" % (file_path, e))
 
     try:
         CHROMA_CLIENT.reset()
     except Exception as e:
-        print(e)
+        log.exception(e)
 
     return True

backend/apps/rag/utils.py

@@ -0,0 +1,346 @@
+import os
+import re
+import logging
+from typing import List
+import requests
+
+
+from huggingface_hub import snapshot_download
+from apps.ollama.main import generate_ollama_embeddings, GenerateEmbeddingsForm
+
+
+from config import SRC_LOG_LEVELS, CHROMA_CLIENT
+
+
+log = logging.getLogger(__name__)
+log.setLevel(SRC_LOG_LEVELS["RAG"])
+
+
+def query_doc(collection_name: str, query: str, k: int, embedding_function):
+    try:
+        # if you use docker use the model from the environment variable
+        collection = CHROMA_CLIENT.get_collection(
+            name=collection_name,
+            embedding_function=embedding_function,
+        )
+        result = collection.query(
+            query_texts=[query],
+            n_results=k,
+        )
+        return result
+    except Exception as e:
+        raise e
+
+
+def query_embeddings_doc(collection_name: str, query_embeddings, k: int):
+    try:
+        # if you use docker use the model from the environment variable
+        log.info(f"query_embeddings_doc {query_embeddings}")
+        collection = CHROMA_CLIENT.get_collection(
+            name=collection_name,
+        )
+        result = collection.query(
+            query_embeddings=[query_embeddings],
+            n_results=k,
+        )
+
+        log.info(f"query_embeddings_doc:result {result}")
+        return result
+    except Exception as e:
+        raise e
+
+
+def merge_and_sort_query_results(query_results, k):
+    # Initialize lists to store combined data
+    combined_ids = []
+    combined_distances = []
+    combined_metadatas = []
+    combined_documents = []
+
+    # Combine data from each dictionary
+    for data in query_results:
+        combined_ids.extend(data["ids"][0])
+        combined_distances.extend(data["distances"][0])
+        combined_metadatas.extend(data["metadatas"][0])
+        combined_documents.extend(data["documents"][0])
+
+    # Create a list of tuples (distance, id, metadata, document)
+    combined = list(
+        zip(combined_distances, combined_ids, combined_metadatas, combined_documents)
+    )
+
+    # Sort the list based on distances
+    combined.sort(key=lambda x: x[0])
+
+    # Unzip the sorted list
+    sorted_distances, sorted_ids, sorted_metadatas, sorted_documents = zip(*combined)
+
+    # Slicing the lists to include only k elements
+    sorted_distances = list(sorted_distances)[:k]
+    sorted_ids = list(sorted_ids)[:k]
+    sorted_metadatas = list(sorted_metadatas)[:k]
+    sorted_documents = list(sorted_documents)[:k]
+
+    # Create the output dictionary
+    merged_query_results = {
+        "ids": [sorted_ids],
+        "distances": [sorted_distances],
+        "metadatas": [sorted_metadatas],
+        "documents": [sorted_documents],
+        "embeddings": None,
+        "uris": None,
+        "data": None,
+    }
+
+    return merged_query_results
+
+
+def query_collection(
+    collection_names: List[str], query: str, k: int, embedding_function
+):
+
+    results = []
+
+    for collection_name in collection_names:
+        try:
+            # if you use docker use the model from the environment variable
+            collection = CHROMA_CLIENT.get_collection(
+                name=collection_name,
+                embedding_function=embedding_function,
+            )
+
+            result = collection.query(
+                query_texts=[query],
+                n_results=k,
+            )
+            results.append(result)
+        except:
+            pass
+
+    return merge_and_sort_query_results(results, k)
+
+
+def query_embeddings_collection(collection_names: List[str], query_embeddings, k: int):
+
+    results = []
+    log.info(f"query_embeddings_collection {query_embeddings}")
+
+    for collection_name in collection_names:
+        try:
+            collection = CHROMA_CLIENT.get_collection(name=collection_name)
+
+            result = collection.query(
+                query_embeddings=[query_embeddings],
+                n_results=k,
+            )
+            results.append(result)
+        except:
+            pass
+
+    return merge_and_sort_query_results(results, k)
+
+
+def rag_template(template: str, context: str, query: str):
+    template = template.replace("[context]", context)
+    template = template.replace("[query]", query)
+    return template
+
+
+def rag_messages(
+    docs,
+    messages,
+    template,
+    k,
+    embedding_engine,
+    embedding_model,
+    embedding_function,
+    openai_key,
+    openai_url,
+):
+    log.debug(
+        f"docs: {docs} {messages} {embedding_engine} {embedding_model} {embedding_function} {openai_key} {openai_url}"
+    )
+
+    last_user_message_idx = None
+    for i in range(len(messages) - 1, -1, -1):
+        if messages[i]["role"] == "user":
+            last_user_message_idx = i
+            break
+
+    user_message = messages[last_user_message_idx]
+
+    if isinstance(user_message["content"], list):
+        # Handle list content input
+        content_type = "list"
+        query = ""
+        for content_item in user_message["content"]:
+            if content_item["type"] == "text":
+                query = content_item["text"]
+                break
+    elif isinstance(user_message["content"], str):
+        # Handle text content input
+        content_type = "text"
+        query = user_message["content"]
+    else:
+        # Fallback in case the input does not match expected types
+        content_type = None
+        query = ""
+
+    relevant_contexts = []
+
+    for doc in docs:
+        context = None
+
+        try:
+
+            if doc["type"] == "text":
+                context = doc["content"]
+            else:
+                if embedding_engine == "":
+                    if doc["type"] == "collection":
+                        context = query_collection(
+                            collection_names=doc["collection_names"],
+                            query=query,
+                            k=k,
+                            embedding_function=embedding_function,
+                        )
+                    else:
+                        context = query_doc(
+                            collection_name=doc["collection_name"],
+                            query=query,
+                            k=k,
+                            embedding_function=embedding_function,
+                        )
+
+                else:
+                    if embedding_engine == "ollama":
+                        query_embeddings = generate_ollama_embeddings(
+                            GenerateEmbeddingsForm(
+                                **{
+                                    "model": embedding_model,
+                                    "prompt": query,
+                                }
+                            )
+                        )
+                    elif embedding_engine == "openai":
+                        query_embeddings = generate_openai_embeddings(
+                            model=embedding_model,
+                            text=query,
+                            key=openai_key,
+                            url=openai_url,
+                        )
+
+                    if doc["type"] == "collection":
+                        context = query_embeddings_collection(
+                            collection_names=doc["collection_names"],
+                            query_embeddings=query_embeddings,
+                            k=k,
+                        )
+                    else:
+                        context = query_embeddings_doc(
+                            collection_name=doc["collection_name"],
+                            query_embeddings=query_embeddings,
+                            k=k,
+                        )
+
+        except Exception as e:
+            log.exception(e)
+            context = None
+
+        relevant_contexts.append(context)
+
+    log.debug(f"relevant_contexts: {relevant_contexts}")
+
+    context_string = ""
+    for context in relevant_contexts:
+        if context:
+            context_string += " ".join(context["documents"][0]) + "\n"
+
+    ra_content = rag_template(
+        template=template,
+        context=context_string,
+        query=query,
+    )
+
+    if content_type == "list":
+        new_content = []
+        for content_item in user_message["content"]:
+            if content_item["type"] == "text":
+                # Update the text item's content with ra_content
+                new_content.append({"type": "text", "text": ra_content})
+            else:
+                # Keep other types of content as they are
+                new_content.append(content_item)
+        new_user_message = {**user_message, "content": new_content}
+    else:
+        new_user_message = {
+            **user_message,
+            "content": ra_content,
+        }
+
+    messages[last_user_message_idx] = new_user_message
+
+    return messages
+
+
+def get_embedding_model_path(
+    embedding_model: str, update_embedding_model: bool = False
+):
+    # Construct huggingface_hub kwargs with local_files_only to return the snapshot path
+    cache_dir = os.getenv("SENTENCE_TRANSFORMERS_HOME")
+
+    local_files_only = not update_embedding_model
+
+    snapshot_kwargs = {
+        "cache_dir": cache_dir,
+        "local_files_only": local_files_only,
+    }
+
+    log.debug(f"embedding_model: {embedding_model}")
+    log.debug(f"snapshot_kwargs: {snapshot_kwargs}")
+
+    # Inspiration from upstream sentence_transformers
+    if (
+        os.path.exists(embedding_model)
+        or ("\\" in embedding_model or embedding_model.count("/") > 1)
+        and local_files_only
+    ):
+        # If fully qualified path exists, return input, else set repo_id
+        return embedding_model
+    elif "/" not in embedding_model:
+        # Set valid repo_id for model short-name
+        embedding_model = "sentence-transformers" + "/" + embedding_model
+
+    snapshot_kwargs["repo_id"] = embedding_model
+
+    # Attempt to query the huggingface_hub library to determine the local path and/or to update
+    try:
+        embedding_model_repo_path = snapshot_download(**snapshot_kwargs)
+        log.debug(f"embedding_model_repo_path: {embedding_model_repo_path}")
+        return embedding_model_repo_path
+    except Exception as e:
+        log.exception(f"Cannot determine embedding model snapshot path: {e}")
+        return embedding_model
+
+
+def generate_openai_embeddings(
+    model: str, text: str, key: str, url: str = "https://api.openai.com"
+):
+    try:
+        r = requests.post(
+            f"{url}/v1/embeddings",
+            headers={
+                "Content-Type": "application/json",
+                "Authorization": f"Bearer {key}",
+            },
+            json={"input": text, "model": model},
+        )
+        r.raise_for_status()
+        data = r.json()
+        if "data" in data:
+            return data["data"][0]["embedding"]
+        else:
+            raise "Something went wrong :/"
+    except Exception as e:
+        print(e)
+        return None

backend/apps/web/internal/db.py

@@ -1,6 +1,22 @@
 from peewee import *
-from config import DATA_DIR
+from peewee_migrate import Router
+from config import SRC_LOG_LEVELS, DATA_DIR
+import os
+import logging
+
+log = logging.getLogger(__name__)
+log.setLevel(SRC_LOG_LEVELS["DB"])
+
+# Check if the file exists
+if os.path.exists(f"{DATA_DIR}/ollama.db"):
+    # Rename the file
+    os.rename(f"{DATA_DIR}/ollama.db", f"{DATA_DIR}/webui.db")
+    log.info("File renamed successfully.")
+else:
+    pass
 
 
-DB = SqliteDatabase(f"{DATA_DIR}/ollama.db")
-DB.connect()
+DB = SqliteDatabase(f"{DATA_DIR}/webui.db")
+router = Router(DB, migrate_dir="apps/web/internal/migrations", logger=log)
+router.run()
+DB.connect(reuse_if_open=True)

backend/apps/web/internal/migrations/001_initial_schema.py

@@ -0,0 +1,149 @@
+"""Peewee migrations -- 001_initial_schema.py.
+
+Some examples (model - class or model name)::
+
+    > Model = migrator.orm['table_name']            # Return model in current state by name
+    > Model = migrator.ModelClass                   # Return model in current state by name
+
+    > migrator.sql(sql)                             # Run custom SQL
+    > migrator.run(func, *args, **kwargs)           # Run python function with the given args
+    > migrator.create_model(Model)                  # Create a model (could be used as decorator)
+    > migrator.remove_model(model, cascade=True)    # Remove a model
+    > migrator.add_fields(model, **fields)          # Add fields to a model
+    > migrator.change_fields(model, **fields)       # Change fields
+    > migrator.remove_fields(model, *field_names, cascade=True)
+    > migrator.rename_field(model, old_field_name, new_field_name)
+    > migrator.rename_table(model, new_table_name)
+    > migrator.add_index(model, *col_names, unique=False)
+    > migrator.add_not_null(model, *field_names)
+    > migrator.add_default(model, field_name, default)
+    > migrator.add_constraint(model, name, sql)
+    > migrator.drop_index(model, *col_names)
+    > migrator.drop_not_null(model, *field_names)
+    > migrator.drop_constraints(model, *constraints)
+
+"""
+
+from contextlib import suppress
+
+import peewee as pw
+from peewee_migrate import Migrator
+
+
+with suppress(ImportError):
+    import playhouse.postgres_ext as pw_pext
+
+
+def migrate(migrator: Migrator, database: pw.Database, *, fake=False):
+    """Write your migrations here."""
+
+    @migrator.create_model
+    class Auth(pw.Model):
+        id = pw.CharField(max_length=255, unique=True)
+        email = pw.CharField(max_length=255)
+        password = pw.CharField(max_length=255)
+        active = pw.BooleanField()
+
+        class Meta:
+            table_name = "auth"
+
+    @migrator.create_model
+    class Chat(pw.Model):
+        id = pw.CharField(max_length=255, unique=True)
+        user_id = pw.CharField(max_length=255)
+        title = pw.CharField()
+        chat = pw.TextField()
+        timestamp = pw.DateField()
+
+        class Meta:
+            table_name = "chat"
+
+    @migrator.create_model
+    class ChatIdTag(pw.Model):
+        id = pw.CharField(max_length=255, unique=True)
+        tag_name = pw.CharField(max_length=255)
+        chat_id = pw.CharField(max_length=255)
+        user_id = pw.CharField(max_length=255)
+        timestamp = pw.DateField()
+
+        class Meta:
+            table_name = "chatidtag"
+
+    @migrator.create_model
+    class Document(pw.Model):
+        id = pw.AutoField()
+        collection_name = pw.CharField(max_length=255, unique=True)
+        name = pw.CharField(max_length=255, unique=True)
+        title = pw.CharField()
+        filename = pw.CharField()
+        content = pw.TextField(null=True)
+        user_id = pw.CharField(max_length=255)
+        timestamp = pw.DateField()
+
+        class Meta:
+            table_name = "document"
+
+    @migrator.create_model
+    class Modelfile(pw.Model):
+        id = pw.AutoField()
+        tag_name = pw.CharField(max_length=255, unique=True)
+        user_id = pw.CharField(max_length=255)
+        modelfile = pw.TextField()
+        timestamp = pw.DateField()
+
+        class Meta:
+            table_name = "modelfile"
+
+    @migrator.create_model
+    class Prompt(pw.Model):
+        id = pw.AutoField()
+        command = pw.CharField(max_length=255, unique=True)
+        user_id = pw.CharField(max_length=255)
+        title = pw.CharField()
+        content = pw.TextField()
+        timestamp = pw.DateField()
+
+        class Meta:
+            table_name = "prompt"
+
+    @migrator.create_model
+    class Tag(pw.Model):
+        id = pw.CharField(max_length=255, unique=True)
+        name = pw.CharField(max_length=255)
+        user_id = pw.CharField(max_length=255)
+        data = pw.TextField(null=True)
+
+        class Meta:
+            table_name = "tag"
+
+    @migrator.create_model
+    class User(pw.Model):
+        id = pw.CharField(max_length=255, unique=True)
+        name = pw.CharField(max_length=255)
+        email = pw.CharField(max_length=255)
+        role = pw.CharField(max_length=255)
+        profile_image_url = pw.CharField(max_length=255)
+        timestamp = pw.DateField()
+
+        class Meta:
+            table_name = "user"
+
+
+def rollback(migrator: Migrator, database: pw.Database, *, fake=False):
+    """Write your rollback migrations here."""
+
+    migrator.remove_model("user")
+
+    migrator.remove_model("tag")
+
+    migrator.remove_model("prompt")
+
+    migrator.remove_model("modelfile")
+
+    migrator.remove_model("document")
+
+    migrator.remove_model("chatidtag")
+
+    migrator.remove_model("chat")
+
+    migrator.remove_model("auth")

backend/apps/web/internal/migrations/002_add_local_sharing.py

@@ -0,0 +1,48 @@
+"""Peewee migrations -- 002_add_local_sharing.py.
+
+Some examples (model - class or model name)::
+
+    > Model = migrator.orm['table_name']            # Return model in current state by name
+    > Model = migrator.ModelClass                   # Return model in current state by name
+
+    > migrator.sql(sql)                             # Run custom SQL
+    > migrator.run(func, *args, **kwargs)           # Run python function with the given args
+    > migrator.create_model(Model)                  # Create a model (could be used as decorator)
+    > migrator.remove_model(model, cascade=True)    # Remove a model
+    > migrator.add_fields(model, **fields)          # Add fields to a model
+    > migrator.change_fields(model, **fields)       # Change fields
+    > migrator.remove_fields(model, *field_names, cascade=True)
+    > migrator.rename_field(model, old_field_name, new_field_name)
+    > migrator.rename_table(model, new_table_name)
+    > migrator.add_index(model, *col_names, unique=False)
+    > migrator.add_not_null(model, *field_names)
+    > migrator.add_default(model, field_name, default)
+    > migrator.add_constraint(model, name, sql)
+    > migrator.drop_index(model, *col_names)
+    > migrator.drop_not_null(model, *field_names)
+    > migrator.drop_constraints(model, *constraints)
+
+"""
+
+from contextlib import suppress
+
+import peewee as pw
+from peewee_migrate import Migrator
+
+
+with suppress(ImportError):
+    import playhouse.postgres_ext as pw_pext
+
+
+def migrate(migrator: Migrator, database: pw.Database, *, fake=False):
+    """Write your migrations here."""
+
+    migrator.add_fields(
+        "chat", share_id=pw.CharField(max_length=255, null=True, unique=True)
+    )
+
+
+def rollback(migrator: Migrator, database: pw.Database, *, fake=False):
+    """Write your rollback migrations here."""
+
+    migrator.remove_fields("chat", "share_id")

backend/apps/web/internal/migrations/003_add_auth_api_key.py

@@ -0,0 +1,48 @@
+"""Peewee migrations -- 002_add_local_sharing.py.
+
+Some examples (model - class or model name)::
+
+    > Model = migrator.orm['table_name']            # Return model in current state by name
+    > Model = migrator.ModelClass                   # Return model in current state by name
+
+    > migrator.sql(sql)                             # Run custom SQL
+    > migrator.run(func, *args, **kwargs)           # Run python function with the given args
+    > migrator.create_model(Model)                  # Create a model (could be used as decorator)
+    > migrator.remove_model(model, cascade=True)    # Remove a model
+    > migrator.add_fields(model, **fields)          # Add fields to a model
+    > migrator.change_fields(model, **fields)       # Change fields
+    > migrator.remove_fields(model, *field_names, cascade=True)
+    > migrator.rename_field(model, old_field_name, new_field_name)
+    > migrator.rename_table(model, new_table_name)
+    > migrator.add_index(model, *col_names, unique=False)
+    > migrator.add_not_null(model, *field_names)
+    > migrator.add_default(model, field_name, default)
+    > migrator.add_constraint(model, name, sql)
+    > migrator.drop_index(model, *col_names)
+    > migrator.drop_not_null(model, *field_names)
+    > migrator.drop_constraints(model, *constraints)
+
+"""
+
+from contextlib import suppress
+
+import peewee as pw
+from peewee_migrate import Migrator
+
+
+with suppress(ImportError):
+    import playhouse.postgres_ext as pw_pext
+
+
+def migrate(migrator: Migrator, database: pw.Database, *, fake=False):
+    """Write your migrations here."""
+
+    migrator.add_fields(
+        "user", api_key=pw.CharField(max_length=255, null=True, unique=True)
+    )
+
+
+def rollback(migrator: Migrator, database: pw.Database, *, fake=False):
+    """Write your rollback migrations here."""
+
+    migrator.remove_fields("user", "api_key")

backend/apps/web/internal/migrations/README.md

@@ -0,0 +1,21 @@
+# Database Migrations
+
+This directory contains all the database migrations for the web app.
+Migrations are done using the [`peewee-migrate`](https://github.com/klen/peewee_migrate) library.
+
+Migrations are automatically ran at app startup.
+
+## Creating a migration
+
+Have you made a change to the schema of an existing model?
+You will need to create a migration file to ensure that existing databases are updated for backwards compatibility.
+
+1. Have a database file (`webui.db`) that has the old schema prior to any of your changes.
+2. Make your changes to the models.
+3. From the `backend` directory, run the following command:
+   ```bash
+   pw_migrate create --auto --auto-source apps.web.models --database sqlite:///${SQLITE_DB} --directory apps/web/internal/migrations ${MIGRATION_NAME}
+   ```
+   - `$SQLITE_DB` should be the path to the database file.
+   - `$MIGRATION_NAME` should be a descriptive name for the migration.
+4. The migration file will be created in the `apps/web/internal/migrations` directory.

backend/apps/web/main.py

@@ -19,6 +19,8 @@ from config import (
     DEFAULT_USER_ROLE,
     ENABLE_SIGNUP,
     USER_PERMISSIONS,
+    WEBHOOK_URL,
+    WEBUI_AUTH_TRUSTED_EMAIL_HEADER,
 )
 
 app = FastAPI()
@@ -32,7 +34,8 @@ app.state.DEFAULT_MODELS = DEFAULT_MODELS
 app.state.DEFAULT_PROMPT_SUGGESTIONS = DEFAULT_PROMPT_SUGGESTIONS
 app.state.DEFAULT_USER_ROLE = DEFAULT_USER_ROLE
 app.state.USER_PERMISSIONS = USER_PERMISSIONS
-
+app.state.WEBHOOK_URL = WEBHOOK_URL
+app.state.AUTH_TRUSTED_EMAIL_HEADER = WEBUI_AUTH_TRUSTED_EMAIL_HEADER
 
 app.add_middleware(
     CORSMiddleware,

backend/apps/web/models/auths.py

@@ -2,6 +2,7 @@ from pydantic import BaseModel
 from typing import List, Union, Optional
 import time
 import uuid
+import logging
 from peewee import *
 
 from apps.web.models.users import UserModel, Users
@@ -9,6 +10,11 @@ from utils.utils import verify_password
 
 from apps.web.internal.db import DB
 
+from config import SRC_LOG_LEVELS
+
+log = logging.getLogger(__name__)
+log.setLevel(SRC_LOG_LEVELS["MODELS"])
+
 ####################
 # DB MODEL
 ####################
@@ -41,6 +47,10 @@ class Token(BaseModel):
     token_type: str
 
 
+class ApiKey(BaseModel):
+    api_key: Optional[str] = None
+
+
 class UserResponse(BaseModel):
     id: str
     email: str
@@ -76,6 +86,7 @@ class SignupForm(BaseModel):
     name: str
     email: str
     password: str
+    profile_image_url: Optional[str] = "/user.png"
 
 
 class AuthsTable:
@@ -84,9 +95,14 @@ class AuthsTable:
         self.db.create_tables([Auth])
 
     def insert_new_auth(
-        self, email: str, password: str, name: str, role: str = "pending"
+        self,
+        email: str,
+        password: str,
+        name: str,
+        profile_image_url: str = "/user.png",
+        role: str = "pending",
     ) -> Optional[UserModel]:
-        print("insert_new_auth")
+        log.info("insert_new_auth")
 
         id = str(uuid.uuid4())
 
@@ -95,7 +111,7 @@ class AuthsTable:
         )
         result = Auth.create(**auth.model_dump())
 
-        user = Users.insert_new_user(id, name, email, role)
+        user = Users.insert_new_user(id, name, email, profile_image_url, role)
 
         if result and user:
             return user
@@ -103,7 +119,7 @@ class AuthsTable:
             return None
 
     def authenticate_user(self, email: str, password: str) -> Optional[UserModel]:
-        print("authenticate_user", email)
+        log.info(f"authenticate_user: {email}")
         try:
             auth = Auth.get(Auth.email == email, Auth.active == True)
             if auth:
@@ -117,6 +133,28 @@ class AuthsTable:
         except:
             return None
 
+    def authenticate_user_by_api_key(self, api_key: str) -> Optional[UserModel]:
+        log.info(f"authenticate_user_by_api_key: {api_key}")
+        # if no api_key, return None
+        if not api_key:
+            return None
+
+        try:
+            user = Users.get_user_by_api_key(api_key)
+            return user if user else None
+        except:
+            return False
+
+    def authenticate_user_by_trusted_header(self, email: str) -> Optional[UserModel]:
+        log.info(f"authenticate_user_by_trusted_header: {email}")
+        try:
+            auth = Auth.get(Auth.email == email, Auth.active == True)
+            if auth:
+                user = Users.get_user_by_id(auth.id)
+                return user
+        except:
+            return None
+
     def update_user_password_by_id(self, id: str, new_password: str) -> bool:
         try:
             query = Auth.update(password=new_password).where(Auth.id == id)

backend/apps/web/models/chats.py

@@ -20,6 +20,7 @@ class Chat(Model):
     title = CharField()
     chat = TextField()  # Save Chat JSON as Text
     timestamp = DateField()
+    share_id = CharField(null=True, unique=True)
 
     class Meta:
         database = DB
@@ -31,6 +32,7 @@ class ChatModel(BaseModel):
     title: str
     chat: str
     timestamp: int  # timestamp in epoch
+    share_id: Optional[str] = None
 
 
 ####################
@@ -52,6 +54,7 @@ class ChatResponse(BaseModel):
     title: str
     chat: dict
     timestamp: int  # timestamp in epoch
+    share_id: Optional[str] = None  # id of the chat to be shared
 
 
 class ChatTitleIdResponse(BaseModel):
@@ -95,12 +98,63 @@ class ChatTable:
         except:
             return None
 
-    def update_chat_by_id(self, id: str, chat: dict) -> Optional[ChatModel]:
+    def insert_shared_chat_by_chat_id(self, chat_id: str) -> Optional[ChatModel]:
+        # Get the existing chat to share
+        chat = Chat.get(Chat.id == chat_id)
+        # Check if the chat is already shared
+        if chat.share_id:
+            return self.get_chat_by_id_and_user_id(chat.share_id, "shared")
+        # Create a new chat with the same data, but with a new ID
+        shared_chat = ChatModel(
+            **{
+                "id": str(uuid.uuid4()),
+                "user_id": f"shared-{chat_id}",
+                "title": chat.title,
+                "chat": chat.chat,
+                "timestamp": int(time.time()),
+            }
+        )
+        shared_result = Chat.create(**shared_chat.model_dump())
+        # Update the original chat with the share_id
+        result = (
+            Chat.update(share_id=shared_chat.id).where(Chat.id == chat_id).execute()
+        )
+
+        return shared_chat if (shared_result and result) else None
+
+    def update_shared_chat_by_chat_id(self, chat_id: str) -> Optional[ChatModel]:
+        try:
+            print("update_shared_chat_by_id")
+            chat = Chat.get(Chat.id == chat_id)
+            print(chat)
+
+            query = Chat.update(
+                title=chat.title,
+                chat=chat.chat,
+            ).where(Chat.id == chat.share_id)
+
+            query.execute()
+
+            chat = Chat.get(Chat.id == chat.share_id)
+            return ChatModel(**model_to_dict(chat))
+        except:
+            return None
+
+    def delete_shared_chat_by_chat_id(self, chat_id: str) -> bool:
+        try:
+            query = Chat.delete().where(Chat.user_id == f"shared-{chat_id}")
+            query.execute()  # Remove the rows, return number of rows removed.
+
+            return True
+        except:
+            return False
+
+    def update_chat_share_id_by_id(
+        self, id: str, share_id: Optional[str]
+    ) -> Optional[ChatModel]:
         try:
             query = Chat.update(
-                chat=json.dumps(chat),
-                title=chat["title"] if "title" in chat else "New Chat",
-                timestamp=int(time.time()),
+                share_id=share_id,
             ).where(Chat.id == id)
             query.execute()
 
@@ -145,6 +199,25 @@ class ChatTable:
             .order_by(Chat.timestamp.desc())
         ]
 
+    def get_chat_by_id(self, id: str) -> Optional[ChatModel]:
+        try:
+            chat = Chat.get(Chat.id == id)
+            return ChatModel(**model_to_dict(chat))
+        except:
+            return None
+
+    def get_chat_by_share_id(self, id: str) -> Optional[ChatModel]:
+        try:
+            chat = Chat.get(Chat.share_id == id)
+
+            if chat:
+                chat = Chat.get(Chat.id == id)
+                return ChatModel(**model_to_dict(chat))
+            else:
+                return None
+        except:
+            return None
+
     def get_chat_by_id_and_user_id(self, id: str, user_id: str) -> Optional[ChatModel]:
         try:
             chat = Chat.get(Chat.id == id, Chat.user_id == user_id)
@@ -163,12 +236,15 @@ class ChatTable:
             query = Chat.delete().where((Chat.id == id) & (Chat.user_id == user_id))
             query.execute()  # Remove the rows, return number of rows removed.
 
-            return True
+            return True and self.delete_shared_chat_by_chat_id(id)
         except:
             return False
 
     def delete_chats_by_user_id(self, user_id: str) -> bool:
         try:
+
+            self.delete_shared_chats_by_user_id(user_id)
+
             query = Chat.delete().where(Chat.user_id == user_id)
             query.execute()  # Remove the rows, return number of rows removed.
 
@@ -176,5 +252,19 @@ class ChatTable:
         except:
             return False
 
+    def delete_shared_chats_by_user_id(self, user_id: str) -> bool:
+        try:
+            shared_chat_ids = [
+                f"shared-{chat.id}"
+                for chat in Chat.select().where(Chat.user_id == user_id)
+            ]
+
+            query = Chat.delete().where(Chat.user_id << shared_chat_ids)
+            query.execute()  # Remove the rows, return number of rows removed.
+
+            return True
+        except:
+            return False
+
 
 Chats = ChatTable(DB)

backend/apps/web/models/documents.py

@@ -3,6 +3,7 @@ from peewee import *
 from playhouse.shortcuts import model_to_dict
 from typing import List, Union, Optional
 import time
+import logging
 
 from utils.utils import decode_token
 from utils.misc import get_gravatar_url
@@ -11,6 +12,11 @@ from apps.web.internal.db import DB
 
 import json
 
+from config import SRC_LOG_LEVELS
+
+log = logging.getLogger(__name__)
+log.setLevel(SRC_LOG_LEVELS["MODELS"])
+
 ####################
 # Documents DB Schema
 ####################
@@ -118,7 +124,7 @@ class DocumentsTable:
             doc = Document.get(Document.name == form_data.name)
             return DocumentModel(**model_to_dict(doc))
         except Exception as e:
-            print(e)
+            log.exception(e)
             return None
 
     def update_doc_content_by_name(
@@ -138,7 +144,7 @@ class DocumentsTable:
             doc = Document.get(Document.name == name)
             return DocumentModel(**model_to_dict(doc))
         except Exception as e:
-            print(e)
+            log.exception(e)
             return None
 
     def delete_doc_by_name(self, name: str) -> bool:

backend/apps/web/models/modelfiles.py

@@ -64,8 +64,8 @@ class ModelfilesTable:
         self.db.create_tables([Modelfile])
 
     def insert_new_modelfile(
-            self, user_id: str,
-            form_data: ModelfileForm) -> Optional[ModelfileModel]:
+        self, user_id: str, form_data: ModelfileForm
+    ) -> Optional[ModelfileModel]:
         if "tagName" in form_data.modelfile:
             modelfile = ModelfileModel(
                 **{
@@ -73,7 +73,8 @@ class ModelfilesTable:
                     "tag_name": form_data.modelfile["tagName"],
                     "modelfile": json.dumps(form_data.modelfile),
                     "timestamp": int(time.time()),
-                })
+                }
+            )
 
             try:
                 result = Modelfile.create(**modelfile.model_dump())
@@ -87,29 +88,28 @@ class ModelfilesTable:
         else:
             return None
 
-    def get_modelfile_by_tag_name(self,
-                                  tag_name: str) -> Optional[ModelfileModel]:
+    def get_modelfile_by_tag_name(self, tag_name: str) -> Optional[ModelfileModel]:
         try:
             modelfile = Modelfile.get(Modelfile.tag_name == tag_name)
             return ModelfileModel(**model_to_dict(modelfile))
         except:
             return None
 
-    def get_modelfiles(self,
-                       skip: int = 0,
-                       limit: int = 50) -> List[ModelfileResponse]:
+    def get_modelfiles(self, skip: int = 0, limit: int = 50) -> List[ModelfileResponse]:
         return [
             ModelfileResponse(
                 **{
                     **model_to_dict(modelfile),
-                    "modelfile":
-                    json.loads(modelfile.modelfile),
-                }) for modelfile in Modelfile.select()
+                    "modelfile": json.loads(modelfile.modelfile),
+                }
+            )
+            for modelfile in Modelfile.select()
             # .limit(limit).offset(skip)
         ]
 
     def update_modelfile_by_tag_name(
-            self, tag_name: str, modelfile: dict) -> Optional[ModelfileModel]:
+        self, tag_name: str, modelfile: dict
+    ) -> Optional[ModelfileModel]:
         try:
             query = Modelfile.update(
                 modelfile=json.dumps(modelfile),

backend/apps/web/models/prompts.py

@@ -52,8 +52,9 @@ class PromptsTable:
         self.db = db
         self.db.create_tables([Prompt])
 
-    def insert_new_prompt(self, user_id: str,
-                          form_data: PromptForm) -> Optional[PromptModel]:
+    def insert_new_prompt(
+        self, user_id: str, form_data: PromptForm
+    ) -> Optional[PromptModel]:
         prompt = PromptModel(
             **{
                 "user_id": user_id,
@@ -61,7 +62,8 @@ class PromptsTable:
                 "title": form_data.title,
                 "content": form_data.content,
                 "timestamp": int(time.time()),
-            })
+            }
+        )
 
         try:
             result = Prompt.create(**prompt.model_dump())
@@ -81,13 +83,14 @@ class PromptsTable:
 
     def get_prompts(self) -> List[PromptModel]:
         return [
-            PromptModel(**model_to_dict(prompt)) for prompt in Prompt.select()
+            PromptModel(**model_to_dict(prompt))
+            for prompt in Prompt.select()
             # .limit(limit).offset(skip)
         ]
 
     def update_prompt_by_command(
-            self, command: str,
-            form_data: PromptForm) -> Optional[PromptModel]:
+        self, command: str, form_data: PromptForm
+    ) -> Optional[PromptModel]:
         try:
             query = Prompt.update(
                 title=form_data.title,

backend/apps/web/models/tags.py

@@ -6,9 +6,15 @@ from playhouse.shortcuts import model_to_dict
 import json
 import uuid
 import time
+import logging
 
 from apps.web.internal.db import DB
 
+from config import SRC_LOG_LEVELS
+
+log = logging.getLogger(__name__)
+log.setLevel(SRC_LOG_LEVELS["MODELS"])
+
 ####################
 # Tag DB Schema
 ####################
@@ -167,17 +173,13 @@ class TagTable:
             .count()
         )
 
-    def delete_tag_by_tag_name_and_chat_id_and_user_id(
-        self, tag_name: str, chat_id: str, user_id: str
-    ) -> bool:
+    def delete_tag_by_tag_name_and_user_id(self, tag_name: str, user_id: str) -> bool:
         try:
             query = ChatIdTag.delete().where(
-                (ChatIdTag.tag_name == tag_name)
-                & (ChatIdTag.chat_id == chat_id)
-                & (ChatIdTag.user_id == user_id)
+                (ChatIdTag.tag_name == tag_name) & (ChatIdTag.user_id == user_id)
             )
             res = query.execute()  # Remove the rows, return number of rows removed.
-            print(res)
+            log.debug(f"res: {res}")
 
             tag_count = self.count_chat_ids_by_tag_name_and_user_id(tag_name, user_id)
             if tag_count == 0:
@@ -189,7 +191,32 @@ class TagTable:
 
             return True
         except Exception as e:
-            print("delete_tag", e)
+            log.error(f"delete_tag: {e}")
+            return False
+
+    def delete_tag_by_tag_name_and_chat_id_and_user_id(
+        self, tag_name: str, chat_id: str, user_id: str
+    ) -> bool:
+        try:
+            query = ChatIdTag.delete().where(
+                (ChatIdTag.tag_name == tag_name)
+                & (ChatIdTag.chat_id == chat_id)
+                & (ChatIdTag.user_id == user_id)
+            )
+            res = query.execute()  # Remove the rows, return number of rows removed.
+            log.debug(f"res: {res}")
+
+            tag_count = self.count_chat_ids_by_tag_name_and_user_id(tag_name, user_id)
+            if tag_count == 0:
+                # Remove tag item from Tag col as well
+                query = Tag.delete().where(
+                    (Tag.name == tag_name) & (Tag.user_id == user_id)
+                )
+                query.execute()  # Remove the rows, return number of rows removed.
+
+            return True
+        except Exception as e:
+            log.error(f"delete_tag: {e}")
             return False
 
     def delete_tags_by_chat_id_and_user_id(self, chat_id: str, user_id: str) -> bool:

backend/apps/web/models/users.py

@@ -20,6 +20,7 @@ class User(Model):
     role = CharField()
     profile_image_url = CharField()
     timestamp = DateField()
+    api_key = CharField(null=True, unique=True)
 
     class Meta:
         database = DB
@@ -30,8 +31,9 @@ class UserModel(BaseModel):
     name: str
     email: str
     role: str = "pending"
-    profile_image_url: str = "/user.png"
+    profile_image_url: str
     timestamp: int  # timestamp in epoch
+    api_key: Optional[str] = None
 
 
 ####################
@@ -57,7 +59,12 @@ class UsersTable:
         self.db.create_tables([User])
 
     def insert_new_user(
-        self, id: str, name: str, email: str, role: str = "pending"
+        self,
+        id: str,
+        name: str,
+        email: str,
+        profile_image_url: str = "/user.png",
+        role: str = "pending",
     ) -> Optional[UserModel]:
         user = UserModel(
             **{
@@ -65,7 +72,7 @@ class UsersTable:
                 "name": name,
                 "email": email,
                 "role": role,
-                "profile_image_url": "/user.png",
+                "profile_image_url": profile_image_url,
                 "timestamp": int(time.time()),
             }
         )
@@ -82,6 +89,13 @@ class UsersTable:
         except:
             return None
 
+    def get_user_by_api_key(self, api_key: str) -> Optional[UserModel]:
+        try:
+            user = User.get(User.api_key == api_key)
+            return UserModel(**model_to_dict(user))
+        except:
+            return None
+
     def get_user_by_email(self, email: str) -> Optional[UserModel]:
         try:
             user = User.get(User.email == email)
@@ -149,5 +163,21 @@ class UsersTable:
         except:
             return False
 
+    def update_user_api_key_by_id(self, id: str, api_key: str) -> str:
+        try:
+            query = User.update(api_key=api_key).where(User.id == id)
+            result = query.execute()
+
+            return True if result == 1 else False
+        except:
+            return False
+
+    def get_user_api_key_by_id(self, id: str) -> Optional[str]:
+        try:
+            user = User.get(User.id == id)
+            return user.api_key
+        except:
+            return None
+
 
 Users = UsersTable(DB)

backend/apps/web/routers/auths.py

@@ -1,13 +1,10 @@
-from fastapi import Response, Request
-from fastapi import Depends, FastAPI, HTTPException, status
-from datetime import datetime, timedelta
-from typing import List, Union
+from fastapi import Request
+from fastapi import Depends, HTTPException, status
 
-from fastapi import APIRouter, status
+from fastapi import APIRouter
 from pydantic import BaseModel
-import time
-import uuid
 import re
+import uuid
 
 from apps.web.models.auths import (
     SigninForm,
@@ -17,6 +14,7 @@ from apps.web.models.auths import (
     UserResponse,
     SigninResponse,
     Auths,
+    ApiKey,
 )
 from apps.web.models.users import Users
 
@@ -25,9 +23,12 @@ from utils.utils import (
     get_current_user,
     get_admin_user,
     create_token,
+    create_api_key,
 )
 from utils.misc import parse_duration, validate_email_format
-from constants import ERROR_MESSAGES
+from utils.webhook import post_webhook
+from constants import ERROR_MESSAGES, WEBHOOK_MESSAGES
+from config import WEBUI_AUTH_TRUSTED_EMAIL_HEADER
 
 router = APIRouter()
 
@@ -78,6 +79,8 @@ async def update_profile(
 async def update_password(
     form_data: UpdatePasswordForm, session_user=Depends(get_current_user)
 ):
+    if WEBUI_AUTH_TRUSTED_EMAIL_HEADER:
+        raise HTTPException(400, detail=ERROR_MESSAGES.ACTION_PROHIBITED)
     if session_user:
         user = Auths.authenticate_user(session_user.email, form_data.password)
 
@@ -97,7 +100,22 @@ async def update_password(
 
 @router.post("/signin", response_model=SigninResponse)
 async def signin(request: Request, form_data: SigninForm):
-    user = Auths.authenticate_user(form_data.email.lower(), form_data.password)
+    if WEBUI_AUTH_TRUSTED_EMAIL_HEADER:
+        if WEBUI_AUTH_TRUSTED_EMAIL_HEADER not in request.headers:
+            raise HTTPException(400, detail=ERROR_MESSAGES.INVALID_TRUSTED_HEADER)
+
+        trusted_email = request.headers[WEBUI_AUTH_TRUSTED_EMAIL_HEADER].lower()
+        if not Users.get_user_by_email(trusted_email.lower()):
+            await signup(
+                request,
+                SignupForm(
+                    email=trusted_email, password=str(uuid.uuid4()), name=trusted_email
+                ),
+            )
+        user = Auths.authenticate_user_by_trusted_header(trusted_email)
+    else:
+        user = Auths.authenticate_user(form_data.email.lower(), form_data.password)
+
     if user:
         token = create_token(
             data={"id": user.id},
@@ -145,7 +163,11 @@ async def signup(request: Request, form_data: SignupForm):
         )
         hashed = get_password_hash(form_data.password)
         user = Auths.insert_new_auth(
-            form_data.email.lower(), hashed, form_data.name, role
+            form_data.email.lower(),
+            hashed,
+            form_data.name,
+            form_data.profile_image_url,
+            role,
         )
 
         if user:
@@ -155,6 +177,17 @@ async def signup(request: Request, form_data: SignupForm):
             )
             # response.set_cookie(key='token', value=token, httponly=True)
 
+            if request.app.state.WEBHOOK_URL:
+                post_webhook(
+                    request.app.state.WEBHOOK_URL,
+                    WEBHOOK_MESSAGES.USER_SIGNUP(user.name),
+                    {
+                        "action": "signup",
+                        "message": WEBHOOK_MESSAGES.USER_SIGNUP(user.name),
+                        "user": user.model_dump_json(exclude_none=True),
+                    },
+                )
+
             return {
                 "token": token,
                 "token_type": "Bearer",
@@ -237,3 +270,40 @@ async def update_token_expires_duration(
         return request.app.state.JWT_EXPIRES_IN
     else:
         return request.app.state.JWT_EXPIRES_IN
+
+
+############################
+# API Key
+############################
+
+
+# create api key
+@router.post("/api_key", response_model=ApiKey)
+async def create_api_key_(user=Depends(get_current_user)):
+    api_key = create_api_key()
+    success = Users.update_user_api_key_by_id(user.id, api_key)
+    if success:
+        return {
+            "api_key": api_key,
+        }
+    else:
+        raise HTTPException(500, detail=ERROR_MESSAGES.CREATE_API_KEY_ERROR)
+
+
+# delete api key
+@router.delete("/api_key", response_model=bool)
+async def delete_api_key(user=Depends(get_current_user)):
+    success = Users.update_user_api_key_by_id(user.id, None)
+    return success
+
+
+# get api key
+@router.get("/api_key", response_model=ApiKey)
+async def get_api_key(user=Depends(get_current_user)):
+    api_key = Users.get_user_api_key_by_id(user.id)
+    if api_key:
+        return {
+            "api_key": api_key,
+        }
+    else:
+        raise HTTPException(404, detail=ERROR_MESSAGES.API_KEY_NOT_FOUND)

backend/apps/web/routers/chats.py

@@ -5,6 +5,7 @@ from utils.utils import get_current_user, get_admin_user
 from fastapi import APIRouter
 from pydantic import BaseModel
 import json
+import logging
 
 from apps.web.models.users import Users
 from apps.web.models.chats import (
@@ -27,6 +28,11 @@ from apps.web.models.tags import (
 
 from constants import ERROR_MESSAGES
 
+from config import SRC_LOG_LEVELS
+
+log = logging.getLogger(__name__)
+log.setLevel(SRC_LOG_LEVELS["MODELS"])
+
 router = APIRouter()
 
 ############################
@@ -78,7 +84,7 @@ async def create_new_chat(form_data: ChatForm, user=Depends(get_current_user)):
         chat = Chats.insert_new_chat(user.id, form_data)
         return ChatResponse(**{**chat.model_dump(), "chat": json.loads(chat.chat)})
     except Exception as e:
-        print(e)
+        log.exception(e)
         raise HTTPException(
             status_code=status.HTTP_400_BAD_REQUEST, detail=ERROR_MESSAGES.DEFAULT()
         )
@@ -95,7 +101,7 @@ async def get_all_tags(user=Depends(get_current_user)):
         tags = Tags.get_tags_by_user_id(user.id)
         return tags
     except Exception as e:
-        print(e)
+        log.exception(e)
         raise HTTPException(
             status_code=status.HTTP_400_BAD_REQUEST, detail=ERROR_MESSAGES.DEFAULT()
         )
@@ -115,9 +121,12 @@ async def get_user_chats_by_tag_name(
         for chat_id_tag in Tags.get_chat_ids_by_tag_name_and_user_id(tag_name, user.id)
     ]
 
-    print(chat_ids)
+    chats = Chats.get_chat_lists_by_chat_ids(chat_ids, skip, limit)
 
-    return Chats.get_chat_lists_by_chat_ids(chat_ids, skip, limit)
+    if len(chats) == 0:
+        Tags.delete_tag_by_tag_name_and_user_id(tag_name, user.id)
+
+    return chats
 
 
 ############################
@@ -180,6 +189,86 @@ async def delete_chat_by_id(request: Request, id: str, user=Depends(get_current_
     return result
 
 
+############################
+# ShareChatById
+############################
+
+
+@router.post("/{id}/share", response_model=Optional[ChatResponse])
+async def share_chat_by_id(id: str, user=Depends(get_current_user)):
+    chat = Chats.get_chat_by_id_and_user_id(id, user.id)
+    if chat:
+        if chat.share_id:
+            shared_chat = Chats.update_shared_chat_by_chat_id(chat.id)
+            return ChatResponse(
+                **{**shared_chat.model_dump(), "chat": json.loads(shared_chat.chat)}
+            )
+
+        shared_chat = Chats.insert_shared_chat_by_chat_id(chat.id)
+        if not shared_chat:
+            raise HTTPException(
+                status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
+                detail=ERROR_MESSAGES.DEFAULT(),
+            )
+
+        return ChatResponse(
+            **{**shared_chat.model_dump(), "chat": json.loads(shared_chat.chat)}
+        )
+    else:
+        raise HTTPException(
+            status_code=status.HTTP_401_UNAUTHORIZED,
+            detail=ERROR_MESSAGES.ACCESS_PROHIBITED,
+        )
+
+
+############################
+# DeletedSharedChatById
+############################
+
+
+@router.delete("/{id}/share", response_model=Optional[bool])
+async def delete_shared_chat_by_id(id: str, user=Depends(get_current_user)):
+    chat = Chats.get_chat_by_id_and_user_id(id, user.id)
+    if chat:
+        if not chat.share_id:
+            return False
+
+        result = Chats.delete_shared_chat_by_chat_id(id)
+        update_result = Chats.update_chat_share_id_by_id(id, None)
+
+        return result and update_result != None
+    else:
+        raise HTTPException(
+            status_code=status.HTTP_401_UNAUTHORIZED,
+            detail=ERROR_MESSAGES.ACCESS_PROHIBITED,
+        )
+
+
+############################
+# GetSharedChatById
+############################
+
+
+@router.get("/share/{share_id}", response_model=Optional[ChatResponse])
+async def get_shared_chat_by_id(share_id: str, user=Depends(get_current_user)):
+    if user.role == "pending":
+        raise HTTPException(
+            status_code=status.HTTP_401_UNAUTHORIZED, detail=ERROR_MESSAGES.NOT_FOUND
+        )
+
+    if user.role == "user":
+        chat = Chats.get_chat_by_share_id(share_id)
+    elif user.role == "admin":
+        chat = Chats.get_chat_by_id(share_id)
+
+    if chat:
+        return ChatResponse(**{**chat.model_dump(), "chat": json.loads(chat.chat)})
+    else:
+        raise HTTPException(
+            status_code=status.HTTP_401_UNAUTHORIZED, detail=ERROR_MESSAGES.NOT_FOUND
+        )
+
+
 ############################
 # GetChatTagsById
 ############################
@@ -268,6 +357,16 @@ async def delete_all_chat_tags_by_id(id: str, user=Depends(get_current_user)):
 
 
 @router.delete("/", response_model=bool)
-async def delete_all_user_chats(user=Depends(get_current_user)):
+async def delete_all_user_chats(request: Request, user=Depends(get_current_user)):
+
+    if (
+        user.role == "user"
+        and not request.app.state.USER_PERMISSIONS["chat"]["deletion"]
+    ):
+        raise HTTPException(
+            status_code=status.HTTP_401_UNAUTHORIZED,
+            detail=ERROR_MESSAGES.ACCESS_PROHIBITED,
+        )
+
     result = Chats.delete_chats_by_user_id(user.id)
     return result

backend/apps/web/routers/configs.py

@@ -10,7 +10,12 @@ import uuid
 
 from apps.web.models.users import Users
 
-from utils.utils import get_password_hash, get_current_user, get_admin_user, create_token
+from utils.utils import (
+    get_password_hash,
+    get_current_user,
+    get_admin_user,
+    create_token,
+)
 from utils.misc import get_gravatar_url, validate_email_format
 from constants import ERROR_MESSAGES
 
@@ -43,7 +48,6 @@ async def set_global_default_models(
     return request.app.state.DEFAULT_MODELS
 
 
-
 @router.post("/default/suggestions", response_model=List[PromptSuggestion])
 async def set_global_default_suggestions(
     request: Request,

backend/apps/web/routers/modelfiles.py

@@ -24,9 +24,9 @@ router = APIRouter()
 
 
 @router.get("/", response_model=List[ModelfileResponse])
-async def get_modelfiles(skip: int = 0,
-                         limit: int = 50,
-                         user=Depends(get_current_user)):
+async def get_modelfiles(
+    skip: int = 0, limit: int = 50, user=Depends(get_current_user)
+):
     return Modelfiles.get_modelfiles(skip, limit)
 
 
@@ -36,17 +36,16 @@ async def get_modelfiles(skip: int = 0,
 
 
 @router.post("/create", response_model=Optional[ModelfileResponse])
-async def create_new_modelfile(form_data: ModelfileForm,
-                               user=Depends(get_admin_user)):
+async def create_new_modelfile(form_data: ModelfileForm, user=Depends(get_admin_user)):
     modelfile = Modelfiles.insert_new_modelfile(user.id, form_data)
 
     if modelfile:
         return ModelfileResponse(
             **{
                 **modelfile.model_dump(),
-                "modelfile":
-                json.loads(modelfile.modelfile),
-            })
+                "modelfile": json.loads(modelfile.modelfile),
+            }
+        )
     else:
         raise HTTPException(
             status_code=status.HTTP_401_UNAUTHORIZED,
@@ -60,17 +59,18 @@ async def create_new_modelfile(form_data: ModelfileForm,
 
 
 @router.post("/", response_model=Optional[ModelfileResponse])
-async def get_modelfile_by_tag_name(form_data: ModelfileTagNameForm,
-                                    user=Depends(get_current_user)):
+async def get_modelfile_by_tag_name(
+    form_data: ModelfileTagNameForm, user=Depends(get_current_user)
+):
     modelfile = Modelfiles.get_modelfile_by_tag_name(form_data.tag_name)
 
     if modelfile:
         return ModelfileResponse(
             **{
                 **modelfile.model_dump(),
-                "modelfile":
-                json.loads(modelfile.modelfile),
-            })
+                "modelfile": json.loads(modelfile.modelfile),
+            }
+        )
     else:
         raise HTTPException(
             status_code=status.HTTP_401_UNAUTHORIZED,
@@ -84,8 +84,9 @@ async def get_modelfile_by_tag_name(form_data: ModelfileTagNameForm,
 
 
 @router.post("/update", response_model=Optional[ModelfileResponse])
-async def update_modelfile_by_tag_name(form_data: ModelfileUpdateForm,
-                                       user=Depends(get_admin_user)):
+async def update_modelfile_by_tag_name(
+    form_data: ModelfileUpdateForm, user=Depends(get_admin_user)
+):
     modelfile = Modelfiles.get_modelfile_by_tag_name(form_data.tag_name)
     if modelfile:
         updated_modelfile = {
@@ -94,14 +95,15 @@ async def update_modelfile_by_tag_name(form_data: ModelfileUpdateForm,
         }
 
         modelfile = Modelfiles.update_modelfile_by_tag_name(
-            form_data.tag_name, updated_modelfile)
+            form_data.tag_name, updated_modelfile
+        )
 
         return ModelfileResponse(
             **{
                 **modelfile.model_dump(),
-                "modelfile":
-                json.loads(modelfile.modelfile),
-            })
+                "modelfile": json.loads(modelfile.modelfile),
+            }
+        )
     else:
         raise HTTPException(
             status_code=status.HTTP_401_UNAUTHORIZED,
@@ -115,7 +117,8 @@ async def update_modelfile_by_tag_name(form_data: ModelfileUpdateForm,
 
 
 @router.delete("/delete", response_model=bool)
-async def delete_modelfile_by_tag_name(form_data: ModelfileTagNameForm,
-                                       user=Depends(get_admin_user)):
+async def delete_modelfile_by_tag_name(
+    form_data: ModelfileTagNameForm, user=Depends(get_admin_user)
+):
     result = Modelfiles.delete_modelfile_by_tag_name(form_data.tag_name)
     return result

backend/apps/web/routers/users.py

@@ -7,6 +7,7 @@ from fastapi import APIRouter
 from pydantic import BaseModel
 import time
 import uuid
+import logging
 
 from apps.web.models.users import UserModel, UserUpdateForm, UserRoleUpdateForm, Users
 from apps.web.models.auths import Auths
@@ -14,6 +15,11 @@ from apps.web.models.auths import Auths
 from utils.utils import get_current_user, get_password_hash, get_admin_user
 from constants import ERROR_MESSAGES
 
+from config import SRC_LOG_LEVELS
+
+log = logging.getLogger(__name__)
+log.setLevel(SRC_LOG_LEVELS["MODELS"])
+
 router = APIRouter()
 
 ############################
@@ -83,7 +89,7 @@ async def update_user_by_id(
 
         if form_data.password:
             hashed = get_password_hash(form_data.password)
-            print(hashed)
+            log.debug(f"hashed: {hashed}")
             Auths.update_user_password_by_id(user_id, hashed)
 
         Auths.update_email_by_id(user_id, form_data.email.lower())

backend/apps/web/routers/utils.py

@@ -1,174 +1,99 @@
-from fastapi import APIRouter, UploadFile, File, BackgroundTasks
+from fastapi import APIRouter, UploadFile, File, Response
 from fastapi import Depends, HTTPException, status
-from starlette.responses import StreamingResponse
-
+from starlette.responses import StreamingResponse, FileResponse
 from pydantic import BaseModel
 
-import requests
-import os
-import aiohttp
-import json
 
+from fpdf import FPDF
+import markdown
+
+
+from utils.utils import get_admin_user
 from utils.misc import calculate_sha256, get_gravatar_url
 
-from config import OLLAMA_API_BASE_URL, DATA_DIR, UPLOAD_DIR
+from config import OLLAMA_BASE_URLS, DATA_DIR, UPLOAD_DIR
 from constants import ERROR_MESSAGES
-
+from typing import List
 
 router = APIRouter()
 
 
-class UploadBlobForm(BaseModel):
-    filename: str
-
-
-from urllib.parse import urlparse
-
-
-def parse_huggingface_url(hf_url):
-    try:
-        # Parse the URL
-        parsed_url = urlparse(hf_url)
-
-        # Get the path and split it into components
-        path_components = parsed_url.path.split("/")
-
-        # Extract the desired output
-        user_repo = "/".join(path_components[1:3])
-        model_file = path_components[-1]
-
-        return model_file
-    except ValueError:
-        return None
-
-
-async def download_file_stream(url, file_path, file_name, chunk_size=1024 * 1024):
-    done = False
-
-    if os.path.exists(file_path):
-        current_size = os.path.getsize(file_path)
-    else:
-        current_size = 0
-
-    headers = {"Range": f"bytes={current_size}-"} if current_size > 0 else {}
-
-    timeout = aiohttp.ClientTimeout(total=600)  # Set the timeout
-
-    async with aiohttp.ClientSession(timeout=timeout) as session:
-        async with session.get(url, headers=headers) as response:
-            total_size = int(response.headers.get("content-length", 0)) + current_size
-
-            with open(file_path, "ab+") as file:
-                async for data in response.content.iter_chunked(chunk_size):
-                    current_size += len(data)
-                    file.write(data)
-
-                    done = current_size == total_size
-                    progress = round((current_size / total_size) * 100, 2)
-                    yield f'data: {{"progress": {progress}, "completed": {current_size}, "total": {total_size}}}\n\n'
-
-                if done:
-                    file.seek(0)
-                    hashed = calculate_sha256(file)
-                    file.seek(0)
-
-                    url = f"{OLLAMA_API_BASE_URL}/blobs/sha256:{hashed}"
-                    response = requests.post(url, data=file)
-
-                    if response.ok:
-                        res = {
-                            "done": done,
-                            "blob": f"sha256:{hashed}",
-                            "name": file_name,
-                        }
-                        os.remove(file_path)
-
-                        yield f"data: {json.dumps(res)}\n\n"
-                    else:
-                        raise "Ollama: Could not create blob, Please try again."
-
-
-@router.get("/download")
-async def download(
-    url: str,
-):
-    # url = "https://huggingface.co/TheBloke/stablelm-zephyr-3b-GGUF/resolve/main/stablelm-zephyr-3b.Q2_K.gguf"
-    file_name = parse_huggingface_url(url)
-
-    if file_name:
-        file_path = f"{UPLOAD_DIR}/{file_name}"
-
-        return StreamingResponse(
-            download_file_stream(url, file_path, file_name),
-            media_type="text/event-stream",
-        )
-    else:
-        return None
-
-
-@router.post("/upload")
-def upload(file: UploadFile = File(...)):
-    file_path = f"{UPLOAD_DIR}/{file.filename}"
-
-    # Save file in chunks
-    with open(file_path, "wb+") as f:
-        for chunk in file.file:
-            f.write(chunk)
-
-    def file_process_stream():
-        total_size = os.path.getsize(file_path)
-        chunk_size = 1024 * 1024
-        try:
-            with open(file_path, "rb") as f:
-                total = 0
-                done = False
-
-                while not done:
-                    chunk = f.read(chunk_size)
-                    if not chunk:
-                        done = True
-                        continue
-
-                    total += len(chunk)
-                    progress = round((total / total_size) * 100, 2)
-
-                    res = {
-                        "progress": progress,
-                        "total": total_size,
-                        "completed": total,
-                    }
-                    yield f"data: {json.dumps(res)}\n\n"
-
-                if done:
-                    f.seek(0)
-                    hashed = calculate_sha256(f)
-                    f.seek(0)
-
-                    url = f"{OLLAMA_API_BASE_URL}/blobs/sha256:{hashed}"
-                    response = requests.post(url, data=f)
-
-                    if response.ok:
-                        res = {
-                            "done": done,
-                            "blob": f"sha256:{hashed}",
-                            "name": file.filename,
-                        }
-                        os.remove(file_path)
-                        yield f"data: {json.dumps(res)}\n\n"
-                    else:
-                        raise Exception(
-                            "Ollama: Could not create blob, Please try again."
-                        )
-
-        except Exception as e:
-            res = {"error": str(e)}
-            yield f"data: {json.dumps(res)}\n\n"
-
-    return StreamingResponse(file_process_stream(), media_type="text/event-stream")
-
-
 @router.get("/gravatar")
 async def get_gravatar(
     email: str,
 ):
     return get_gravatar_url(email)
+
+
+class MarkdownForm(BaseModel):
+    md: str
+
+
+@router.post("/markdown")
+async def get_html_from_markdown(
+    form_data: MarkdownForm,
+):
+    return {"html": markdown.markdown(form_data.md)}
+
+
+class ChatForm(BaseModel):
+    title: str
+    messages: List[dict]
+
+
+@router.post("/pdf")
+async def download_chat_as_pdf(
+    form_data: ChatForm,
+):
+    pdf = FPDF()
+    pdf.add_page()
+
+    STATIC_DIR = "./static"
+    FONTS_DIR = f"{STATIC_DIR}/fonts"
+
+    pdf.add_font("NotoSans", "", f"{FONTS_DIR}/NotoSans-Regular.ttf")
+    pdf.add_font("NotoSans", "b", f"{FONTS_DIR}/NotoSans-Bold.ttf")
+    pdf.add_font("NotoSans", "i", f"{FONTS_DIR}/NotoSans-Italic.ttf")
+    pdf.add_font("NotoSansKR", "", f"{FONTS_DIR}/NotoSansKR-Regular.ttf")
+    pdf.add_font("NotoSansJP", "", f"{FONTS_DIR}/NotoSansJP-Regular.ttf")
+
+    pdf.set_font("NotoSans", size=12)
+    pdf.set_fallback_fonts(["NotoSansKR", "NotoSansJP"])
+
+    pdf.set_auto_page_break(auto=True, margin=15)
+
+    # Adjust the effective page width for multi_cell
+    effective_page_width = (
+        pdf.w - 2 * pdf.l_margin - 10
+    )  # Subtracted an additional 10 for extra padding
+
+    # Add chat messages
+    for message in form_data.messages:
+        role = message["role"]
+        content = message["content"]
+        pdf.set_font("NotoSans", "B", size=14)  # Bold for the role
+        pdf.multi_cell(effective_page_width, 10, f"{role.upper()}", 0, "L")
+        pdf.ln(1)  # Extra space between messages
+
+        pdf.set_font("NotoSans", size=10)  # Regular for content
+        pdf.multi_cell(effective_page_width, 6, content, 0, "L")
+        pdf.ln(1.5)  # Extra space between messages
+
+    # Save the pdf with name .pdf
+    pdf_bytes = pdf.output()
+
+    return Response(
+        content=bytes(pdf_bytes),
+        media_type="application/pdf",
+        headers={"Content-Disposition": f"attachment;filename=chat.pdf"},
+    )
+
+
+@router.get("/db/download")
+async def download_db(user=Depends(get_admin_user)):
+
+    return FileResponse(
+        f"{DATA_DIR}/webui.db",
+        media_type="application/octet-stream",
+        filename="webui.db",
+    )

backend/config.py

@@ -1,4 +1,6 @@
 import os
+import sys
+import logging
 import chromadb
 from chromadb import Settings
 from base64 import b64encode
@@ -16,15 +18,60 @@ from secrets import token_bytes
 from constants import ERROR_MESSAGES
 
 
+####################################
+# LOGGING
+####################################
+
+log_levels = ["CRITICAL", "ERROR", "WARNING", "INFO", "DEBUG"]
+
+GLOBAL_LOG_LEVEL = os.environ.get("GLOBAL_LOG_LEVEL", "").upper()
+if GLOBAL_LOG_LEVEL in log_levels:
+    logging.basicConfig(stream=sys.stdout, level=GLOBAL_LOG_LEVEL, force=True)
+else:
+    GLOBAL_LOG_LEVEL = "INFO"
+
+log = logging.getLogger(__name__)
+log.info(f"GLOBAL_LOG_LEVEL: {GLOBAL_LOG_LEVEL}")
+
+log_sources = [
+    "AUDIO",
+    "COMFYUI",
+    "CONFIG",
+    "DB",
+    "IMAGES",
+    "LITELLM",
+    "MAIN",
+    "MODELS",
+    "OLLAMA",
+    "OPENAI",
+    "RAG",
+    "WEBHOOK",
+]
+
+SRC_LOG_LEVELS = {}
+
+for source in log_sources:
+    log_env_var = source + "_LOG_LEVEL"
+    SRC_LOG_LEVELS[source] = os.environ.get(log_env_var, "").upper()
+    if SRC_LOG_LEVELS[source] not in log_levels:
+        SRC_LOG_LEVELS[source] = GLOBAL_LOG_LEVEL
+    log.info(f"{log_env_var}: {SRC_LOG_LEVELS[source]}")
+
+log.setLevel(SRC_LOG_LEVELS["CONFIG"])
+
+####################################
+# Load .env file
+####################################
+
 try:
     from dotenv import load_dotenv, find_dotenv
 
     load_dotenv(find_dotenv("../.env"))
 except ImportError:
-    print("dotenv not installed, skipping...")
+    log.warning("dotenv not installed, skipping...")
 
-WEBUI_NAME = "Open WebUI"
-shutil.copyfile("../build/favicon.png", "./static/favicon.png")
+WEBUI_NAME = os.environ.get("WEBUI_NAME", "Open WebUI")
+WEBUI_FAVICON_URL = "https://openwebui.com/favicon.png"
 
 ####################################
 # ENV (dev,test,prod)
@@ -99,36 +146,6 @@ for version in soup.find_all("h2"):
 
 CHANGELOG = changelog_json
 
-
-####################################
-# CUSTOM_NAME
-####################################
-
-CUSTOM_NAME = os.environ.get("CUSTOM_NAME", "")
-if CUSTOM_NAME:
-    try:
-        r = requests.get(f"https://api.openwebui.com/api/v1/custom/{CUSTOM_NAME}")
-        data = r.json()
-        if r.ok:
-            if "logo" in data:
-                url = (
-                    f"https://api.openwebui.com{data['logo']}"
-                    if data["logo"][0] == "/"
-                    else data["logo"]
-                )
-
-                r = requests.get(url, stream=True)
-                if r.status_code == 200:
-                    with open("./static/favicon.png", "wb") as f:
-                        r.raw.decode_content = True
-                        shutil.copyfileobj(r.raw, f)
-
-            WEBUI_NAME = data["name"]
-    except Exception as e:
-        print(e)
-        pass
-
-
 ####################################
 # DATA/FRONTEND BUILD DIR
 ####################################
@@ -142,6 +159,47 @@ try:
 except:
     CONFIG_DATA = {}
 
+####################################
+# Static DIR
+####################################
+
+STATIC_DIR = str(Path(os.getenv("STATIC_DIR", "./static")).resolve())
+
+shutil.copyfile(f"{FRONTEND_BUILD_DIR}/favicon.png", f"{STATIC_DIR}/favicon.png")
+
+####################################
+# CUSTOM_NAME
+####################################
+
+CUSTOM_NAME = os.environ.get("CUSTOM_NAME", "")
+
+if CUSTOM_NAME:
+    try:
+        r = requests.get(f"https://api.openwebui.com/api/v1/custom/{CUSTOM_NAME}")
+        data = r.json()
+        if r.ok:
+            if "logo" in data:
+                WEBUI_FAVICON_URL = url = (
+                    f"https://api.openwebui.com{data['logo']}"
+                    if data["logo"][0] == "/"
+                    else data["logo"]
+                )
+
+                r = requests.get(url, stream=True)
+                if r.status_code == 200:
+                    with open(f"{STATIC_DIR}/favicon.png", "wb") as f:
+                        r.raw.decode_content = True
+                        shutil.copyfileobj(r.raw, f)
+
+            WEBUI_NAME = data["name"]
+    except Exception as e:
+        log.exception(e)
+        pass
+else:
+    if WEBUI_NAME != "Open WebUI":
+        WEBUI_NAME += " (Open WebUI)"
+
+
 ####################################
 # File Upload DIR
 ####################################
@@ -194,22 +252,47 @@ def create_config_file(file_path):
 LITELLM_CONFIG_PATH = f"{DATA_DIR}/litellm/config.yaml"
 
 if not os.path.exists(LITELLM_CONFIG_PATH):
-    print("Config file doesn't exist. Creating...")
+    log.info("Config file doesn't exist. Creating...")
     create_config_file(LITELLM_CONFIG_PATH)
-    print("Config file created successfully.")
+    log.info("Config file created successfully.")
 
 
 ####################################
-# OLLAMA_API_BASE_URL
+# OLLAMA_BASE_URL
 ####################################
 
 OLLAMA_API_BASE_URL = os.environ.get(
     "OLLAMA_API_BASE_URL", "http://localhost:11434/api"
 )
 
+OLLAMA_BASE_URL = os.environ.get("OLLAMA_BASE_URL", "")
+K8S_FLAG = os.environ.get("K8S_FLAG", "")
+USE_OLLAMA_DOCKER = os.environ.get("USE_OLLAMA_DOCKER", "false")
+
+if OLLAMA_BASE_URL == "" and OLLAMA_API_BASE_URL != "":
+    OLLAMA_BASE_URL = (
+        OLLAMA_API_BASE_URL[:-4]
+        if OLLAMA_API_BASE_URL.endswith("/api")
+        else OLLAMA_API_BASE_URL
+    )
+
 if ENV == "prod":
-    if OLLAMA_API_BASE_URL == "/ollama/api":
-        OLLAMA_API_BASE_URL = "http://host.docker.internal:11434/api"
+    if OLLAMA_BASE_URL == "/ollama" and not K8S_FLAG:
+        if USE_OLLAMA_DOCKER.lower() == "true":
+            # if you use all-in-one docker container (Open WebUI + Ollama)
+            # with the docker build arg USE_OLLAMA=true (--build-arg="USE_OLLAMA=true") this only works with http://localhost:11434
+            OLLAMA_BASE_URL = "http://localhost:11434"
+        else:
+            OLLAMA_BASE_URL = "http://host.docker.internal:11434"
+    elif K8S_FLAG:
+        OLLAMA_BASE_URL = "http://ollama-service.open-webui.svc.cluster.local:11434"
+
+
+OLLAMA_BASE_URLS = os.environ.get("OLLAMA_BASE_URLS", "")
+OLLAMA_BASE_URLS = OLLAMA_BASE_URLS if OLLAMA_BASE_URLS != "" else OLLAMA_BASE_URL
+
+OLLAMA_BASE_URLS = [url.strip() for url in OLLAMA_BASE_URLS.split(";")]
+
 
 ####################################
 # OPENAI_API
@@ -218,15 +301,31 @@ if ENV == "prod":
 OPENAI_API_KEY = os.environ.get("OPENAI_API_KEY", "")
 OPENAI_API_BASE_URL = os.environ.get("OPENAI_API_BASE_URL", "")
 
+
 if OPENAI_API_BASE_URL == "":
     OPENAI_API_BASE_URL = "https://api.openai.com/v1"
 
+OPENAI_API_KEYS = os.environ.get("OPENAI_API_KEYS", "")
+OPENAI_API_KEYS = OPENAI_API_KEYS if OPENAI_API_KEYS != "" else OPENAI_API_KEY
+
+OPENAI_API_KEYS = [url.strip() for url in OPENAI_API_KEYS.split(";")]
+
+
+OPENAI_API_BASE_URLS = os.environ.get("OPENAI_API_BASE_URLS", "")
+OPENAI_API_BASE_URLS = (
+    OPENAI_API_BASE_URLS if OPENAI_API_BASE_URLS != "" else OPENAI_API_BASE_URL
+)
+
+OPENAI_API_BASE_URLS = [
+    url.strip() if url != "" else "https://api.openai.com/v1"
+    for url in OPENAI_API_BASE_URLS.split(";")
+]
 
 ####################################
 # WEBUI
 ####################################
 
-ENABLE_SIGNUP = os.environ.get("ENABLE_SIGNUP", True)
+ENABLE_SIGNUP = os.environ.get("ENABLE_SIGNUP", "True").lower() == "true"
 DEFAULT_MODELS = os.environ.get("DEFAULT_MODELS", None)
 
 
@@ -257,8 +356,19 @@ DEFAULT_PROMPT_SUGGESTIONS = (
 
 
 DEFAULT_USER_ROLE = os.getenv("DEFAULT_USER_ROLE", "pending")
-USER_PERMISSIONS = {"chat": {"deletion": True}}
 
+USER_PERMISSIONS_CHAT_DELETION = (
+    os.environ.get("USER_PERMISSIONS_CHAT_DELETION", "True").lower() == "true"
+)
+
+USER_PERMISSIONS = {"chat": {"deletion": USER_PERMISSIONS_CHAT_DELETION}}
+
+
+MODEL_FILTER_ENABLED = os.environ.get("MODEL_FILTER_ENABLED", "False").lower() == "true"
+MODEL_FILTER_LIST = os.environ.get("MODEL_FILTER_LIST", "")
+MODEL_FILTER_LIST = [model.strip() for model in MODEL_FILTER_LIST.split(";")]
+
+WEBHOOK_URL = os.environ.get("WEBHOOK_URL", "")
 
 ####################################
 # WEBUI_VERSION
@@ -271,6 +381,9 @@ WEBUI_VERSION = os.environ.get("WEBUI_VERSION", "v1.0.0-alpha.100")
 ####################################
 
 WEBUI_AUTH = True
+WEBUI_AUTH_TRUSTED_EMAIL_HEADER = os.environ.get(
+    "WEBUI_AUTH_TRUSTED_EMAIL_HEADER", None
+)
 
 ####################################
 # WEBUI_SECRET_KEY
@@ -292,11 +405,26 @@ if WEBUI_AUTH and WEBUI_SECRET_KEY == "":
 
 CHROMA_DATA_PATH = f"{DATA_DIR}/vector_db"
 # this uses the model defined in the Dockerfile ENV variable. If you dont use docker or docker based deployments such as k8s, the default embedding model will be used (all-MiniLM-L6-v2)
+
+RAG_EMBEDDING_ENGINE = os.environ.get("RAG_EMBEDDING_ENGINE", "")
+
 RAG_EMBEDDING_MODEL = os.environ.get("RAG_EMBEDDING_MODEL", "all-MiniLM-L6-v2")
-# device type ebbeding models - "cpu" (default), "cuda" (nvidia gpu required) or "mps" (apple silicon) - choosing this right can lead to better performance
-RAG_EMBEDDING_MODEL_DEVICE_TYPE = os.environ.get(
-    "RAG_EMBEDDING_MODEL_DEVICE_TYPE", "cpu"
+log.info(f"Embedding model set: {RAG_EMBEDDING_MODEL}"),
+
+RAG_EMBEDDING_MODEL_AUTO_UPDATE = (
+    os.environ.get("RAG_EMBEDDING_MODEL_AUTO_UPDATE", "").lower() == "true"
 )
+
+
+# device type embedding models - "cpu" (default), "cuda" (nvidia gpu required) or "mps" (apple silicon) - choosing this right can lead to better performance
+USE_CUDA = os.environ.get("USE_CUDA_DOCKER", "false")
+
+if USE_CUDA.lower() == "true":
+    DEVICE_TYPE = "cuda"
+else:
+    DEVICE_TYPE = "cpu"
+
+
 CHROMA_CLIENT = chromadb.PersistentClient(
     path=CHROMA_DATA_PATH,
     settings=Settings(allow_reset=True, anonymized_telemetry=False),
@@ -325,10 +453,17 @@ Query: [query]"""
 
 WHISPER_MODEL = os.getenv("WHISPER_MODEL", "base")
 WHISPER_MODEL_DIR = os.getenv("WHISPER_MODEL_DIR", f"{CACHE_DIR}/whisper/models")
+WHISPER_MODEL_AUTO_UPDATE = (
+    os.environ.get("WHISPER_MODEL_AUTO_UPDATE", "").lower() == "true"
+)
 
 
 ####################################
 # Images
 ####################################
 
+ENABLE_IMAGE_GENERATION = (
+    os.environ.get("ENABLE_IMAGE_GENERATION", "").lower() == "true"
+)
 AUTOMATIC1111_BASE_URL = os.getenv("AUTOMATIC1111_BASE_URL", "")
+COMFYUI_BASE_URL = os.getenv("COMFYUI_BASE_URL", "")

backend/constants.py

@@ -5,6 +5,13 @@ class MESSAGES(str, Enum):
     DEFAULT = lambda msg="": f"{msg if msg else ''}"
 
 
+class WEBHOOK_MESSAGES(str, Enum):
+    DEFAULT = lambda msg="": f"{msg if msg else ''}"
+    USER_SIGNUP = lambda username="": (
+        f"New user signed up: {username}" if username else "New user signed up"
+    )
+
+
 class ERROR_MESSAGES(str, Enum):
     def __str__(self) -> str:
         return super().__str__()
@@ -13,6 +20,7 @@ class ERROR_MESSAGES(str, Enum):
     ENV_VAR_NOT_FOUND = "Required environment variable not found. Terminating now."
     CREATE_USER_ERROR = "Oops! Something went wrong while creating your account. Please try again later. If the issue persists, contact support for assistance."
     DELETE_USER_ERROR = "Oops! Something went wrong. We encountered an issue while trying to delete the user. Please give it another shot."
+    EMAIL_MISMATCH = "Uh-oh! This email does not match the email your provider is registered with. Please check your email and try again."
     EMAIL_TAKEN = "Uh-oh! This email is already registered. Sign in with your existing account or choose another email to start anew."
     USERNAME_TAKEN = (
         "Uh-oh! This username is already registered. Please choose another username."
@@ -29,6 +37,7 @@ class ERROR_MESSAGES(str, Enum):
     INVALID_PASSWORD = (
         "The password provided is incorrect. Please check for typos and try again."
     )
+    INVALID_TRUSTED_HEADER = "Your provider has not provided a trusted header. Please contact your administrator for assistance."
     UNAUTHORIZED = "401 Unauthorized"
     ACCESS_PROHIBITED = "You do not have permission to access this resource. Please contact your administrator for assistance."
     ACTION_PROHIBITED = (
@@ -41,9 +50,18 @@ class ERROR_MESSAGES(str, Enum):
     NOT_FOUND = "We could not find what you're looking for :/"
     USER_NOT_FOUND = "We could not find what you're looking for :/"
     API_KEY_NOT_FOUND = "Oops! It looks like there's a hiccup. The API key is missing. Please make sure to provide a valid API key to access this feature."
+
     MALICIOUS = "Unusual activities detected, please try again in a few minutes."
 
     PANDOC_NOT_INSTALLED = "Pandoc is not installed on the server. Please contact your administrator for assistance."
     INCORRECT_FORMAT = (
-        lambda err="": f"Invalid format. Please use the correct format{err if err else ''}"
+        lambda err="": f"Invalid format. Please use the correct format{err}"
     )
+    RATE_LIMIT_EXCEEDED = "API rate limit exceeded"
+
+    MODEL_NOT_FOUND = lambda name="": f"Model '{name}' was not found"
+    OPENAI_NOT_FOUND = lambda name="": "OpenAI API was not found"
+    OLLAMA_NOT_FOUND = "WebUI could not connect to Ollama"
+    CREATE_API_KEY_ERROR = "Oops! Something went wrong while creating your API key. Please try again later. If the issue persists, contact support for assistance."
+
+    EMPTY_CONTENT = "The content provided is empty. Please ensure that there is text or data present before proceeding."

backend/data/config.json

@@ -1,34 +1,24 @@
 {
-    "ui": {
-        "prompt_suggestions": [
-            {
-                "title": [
-                    "Help me study",
-                    "vocabulary for a college entrance exam"
-                ],
-                "content": "Help me study vocabulary: write a sentence for me to fill in the blank, and I'll try to pick the correct option."
-            },
-            {
-                "title": [
-                    "Give me ideas",
-                    "for what to do with my kids' art"
-                ],
-                "content": "What are 5 creative things I could do with my kids' art? I don't want to throw them away, but it's also so much clutter."
-            },
-            {
-                "title": [
-                    "Tell me a fun fact",
-                    "about the Roman Empire"
-                ],
-                "content": "Tell me a random fun fact about the Roman Empire"
-            },
-            {
-                "title": [
-                    "Show me a code snippet",
-                    "of a website's sticky header"
-                ],
-                "content": "Show me a code snippet of a website's sticky header in CSS and JavaScript."
-            }
-        ]
-    }
-}
+	"version": 0,
+	"ui": {
+		"default_locale": "en-US",
+		"prompt_suggestions": [
+			{
+				"title": ["Help me study", "vocabulary for a college entrance exam"],
+				"content": "Help me study vocabulary: write a sentence for me to fill in the blank, and I'll try to pick the correct option."
+			},
+			{
+				"title": ["Give me ideas", "for what to do with my kids' art"],
+				"content": "What are 5 creative things I could do with my kids' art? I don't want to throw them away, but it's also so much clutter."
+			},
+			{
+				"title": ["Tell me a fun fact", "about the Roman Empire"],
+				"content": "Tell me a random fun fact about the Roman Empire"
+			},
+			{
+				"title": ["Show me a code snippet", "of a website's sticky header"],
+				"content": "Show me a code snippet of a website's sticky header in CSS and JavaScript."
+			}
+		]
+	}
+}

backend/main.py

@@ -4,29 +4,55 @@ import markdown
 import time
 import os
 import sys
+import logging
+import aiohttp
+import requests
 
-from fastapi import FastAPI, Request, Depends
+from fastapi import FastAPI, Request, Depends, status
 from fastapi.staticfiles import StaticFiles
 from fastapi import HTTPException
-from fastapi.responses import JSONResponse
 from fastapi.middleware.wsgi import WSGIMiddleware
 from fastapi.middleware.cors import CORSMiddleware
 from starlette.exceptions import HTTPException as StarletteHTTPException
+from starlette.middleware.base import BaseHTTPMiddleware
 
 
-from litellm.proxy.proxy_server import ProxyConfig, initialize
-from litellm.proxy.proxy_server import app as litellm_app
-
 from apps.ollama.main import app as ollama_app
 from apps.openai.main import app as openai_app
+
+from apps.litellm.main import app as litellm_app, startup as litellm_app_startup
 from apps.audio.main import app as audio_app
 from apps.images.main import app as images_app
 from apps.rag.main import app as rag_app
 from apps.web.main import app as webui_app
 
+from pydantic import BaseModel
+from typing import List
 
-from config import WEBUI_NAME, ENV, VERSION, CHANGELOG, FRONTEND_BUILD_DIR
-from utils.utils import get_http_authorization_cred, get_current_user
+
+from utils.utils import get_admin_user
+from apps.rag.utils import rag_messages
+
+from config import (
+    CONFIG_DATA,
+    WEBUI_NAME,
+    ENV,
+    VERSION,
+    CHANGELOG,
+    FRONTEND_BUILD_DIR,
+    CACHE_DIR,
+    STATIC_DIR,
+    MODEL_FILTER_ENABLED,
+    MODEL_FILTER_LIST,
+    GLOBAL_LOG_LEVEL,
+    SRC_LOG_LEVELS,
+    WEBHOOK_URL,
+)
+from constants import ERROR_MESSAGES
+
+logging.basicConfig(stream=sys.stdout, level=GLOBAL_LOG_LEVEL)
+log = logging.getLogger(__name__)
+log.setLevel(SRC_LOG_LEVELS["MAIN"])
 
 
 class SPAStaticFiles(StaticFiles):
@@ -40,25 +66,89 @@ class SPAStaticFiles(StaticFiles):
                 raise ex
 
 
-proxy_config = ProxyConfig()
-
-
-async def config():
-    router, model_list, general_settings = await proxy_config.load_config(
-        router=None, config_file_path="./data/litellm/config.yaml"
-    )
-
-    await initialize(config="./data/litellm/config.yaml", telemetry=False)
-
-
-async def startup():
-    await config()
+print(
+    f"""
+  ___                    __        __   _     _   _ ___ 
+ / _ \ _ __   ___ _ __   \ \      / /__| |__ | | | |_ _|
+| | | | '_ \ / _ \ '_ \   \ \ /\ / / _ \ '_ \| | | || | 
+| |_| | |_) |  __/ | | |   \ V  V /  __/ |_) | |_| || | 
+ \___/| .__/ \___|_| |_|    \_/\_/ \___|_.__/ \___/|___|
+      |_|                                               
 
+      
+v{VERSION} - building the best open-source AI user interface.      
+https://github.com/open-webui/open-webui
+"""
+)
 
 app = FastAPI(docs_url="/docs" if ENV == "dev" else None, redoc_url=None)
 
+app.state.MODEL_FILTER_ENABLED = MODEL_FILTER_ENABLED
+app.state.MODEL_FILTER_LIST = MODEL_FILTER_LIST
+
+app.state.WEBHOOK_URL = WEBHOOK_URL
+
 origins = ["*"]
 
+
+class RAGMiddleware(BaseHTTPMiddleware):
+    async def dispatch(self, request: Request, call_next):
+        if request.method == "POST" and (
+            "/api/chat" in request.url.path or "/chat/completions" in request.url.path
+        ):
+            log.debug(f"request.url.path: {request.url.path}")
+
+            # Read the original request body
+            body = await request.body()
+            # Decode body to string
+            body_str = body.decode("utf-8")
+            # Parse string to JSON
+            data = json.loads(body_str) if body_str else {}
+
+            # Example: Add a new key-value pair or modify existing ones
+            # data["modified"] = True  # Example modification
+            if "docs" in data:
+                data = {**data}
+                data["messages"] = rag_messages(
+                    data["docs"],
+                    data["messages"],
+                    rag_app.state.RAG_TEMPLATE,
+                    rag_app.state.TOP_K,
+                    rag_app.state.RAG_EMBEDDING_ENGINE,
+                    rag_app.state.RAG_EMBEDDING_MODEL,
+                    rag_app.state.sentence_transformer_ef,
+                    rag_app.state.RAG_OPENAI_API_KEY,
+                    rag_app.state.RAG_OPENAI_API_BASE_URL,
+                )
+                del data["docs"]
+
+                log.debug(f"data['messages']: {data['messages']}")
+
+            modified_body_bytes = json.dumps(data).encode("utf-8")
+
+            # Replace the request body with the modified one
+            request._body = modified_body_bytes
+
+            # Set custom header to ensure content-length matches new body length
+            request.headers.__dict__["_list"] = [
+                (b"content-length", str(len(modified_body_bytes)).encode("utf-8")),
+                *[
+                    (k, v)
+                    for k, v in request.headers.raw
+                    if k.lower() != b"content-length"
+                ],
+            ]
+
+        response = await call_next(request)
+        return response
+
+    async def _receive(self, body: bytes):
+        return {"type": "http.request", "body": body, "more_body": False}
+
+
+app.add_middleware(RAGMiddleware)
+
+
 app.add_middleware(
     CORSMiddleware,
     allow_origins=origins,
@@ -68,11 +158,6 @@ app.add_middleware(
 )
 
 
-@app.on_event("startup")
-async def on_startup():
-    await startup()
-
-
 @app.middleware("http")
 async def check_url(request: Request, call_next):
     start_time = int(time.time())
@@ -83,25 +168,15 @@ async def check_url(request: Request, call_next):
     return response
 
 
-@litellm_app.middleware("http")
-async def auth_middleware(request: Request, call_next):
-    auth_header = request.headers.get("Authorization", "")
-
-    if ENV != "dev":
-        try:
-            user = get_current_user(get_http_authorization_cred(auth_header))
-            print(user)
-        except Exception as e:
-            return JSONResponse(status_code=400, content={"detail": str(e)})
-
-    response = await call_next(request)
-    return response
+@app.on_event("startup")
+async def on_startup():
+    await litellm_app_startup()
 
 
 app.mount("/api/v1", webui_app)
 app.mount("/litellm/api", litellm_app)
 
-app.mount("/ollama/api", ollama_app)
+app.mount("/ollama", ollama_app)
 app.mount("/openai/api", openai_app)
 
 app.mount("/images/api/v1", images_app)
@@ -111,24 +186,129 @@ app.mount("/rag/api/v1", rag_app)
 
 @app.get("/api/config")
 async def get_app_config():
+    # Checking and Handling the Absence of 'ui' in CONFIG_DATA
 
+    default_locale = "en-US"
+    if "ui" in CONFIG_DATA:
+        default_locale = CONFIG_DATA["ui"].get("default_locale", "en-US")
+
+    # The Rest of the Function Now Uses the Variables Defined Above
     return {
         "status": True,
         "name": WEBUI_NAME,
         "version": VERSION,
+        "default_locale": default_locale,
         "images": images_app.state.ENABLED,
         "default_models": webui_app.state.DEFAULT_MODELS,
         "default_prompt_suggestions": webui_app.state.DEFAULT_PROMPT_SUGGESTIONS,
+        "trusted_header_auth": bool(webui_app.state.AUTH_TRUSTED_EMAIL_HEADER),
+    }
+
+
+@app.get("/api/config/model/filter")
+async def get_model_filter_config(user=Depends(get_admin_user)):
+    return {
+        "enabled": app.state.MODEL_FILTER_ENABLED,
+        "models": app.state.MODEL_FILTER_LIST,
+    }
+
+
+class ModelFilterConfigForm(BaseModel):
+    enabled: bool
+    models: List[str]
+
+
+@app.post("/api/config/model/filter")
+async def update_model_filter_config(
+    form_data: ModelFilterConfigForm, user=Depends(get_admin_user)
+):
+    app.state.MODEL_FILTER_ENABLED = form_data.enabled
+    app.state.MODEL_FILTER_LIST = form_data.models
+
+    ollama_app.state.MODEL_FILTER_ENABLED = app.state.MODEL_FILTER_ENABLED
+    ollama_app.state.MODEL_FILTER_LIST = app.state.MODEL_FILTER_LIST
+
+    openai_app.state.MODEL_FILTER_ENABLED = app.state.MODEL_FILTER_ENABLED
+    openai_app.state.MODEL_FILTER_LIST = app.state.MODEL_FILTER_LIST
+
+    litellm_app.state.MODEL_FILTER_ENABLED = app.state.MODEL_FILTER_ENABLED
+    litellm_app.state.MODEL_FILTER_LIST = app.state.MODEL_FILTER_LIST
+
+    return {
+        "enabled": app.state.MODEL_FILTER_ENABLED,
+        "models": app.state.MODEL_FILTER_LIST,
+    }
+
+
+@app.get("/api/webhook")
+async def get_webhook_url(user=Depends(get_admin_user)):
+    return {
+        "url": app.state.WEBHOOK_URL,
+    }
+
+
+class UrlForm(BaseModel):
+    url: str
+
+
+@app.post("/api/webhook")
+async def update_webhook_url(form_data: UrlForm, user=Depends(get_admin_user)):
+    app.state.WEBHOOK_URL = form_data.url
+
+    webui_app.state.WEBHOOK_URL = app.state.WEBHOOK_URL
+
+    return {
+        "url": app.state.WEBHOOK_URL,
+    }
+
+
+@app.get("/api/version")
+async def get_app_config():
+    return {
+        "version": VERSION,
     }
 
 
 @app.get("/api/changelog")
 async def get_app_changelog():
-    return CHANGELOG
+    return {key: CHANGELOG[key] for idx, key in enumerate(CHANGELOG) if idx < 5}
 
 
-app.mount("/static", StaticFiles(directory="static"), name="static")
+@app.get("/api/version/updates")
+async def get_app_latest_release_version():
+    try:
+        async with aiohttp.ClientSession() as session:
+            async with session.get(
+                "https://api.github.com/repos/open-webui/open-webui/releases/latest"
+            ) as response:
+                response.raise_for_status()
+                data = await response.json()
+                latest_version = data["tag_name"]
 
+                return {"current": VERSION, "latest": latest_version[1:]}
+    except aiohttp.ClientError as e:
+        raise HTTPException(
+            status_code=status.HTTP_503_SERVICE_UNAVAILABLE,
+            detail=ERROR_MESSAGES.RATE_LIMIT_EXCEEDED,
+        )
+
+
+@app.get("/manifest.json")
+async def get_manifest_json():
+    return {
+        "name": WEBUI_NAME,
+        "short_name": WEBUI_NAME,
+        "start_url": "/",
+        "display": "standalone",
+        "background_color": "#343541",
+        "theme_color": "#343541",
+        "orientation": "portrait-primary",
+        "icons": [{"src": "/favicon.png", "type": "image/png", "sizes": "844x884"}],
+    }
+
+
+app.mount("/static", StaticFiles(directory=STATIC_DIR), name="static")
+app.mount("/cache", StaticFiles(directory=CACHE_DIR), name="cache")
 
 app.mount(
     "/",

backend/requirements.txt

@@ -14,14 +14,19 @@ uuid
 requests
 aiohttp
 peewee
+peewee-migrate
 bcrypt
 
-litellm
+litellm==1.30.7
+boto3
+
+argon2-cffi
 apscheduler
 google-generativeai
 
 langchain
 langchain-community
+fake_useragent
 chromadb
 sentence_transformers
 pypdf
@@ -34,9 +39,15 @@ openpyxl
 pyxlsb
 xlrd
 
+opencv-python-headless
+rapidocr-onnxruntime
+
+fpdf2
+
 faster-whisper
 
 PyJWT
 pyjwt[crypto]
 
 black
+langfuse

backend/start.sh

@@ -7,16 +7,26 @@ KEY_FILE=.webui_secret_key
 
 PORT="${PORT:-8080}"
 if test "$WEBUI_SECRET_KEY $WEBUI_JWT_SECRET_KEY" = " "; then
-  echo No WEBUI_SECRET_KEY provided
+  echo "No WEBUI_SECRET_KEY provided"
 
   if ! [ -e "$KEY_FILE" ]; then
-    echo Generating WEBUI_SECRET_KEY
+    echo "Generating WEBUI_SECRET_KEY"
     # Generate a random value to use as a WEBUI_SECRET_KEY in case the user didn't provide one.
-    echo $(head -c 12 /dev/random | base64) > $KEY_FILE
+    echo $(head -c 12 /dev/random | base64) > "$KEY_FILE"
   fi
 
-  echo Loading WEBUI_SECRET_KEY from $KEY_FILE
-  WEBUI_SECRET_KEY=`cat $KEY_FILE`
+  echo "Loading WEBUI_SECRET_KEY from $KEY_FILE"
+  WEBUI_SECRET_KEY=$(cat "$KEY_FILE")
 fi
 
-WEBUI_SECRET_KEY="$WEBUI_SECRET_KEY" exec uvicorn main:app --host 0.0.0.0 --port "$PORT" --forwarded-allow-ips '*'
+if [ "$USE_OLLAMA_DOCKER" = "true" ]; then
+    echo "USE_OLLAMA is set to true, starting ollama serve."
+    ollama serve &
+fi
+
+if [ "$USE_CUDA_DOCKER" = "true" ]; then
+  echo "CUDA is enabled, appending LD_LIBRARY_PATH to include torch/cudnn & cublas libraries."
+  export LD_LIBRARY_PATH="$LD_LIBRARY_PATH:/usr/local/lib/python3.11/site-packages/torch/lib:/usr/local/lib/python3.11/site-packages/nvidia/cudnn/lib"
+fi
+
+WEBUI_SECRET_KEY="$WEBUI_SECRET_KEY" exec uvicorn main:app --host 0.0.0.0 --port "$PORT" --forwarded-allow-ips '*'

backend/utils/utils.py

@@ -1,6 +1,8 @@
 from fastapi.security import HTTPBearer, HTTPAuthorizationCredentials
 from fastapi import HTTPException, status, Depends
+
 from apps.web.models.users import Users
+
 from pydantic import BaseModel
 from typing import Union, Optional
 from constants import ERROR_MESSAGES
@@ -8,6 +10,7 @@ from passlib.context import CryptContext
 from datetime import datetime, timedelta
 import requests
 import jwt
+import uuid
 import logging
 import config
 
@@ -58,6 +61,11 @@ def extract_token_from_auth_header(auth_header: str):
     return auth_header[len("Bearer ") :]
 
 
+def create_api_key():
+    key = str(uuid.uuid4()).replace("-", "")
+    return f"sk-{key}"
+
+
 def get_http_authorization_cred(auth_header: str):
     try:
         scheme, credentials = auth_header.split(" ")
@@ -69,6 +77,10 @@ def get_http_authorization_cred(auth_header: str):
 def get_current_user(
     auth_token: HTTPAuthorizationCredentials = Depends(bearer_security),
 ):
+    # auth by api key
+    if auth_token.credentials.startswith("sk-"):
+        return get_current_user_by_api_key(auth_token.credentials)
+    # auth by jwt token
     data = decode_token(auth_token.credentials)
     if data != None and "id" in data:
         user = Users.get_user_by_id(data["id"])
@@ -85,6 +97,16 @@ def get_current_user(
         )
 
 
+def get_current_user_by_api_key(api_key: str):
+    user = Users.get_user_by_api_key(api_key)
+    if user is None:
+        raise HTTPException(
+            status_code=status.HTTP_401_UNAUTHORIZED,
+            detail=ERROR_MESSAGES.INVALID_TOKEN,
+        )
+    return user
+
+
 def get_verified_user(user=Depends(get_current_user)):
     if user.role not in {"user", "admin"}:
         raise HTTPException(

backend/utils/webhook.py

@@ -0,0 +1,54 @@
+import json
+import requests
+import logging
+
+from config import SRC_LOG_LEVELS, VERSION, WEBUI_FAVICON_URL, WEBUI_NAME
+
+log = logging.getLogger(__name__)
+log.setLevel(SRC_LOG_LEVELS["WEBHOOK"])
+
+
+def post_webhook(url: str, message: str, event_data: dict) -> bool:
+    try:
+        payload = {}
+
+        # Slack and Google Chat Webhooks
+        if "https://hooks.slack.com" in url or "https://chat.googleapis.com" in url:
+            payload["text"] = message
+        # Discord Webhooks
+        elif "https://discord.com/api/webhooks" in url:
+            payload["content"] = message
+        # Microsoft Teams Webhooks
+        elif "webhook.office.com" in url:
+            action = event_data.get("action", "undefined")
+            facts = [
+                {"name": name, "value": value}
+                for name, value in json.loads(event_data.get("user", {})).items()
+            ]
+            payload = {
+                "@type": "MessageCard",
+                "@context": "http://schema.org/extensions",
+                "themeColor": "0076D7",
+                "summary": message,
+                "sections": [
+                    {
+                        "activityTitle": message,
+                        "activitySubtitle": f"{WEBUI_NAME} ({VERSION}) - {action}",
+                        "activityImage": WEBUI_FAVICON_URL,
+                        "facts": facts,
+                        "markdown": True,
+                    }
+                ],
+            }
+        # Default Payload
+        else:
+            payload = {**event_data}
+
+        log.debug(f"payload: {payload}")
+        r = requests.post(url, json=payload)
+        r.raise_for_status()
+        log.debug(f"r.text: {r.text}")
+        return True
+    except Exception as e:
+        log.exception(e)
+        return False

confirm_remove.sh

@@ -0,0 +1,8 @@
+#!/bin/bash
+echo "Warning: This will remove all containers and volumes, including persistent data. Do you want to continue? [Y/N]"
+read ans
+if [ "$ans" == "Y" ] || [ "$ans" == "y" ]; then
+  docker-compose down -v
+else
+  echo "Operation cancelled."
+fi

docker-compose.amdgpu.yaml

@@ -0,0 +1,8 @@
+services:
+  ollama:
+    devices:
+      - /dev/kfd:/dev/kfd
+      - /dev/dri:/dev/dri
+    image: ollama/ollama:${OLLAMA_DOCKER_TAG-rocm}
+    environment:
+      - 'HSA_OVERRIDE_GFX_VERSION=${HSA_OVERRIDE_GFX_VERSION-11.0.0}'

docker-compose.yaml

@@ -8,15 +8,15 @@ services:
     pull_policy: always
     tty: true
     restart: unless-stopped
-    image: ollama/ollama:latest
+    image: ollama/ollama:${OLLAMA_DOCKER_TAG-latest}
 
   open-webui:
     build:
       context: .
       args:
-        OLLAMA_API_BASE_URL: '/ollama/api'
+        OLLAMA_BASE_URL: '/ollama'
       dockerfile: Dockerfile
-    image: ghcr.io/open-webui/open-webui:main
+    image: ghcr.io/open-webui/open-webui:${WEBUI_DOCKER_TAG-main}
     container_name: open-webui
     volumes:
       - open-webui:/app/backend/data
@@ -25,7 +25,7 @@ services:
     ports:
       - ${OPEN_WEBUI_PORT-3000}:8080
     environment:
-      - 'OLLAMA_API_BASE_URL=http://ollama:11434/api'
+      - 'OLLAMA_BASE_URL=http://ollama:11434'
       - 'WEBUI_SECRET_KEY='
     extra_hosts:
       - host.docker.internal:host-gateway

docs/CONTRIBUTING.md

@@ -50,6 +50,18 @@ We welcome pull requests. Before submitting one, please:
 
 Help us make Open WebUI more accessible by improving documentation, writing tutorials, or creating guides on setting up and optimizing the web UI.
 
+### 🌐 Translations and Internationalization
+
+Help us make Open WebUI available to a wider audience. In this section, we'll guide you through the process of adding new translations to the project.
+
+We use JSON files to store translations. You can find the existing translation files in the `src/lib/i18n/locales` directory. Each directory corresponds to a specific language, for example, `en-US` for English (US), `fr-FR` for French (France) and so on. You can refer to [ISO 639 Language Codes][http://www.lingoes.net/en/translator/langcode.htm] to find the appropriate code for a specific language.
+
+To add a new language:
+
+- Create a new directory in the `src/lib/i18n/locales` path with the appropriate language code as its name. For instance, if you're adding translations for Spanish (Spain), create a new directory named `es-ES`.
+- Copy the American English translation file(s) (from `en-US` directory in `src/lib/i18n/locale`) to this new directory and update the string values in JSON format according to your language. Make sure to preserve the structure of the JSON object.
+- Add the language code and its respective title to languages file at `src/lib/i18n/locales/languages.json`.
+
 ### 🤔 Questions & Feedback
 
 Got questions or feedback? Join our [Discord community](https://discord.gg/5rJgQTnV4s) or open an issue. We're here to help!

i18next-parser.config.ts

@@ -0,0 +1,38 @@
+// i18next-parser.config.ts
+import { getLanguages } from './src/lib/i18n/index.ts';
+
+const getLangCodes = async () => {
+	const languages = await getLanguages();
+	return languages.map((l) => l.code);
+};
+
+export default {
+	contextSeparator: '_',
+	createOldCatalogs: false,
+	defaultNamespace: 'translation',
+	defaultValue: '',
+	indentation: 2,
+	keepRemoved: false,
+	keySeparator: false,
+	lexers: {
+		svelte: ['JavascriptLexer'],
+		js: ['JavascriptLexer'],
+		ts: ['JavascriptLexer'],
+
+		default: ['JavascriptLexer']
+	},
+	lineEnding: 'auto',
+	locales: await getLangCodes(),
+	namespaceSeparator: false,
+	output: 'src/lib/i18n/locales/$LOCALE/$NAMESPACE.json',
+	pluralSeparator: '_',
+	input: 'src/**/*.{js,svelte}',
+	sort: true,
+	verbose: true,
+	failOnWarnings: false,
+	failOnUpdate: false,
+	customValueTemplate: null,
+	resetDefaultValueLocale: null,
+	i18nextOptions: null,
+	yamlOptions: null
+};

kubernetes/helm/templates/_helpers.tpl

@@ -7,7 +7,11 @@ ollama
 {{- end -}}
 
 {{- define "ollama.url" -}}
-{{- printf "http://%s.%s.svc.cluster.local:%d/api" (include "ollama.name" .) (.Release.Namespace) (.Values.ollama.service.port | int) }}
+{{- if .Values.ollama.externalHost }}
+{{- printf .Values.ollama.externalHost }}
+{{- else }}
+{{- printf "http://%s.%s.svc.cluster.local:%d" (include "ollama.name" .) (.Release.Namespace) (.Values.ollama.service.port | int) }}
+{{- end }}
 {{- end }}
 
 {{- define "chart.name" -}}

kubernetes/helm/templates/ollama-service.yaml

@@ -1,3 +1,4 @@
+{{- if not .Values.ollama.externalHost }}
 apiVersion: v1
 kind: Service
 metadata:
@@ -19,3 +20,4 @@ spec:
     port: {{ .port }}
     targetPort: http
 {{- end }}
+{{- end }}

kubernetes/helm/templates/ollama-statefulset.yaml

@@ -1,3 +1,4 @@
+{{- if not .Values.ollama.externalHost }}
 apiVersion: apps/v1
 kind: StatefulSet
 metadata:
@@ -88,9 +89,10 @@ spec:
       resources:
         requests:
           storage: {{ .Values.ollama.persistence.size | quote }}
-      storageClass: {{ .Values.ollama.persistence.storageClass }}
+      storageClassName: {{ .Values.ollama.persistence.storageClass }}
       {{- with .Values.ollama.persistence.selector }}
       selector:
         {{- toYaml . | nindent 8 }}
       {{- end }}
       {{- end }}
+{{- end }}

kubernetes/helm/templates/webui-deployment.yaml

@@ -40,7 +40,7 @@ spec:
         - name: data
           mountPath: /app/backend/data
         env:
-        - name: OLLAMA_API_BASE_URL
+        - name: OLLAMA_BASE_URL
           value: {{ include "ollama.url" . | quote }}
         tty: true
       {{- with .Values.webui.nodeSelector }}

kubernetes/helm/templates/webui-pvc.yaml

@@ -17,7 +17,9 @@ spec:
   resources:
     requests:
       storage: {{ .Values.webui.persistence.size }}
-  storageClass: {{ .Values.webui.persistence.storageClass }}
+  {{- if .Values.webui.persistence.storageClass }}
+  storageClassName: {{ .Values.webui.persistence.storageClass }}
+  {{- end }}
   {{- with .Values.webui.persistence.selector }}
   selector:
     {{- toYaml . | nindent 4 }}

kubernetes/helm/templates/webui-service.yaml

@@ -4,6 +4,9 @@ metadata:
   name: {{ include "open-webui.name" . }}
   labels:
     {{- include "open-webui.labels" . | nindent 4 }}
+    {{- with .Values.webui.service.labels }}
+    {{- toYaml . | nindent 4 }}
+    {{- end }}
   {{- with .Values.webui.service.annotations }}
   annotations:
     {{- toYaml . | nindent 4 }}
@@ -11,14 +14,16 @@ metadata:
 spec:
   selector:
     {{- include "open-webui.selectorLabels" . | nindent 4 }}
-{{- with .Values.webui.service }}
-  type: {{ .type }}
+  type: {{ .Values.webui.service.type | default "ClusterIP" }}
   ports:
   - protocol: TCP
     name: http
-    port: {{ .port }}
+    port: {{ .Values.webui.service.port }}
     targetPort: http
-    {{- if .nodePort }}
-    nodePort: {{ .nodePort | int }}
+    {{- if .Values.webui.service.nodePort }}
+    nodePort: {{ .Values.webui.service.nodePort | int }}
     {{- end }}
-{{- end }}
+  {{- if .Values.webui.service.loadBalancerClass }}
+  loadBalancerClass: {{ .Values.webui.service.loadBalancerClass | quote }}
+  {{- end }}
+

kubernetes/helm/values.yaml

@@ -1,6 +1,7 @@
 nameOverride: ""
 
 ollama:
+  externalHost: ""
   annotations: {}
   podAnnotations: {}
   replicaCount: 1
@@ -70,3 +71,5 @@ webui:
     port: 80
     containerPort: 8080
     nodePort: ""
+    labels: {}
+    loadBalancerClass: "" 

kubernetes/manifest/base/webui-deployment.yaml

@@ -26,8 +26,8 @@ spec:
             cpu: "1000m"
             memory: "1Gi"
         env:
-        - name: OLLAMA_API_BASE_URL
-          value: "http://ollama-service.open-webui.svc.cluster.local:11434/api"
+        - name: OLLAMA_BASE_URL
+          value: "http://ollama-service.open-webui.svc.cluster.local:11434"
         tty: true
         volumeMounts:
         - name: webui-volume
@@ -35,4 +35,4 @@ spec:
       volumes:
       - name: webui-volume
         persistentVolumeClaim:
-          claimName: ollama-webui-pvc          
+          claimName: open-webui-pvc          

kubernetes/manifest/base/webui-pvc.yaml

@@ -2,8 +2,8 @@ apiVersion: v1
 kind: PersistentVolumeClaim
 metadata:
   labels:
-    app: ollama-webui
-  name: ollama-webui-pvc
+    app: open-webui
+  name: open-webui-pvc
   namespace: open-webui
 spec:
   accessModes: ["ReadWriteOnce"]

package.json

@@ -1,6 +1,6 @@
 {
 	"name": "open-webui",
-	"version": "0.1.103",
+	"version": "0.1.119",
 	"private": true,
 	"scripts": {
 		"dev": "vite dev --host",
@@ -13,7 +13,8 @@
 		"lint:types": "npm run check",
 		"lint:backend": "pylint backend/",
 		"format": "prettier --plugin-search-dir --write '**/*.{js,ts,svelte,css,md,html,json}'",
-		"format:backend": "yapf --recursive backend -p -i"
+		"format:backend": "black . --exclude \"/venv/\"",
+		"i18n:parse": "i18next --config i18next-parser.config.ts && prettier --write 'src/lib/i18n/**/*.{js,json}'"
 	},
 	"devDependencies": {
 		"@sveltejs/adapter-auto": "^2.0.0",
@@ -27,6 +28,7 @@
 		"eslint": "^8.56.0",
 		"eslint-config-prettier": "^8.5.0",
 		"eslint-plugin-svelte": "^2.30.0",
+		"i18next-parser": "^8.13.0",
 		"postcss": "^8.4.31",
 		"prettier": "^2.8.0",
 		"prettier-plugin-svelte": "^2.10.1",
@@ -42,15 +44,20 @@
 	"dependencies": {
 		"@sveltejs/adapter-node": "^1.3.1",
 		"async": "^3.2.5",
+		"bits-ui": "^0.19.7",
 		"dayjs": "^1.11.10",
 		"file-saver": "^2.0.5",
 		"highlight.js": "^11.9.0",
+		"i18next": "^23.10.0",
+		"i18next-browser-languagedetector": "^7.2.0",
+		"i18next-resources-to-backend": "^1.2.0",
 		"idb": "^7.1.1",
 		"js-sha256": "^0.10.1",
+		"jspdf": "^2.5.1",
 		"katex": "^0.16.9",
 		"marked": "^9.1.0",
-		"svelte-french-toast": "^1.2.0",
+		"svelte-sonner": "^0.3.19",
 		"tippy.js": "^6.3.7",
 		"uuid": "^9.0.1"
 	}
-}
+}

run-compose.sh

@@ -182,7 +182,7 @@ else
         export OLLAMA_DATA_DIR=$data_dir # Set OLLAMA_DATA_DIR environment variable
     fi
     if [[ -n $webui_port ]]; then
-        export OLLAMA_WEBUI_PORT=$webui_port # Set OLLAMA_WEBUI_PORT environment variable
+        export OPEN_WEBUI_PORT=$webui_port # Set OPEN_WEBUI_PORT environment variable
     fi
     DEFAULT_COMPOSE_COMMAND+=" up -d"
     DEFAULT_COMPOSE_COMMAND+=" --remove-orphans"

src/app.css

@@ -28,6 +28,25 @@ math {
 	@apply rounded-lg;
 }
 
+ol > li {
+	counter-increment: list-number;
+	display: block;
+	margin-bottom: 0;
+	margin-top: 0;
+	min-height: 28px;
+}
+
+.prose ol > li::before {
+	content: counters(list-number, '.') '.';
+	padding-right: 0.5rem;
+	color: var(--tw-prose-counters);
+	font-weight: 400;
+}
+
+li p {
+	display: inline;
+}
+
 ::-webkit-scrollbar-thumb {
 	--tw-border-opacity: 1;
 	background-color: rgba(217, 217, 227, 0.8);
@@ -59,3 +78,7 @@ select {
 	/* for Chrome */
 	-webkit-appearance: none;
 }
+
+.katex-mathml {
+	display: none;
+}

src/app.html

@@ -3,23 +3,44 @@
 	<head>
 		<meta charset="utf-8" />
 		<link rel="icon" href="%sveltekit.assets%/favicon.png" />
-		<link rel="manifest" href="%sveltekit.assets%/manifest.json" />
+		<link rel="manifest" href="%sveltekit.assets%/manifest.json" crossorigin="use-credentials" />
 		<meta name="viewport" content="width=device-width, initial-scale=1, maximum-scale=1" />
 		<meta name="robots" content="noindex,nofollow" />
 		<script>
 			// On page load or when changing themes, best to add inline in `head` to avoid FOUC
-			if (
-				localStorage.theme === 'light' ||
-				(!('theme' in localStorage) && window.matchMedia('(prefers-color-scheme: light)').matches)
-			) {
-				document.documentElement.classList.add('light');
-			} else if (localStorage.theme) {
-				localStorage.theme.split(' ').forEach((e) => {
-					document.documentElement.classList.add(e);
+			(() => {
+				if (localStorage?.theme && localStorage?.theme.includes('oled')) {
+					document.documentElement.style.setProperty('--color-gray-900', '#000000');
+					document.documentElement.style.setProperty('--color-gray-950', '#000000');
+					document.documentElement.classList.add('dark');
+				} else if (
+					localStorage.theme === 'light' ||
+					(!('theme' in localStorage) && window.matchMedia('(prefers-color-scheme: light)').matches)
+				) {
+					document.documentElement.classList.add('light');
+				} else if (localStorage.theme && localStorage.theme !== 'system') {
+					localStorage.theme.split(' ').forEach((e) => {
+						document.documentElement.classList.add(e);
+					});
+				} else if (localStorage.theme && localStorage.theme === 'system') {
+					systemTheme = window.matchMedia('(prefers-color-scheme: dark)').matches;
+					document.documentElement.classList.add(systemTheme ? 'dark' : 'light');
+				} else {
+					document.documentElement.classList.add('dark');
+				}
+
+				window.matchMedia('(prefers-color-scheme: dark)').addListener((e) => {
+					if (localStorage.theme === 'system') {
+						if (e.matches) {
+							document.documentElement.classList.add('dark');
+							document.documentElement.classList.remove('light');
+						} else {
+							document.documentElement.classList.add('light');
+							document.documentElement.classList.remove('dark');
+						}
+					}
 				});
-			} else {
-				document.documentElement.classList.add('dark');
-			}
+			})();
 		</script>
 
 		%sveltekit.head%

src/lib/apis/auths/index.ts

@@ -58,7 +58,12 @@ export const userSignIn = async (email: string, password: string) => {
 	return res;
 };
 
-export const userSignUp = async (name: string, email: string, password: string) => {
+export const userSignUp = async (
+	name: string,
+	email: string,
+	password: string,
+	profile_image_url: string
+) => {
 	let error = null;
 
 	const res = await fetch(`${WEBUI_API_BASE_URL}/auths/signup`, {
@@ -69,7 +74,8 @@ export const userSignUp = async (name: string, email: string, password: string)
 		body: JSON.stringify({
 			name: name,
 			email: email,
-			password: password
+			password: password,
+			profile_image_url: profile_image_url
 		})
 	})
 		.then(async (res) => {
@@ -318,3 +324,78 @@ export const updateJWTExpiresDuration = async (token: string, duration: string)
 
 	return res;
 };
+
+export const createAPIKey = async (token: string) => {
+	let error = null;
+
+	const res = await fetch(`${WEBUI_API_BASE_URL}/auths/api_key`, {
+		method: 'POST',
+		headers: {
+			'Content-Type': 'application/json',
+			Authorization: `Bearer ${token}`
+		}
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.catch((err) => {
+			console.log(err);
+			error = err.detail;
+			return null;
+		});
+	if (error) {
+		throw error;
+	}
+	return res.api_key;
+};
+
+export const getAPIKey = async (token: string) => {
+	let error = null;
+
+	const res = await fetch(`${WEBUI_API_BASE_URL}/auths/api_key`, {
+		method: 'GET',
+		headers: {
+			'Content-Type': 'application/json',
+			Authorization: `Bearer ${token}`
+		}
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.catch((err) => {
+			console.log(err);
+			error = err.detail;
+			return null;
+		});
+	if (error) {
+		throw error;
+	}
+	return res.api_key;
+};
+
+export const deleteAPIKey = async (token: string) => {
+	let error = null;
+
+	const res = await fetch(`${WEBUI_API_BASE_URL}/auths/api_key`, {
+		method: 'DELETE',
+		headers: {
+			'Content-Type': 'application/json',
+			Authorization: `Bearer ${token}`
+		}
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.catch((err) => {
+			console.log(err);
+			error = err.detail;
+			return null;
+		});
+	if (error) {
+		throw error;
+	}
+	return res;
+};

src/lib/apis/chats/index.ts

@@ -218,6 +218,102 @@ export const getChatById = async (token: string, id: string) => {
 	return res;
 };
 
+export const getChatByShareId = async (token: string, share_id: string) => {
+	let error = null;
+
+	const res = await fetch(`${WEBUI_API_BASE_URL}/chats/share/${share_id}`, {
+		method: 'GET',
+		headers: {
+			Accept: 'application/json',
+			'Content-Type': 'application/json',
+			...(token && { authorization: `Bearer ${token}` })
+		}
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.then((json) => {
+			return json;
+		})
+		.catch((err) => {
+			error = err;
+
+			console.log(err);
+			return null;
+		});
+
+	if (error) {
+		throw error;
+	}
+
+	return res;
+};
+
+export const shareChatById = async (token: string, id: string) => {
+	let error = null;
+
+	const res = await fetch(`${WEBUI_API_BASE_URL}/chats/${id}/share`, {
+		method: 'POST',
+		headers: {
+			Accept: 'application/json',
+			'Content-Type': 'application/json',
+			...(token && { authorization: `Bearer ${token}` })
+		}
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.then((json) => {
+			return json;
+		})
+		.catch((err) => {
+			error = err;
+
+			console.log(err);
+			return null;
+		});
+
+	if (error) {
+		throw error;
+	}
+
+	return res;
+};
+
+export const deleteSharedChatById = async (token: string, id: string) => {
+	let error = null;
+
+	const res = await fetch(`${WEBUI_API_BASE_URL}/chats/${id}/share`, {
+		method: 'DELETE',
+		headers: {
+			Accept: 'application/json',
+			'Content-Type': 'application/json',
+			...(token && { authorization: `Bearer ${token}` })
+		}
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.then((json) => {
+			return json;
+		})
+		.catch((err) => {
+			error = err;
+
+			console.log(err);
+			return null;
+		});
+
+	if (error) {
+		throw error;
+	}
+
+	return res;
+};
+
 export const updateChatById = async (token: string, id: string, chat: object) => {
 	let error = null;
 
@@ -439,7 +535,7 @@ export const deleteAllChats = async (token: string) => {
 			return json;
 		})
 		.catch((err) => {
-			error = err;
+			error = err.detail;
 
 			console.log(err);
 			return null;

src/lib/apis/documents/index.ts

@@ -5,7 +5,8 @@ export const createNewDoc = async (
 	collection_name: string,
 	filename: string,
 	name: string,
-	title: string
+	title: string,
+	content: object | null = null
 ) => {
 	let error = null;
 
@@ -20,7 +21,8 @@ export const createNewDoc = async (
 			collection_name: collection_name,
 			filename: filename,
 			name: name,
-			title: title
+			title: title,
+			...(content ? { content: JSON.stringify(content) } : {})
 		})
 	})
 		.then(async (res) => {

src/lib/apis/images/index.ts

@@ -1,9 +1,9 @@
 import { IMAGES_API_BASE_URL } from '$lib/constants';
 
-export const getImageGenerationEnabledStatus = async (token: string = '') => {
+export const getImageGenerationConfig = async (token: string = '') => {
 	let error = null;
 
-	const res = await fetch(`${IMAGES_API_BASE_URL}/enabled`, {
+	const res = await fetch(`${IMAGES_API_BASE_URL}/config`, {
 		method: 'GET',
 		headers: {
 			Accept: 'application/json',
@@ -32,10 +32,50 @@ export const getImageGenerationEnabledStatus = async (token: string = '') => {
 	return res;
 };
 
-export const toggleImageGenerationEnabledStatus = async (token: string = '') => {
+export const updateImageGenerationConfig = async (
+	token: string = '',
+	engine: string,
+	enabled: boolean
+) => {
 	let error = null;
 
-	const res = await fetch(`${IMAGES_API_BASE_URL}/enabled/toggle`, {
+	const res = await fetch(`${IMAGES_API_BASE_URL}/config/update`, {
+		method: 'POST',
+		headers: {
+			Accept: 'application/json',
+			'Content-Type': 'application/json',
+			...(token && { authorization: `Bearer ${token}` })
+		},
+		body: JSON.stringify({
+			engine,
+			enabled
+		})
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.catch((err) => {
+			console.log(err);
+			if ('detail' in err) {
+				error = err.detail;
+			} else {
+				error = 'Server connection failed';
+			}
+			return null;
+		});
+
+	if (error) {
+		throw error;
+	}
+
+	return res;
+};
+
+export const getOpenAIKey = async (token: string = '') => {
+	let error = null;
+
+	const res = await fetch(`${IMAGES_API_BASE_URL}/key`, {
 		method: 'GET',
 		headers: {
 			Accept: 'application/json',
@@ -61,10 +101,45 @@ export const toggleImageGenerationEnabledStatus = async (token: string = '') =>
 		throw error;
 	}
 
-	return res;
+	return res.OPENAI_API_KEY;
 };
 
-export const getAUTOMATIC1111Url = async (token: string = '') => {
+export const updateOpenAIKey = async (token: string = '', key: string) => {
+	let error = null;
+
+	const res = await fetch(`${IMAGES_API_BASE_URL}/key/update`, {
+		method: 'POST',
+		headers: {
+			Accept: 'application/json',
+			'Content-Type': 'application/json',
+			...(token && { authorization: `Bearer ${token}` })
+		},
+		body: JSON.stringify({
+			key: key
+		})
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.catch((err) => {
+			console.log(err);
+			if ('detail' in err) {
+				error = err.detail;
+			} else {
+				error = 'Server connection failed';
+			}
+			return null;
+		});
+
+	if (error) {
+		throw error;
+	}
+
+	return res.OPENAI_API_KEY;
+};
+
+export const getImageGenerationEngineUrls = async (token: string = '') => {
 	let error = null;
 
 	const res = await fetch(`${IMAGES_API_BASE_URL}/url`, {
@@ -93,10 +168,10 @@ export const getAUTOMATIC1111Url = async (token: string = '') => {
 		throw error;
 	}
 
-	return res.AUTOMATIC1111_BASE_URL;
+	return res;
 };
 
-export const updateAUTOMATIC1111Url = async (token: string = '', url: string) => {
+export const updateImageGenerationEngineUrls = async (token: string = '', urls: object = {}) => {
 	let error = null;
 
 	const res = await fetch(`${IMAGES_API_BASE_URL}/url/update`, {
@@ -107,7 +182,7 @@ export const updateAUTOMATIC1111Url = async (token: string = '', url: string) =>
 			...(token && { authorization: `Bearer ${token}` })
 		},
 		body: JSON.stringify({
-			url: url
+			...urls
 		})
 	})
 		.then(async (res) => {
@@ -128,7 +203,7 @@ export const updateAUTOMATIC1111Url = async (token: string = '', url: string) =>
 		throw error;
 	}
 
-	return res.AUTOMATIC1111_BASE_URL;
+	return res;
 };
 
 export const getImageSize = async (token: string = '') => {
@@ -263,7 +338,7 @@ export const updateImageSteps = async (token: string = '', steps: number) => {
 	return res.IMAGE_STEPS;
 };
 
-export const getDiffusionModels = async (token: string = '') => {
+export const getImageGenerationModels = async (token: string = '') => {
 	let error = null;
 
 	const res = await fetch(`${IMAGES_API_BASE_URL}/models`, {
@@ -295,7 +370,7 @@ export const getDiffusionModels = async (token: string = '') => {
 	return res;
 };
 
-export const getDefaultDiffusionModel = async (token: string = '') => {
+export const getDefaultImageGenerationModel = async (token: string = '') => {
 	let error = null;
 
 	const res = await fetch(`${IMAGES_API_BASE_URL}/models/default`, {
@@ -327,7 +402,7 @@ export const getDefaultDiffusionModel = async (token: string = '') => {
 	return res.model;
 };
 
-export const updateDefaultDiffusionModel = async (token: string = '', model: string) => {
+export const updateDefaultImageGenerationModel = async (token: string = '', model: string) => {
 	let error = null;
 
 	const res = await fetch(`${IMAGES_API_BASE_URL}/models/default/update`, {

src/lib/apis/index.ts

@@ -19,6 +19,10 @@ export const getBackendConfig = async () => {
 			return null;
 		});
 
+	if (error) {
+		throw error;
+	}
+
 	return res;
 };
 
@@ -41,5 +45,154 @@ export const getChangelog = async () => {
 			return null;
 		});
 
+	if (error) {
+		throw error;
+	}
+
 	return res;
 };
+
+export const getVersionUpdates = async () => {
+	let error = null;
+
+	const res = await fetch(`${WEBUI_BASE_URL}/api/version/updates`, {
+		method: 'GET',
+		headers: {
+			'Content-Type': 'application/json'
+		}
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.catch((err) => {
+			console.log(err);
+			error = err;
+			return null;
+		});
+
+	if (error) {
+		throw error;
+	}
+
+	return res;
+};
+
+export const getModelFilterConfig = async (token: string) => {
+	let error = null;
+
+	const res = await fetch(`${WEBUI_BASE_URL}/api/config/model/filter`, {
+		method: 'GET',
+		headers: {
+			'Content-Type': 'application/json',
+			Authorization: `Bearer ${token}`
+		}
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.catch((err) => {
+			console.log(err);
+			error = err;
+			return null;
+		});
+
+	if (error) {
+		throw error;
+	}
+
+	return res;
+};
+
+export const updateModelFilterConfig = async (
+	token: string,
+	enabled: boolean,
+	models: string[]
+) => {
+	let error = null;
+
+	const res = await fetch(`${WEBUI_BASE_URL}/api/config/model/filter`, {
+		method: 'POST',
+		headers: {
+			'Content-Type': 'application/json',
+			Authorization: `Bearer ${token}`
+		},
+		body: JSON.stringify({
+			enabled: enabled,
+			models: models
+		})
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.catch((err) => {
+			console.log(err);
+			error = err;
+			return null;
+		});
+
+	if (error) {
+		throw error;
+	}
+
+	return res;
+};
+
+export const getWebhookUrl = async (token: string) => {
+	let error = null;
+
+	const res = await fetch(`${WEBUI_BASE_URL}/api/webhook`, {
+		method: 'GET',
+		headers: {
+			'Content-Type': 'application/json',
+			Authorization: `Bearer ${token}`
+		}
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.catch((err) => {
+			console.log(err);
+			error = err;
+			return null;
+		});
+
+	if (error) {
+		throw error;
+	}
+
+	return res.url;
+};
+
+export const updateWebhookUrl = async (token: string, url: string) => {
+	let error = null;
+
+	const res = await fetch(`${WEBUI_BASE_URL}/api/webhook`, {
+		method: 'POST',
+		headers: {
+			'Content-Type': 'application/json',
+			Authorization: `Bearer ${token}`
+		},
+		body: JSON.stringify({
+			url: url
+		})
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.catch((err) => {
+			console.log(err);
+			error = err;
+			return null;
+		});
+
+	if (error) {
+		throw error;
+	}
+
+	return res.url;
+};

src/lib/apis/litellm/index.ts

@@ -33,7 +33,7 @@ export const getLiteLLMModels = async (token: string = '') => {
 					id: model.id,
 					name: model.name ?? model.id,
 					external: true,
-					source: 'litellm'
+					source: 'LiteLLM'
 				}))
 				.sort((a, b) => {
 					return a.name.localeCompare(b.name);
@@ -77,6 +77,7 @@ type AddLiteLLMModelForm = {
 	api_base: string;
 	api_key: string;
 	rpm: string;
+	max_tokens: string;
 };
 
 export const addLiteLLMModel = async (token: string = '', payload: AddLiteLLMModelForm) => {
@@ -95,7 +96,8 @@ export const addLiteLLMModel = async (token: string = '', payload: AddLiteLLMMod
 				model: payload.model,
 				...(payload.api_base === '' ? {} : { api_base: payload.api_base }),
 				...(payload.api_key === '' ? {} : { api_key: payload.api_key }),
-				...(isNaN(parseInt(payload.rpm)) ? {} : { rpm: parseInt(payload.rpm) })
+				...(isNaN(parseInt(payload.rpm)) ? {} : { rpm: parseInt(payload.rpm) }),
+				...(payload.max_tokens === '' ? {} : { max_tokens: payload.max_tokens })
 			}
 		})
 	})

src/lib/apis/ollama/index.ts

@@ -1,9 +1,10 @@
 import { OLLAMA_API_BASE_URL } from '$lib/constants';
+import { promptTemplate } from '$lib/utils';
 
-export const getOllamaAPIUrl = async (token: string = '') => {
+export const getOllamaUrls = async (token: string = '') => {
 	let error = null;
 
-	const res = await fetch(`${OLLAMA_API_BASE_URL}/url`, {
+	const res = await fetch(`${OLLAMA_API_BASE_URL}/urls`, {
 		method: 'GET',
 		headers: {
 			Accept: 'application/json',
@@ -29,13 +30,13 @@ export const getOllamaAPIUrl = async (token: string = '') => {
 		throw error;
 	}
 
-	return res.OLLAMA_API_BASE_URL;
+	return res.OLLAMA_BASE_URLS;
 };
 
-export const updateOllamaAPIUrl = async (token: string = '', url: string) => {
+export const updateOllamaUrls = async (token: string = '', urls: string[]) => {
 	let error = null;
 
-	const res = await fetch(`${OLLAMA_API_BASE_URL}/url/update`, {
+	const res = await fetch(`${OLLAMA_API_BASE_URL}/urls/update`, {
 		method: 'POST',
 		headers: {
 			Accept: 'application/json',
@@ -43,7 +44,7 @@ export const updateOllamaAPIUrl = async (token: string = '', url: string) => {
 			...(token && { authorization: `Bearer ${token}` })
 		},
 		body: JSON.stringify({
-			url: url
+			urls: urls
 		})
 	})
 		.then(async (res) => {
@@ -64,13 +65,13 @@ export const updateOllamaAPIUrl = async (token: string = '', url: string) => {
 		throw error;
 	}
 
-	return res.OLLAMA_API_BASE_URL;
+	return res.OLLAMA_BASE_URLS;
 };
 
 export const getOllamaVersion = async (token: string = '') => {
 	let error = null;
 
-	const res = await fetch(`${OLLAMA_API_BASE_URL}/version`, {
+	const res = await fetch(`${OLLAMA_API_BASE_URL}/api/version`, {
 		method: 'GET',
 		headers: {
 			Accept: 'application/json',
@@ -102,7 +103,7 @@ export const getOllamaVersion = async (token: string = '') => {
 export const getOllamaModels = async (token: string = '') => {
 	let error = null;
 
-	const res = await fetch(`${OLLAMA_API_BASE_URL}/tags`, {
+	const res = await fetch(`${OLLAMA_API_BASE_URL}/api/tags`, {
 		method: 'GET',
 		headers: {
 			Accept: 'application/json',
@@ -144,14 +145,15 @@ export const generateTitle = async (
 ) => {
 	let error = null;
 
-	template = template.replace(/{{prompt}}/g, prompt);
+	template = promptTemplate(template, prompt);
 
 	console.log(template);
 
-	const res = await fetch(`${OLLAMA_API_BASE_URL}/generate`, {
+	const res = await fetch(`${OLLAMA_API_BASE_URL}/api/generate`, {
 		method: 'POST',
 		headers: {
-			'Content-Type': 'text/event-stream',
+			Accept: 'application/json',
+			'Content-Type': 'application/json',
 			Authorization: `Bearer ${token}`
 		},
 		body: JSON.stringify({
@@ -186,10 +188,11 @@ export const generatePrompt = async (token: string = '', model: string, conversa
 		conversation = '[no existing conversation]';
 	}
 
-	const res = await fetch(`${OLLAMA_API_BASE_URL}/generate`, {
+	const res = await fetch(`${OLLAMA_API_BASE_URL}/api/generate`, {
 		method: 'POST',
 		headers: {
-			'Content-Type': 'text/event-stream',
+			Accept: 'application/json',
+			'Content-Type': 'application/json',
 			Authorization: `Bearer ${token}`
 		},
 		body: JSON.stringify({
@@ -217,15 +220,69 @@ export const generatePrompt = async (token: string = '', model: string, conversa
 	return res;
 };
 
+export const generateEmbeddings = async (token: string = '', model: string, text: string) => {
+	let error = null;
+
+	const res = await fetch(`${OLLAMA_API_BASE_URL}/api/embeddings`, {
+		method: 'POST',
+		headers: {
+			Accept: 'application/json',
+			'Content-Type': 'application/json',
+			Authorization: `Bearer ${token}`
+		},
+		body: JSON.stringify({
+			model: model,
+			prompt: text
+		})
+	}).catch((err) => {
+		error = err;
+		return null;
+	});
+
+	if (error) {
+		throw error;
+	}
+
+	return res;
+};
+
+export const generateTextCompletion = async (token: string = '', model: string, text: string) => {
+	let error = null;
+
+	const res = await fetch(`${OLLAMA_API_BASE_URL}/api/generate`, {
+		method: 'POST',
+		headers: {
+			Accept: 'application/json',
+			'Content-Type': 'application/json',
+			Authorization: `Bearer ${token}`
+		},
+		body: JSON.stringify({
+			model: model,
+			prompt: text,
+			stream: true
+		})
+	}).catch((err) => {
+		error = err;
+		return null;
+	});
+
+	if (error) {
+		throw error;
+	}
+
+	return res;
+};
+
 export const generateChatCompletion = async (token: string = '', body: object) => {
 	let controller = new AbortController();
 	let error = null;
 
-	const res = await fetch(`${OLLAMA_API_BASE_URL}/chat`, {
+	const res = await fetch(`${OLLAMA_API_BASE_URL}/api/chat`, {
 		signal: controller.signal,
 		method: 'POST',
 		headers: {
-			'Content-Type': 'text/event-stream',
+			Accept: 'application/json',
+			'Content-Type': 'application/json',
 			Authorization: `Bearer ${token}`
 		},
 		body: JSON.stringify(body)
@@ -241,7 +298,7 @@ export const generateChatCompletion = async (token: string = '', body: object) =
 	return [res, controller];
 };
 
-export const cancelChatCompletion = async (token: string = '', requestId: string) => {
+export const cancelOllamaRequest = async (token: string = '', requestId: string) => {
 	let error = null;
 
 	const res = await fetch(`${OLLAMA_API_BASE_URL}/cancel/${requestId}`, {
@@ -265,10 +322,11 @@ export const cancelChatCompletion = async (token: string = '', requestId: string
 export const createModel = async (token: string, tagName: string, content: string) => {
 	let error = null;
 
-	const res = await fetch(`${OLLAMA_API_BASE_URL}/create`, {
+	const res = await fetch(`${OLLAMA_API_BASE_URL}/api/create`, {
 		method: 'POST',
 		headers: {
-			'Content-Type': 'text/event-stream',
+			Accept: 'application/json',
+			'Content-Type': 'application/json',
 			Authorization: `Bearer ${token}`
 		},
 		body: JSON.stringify({
@@ -287,19 +345,23 @@ export const createModel = async (token: string, tagName: string, content: strin
 	return res;
 };
 
-export const deleteModel = async (token: string, tagName: string) => {
+export const deleteModel = async (token: string, tagName: string, urlIdx: string | null = null) => {
 	let error = null;
 
-	const res = await fetch(`${OLLAMA_API_BASE_URL}/delete`, {
-		method: 'DELETE',
-		headers: {
-			'Content-Type': 'text/event-stream',
-			Authorization: `Bearer ${token}`
-		},
-		body: JSON.stringify({
-			name: tagName
-		})
-	})
+	const res = await fetch(
+		`${OLLAMA_API_BASE_URL}/api/delete${urlIdx !== null ? `/${urlIdx}` : ''}`,
+		{
+			method: 'DELETE',
+			headers: {
+				Accept: 'application/json',
+				'Content-Type': 'application/json',
+				Authorization: `Bearer ${token}`
+			},
+			body: JSON.stringify({
+				name: tagName
+			})
+		}
+	)
 		.then(async (res) => {
 			if (!res.ok) throw await res.json();
 			return res.json();
@@ -310,7 +372,12 @@ export const deleteModel = async (token: string, tagName: string) => {
 		})
 		.catch((err) => {
 			console.log(err);
-			error = err.error;
+			error = err;
+
+			if ('detail' in err) {
+				error = err.detail;
+			}
+
 			return null;
 		});
 
@@ -321,13 +388,14 @@ export const deleteModel = async (token: string, tagName: string) => {
 	return res;
 };
 
-export const pullModel = async (token: string, tagName: string) => {
+export const pullModel = async (token: string, tagName: string, urlIdx: string | null = null) => {
 	let error = null;
 
-	const res = await fetch(`${OLLAMA_API_BASE_URL}/pull`, {
+	const res = await fetch(`${OLLAMA_API_BASE_URL}/api/pull${urlIdx !== null ? `/${urlIdx}` : ''}`, {
 		method: 'POST',
 		headers: {
-			'Content-Type': 'text/event-stream',
+			Accept: 'application/json',
+			'Content-Type': 'application/json',
 			Authorization: `Bearer ${token}`
 		},
 		body: JSON.stringify({
@@ -349,6 +417,73 @@ export const pullModel = async (token: string, tagName: string) => {
 	return res;
 };
 
+export const downloadModel = async (
+	token: string,
+	download_url: string,
+	urlIdx: string | null = null
+) => {
+	let error = null;
+
+	const res = await fetch(
+		`${OLLAMA_API_BASE_URL}/models/download${urlIdx !== null ? `/${urlIdx}` : ''}`,
+		{
+			method: 'POST',
+			headers: {
+				Accept: 'application/json',
+				'Content-Type': 'application/json',
+				Authorization: `Bearer ${token}`
+			},
+			body: JSON.stringify({
+				url: download_url
+			})
+		}
+	).catch((err) => {
+		console.log(err);
+		error = err;
+
+		if ('detail' in err) {
+			error = err.detail;
+		}
+
+		return null;
+	});
+	if (error) {
+		throw error;
+	}
+	return res;
+};
+
+export const uploadModel = async (token: string, file: File, urlIdx: string | null = null) => {
+	let error = null;
+
+	const formData = new FormData();
+	formData.append('file', file);
+
+	const res = await fetch(
+		`${OLLAMA_API_BASE_URL}/models/upload${urlIdx !== null ? `/${urlIdx}` : ''}`,
+		{
+			method: 'POST',
+			headers: {
+				Authorization: `Bearer ${token}`
+			},
+			body: formData
+		}
+	).catch((err) => {
+		console.log(err);
+		error = err;
+
+		if ('detail' in err) {
+			error = err.detail;
+		}
+
+		return null;
+	});
+	if (error) {
+		throw error;
+	}
+	return res;
+};
+
 // export const pullModel = async (token: string, tagName: string) => {
 // 	return await fetch(`${OLLAMA_API_BASE_URL}/pull`, {
 // 		method: 'POST',

src/lib/apis/openai/index.ts

@@ -1,9 +1,10 @@
 import { OPENAI_API_BASE_URL } from '$lib/constants';
+import { promptTemplate } from '$lib/utils';
 
-export const getOpenAIUrl = async (token: string = '') => {
+export const getOpenAIUrls = async (token: string = '') => {
 	let error = null;
 
-	const res = await fetch(`${OPENAI_API_BASE_URL}/url`, {
+	const res = await fetch(`${OPENAI_API_BASE_URL}/urls`, {
 		method: 'GET',
 		headers: {
 			Accept: 'application/json',
@@ -29,13 +30,13 @@ export const getOpenAIUrl = async (token: string = '') => {
 		throw error;
 	}
 
-	return res.OPENAI_API_BASE_URL;
+	return res.OPENAI_API_BASE_URLS;
 };
 
-export const updateOpenAIUrl = async (token: string = '', url: string) => {
+export const updateOpenAIUrls = async (token: string = '', urls: string[]) => {
 	let error = null;
 
-	const res = await fetch(`${OPENAI_API_BASE_URL}/url/update`, {
+	const res = await fetch(`${OPENAI_API_BASE_URL}/urls/update`, {
 		method: 'POST',
 		headers: {
 			Accept: 'application/json',
@@ -43,7 +44,7 @@ export const updateOpenAIUrl = async (token: string = '', url: string) => {
 			...(token && { authorization: `Bearer ${token}` })
 		},
 		body: JSON.stringify({
-			url: url
+			urls: urls
 		})
 	})
 		.then(async (res) => {
@@ -64,13 +65,13 @@ export const updateOpenAIUrl = async (token: string = '', url: string) => {
 		throw error;
 	}
 
-	return res.OPENAI_API_BASE_URL;
+	return res.OPENAI_API_BASE_URLS;
 };
 
-export const getOpenAIKey = async (token: string = '') => {
+export const getOpenAIKeys = async (token: string = '') => {
 	let error = null;
 
-	const res = await fetch(`${OPENAI_API_BASE_URL}/key`, {
+	const res = await fetch(`${OPENAI_API_BASE_URL}/keys`, {
 		method: 'GET',
 		headers: {
 			Accept: 'application/json',
@@ -96,13 +97,13 @@ export const getOpenAIKey = async (token: string = '') => {
 		throw error;
 	}
 
-	return res.OPENAI_API_KEY;
+	return res.OPENAI_API_KEYS;
 };
 
-export const updateOpenAIKey = async (token: string = '', key: string) => {
+export const updateOpenAIKeys = async (token: string = '', keys: string[]) => {
 	let error = null;
 
-	const res = await fetch(`${OPENAI_API_BASE_URL}/key/update`, {
+	const res = await fetch(`${OPENAI_API_BASE_URL}/keys/update`, {
 		method: 'POST',
 		headers: {
 			Accept: 'application/json',
@@ -110,7 +111,7 @@ export const updateOpenAIKey = async (token: string = '', key: string) => {
 			...(token && { authorization: `Bearer ${token}` })
 		},
 		body: JSON.stringify({
-			key: key
+			keys: keys
 		})
 	})
 		.then(async (res) => {
@@ -131,7 +132,7 @@ export const updateOpenAIKey = async (token: string = '', key: string) => {
 		throw error;
 	}
 
-	return res.OPENAI_API_KEY;
+	return res.OPENAI_API_KEYS;
 };
 
 export const getOpenAIModels = async (token: string = '') => {
@@ -150,7 +151,6 @@ export const getOpenAIModels = async (token: string = '') => {
 			return res.json();
 		})
 		.catch((err) => {
-			console.log(err);
 			error = `OpenAI: ${err?.error?.message ?? 'Network Problem'}`;
 			return [];
 		});
@@ -264,3 +264,53 @@ export const synthesizeOpenAISpeech = async (
 
 	return res;
 };
+
+export const generateTitle = async (
+	token: string = '',
+	template: string,
+	model: string,
+	prompt: string,
+	url: string = OPENAI_API_BASE_URL
+) => {
+	let error = null;
+
+	template = promptTemplate(template, prompt);
+
+	console.log(template);
+
+	const res = await fetch(`${url}/chat/completions`, {
+		method: 'POST',
+		headers: {
+			Accept: 'application/json',
+			'Content-Type': 'application/json',
+			Authorization: `Bearer ${token}`
+		},
+		body: JSON.stringify({
+			model: model,
+			messages: [
+				{
+					role: 'user',
+					content: template
+				}
+			],
+			stream: false
+		})
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.catch((err) => {
+			console.log(err);
+			if ('detail' in err) {
+				error = err.detail;
+			}
+			return null;
+		});
+
+	if (error) {
+		throw error;
+	}
+
+	return res?.choices[0]?.message?.content ?? 'New Chat';
+};

src/lib/apis/rag/index.ts

@@ -1,9 +1,9 @@
 import { RAG_API_BASE_URL } from '$lib/constants';
 
-export const getChunkParams = async (token: string) => {
+export const getRAGConfig = async (token: string) => {
 	let error = null;
 
-	const res = await fetch(`${RAG_API_BASE_URL}/chunk`, {
+	const res = await fetch(`${RAG_API_BASE_URL}/config`, {
 		method: 'GET',
 		headers: {
 			'Content-Type': 'application/json',
@@ -27,18 +27,27 @@ export const getChunkParams = async (token: string) => {
 	return res;
 };
 
-export const updateChunkParams = async (token: string, size: number, overlap: number) => {
+type ChunkConfigForm = {
+	chunk_size: number;
+	chunk_overlap: number;
+};
+
+type RAGConfigForm = {
+	pdf_extract_images: boolean;
+	chunk: ChunkConfigForm;
+};
+
+export const updateRAGConfig = async (token: string, payload: RAGConfigForm) => {
 	let error = null;
 
-	const res = await fetch(`${RAG_API_BASE_URL}/chunk/update`, {
+	const res = await fetch(`${RAG_API_BASE_URL}/config/update`, {
 		method: 'POST',
 		headers: {
 			'Content-Type': 'application/json',
 			Authorization: `Bearer ${token}`
 		},
 		body: JSON.stringify({
-			chunk_size: size,
-			chunk_overlap: overlap
+			...payload
 		})
 	})
 		.then(async (res) => {
@@ -85,17 +94,49 @@ export const getRAGTemplate = async (token: string) => {
 	return res?.template ?? '';
 };
 
-export const updateRAGTemplate = async (token: string, template: string) => {
+export const getQuerySettings = async (token: string) => {
 	let error = null;
 
-	const res = await fetch(`${RAG_API_BASE_URL}/template/update`, {
+	const res = await fetch(`${RAG_API_BASE_URL}/query/settings`, {
+		method: 'GET',
+		headers: {
+			'Content-Type': 'application/json',
+			Authorization: `Bearer ${token}`
+		}
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.catch((err) => {
+			console.log(err);
+			error = err.detail;
+			return null;
+		});
+
+	if (error) {
+		throw error;
+	}
+
+	return res;
+};
+
+type QuerySettings = {
+	k: number | null;
+	template: string | null;
+};
+
+export const updateQuerySettings = async (token: string, settings: QuerySettings) => {
+	let error = null;
+
+	const res = await fetch(`${RAG_API_BASE_URL}/query/settings/update`, {
 		method: 'POST',
 		headers: {
 			'Content-Type': 'application/json',
 			Authorization: `Bearer ${token}`
 		},
 		body: JSON.stringify({
-			template: template
+			...settings
 		})
 	})
 		.then(async (res) => {
@@ -183,7 +224,7 @@ export const queryDoc = async (
 	token: string,
 	collection_name: string,
 	query: string,
-	k: number
+	k: number | null = null
 ) => {
 	let error = null;
 
@@ -220,7 +261,7 @@ export const queryCollection = async (
 	token: string,
 	collection_names: string,
 	query: string,
-	k: number
+	k: number | null = null
 ) => {
 	let error = null;
 
@@ -304,3 +345,71 @@ export const resetVectorDB = async (token: string) => {
 
 	return res;
 };
+
+export const getEmbeddingConfig = async (token: string) => {
+	let error = null;
+
+	const res = await fetch(`${RAG_API_BASE_URL}/embedding`, {
+		method: 'GET',
+		headers: {
+			'Content-Type': 'application/json',
+			Authorization: `Bearer ${token}`
+		}
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.catch((err) => {
+			console.log(err);
+			error = err.detail;
+			return null;
+		});
+
+	if (error) {
+		throw error;
+	}
+
+	return res;
+};
+
+type OpenAIConfigForm = {
+	key: string;
+	url: string;
+};
+
+type EmbeddingModelUpdateForm = {
+	openai_config?: OpenAIConfigForm;
+	embedding_engine: string;
+	embedding_model: string;
+};
+
+export const updateEmbeddingConfig = async (token: string, payload: EmbeddingModelUpdateForm) => {
+	let error = null;
+
+	const res = await fetch(`${RAG_API_BASE_URL}/embedding/update`, {
+		method: 'POST',
+		headers: {
+			'Content-Type': 'application/json',
+			Authorization: `Bearer ${token}`
+		},
+		body: JSON.stringify({
+			...payload
+		})
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.catch((err) => {
+			console.log(err);
+			error = err.detail;
+			return null;
+		});
+
+	if (error) {
+		throw error;
+	}
+
+	return res;
+};

src/lib/apis/utils/index.ts

@@ -21,3 +21,86 @@ export const getGravatarUrl = async (email: string) => {
 
 	return res;
 };
+
+export const downloadChatAsPDF = async (chat: object) => {
+	let error = null;
+
+	const blob = await fetch(`${WEBUI_API_BASE_URL}/utils/pdf`, {
+		method: 'POST',
+		headers: {
+			'Content-Type': 'application/json'
+		},
+		body: JSON.stringify({
+			title: chat.title,
+			messages: chat.messages
+		})
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.blob();
+		})
+		.catch((err) => {
+			console.log(err);
+			error = err;
+			return null;
+		});
+
+	return blob;
+};
+
+export const getHTMLFromMarkdown = async (md: string) => {
+	let error = null;
+
+	const res = await fetch(`${WEBUI_API_BASE_URL}/utils/markdown`, {
+		method: 'POST',
+		headers: {
+			'Content-Type': 'application/json'
+		},
+		body: JSON.stringify({
+			md: md
+		})
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.catch((err) => {
+			console.log(err);
+			error = err;
+			return null;
+		});
+
+	return res.html;
+};
+
+export const downloadDatabase = async (token: string) => {
+	let error = null;
+
+	const res = await fetch(`${WEBUI_API_BASE_URL}/utils/db/download`, {
+		method: 'GET',
+		headers: {
+			'Content-Type': 'application/json',
+			Authorization: `Bearer ${token}`
+		}
+	})
+		.then((response) => {
+			if (!response.ok) {
+				throw new Error('Network response was not ok');
+			}
+			return response.blob();
+		})
+		.then((blob) => {
+			const url = window.URL.createObjectURL(blob);
+			const a = document.createElement('a');
+			a.href = url;
+			a.download = 'webui.db';
+			document.body.appendChild(a);
+			a.click();
+			window.URL.revokeObjectURL(url);
+		})
+		.catch((err) => {
+			console.log(err);
+			error = err;
+			return null;
+		});
+};

src/lib/components/AddFilesPlaceholder.svelte

@@ -1,8 +1,13 @@
+<script>
+	import { getContext } from 'svelte';
+	const i18n = getContext('i18n');
+</script>
+
 <div class="  text-center text-6xl mb-3">📄</div>
-<div class="text-center dark:text-white text-2xl font-semibold z-50">Add Files</div>
+<div class="text-center dark:text-white text-2xl font-semibold z-50">{$i18n.t('Add Files')}</div>
 
 <slot
 	><div class=" mt-2 text-center text-sm dark:text-gray-200 w-full">
-		Drop any files here to add to the conversation
+		{$i18n.t('Drop any files here to add to the conversation')}
 	</div>
 </slot>

src/lib/components/ChangelogModal.svelte

@@ -1,5 +1,5 @@
 <script lang="ts">
-	import { onMount } from 'svelte';
+	import { onMount, getContext } from 'svelte';
 	import { Confetti } from 'svelte-confetti';
 
 	import { WEBUI_NAME, config } from '$lib/stores';
@@ -9,6 +9,8 @@
 
 	import Modal from './common/Modal.svelte';
 
+	const i18n = getContext('i18n');
+
 	export let show = false;
 
 	let changelog = null;
@@ -23,12 +25,14 @@
 	<div class="px-5 py-4 dark:text-gray-300">
 		<div class="flex justify-between items-start">
 			<div class="text-xl font-bold">
-				What’s New in {$WEBUI_NAME}
+				{$i18n.t('What’s New in')}
+				{$WEBUI_NAME}
 				<Confetti x={[-1, -0.25]} y={[0, 0.5]} />
 			</div>
 			<button
 				class="self-center"
 				on:click={() => {
+					localStorage.version = $config.version;
 					show = false;
 				}}
 			>
@@ -45,7 +49,7 @@
 			</button>
 		</div>
 		<div class="flex items-center mt-1">
-			<div class="text-sm dark:text-gray-200">Release Notes</div>
+			<div class="text-sm dark:text-gray-200">{$i18n.t('Release Notes')}</div>
 			<div class="flex self-center w-[1px] h-6 mx-2.5 bg-gray-200 dark:bg-gray-700" />
 			<div class="text-sm dark:text-gray-200">
 				v{WEBUI_VERSION}
@@ -108,7 +112,7 @@
 				}}
 				class=" px-4 py-2 bg-emerald-600 hover:bg-emerald-700 text-gray-100 transition rounded"
 			>
-				<span class="relative">Okay, Let's Go!</span>
+				<span class="relative">{$i18n.t("Okay, Let's Go!")}</span>
 			</button>
 		</div>
 	</div>

src/lib/components/admin/EditUserModal.svelte

@@ -1,12 +1,13 @@
 <script lang="ts">
-	import toast from 'svelte-french-toast';
+	import { toast } from 'svelte-sonner';
 	import dayjs from 'dayjs';
 	import { createEventDispatcher } from 'svelte';
-	import { onMount } from 'svelte';
+	import { onMount, getContext } from 'svelte';
 
 	import { updateUserById } from '$lib/apis/users';
 	import Modal from '../common/Modal.svelte';
 
+	const i18n = getContext('i18n');
 	const dispatch = createEventDispatcher();
 
 	export let show = false;
@@ -42,7 +43,7 @@
 <Modal size="sm" bind:show>
 	<div>
 		<div class=" flex justify-between dark:text-gray-300 px-5 py-4">
-			<div class=" text-lg font-medium self-center">Edit User</div>
+			<div class=" text-lg font-medium self-center">{$i18n.t('Edit User')}</div>
 			<button
 				class="self-center"
 				on:click={() => {
@@ -84,7 +85,8 @@
 							<div class=" self-center capitalize font-semibold">{selectedUser.name}</div>
 
 							<div class="text-xs text-gray-500">
-								Created at {dayjs(selectedUser.timestamp * 1000).format('MMMM DD, YYYY')}
+								{$i18n.t('Created at')}
+								{dayjs(selectedUser.timestamp * 1000).format($i18n.t('MMMM DD, YYYY'))}
 							</div>
 						</div>
 					</div>
@@ -93,7 +95,7 @@
 
 					<div class=" flex flex-col space-y-1.5">
 						<div class="flex flex-col w-full">
-							<div class=" mb-1 text-xs text-gray-500">Email</div>
+							<div class=" mb-1 text-xs text-gray-500">{$i18n.t('Email')}</div>
 
 							<div class="flex-1">
 								<input
@@ -108,7 +110,7 @@
 						</div>
 
 						<div class="flex flex-col w-full">
-							<div class=" mb-1 text-xs text-gray-500">Name</div>
+							<div class=" mb-1 text-xs text-gray-500">{$i18n.t('Name')}</div>
 
 							<div class="flex-1">
 								<input
@@ -122,7 +124,7 @@
 						</div>
 
 						<div class="flex flex-col w-full">
-							<div class=" mb-1 text-xs text-gray-500">New Password</div>
+							<div class=" mb-1 text-xs text-gray-500">{$i18n.t('New Password')}</div>
 
 							<div class="flex-1">
 								<input
@@ -140,7 +142,7 @@
 							class=" px-4 py-2 bg-emerald-600 hover:bg-emerald-700 text-gray-100 transition rounded"
 							type="submit"
 						>
-							Save
+							{$i18n.t('Save')}
 						</button>
 					</div>
 				</form>

src/lib/components/admin/Settings/Database.svelte

@@ -0,0 +1,65 @@
+<script lang="ts">
+	import { downloadDatabase } from '$lib/apis/utils';
+	import { onMount, getContext } from 'svelte';
+
+	const i18n = getContext('i18n');
+
+	export let saveHandler: Function;
+
+	onMount(async () => {
+		// permissions = await getUserPermissions(localStorage.token);
+	});
+</script>
+
+<form
+	class="flex flex-col h-full justify-between space-y-3 text-sm"
+	on:submit|preventDefault={async () => {
+		saveHandler();
+	}}
+>
+	<div class=" space-y-3 pr-1.5 overflow-y-scroll max-h-80">
+		<div>
+			<div class=" mb-2 text-sm font-medium">{$i18n.t('Database')}</div>
+
+			<div class="  flex w-full justify-between">
+				<!-- <div class=" self-center text-xs font-medium">{$i18n.t('Allow Chat Deletion')}</div> -->
+
+				<button
+					class=" flex rounded-md py-1.5 px-3 w-full hover:bg-gray-200 dark:hover:bg-gray-800 transition"
+					type="button"
+					on:click={() => {
+						// exportAllUserChats();
+
+						downloadDatabase(localStorage.token);
+					}}
+				>
+					<div class=" self-center mr-3">
+						<svg
+							xmlns="http://www.w3.org/2000/svg"
+							viewBox="0 0 16 16"
+							fill="currentColor"
+							class="w-4 h-4"
+						>
+							<path d="M2 3a1 1 0 0 1 1-1h10a1 1 0 0 1 1 1v1a1 1 0 0 1-1 1H3a1 1 0 0 1-1-1V3Z" />
+							<path
+								fill-rule="evenodd"
+								d="M13 6H3v6a2 2 0 0 0 2 2h6a2 2 0 0 0 2-2V6ZM8.75 7.75a.75.75 0 0 0-1.5 0v2.69L6.03 9.22a.75.75 0 0 0-1.06 1.06l2.5 2.5a.75.75 0 0 0 1.06 0l2.5-2.5a.75.75 0 1 0-1.06-1.06l-1.22 1.22V7.75Z"
+								clip-rule="evenodd"
+							/>
+						</svg>
+					</div>
+					<div class=" self-center text-sm font-medium">{$i18n.t('Download Database')}</div>
+				</button>
+			</div>
+		</div>
+	</div>
+
+	<!-- <div class="flex justify-end pt-3 text-sm font-medium">
+		<button
+			class=" px-4 py-2 bg-emerald-600 hover:bg-emerald-700 text-gray-100 transition rounded"
+			type="submit"
+		>
+			Save
+		</button>
+	</div> -->
+</form>

src/lib/components/admin/Settings/General.svelte

@@ -1,4 +1,5 @@
 <script lang="ts">
+	import { getWebhookUrl, updateWebhookUrl } from '$lib/apis';
 	import {
 		getDefaultUserRole,
 		getJWTExpiresDuration,
@@ -7,13 +8,17 @@
 		updateDefaultUserRole,
 		updateJWTExpiresDuration
 	} from '$lib/apis/auths';
-	import { onMount } from 'svelte';
+	import { onMount, getContext } from 'svelte';
+
+	const i18n = getContext('i18n');
 
 	export let saveHandler: Function;
 	let signUpEnabled = true;
 	let defaultUserRole = 'pending';
 	let JWTExpiresIn = '';
 
+	let webhookUrl = '';
+
 	const toggleSignUpEnabled = async () => {
 		signUpEnabled = await toggleSignUpEnabledStatus(localStorage.token);
 	};
@@ -26,27 +31,32 @@
 		JWTExpiresIn = await updateJWTExpiresDuration(localStorage.token, duration);
 	};
 
+	const updateWebhookUrlHandler = async () => {
+		webhookUrl = await updateWebhookUrl(localStorage.token, webhookUrl);
+	};
+
 	onMount(async () => {
 		signUpEnabled = await getSignUpEnabledStatus(localStorage.token);
 		defaultUserRole = await getDefaultUserRole(localStorage.token);
 		JWTExpiresIn = await getJWTExpiresDuration(localStorage.token);
+		webhookUrl = await getWebhookUrl(localStorage.token);
 	});
 </script>
 
 <form
 	class="flex flex-col h-full justify-between space-y-3 text-sm"
 	on:submit|preventDefault={() => {
-		// console.log('submit');
 		updateJWTExpiresDurationHandler(JWTExpiresIn);
+		updateWebhookUrlHandler();
 		saveHandler();
 	}}
 >
 	<div class=" space-y-3 pr-1.5 overflow-y-scroll max-h-80">
 		<div>
-			<div class=" mb-2 text-sm font-medium">General Settings</div>
+			<div class=" mb-2 text-sm font-medium">{$i18n.t('General Settings')}</div>
 
 			<div class="  flex w-full justify-between">
-				<div class=" self-center text-xs font-medium">Enable New Sign Ups</div>
+				<div class=" self-center text-xs font-medium">{$i18n.t('Enable New Sign Ups')}</div>
 
 				<button
 					class="p-1 px-3 text-xs flex rounded transition"
@@ -66,7 +76,7 @@
 								d="M11.5 1A3.5 3.5 0 0 0 8 4.5V7H2.5A1.5 1.5 0 0 0 1 8.5v5A1.5 1.5 0 0 0 2.5 15h7a1.5 1.5 0 0 0 1.5-1.5v-5A1.5 1.5 0 0 0 9.5 7V4.5a2 2 0 1 1 4 0v1.75a.75.75 0 0 0 1.5 0V4.5A3.5 3.5 0 0 0 11.5 1Z"
 							/>
 						</svg>
-						<span class="ml-2 self-center">Enabled</span>
+						<span class="ml-2 self-center">{$i18n.t('Enabled')}</span>
 					{:else}
 						<svg
 							xmlns="http://www.w3.org/2000/svg"
@@ -81,25 +91,25 @@
 							/>
 						</svg>
 
-						<span class="ml-2 self-center">Disabled</span>
+						<span class="ml-2 self-center">{$i18n.t('Disabled')}</span>
 					{/if}
 				</button>
 			</div>
 
 			<div class=" flex w-full justify-between">
-				<div class=" self-center text-xs font-medium">Default User Role</div>
+				<div class=" self-center text-xs font-medium">{$i18n.t('Default User Role')}</div>
 				<div class="flex items-center relative">
 					<select
-						class="w-fit pr-8 rounded py-2 px-2 text-xs bg-transparent outline-none text-right"
+						class="dark:bg-gray-900 w-fit pr-8 rounded py-2 px-2 text-xs bg-transparent outline-none text-right"
 						bind:value={defaultUserRole}
 						placeholder="Select a theme"
 						on:change={(e) => {
 							updateDefaultUserRoleHandler(e.target.value);
 						}}
 					>
-						<option value="pending">Pending</option>
-						<option value="user">User</option>
-						<option value="admin">Admin</option>
+						<option value="pending">{$i18n.t('pending')}</option>
+						<option value="user">{$i18n.t('user')}</option>
+						<option value="admin">{$i18n.t('admin')}</option>
 					</select>
 				</div>
 			</div>
@@ -108,7 +118,24 @@
 
 			<div class=" w-full justify-between">
 				<div class="flex w-full justify-between">
-					<div class=" self-center text-xs font-medium">JWT Expiration</div>
+					<div class=" self-center text-xs font-medium">{$i18n.t('Webhook URL')}</div>
+				</div>
+
+				<div class="flex mt-2 space-x-2">
+					<input
+						class="w-full rounded py-1.5 px-4 text-sm dark:text-gray-300 dark:bg-gray-800 outline-none border border-gray-100 dark:border-gray-600"
+						type="text"
+						placeholder={`https://example.com/webhook`}
+						bind:value={webhookUrl}
+					/>
+				</div>
+			</div>
+
+			<hr class=" dark:border-gray-700 my-3" />
+
+			<div class=" w-full justify-between">
+				<div class="flex w-full justify-between">
+					<div class=" self-center text-xs font-medium">{$i18n.t('JWT Expiration')}</div>
 				</div>
 
 				<div class="flex mt-2 space-x-2">
@@ -121,8 +148,9 @@
 				</div>
 
 				<div class="mt-2 text-xs text-gray-400 dark:text-gray-500">
-					Valid time units: <span class=" text-gray-300 font-medium"
-						>'s', 'm', 'h', 'd', 'w' or '-1' for no expiration.</span
+					{$i18n.t('Valid time units:')}
+					<span class=" text-gray-300 font-medium"
+						>{$i18n.t("'s', 'm', 'h', 'd', 'w' or '-1' for no expiration.")}</span
 					>
 				</div>
 			</div>
@@ -134,7 +162,7 @@
 			class=" px-4 py-2 bg-emerald-600 hover:bg-emerald-700 text-gray-100 transition rounded"
 			type="submit"
 		>
-			Save
+			{$i18n.t('Save')}
 		</button>
 	</div>
 </form>

src/lib/components/admin/Settings/Users.svelte

@@ -1,10 +1,17 @@
 <script lang="ts">
+	import { getModelFilterConfig, updateModelFilterConfig } from '$lib/apis';
 	import { getSignUpEnabledStatus, toggleSignUpEnabledStatus } from '$lib/apis/auths';
 	import { getUserPermissions, updateUserPermissions } from '$lib/apis/users';
-	import { onMount } from 'svelte';
+
+	import { onMount, getContext } from 'svelte';
+	import { models } from '$lib/stores';
+
+	const i18n = getContext('i18n');
 
 	export let saveHandler: Function;
 
+	let whitelistEnabled = false;
+	let whitelistModels = [''];
 	let permissions = {
 		chat: {
 			deletion: true
@@ -13,6 +20,13 @@
 
 	onMount(async () => {
 		permissions = await getUserPermissions(localStorage.token);
+
+		const res = await getModelFilterConfig(localStorage.token);
+		if (res) {
+			whitelistEnabled = res.enabled;
+
+			whitelistModels = res.models.length > 0 ? res.models : [''];
+		}
 	});
 </script>
 
@@ -21,15 +35,17 @@
 	on:submit|preventDefault={async () => {
 		// console.log('submit');
 		await updateUserPermissions(localStorage.token, permissions);
+
+		await updateModelFilterConfig(localStorage.token, whitelistEnabled, whitelistModels);
 		saveHandler();
 	}}
 >
 	<div class=" space-y-3 pr-1.5 overflow-y-scroll max-h-80">
 		<div>
-			<div class=" mb-2 text-sm font-medium">User Permissions</div>
+			<div class=" mb-2 text-sm font-medium">{$i18n.t('User Permissions')}</div>
 
 			<div class="  flex w-full justify-between">
-				<div class=" self-center text-xs font-medium">Allow Chat Deletion</div>
+				<div class=" self-center text-xs font-medium">{$i18n.t('Allow Chat Deletion')}</div>
 
 				<button
 					class="p-1 px-3 text-xs flex rounded transition"
@@ -49,7 +65,7 @@
 								d="M11.5 1A3.5 3.5 0 0 0 8 4.5V7H2.5A1.5 1.5 0 0 0 1 8.5v5A1.5 1.5 0 0 0 2.5 15h7a1.5 1.5 0 0 0 1.5-1.5v-5A1.5 1.5 0 0 0 9.5 7V4.5a2 2 0 1 1 4 0v1.75a.75.75 0 0 0 1.5 0V4.5A3.5 3.5 0 0 0 11.5 1Z"
 							/>
 						</svg>
-						<span class="ml-2 self-center">Allow</span>
+						<span class="ml-2 self-center">{$i18n.t('Allow')}</span>
 					{:else}
 						<svg
 							xmlns="http://www.w3.org/2000/svg"
@@ -64,11 +80,112 @@
 							/>
 						</svg>
 
-						<span class="ml-2 self-center">Don't Allow</span>
+						<span class="ml-2 self-center">{$i18n.t("Don't Allow")}</span>
 					{/if}
 				</button>
 			</div>
 		</div>
+
+		<hr class=" dark:border-gray-700 my-2" />
+
+		<div class="mt-2 space-y-3 pr-1.5">
+			<div>
+				<div class="mb-2">
+					<div class="flex justify-between items-center text-xs">
+						<div class=" text-sm font-medium">{$i18n.t('Manage Models')}</div>
+					</div>
+				</div>
+
+				<div class=" space-y-3">
+					<div>
+						<div class="flex justify-between items-center text-xs">
+							<div class=" text-xs font-medium">{$i18n.t('Model Whitelisting')}</div>
+
+							<button
+								class=" text-xs font-medium text-gray-500"
+								type="button"
+								on:click={() => {
+									whitelistEnabled = !whitelistEnabled;
+								}}>{whitelistEnabled ? $i18n.t('On') : $i18n.t('Off')}</button
+							>
+						</div>
+					</div>
+
+					{#if whitelistEnabled}
+						<div>
+							<div class=" space-y-1.5">
+								{#each whitelistModels as modelId, modelIdx}
+									<div class="flex w-full">
+										<div class="flex-1 mr-2">
+											<select
+												class="w-full rounded-lg py-2 px-4 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none"
+												bind:value={modelId}
+												placeholder="Select a model"
+											>
+												<option value="" disabled selected>{$i18n.t('Select a model')}</option>
+												{#each $models.filter((model) => model.id) as model}
+													<option value={model.id} class="bg-gray-100 dark:bg-gray-700"
+														>{model.name}</option
+													>
+												{/each}
+											</select>
+										</div>
+
+										{#if modelIdx === 0}
+											<button
+												class="px-2.5 bg-gray-100 hover:bg-gray-200 text-gray-800 dark:bg-gray-900 dark:text-white rounded-lg transition"
+												type="button"
+												on:click={() => {
+													if (whitelistModels.at(-1) !== '') {
+														whitelistModels = [...whitelistModels, ''];
+													}
+												}}
+											>
+												<svg
+													xmlns="http://www.w3.org/2000/svg"
+													viewBox="0 0 16 16"
+													fill="currentColor"
+													class="w-4 h-4"
+												>
+													<path
+														d="M8.75 3.75a.75.75 0 0 0-1.5 0v3.5h-3.5a.75.75 0 0 0 0 1.5h3.5v3.5a.75.75 0 0 0 1.5 0v-3.5h3.5a.75.75 0 0 0 0-1.5h-3.5v-3.5Z"
+													/>
+												</svg>
+											</button>
+										{:else}
+											<button
+												class="px-2.5 bg-gray-100 hover:bg-gray-200 text-gray-800 dark:bg-gray-900 dark:text-white rounded-lg transition"
+												type="button"
+												on:click={() => {
+													whitelistModels.splice(modelIdx, 1);
+													whitelistModels = whitelistModels;
+												}}
+											>
+												<svg
+													xmlns="http://www.w3.org/2000/svg"
+													viewBox="0 0 16 16"
+													fill="currentColor"
+													class="w-4 h-4"
+												>
+													<path d="M3.75 7.25a.75.75 0 0 0 0 1.5h8.5a.75.75 0 0 0 0-1.5h-8.5Z" />
+												</svg>
+											</button>
+										{/if}
+									</div>
+								{/each}
+							</div>
+
+							<div class="flex justify-end items-center text-xs mt-1.5 text-right">
+								<div class=" text-xs font-medium">
+									{whitelistModels.length}
+									{$i18n.t('Model(s) Whitelisted')}
+								</div>
+							</div>
+						</div>
+					{/if}
+				</div>
+			</div>
+		</div>
 	</div>
 
 	<div class="flex justify-end pt-3 text-sm font-medium">
@@ -76,7 +193,7 @@
 			class=" px-4 py-2 bg-emerald-600 hover:bg-emerald-700 text-gray-100 transition rounded"
 			type="submit"
 		>
-			Save
+			{$i18n.t('Save')}
 		</button>
 	</div>
 </form>

src/lib/components/admin/SettingsModal.svelte

@@ -1,9 +1,13 @@
 <script>
+	import { getContext } from 'svelte';
 	import Modal from '../common/Modal.svelte';
+	import Database from './Settings/Database.svelte';
 
 	import General from './Settings/General.svelte';
 	import Users from './Settings/Users.svelte';
 
+	const i18n = getContext('i18n');
+
 	export let show = false;
 
 	let selectedTab = 'general';
@@ -12,7 +16,7 @@
 <Modal bind:show>
 	<div>
 		<div class=" flex justify-between dark:text-gray-300 px-5 py-4">
-			<div class=" text-lg font-medium self-center">Admin Settings</div>
+			<div class=" text-lg font-medium self-center">{$i18n.t('Admin Settings')}</div>
 			<button
 				class="self-center"
 				on:click={() => {
@@ -60,7 +64,7 @@
 							/>
 						</svg>
 					</div>
-					<div class=" self-center">General</div>
+					<div class=" self-center">{$i18n.t('General')}</div>
 				</button>
 
 				<button
@@ -84,7 +88,35 @@
 							/>
 						</svg>
 					</div>
-					<div class=" self-center">Users</div>
+					<div class=" self-center">{$i18n.t('Users')}</div>
+				</button>
+
+				<button
+					class="px-2.5 py-2.5 min-w-fit rounded-lg flex-1 md:flex-none flex text-right transition {selectedTab ===
+					'db'
+						? 'bg-gray-200 dark:bg-gray-700'
+						: ' hover:bg-gray-300 dark:hover:bg-gray-800'}"
+					on:click={() => {
+						selectedTab = 'db';
+					}}
+				>
+					<div class=" self-center mr-2">
+						<svg
+							xmlns="http://www.w3.org/2000/svg"
+							viewBox="0 0 16 16"
+							fill="currentColor"
+							class="w-4 h-4"
+						>
+							<path d="M8 7c3.314 0 6-1.343 6-3s-2.686-3-6-3-6 1.343-6 3 2.686 3 6 3Z" />
+							<path
+								d="M8 8.5c1.84 0 3.579-.37 4.914-1.037A6.33 6.33 0 0 0 14 6.78V8c0 1.657-2.686 3-6 3S2 9.657 2 8V6.78c.346.273.72.5 1.087.683C4.42 8.131 6.16 8.5 8 8.5Z"
+							/>
+							<path
+								d="M8 12.5c1.84 0 3.579-.37 4.914-1.037.366-.183.74-.41 1.086-.684V12c0 1.657-2.686 3-6 3s-6-1.343-6-3v-1.22c.346.273.72.5 1.087.683C4.42 12.131 6.16 12.5 8 12.5Z"
+							/>
+						</svg>
+					</div>
+					<div class=" self-center">{$i18n.t('Database')}</div>
 				</button>
 			</div>
 			<div class="flex-1 md:min-h-[380px]">
@@ -100,6 +132,12 @@
 							show = false;
 						}}
 					/>
+				{:else if selectedTab === 'db'}
+					<Database
+						saveHandler={() => {
+							show = false;
+						}}
+					/>
 				{/if}
 			</div>
 		</div>

src/lib/components/chat/MessageInput.svelte

@@ -1,6 +1,6 @@
 <script lang="ts">
-	import toast from 'svelte-french-toast';
-	import { onMount, tick } from 'svelte';
+	import { toast } from 'svelte-sonner';
+	import { onMount, tick, getContext } from 'svelte';
 	import { settings } from '$lib/stores';
 	import { blobToFile, calculateSHA256, findWordIndices } from '$lib/utils';
 
@@ -12,13 +12,16 @@
 	import Documents from './MessageInput/Documents.svelte';
 	import Models from './MessageInput/Models.svelte';
 	import { transcribeAudio } from '$lib/apis/audio';
+	import Tooltip from '../common/Tooltip.svelte';
+
+	const i18n = getContext('i18n');
 
 	export let submitPrompt: Function;
 	export let stopResponse: Function;
 
 	export let suggestionPrompts = [];
 	export let autoScroll = true;
-
+	let chatTextAreaElement: HTMLTextAreaElement;
 	let filesInputElement;
 
 	let promptsElement;
@@ -42,11 +45,9 @@
 	let speechRecognition;
 
 	$: if (prompt) {
-		const chatInput = document.getElementById('chat-textarea');
-
-		if (chatInput) {
-			chatInput.style.height = '';
-			chatInput.style.height = Math.min(chatInput.scrollHeight, 200) + 'px';
+		if (chatTextAreaElement) {
+			chatTextAreaElement.style.height = '';
+			chatTextAreaElement.style.height = Math.min(chatTextAreaElement.scrollHeight, 200) + 'px';
 		}
 	}
 
@@ -85,9 +86,7 @@
 			if (res) {
 				prompt = res.text;
 				await tick();
-
-				const inputElement = document.getElementById('chat-textarea');
-				inputElement?.focus();
+				chatTextAreaElement?.focus();
 
 				if (prompt !== '' && $settings?.speechAutoSend === true) {
 					submitPrompt(prompt, user);
@@ -190,8 +189,7 @@
 						prompt = `${prompt}${transcript}`;
 
 						await tick();
-						const inputElement = document.getElementById('chat-textarea');
-						inputElement?.focus();
+						chatTextAreaElement?.focus();
 
 						// Restart the inactivity timeout
 						timeoutId = setTimeout(() => {
@@ -213,11 +211,11 @@
 					// Event triggered when an error occurs
 					speechRecognition.onerror = function (event) {
 						console.log(event);
-						toast.error(`Speech recognition error: ${event.error}`);
+						toast.error($i18n.t(`Speech recognition error: {{error}}`, { error: event.error }));
 						isRecording = false;
 					};
 				} else {
-					toast.error('SpeechRecognition API is not supported in this browser.');
+					toast.error($i18n.t('SpeechRecognition API is not supported in this browser.'));
 				}
 			}
 		}
@@ -293,8 +291,17 @@
 	};
 
 	onMount(() => {
+		window.setTimeout(() => chatTextAreaElement?.focus(), 0);
+
 		const dropZone = document.querySelector('body');
 
+		const handleKeyDown = (event: KeyboardEvent) => {
+			if (event.key === 'Escape') {
+				console.log('Escape');
+				dragged = false;
+			}
+		};
+
 		const onDragOver = (e) => {
 			e.preventDefault();
 			dragged = true;
@@ -335,23 +342,30 @@
 						uploadDoc(file);
 					} else {
 						toast.error(
-							`Unknown File Type '${file['type']}', but accepting and treating as plain text`
+							$i18n.t(
+								`Unknown File Type '{{file_type}}', but accepting and treating as plain text`,
+								{ file_type: file['type'] }
+							)
 						);
 						uploadDoc(file);
 					}
 				} else {
-					toast.error(`File not found.`);
+					toast.error($i18n.t(`File not found.`));
 				}
 			}
 
 			dragged = false;
 		};
 
+		window.addEventListener('keydown', handleKeyDown);
+
 		dropZone?.addEventListener('dragover', onDragOver);
 		dropZone?.addEventListener('drop', onDrop);
 		dropZone?.addEventListener('dragleave', onDragLeave);
 
 		return () => {
+			window.removeEventListener('keydown', handleKeyDown);
+
 			dropZone?.removeEventListener('dragover', onDragOver);
 			dropZone?.removeEventListener('drop', onDrop);
 			dropZone?.removeEventListener('dragleave', onDragLeave);
@@ -361,12 +375,12 @@
 
 {#if dragged}
 	<div
-		class="fixed w-full h-full flex z-50 touch-none pointer-events-none"
+		class="fixed lg:w-[calc(100%-260px)] w-full h-full flex z-50 touch-none pointer-events-none"
 		id="dropzone"
 		role="region"
 		aria-label="Drag and Drop Container"
 	>
-		<div class="absolute rounded-xl w-full h-full backdrop-blur bg-gray-800/40 flex justify-center">
+		<div class="absolute w-full h-full backdrop-blur bg-gray-800/40 flex justify-center">
 			<div class="m-auto pt-64 flex flex-col justify-center">
 				<div class="max-w-md">
 					<AddFilesPlaceholder />
@@ -479,18 +493,21 @@
 								filesInputElement.value = '';
 							} else {
 								toast.error(
-									`Unknown File Type '${file['type']}', but accepting and treating as plain text`
+									$i18n.t(
+										`Unknown File Type '{{file_type}}', but accepting and treating as plain text`,
+										{ file_type: file['type'] }
+									)
 								);
 								uploadDoc(file);
 								filesInputElement.value = '';
 							}
 						} else {
-							toast.error(`File not found.`);
+							toast.error($i18n.t(`File not found.`));
 						}
 					}}
 				/>
 				<form
-					class=" flex flex-col relative w-full rounded-xl border dark:border-gray-700 bg-white dark:bg-gray-900 dark:text-gray-100"
+					class=" flex flex-col relative w-full rounded-3xl px-1.5 border border-gray-100 dark:border-gray-850 bg-white dark:bg-gray-900 dark:text-gray-100"
 					on:submit|preventDefault={() => {
 						submitPrompt(prompt, user);
 					}}
@@ -572,7 +589,7 @@
 													{file.name}
 												</div>
 
-												<div class=" text-gray-500 text-sm">Document</div>
+												<div class=" text-gray-500 text-sm">{$i18n.t('Document')}</div>
 											</div>
 										</div>
 									{:else if file.type === 'collection'}
@@ -600,7 +617,7 @@
 													{file?.title ?? `#${file.name}`}
 												</div>
 
-												<div class=" text-gray-500 text-sm">Collection</div>
+												<div class=" text-gray-500 text-sm">{$i18n.t('Collection')}</div>
 											</div>
 										</div>
 									{/if}
@@ -633,40 +650,41 @@
 
 					<div class=" flex">
 						{#if fileUploadEnabled}
-							<div class=" self-end mb-2 ml-1.5">
-								<button
-									class="  text-gray-600 dark:text-gray-200 transition rounded-lg p-1 ml-1"
-									type="button"
-									on:click={() => {
-										filesInputElement.click();
-									}}
-								>
-									<svg
-										xmlns="http://www.w3.org/2000/svg"
-										viewBox="0 0 20 20"
-										fill="currentColor"
-										class="w-5 h-5"
+							<div class=" self-end mb-2 ml-1">
+								<Tooltip content={$i18n.t('Upload files')}>
+									<button
+										class="bg-gray-50 hover:bg-gray-100 text-gray-800 dark:bg-gray-850 dark:text-white dark:hover:bg-gray-800 transition rounded-full p-1.5"
+										type="button"
+										on:click={() => {
+											filesInputElement.click();
+										}}
 									>
-										<path
-											fill-rule="evenodd"
-											d="M15.621 4.379a3 3 0 00-4.242 0l-7 7a3 3 0 004.241 4.243h.001l.497-.5a.75.75 0 011.064 1.057l-.498.501-.002.002a4.5 4.5 0 01-6.364-6.364l7-7a4.5 4.5 0 016.368 6.36l-3.455 3.553A2.625 2.625 0 119.52 9.52l3.45-3.451a.75.75 0 111.061 1.06l-3.45 3.451a1.125 1.125 0 001.587 1.595l3.454-3.553a3 3 0 000-4.242z"
-											clip-rule="evenodd"
-										/>
-									</svg>
-								</button>
+										<svg
+											xmlns="http://www.w3.org/2000/svg"
+											viewBox="0 0 16 16"
+											fill="currentColor"
+											class="w-[1.2rem] h-[1.2rem]"
+										>
+											<path
+												d="M8.75 3.75a.75.75 0 0 0-1.5 0v3.5h-3.5a.75.75 0 0 0 0 1.5h3.5v3.5a.75.75 0 0 0 1.5 0v-3.5h3.5a.75.75 0 0 0 0-1.5h-3.5v-3.5Z"
+											/>
+										</svg>
+									</button>
+								</Tooltip>
 							</div>
 						{/if}
 
 						<textarea
 							id="chat-textarea"
-							class=" dark:bg-gray-900 dark:text-gray-100 outline-none w-full py-3 px-2 {fileUploadEnabled
+							bind:this={chatTextAreaElement}
+							class=" dark:bg-gray-900 dark:text-gray-100 outline-none w-full py-3 px-3 {fileUploadEnabled
 								? ''
 								: ' pl-4'} rounded-xl resize-none h-[48px]"
 							placeholder={chatInputPlaceholder !== ''
 								? chatInputPlaceholder
 								: isRecording
-								? 'Listening...'
-								: 'Send a message'}
+								? $i18n.t('Listening...')
+								: $i18n.t('Send a Message')}
 							bind:value={prompt}
 							on:keypress={(e) => {
 								if (e.keyCode == 13 && !e.shiftKey) {
@@ -803,92 +821,102 @@
 							}}
 						/>
 
-						<div class="self-end mb-2 flex space-x-0.5 mr-2">
+						<div class="self-end mb-2 flex space-x-1 mr-1">
 							{#if messages.length == 0 || messages.at(-1).done == true}
-								{#if speechRecognitionEnabled}
+								<Tooltip content={$i18n.t('Record voice')}>
+									{#if speechRecognitionEnabled}
+										<button
+											id="voice-input-button"
+											class=" text-gray-600 dark:text-gray-300 hover:bg-gray-50 dark:hover:bg-gray-850 transition rounded-full p-1.5 mr-0.5 self-center"
+											type="button"
+											on:click={() => {
+												speechRecognitionHandler();
+											}}
+										>
+											{#if isRecording}
+												<svg
+													class=" w-5 h-5 translate-y-[0.5px]"
+													fill="currentColor"
+													viewBox="0 0 24 24"
+													xmlns="http://www.w3.org/2000/svg"
+													><style>
+														.spinner_qM83 {
+															animation: spinner_8HQG 1.05s infinite;
+														}
+														.spinner_oXPr {
+															animation-delay: 0.1s;
+														}
+														.spinner_ZTLf {
+															animation-delay: 0.2s;
+														}
+														@keyframes spinner_8HQG {
+															0%,
+															57.14% {
+																animation-timing-function: cubic-bezier(0.33, 0.66, 0.66, 1);
+																transform: translate(0);
+															}
+															28.57% {
+																animation-timing-function: cubic-bezier(0.33, 0, 0.66, 0.33);
+																transform: translateY(-6px);
+															}
+															100% {
+																transform: translate(0);
+															}
+														}
+													</style><circle class="spinner_qM83" cx="4" cy="12" r="2.5" /><circle
+														class="spinner_qM83 spinner_oXPr"
+														cx="12"
+														cy="12"
+														r="2.5"
+													/><circle
+														class="spinner_qM83 spinner_ZTLf"
+														cx="20"
+														cy="12"
+														r="2.5"
+													/></svg
+												>
+											{:else}
+												<svg
+													xmlns="http://www.w3.org/2000/svg"
+													viewBox="0 0 20 20"
+													fill="currentColor"
+													class="w-5 h-5 translate-y-[0.5px]"
+												>
+													<path d="M7 4a3 3 0 016 0v6a3 3 0 11-6 0V4z" />
+													<path
+														d="M5.5 9.643a.75.75 0 00-1.5 0V10c0 3.06 2.29 5.585 5.25 5.954V17.5h-1.5a.75.75 0 000 1.5h4.5a.75.75 0 000-1.5h-1.5v-1.546A6.001 6.001 0 0016 10v-.357a.75.75 0 00-1.5 0V10a4.5 4.5 0 01-9 0v-.357z"
+													/>
+												</svg>
+											{/if}
+										</button>
+									{/if}
+								</Tooltip>
+
+								<Tooltip content={$i18n.t('Send message')}>
 									<button
-										id="voice-input-button"
-										class=" text-gray-600 dark:text-gray-300 transition rounded-lg p-1.5 mr-0.5 self-center"
-										type="button"
-										on:click={() => {
-											speechRecognitionHandler();
-										}}
+										class="{prompt !== ''
+											? 'bg-black text-white hover:bg-gray-900 dark:bg-white dark:text-black dark:hover:bg-gray-100 '
+											: 'text-white bg-gray-100 dark:text-gray-900 dark:bg-gray-800 disabled'} transition rounded-full p-1.5 self-center"
+										type="submit"
+										disabled={prompt === ''}
 									>
-										{#if isRecording}
-											<svg
-												class=" w-5 h-5 translate-y-[0.5px]"
-												fill="currentColor"
-												viewBox="0 0 24 24"
-												xmlns="http://www.w3.org/2000/svg"
-												><style>
-													.spinner_qM83 {
-														animation: spinner_8HQG 1.05s infinite;
-													}
-													.spinner_oXPr {
-														animation-delay: 0.1s;
-													}
-													.spinner_ZTLf {
-														animation-delay: 0.2s;
-													}
-													@keyframes spinner_8HQG {
-														0%,
-														57.14% {
-															animation-timing-function: cubic-bezier(0.33, 0.66, 0.66, 1);
-															transform: translate(0);
-														}
-														28.57% {
-															animation-timing-function: cubic-bezier(0.33, 0, 0.66, 0.33);
-															transform: translateY(-6px);
-														}
-														100% {
-															transform: translate(0);
-														}
-													}
-												</style><circle class="spinner_qM83" cx="4" cy="12" r="2.5" /><circle
-													class="spinner_qM83 spinner_oXPr"
-													cx="12"
-													cy="12"
-													r="2.5"
-												/><circle class="spinner_qM83 spinner_ZTLf" cx="20" cy="12" r="2.5" /></svg
-											>
-										{:else}
-											<svg
-												xmlns="http://www.w3.org/2000/svg"
-												viewBox="0 0 20 20"
-												fill="currentColor"
-												class="w-5 h-5 translate-y-[0.5px]"
-											>
-												<path d="M7 4a3 3 0 016 0v6a3 3 0 11-6 0V4z" />
-												<path
-													d="M5.5 9.643a.75.75 0 00-1.5 0V10c0 3.06 2.29 5.585 5.25 5.954V17.5h-1.5a.75.75 0 000 1.5h4.5a.75.75 0 000-1.5h-1.5v-1.546A6.001 6.001 0 0016 10v-.357a.75.75 0 00-1.5 0V10a4.5 4.5 0 01-9 0v-.357z"
-												/>
-											</svg>
-										{/if}
+										<svg
+											xmlns="http://www.w3.org/2000/svg"
+											viewBox="0 0 16 16"
+											fill="currentColor"
+											class="w-5 h-5"
+										>
+											<path
+												fill-rule="evenodd"
+												d="M8 14a.75.75 0 0 1-.75-.75V4.56L4.03 7.78a.75.75 0 0 1-1.06-1.06l4.5-4.5a.75.75 0 0 1 1.06 0l4.5 4.5a.75.75 0 0 1-1.06 1.06L8.75 4.56v8.69A.75.75 0 0 1 8 14Z"
+												clip-rule="evenodd"
+											/>
+										</svg>
 									</button>
-								{/if}
-								<button
-									class="{prompt !== ''
-										? 'bg-black text-white hover:bg-gray-900 dark:bg-white dark:text-black dark:hover:bg-gray-100 '
-										: 'text-white bg-gray-100 dark:text-gray-900 dark:bg-gray-800 disabled'} transition rounded-lg p-1 mr-0.5 w-7 h-7 self-center"
-									type="submit"
-									disabled={prompt === ''}
-								>
-									<svg
-										xmlns="http://www.w3.org/2000/svg"
-										viewBox="0 0 16 16"
-										fill="currentColor"
-										class="w-4.5 h-4.5 mx-auto"
-									>
-										<path
-											fill-rule="evenodd"
-											d="M8 14a.75.75 0 0 1-.75-.75V4.56L4.03 7.78a.75.75 0 0 1-1.06-1.06l4.5-4.5a.75.75 0 0 1 1.06 0l4.5 4.5a.75.75 0 0 1-1.06 1.06L8.75 4.56v8.69A.75.75 0 0 1 8 14Z"
-											clip-rule="evenodd"
-										/>
-									</svg>
-								</button>
+								</Tooltip>
 							{:else}
 								<button
-									class="bg-white hover:bg-gray-100 text-gray-800 dark:bg-gray-700 dark:text-white dark:hover:bg-gray-800 transition rounded-lg p-1.5"
+									class="bg-white hover:bg-gray-100 text-gray-800 dark:bg-gray-700 dark:text-white dark:hover:bg-gray-800 transition rounded-full p-1.5"
 									on:click={stopResponse}
 								>
 									<svg
@@ -910,7 +938,7 @@
 				</form>
 
 				<div class="mt-1.5 text-xs text-gray-500 text-center">
-					LLMs can make mistakes. Verify important information.
+					{$i18n.t('LLMs can make mistakes. Verify important information.')}
 				</div>
 			</div>
 		</div>

src/lib/components/chat/MessageInput/Documents.svelte

@@ -3,8 +3,10 @@
 
 	import { documents } from '$lib/stores';
 	import { removeFirstHashWord, isValidHttpUrl } from '$lib/utils';
-	import { tick } from 'svelte';
-	import toast from 'svelte-french-toast';
+	import { tick, getContext } from 'svelte';
+	import { toast } from 'svelte-sonner';
+
+	const i18n = getContext('i18n');
 
 	export let prompt = '';
 
@@ -89,16 +91,16 @@
 
 {#if filteredItems.length > 0 || prompt.split(' ')?.at(0)?.substring(1).startsWith('http')}
 	<div class="md:px-2 mb-3 text-left w-full absolute bottom-0 left-0 right-0">
-		<div class="flex w-full rounded-lg border border-gray-100 dark:border-gray-700">
-			<div class=" bg-gray-100 dark:bg-gray-700 w-10 rounded-l-lg text-center">
+		<div class="flex w-full px-2">
+			<div class=" bg-gray-100 dark:bg-gray-700 w-10 rounded-l-xl text-center">
 				<div class=" text-lg font-semibold mt-2">#</div>
 			</div>
 
-			<div class="max-h-60 flex flex-col w-full rounded-r-lg">
-				<div class=" overflow-y-auto bg-white p-2 rounded-tr-lg space-y-0.5">
+			<div class="max-h-60 flex flex-col w-full rounded-r-xl bg-white">
+				<div class="m-1 overflow-y-auto p-1 rounded-r-xl space-y-0.5">
 					{#each filteredItems as doc, docIdx}
 						<button
-							class=" px-3 py-1.5 rounded-lg w-full text-left {docIdx === selectedIdx
+							class=" px-3 py-1.5 rounded-xl w-full text-left {docIdx === selectedIdx
 								? ' bg-gray-100 selected-command-option-button'
 								: ''}"
 							type="button"
@@ -117,7 +119,7 @@
 									{doc?.title ?? `#${doc.name}`}
 								</div>
 
-								<div class=" text-xs text-gray-600 line-clamp-1">Collection</div>
+								<div class=" text-xs text-gray-600 line-clamp-1">{$i18n.t('Collection')}</div>
 							{:else}
 								<div class=" font-medium text-black line-clamp-1">
 									#{doc.name} ({doc.filename})
@@ -132,7 +134,7 @@
 
 					{#if prompt.split(' ')?.at(0)?.substring(1).startsWith('http')}
 						<button
-							class="px-3 py-1.5 rounded-lg w-full text-left bg-gray-100 selected-command-option-button"
+							class="px-3 py-1.5 rounded-xl w-full text-left bg-gray-100 selected-command-option-button"
 							type="button"
 							on:click={() => {
 								const url = prompt.split(' ')?.at(0)?.substring(1);
@@ -140,7 +142,9 @@
 									confirmSelectWeb(url);
 								} else {
 									toast.error(
-										'Oops! Looks like the URL is invalid. Please double-check and try again.'
+										$i18n.t(
+											'Oops! Looks like the URL is invalid. Please double-check and try again.'
+										)
 									);
 								}
 							}}
@@ -149,7 +153,7 @@
 								{prompt.split(' ')?.at(0)?.substring(1)}
 							</div>
 
-							<div class=" text-xs text-gray-600 line-clamp-1">Web</div>
+							<div class=" text-xs text-gray-600 line-clamp-1">{$i18n.t('Web')}</div>
 						</button>
 					{/if}
 				</div>

src/lib/components/chat/MessageInput/Models.svelte

@@ -2,8 +2,10 @@
 	import { generatePrompt } from '$lib/apis/ollama';
 	import { models } from '$lib/stores';
 	import { splitStream } from '$lib/utils';
-	import { tick } from 'svelte';
-	import toast from 'svelte-french-toast';
+	import { tick, getContext } from 'svelte';
+	import { toast } from 'svelte-sonner';
+
+	const i18n = getContext('i18n');
 
 	export let prompt = '';
 	export let user = null;
@@ -41,7 +43,7 @@
 		user = JSON.parse(JSON.stringify(model.name));
 		await tick();
 
-		chatInputPlaceholder = `'${model.name}' is thinking...`;
+		chatInputPlaceholder = $i18n.t('{{modelName}} is thinking...', { modelName: model.name });
 
 		const chatInputElement = document.getElementById('chat-textarea');
 
@@ -79,14 +81,18 @@
 								throw data;
 							}
 
-							if (data.done == false) {
-								if (prompt == '' && data.response == '\n') {
-									continue;
-								} else {
-									prompt += data.response;
-									console.log(data.response);
-									chatInputElement.scrollTop = chatInputElement.scrollHeight;
-									await tick();
+							if ('id' in data) {
+								console.log(data);
+							} else {
+								if (data.done == false) {
+									if (prompt == '' && data.response == '\n') {
+										continue;
+									} else {
+										prompt += data.response;
+										console.log(data.response);
+										chatInputElement.scrollTop = chatInputElement.scrollHeight;
+										await tick();
+									}
 								}
 							}
 						}
@@ -109,7 +115,9 @@
 					toast.error(error.error);
 				}
 			} else {
-				toast.error(`Uh-oh! There was an issue connecting to Ollama.`);
+				toast.error(
+					$i18n.t('Uh-oh! There was an issue connecting to {{provider}}.', { provider: 'llama' })
+				);
 			}
 		}
 
@@ -121,16 +129,16 @@
 
 {#if filteredModels.length > 0}
 	<div class="md:px-2 mb-3 text-left w-full absolute bottom-0 left-0 right-0">
-		<div class="flex w-full rounded-lg border border-gray-100 dark:border-gray-700">
-			<div class=" bg-gray-100 dark:bg-gray-700 w-10 rounded-l-lg text-center">
+		<div class="flex w-full px-2">
+			<div class=" bg-gray-100 dark:bg-gray-700 w-10 rounded-l-xl text-center">
 				<div class=" text-lg font-semibold mt-2">@</div>
 			</div>
 
-			<div class="max-h-60 flex flex-col w-full rounded-r-lg">
-				<div class=" overflow-y-auto bg-white p-2 rounded-tr-lg space-y-0.5">
+			<div class="max-h-60 flex flex-col w-full rounded-r-xl bg-white">
+				<div class="m-1 overflow-y-auto p-1 rounded-r-xl space-y-0.5">
 					{#each filteredModels as model, modelIdx}
 						<button
-							class=" px-3 py-1.5 rounded-lg w-full text-left {modelIdx === selectedIdx
+							class=" px-3 py-1.5 rounded-xl w-full text-left {modelIdx === selectedIdx
 								? ' bg-gray-100 selected-command-option-button'
 								: ''}"
 							type="button"

src/lib/components/chat/MessageInput/PromptCommands.svelte

@@ -1,8 +1,10 @@
 <script lang="ts">
 	import { prompts } from '$lib/stores';
 	import { findWordIndices } from '$lib/utils';
-	import { tick } from 'svelte';
-	import toast from 'svelte-french-toast';
+	import { tick, getContext } from 'svelte';
+	import { toast } from 'svelte-sonner';
+
+	const i18n = getContext('i18n');
 
 	export let prompt = '';
 	let selectedCommandIdx = 0;
@@ -29,7 +31,7 @@
 
 		if (command.content.includes('{{CLIPBOARD}}')) {
 			const clipboardText = await navigator.clipboard.readText().catch((err) => {
-				toast.error('Failed to read clipboard contents');
+				toast.error($i18n.t('Failed to read clipboard contents'));
 				return '{{CLIPBOARD}}';
 			});
 
@@ -60,16 +62,16 @@
 
 {#if filteredPromptCommands.length > 0}
 	<div class="md:px-2 mb-3 text-left w-full absolute bottom-0 left-0 right-0">
-		<div class="flex w-full rounded-lg border border-gray-100 dark:border-gray-700">
-			<div class=" bg-gray-100 dark:bg-gray-700 w-10 rounded-l-lg text-center">
+		<div class="flex w-full px-2">
+			<div class=" bg-gray-100 dark:bg-gray-700 w-10 rounded-l-xl text-center">
 				<div class=" text-lg font-semibold mt-2">/</div>
 			</div>
 
-			<div class="max-h-60 flex flex-col w-full rounded-r-lg">
-				<div class=" overflow-y-auto bg-white p-2 rounded-tr-lg space-y-0.5">
+			<div class="max-h-60 flex flex-col w-full rounded-r-xl bg-white">
+				<div class="m-1 overflow-y-auto p-1 rounded-r-xl space-y-0.5">
 					{#each filteredPromptCommands as command, commandIdx}
 						<button
-							class=" px-3 py-1.5 rounded-lg w-full text-left {commandIdx === selectedCommandIdx
+							class=" px-3 py-1.5 rounded-xl w-full text-left {commandIdx === selectedCommandIdx
 								? ' bg-gray-100 selected-command-option-button'
 								: ''}"
 							type="button"
@@ -93,7 +95,7 @@
 				</div>
 
 				<div
-					class=" px-2 pb-1 text-xs text-gray-600 bg-white rounded-br-lg flex items-center space-x-1"
+					class=" px-2 pb-1 text-xs text-gray-600 bg-white rounded-br-xl flex items-center space-x-1"
 				>
 					<div>
 						<svg
@@ -113,8 +115,9 @@
 					</div>
 
 					<div class="line-clamp-1">
-						Tip: Update multiple variable slots consecutively by pressing the tab key in the chat
-						input after each replacement.
+						{$i18n.t(
+							'Tip: Update multiple variable slots consecutively by pressing the tab key in the chat input after each replacement.'
+						)}
 					</div>
 				</div>
 			</div>

src/lib/components/chat/MessageInput/Suggestions.svelte

@@ -10,45 +10,47 @@
 			: suggestionPrompts.sort(() => Math.random() - 0.5).slice(0, 4);
 </script>
 
-<div class=" flex flex-wrap-reverse mb-3 md:p-1 text-left w-full">
-	{#each prompts as prompt, promptIdx}
-		<div
-			class="{promptIdx > 1 ? 'hidden sm:inline-flex' : ''} basis-full sm:basis-1/2 p-[5px] px-2"
-		>
-			<button
-				class=" flex-1 flex justify-between w-full h-full px-4 py-2.5 bg-white hover:bg-gray-50 dark:bg-gray-900 dark:hover:bg-gray-700 outline outline-1 outline-gray-200 dark:outline-gray-800 rounded-lg transition group"
-				on:click={() => {
-					submitPrompt(prompt.content);
-				}}
+<div class=" mb-3 md:p-1 text-left w-full">
+	<div class=" flex flex-wrap-reverse px-2 text-left">
+		{#each prompts as prompt, promptIdx}
+			<div
+				class="{promptIdx > 1 ? 'hidden sm:inline-flex' : ''} basis-full sm:basis-1/2 p-[5px] px-1"
 			>
-				<div class="flex flex-col text-left self-center">
-					{#if prompt.title && prompt.title[0] !== ''}
-						<div class="text-sm font-medium dark:text-gray-300">{prompt.title[0]}</div>
-						<div class="text-sm text-gray-500 line-clamp-1">{prompt.title[1]}</div>
-					{:else}
-						<div class=" self-center text-sm font-medium dark:text-gray-300 line-clamp-2">
-							{prompt.content}
-						</div>
-					{/if}
-				</div>
-
-				<div
-					class="self-center p-1 rounded-lg text-white group-hover:bg-gray-100 group-hover:text-gray-800 dark:group-hover:bg-gray-800 dark:group-hover:text-gray-100 dark:text-gray-900 transition"
+				<button
+					class=" flex-1 flex justify-between w-full h-full px-4 py-2.5 bg-gray-50 hover:bg-gray-100 dark:bg-gray-850 dark:hover:bg-gray-800 rounded-2xl transition group"
+					on:click={() => {
+						submitPrompt(prompt.content);
+					}}
 				>
-					<svg
-						xmlns="http://www.w3.org/2000/svg"
-						viewBox="0 0 16 16"
-						fill="currentColor"
-						class="w-4 h-4"
+					<div class="flex flex-col text-left self-center">
+						{#if prompt.title && prompt.title[0] !== ''}
+							<div class="text-sm font-medium dark:text-gray-300">{prompt.title[0]}</div>
+							<div class="text-sm text-gray-500 line-clamp-1">{prompt.title[1]}</div>
+						{:else}
+							<div class=" self-center text-sm font-medium dark:text-gray-300 line-clamp-2">
+								{prompt.content}
+							</div>
+						{/if}
+					</div>
+
+					<div
+						class="self-center p-1 rounded-lg text-gray-50 group-hover:text-gray-800 dark:text-gray-850 dark:group-hover:text-gray-100 transition"
 					>
-						<path
-							fill-rule="evenodd"
-							d="M8 14a.75.75 0 0 1-.75-.75V4.56L4.03 7.78a.75.75 0 0 1-1.06-1.06l4.5-4.5a.75.75 0 0 1 1.06 0l4.5 4.5a.75.75 0 0 1-1.06 1.06L8.75 4.56v8.69A.75.75 0 0 1 8 14Z"
-							clip-rule="evenodd"
-						/>
-					</svg>
-				</div>
-			</button>
-		</div>
-	{/each}
+						<svg
+							xmlns="http://www.w3.org/2000/svg"
+							viewBox="0 0 16 16"
+							fill="currentColor"
+							class="w-4 h-4"
+						>
+							<path
+								fill-rule="evenodd"
+								d="M8 14a.75.75 0 0 1-.75-.75V4.56L4.03 7.78a.75.75 0 0 1-1.06-1.06l4.5-4.5a.75.75 0 0 1 1.06 0l4.5 4.5a.75.75 0 0 1-1.06 1.06L8.75 4.56v8.69A.75.75 0 0 1 8 14Z"
+								clip-rule="evenodd"
+							/>
+						</svg>
+					</div>
+				</button>
+			</div>
+		{/each}
+	</div>
 </div>

src/lib/components/chat/Messages.svelte

@@ -2,9 +2,9 @@
 	import { v4 as uuidv4 } from 'uuid';
 
 	import { chats, config, modelfiles, settings, user } from '$lib/stores';
-	import { tick } from 'svelte';
+	import { tick, getContext } from 'svelte';
 
-	import toast from 'svelte-french-toast';
+	import { toast } from 'svelte-sonner';
 	import { getChatList, updateChatById } from '$lib/apis/chats';
 
 	import UserMessage from './Messages/UserMessage.svelte';
@@ -13,7 +13,10 @@
 	import Spinner from '../common/Spinner.svelte';
 	import { imageGenerations } from '$lib/apis/images';
 
+	const i18n = getContext('i18n');
+
 	export let chatId = '';
+	export let readOnly = false;
 	export let sendPrompt: Function;
 	export let continueGeneration: Function;
 	export let regenerateResponse: Function;
@@ -67,7 +70,7 @@
 		navigator.clipboard.writeText(text).then(
 			function () {
 				console.log('Async: Copying to clipboard was successful!');
-				toast.success('Copying to clipboard was successful!');
+				toast.success($i18n.t('Copying to clipboard was successful!'));
 			},
 			function (err) {
 				console.error('Async: Could not copy text: ', err);
@@ -104,12 +107,8 @@
 		await sendPrompt(userPrompt, userMessageId, chatId);
 	};
 
-	const confirmEditResponseMessage = async (messageId, content) => {
-		history.messages[messageId].originalContent = history.messages[messageId].content;
-		history.messages[messageId].content = content;
-
+	const updateChatMessages = async () => {
 		await tick();
-
 		await updateChatById(localStorage.token, chatId, {
 			messages: messages,
 			history: history
@@ -118,15 +117,20 @@
 		await chats.set(await getChatList(localStorage.token));
 	};
 
-	const rateMessage = async (messageId, rating) => {
-		history.messages[messageId].rating = rating;
-		await tick();
-		await updateChatById(localStorage.token, chatId, {
-			messages: messages,
-			history: history
-		});
+	const confirmEditResponseMessage = async (messageId, content) => {
+		history.messages[messageId].originalContent = history.messages[messageId].content;
+		history.messages[messageId].content = content;
 
-		await chats.set(await getChatList(localStorage.token));
+		await updateChatMessages();
+	};
+
+	const rateMessage = async (messageId, rating) => {
+		history.messages[messageId].annotation = {
+			...history.messages[messageId].annotation,
+			rating: rating
+		};
+
+		await updateChatMessages();
 	};
 
 	const showPreviousMessage = async (message) => {
@@ -223,33 +227,80 @@
 		}, 100);
 	};
 
-	// TODO: change delete behaviour
-	// const deleteMessageAndDescendants = async (messageId: string) => {
-	// 	if (history.messages[messageId]) {
-	// 		history.messages[messageId].deleted = true;
-
-	// 		for (const childId of history.messages[messageId].childrenIds) {
-	// 			await deleteMessageAndDescendants(childId);
-	// 		}
-	// 	}
-	// };
-
-	// const triggerDeleteMessageRecursive = async (messageId: string) => {
-	// 	await deleteMessageAndDescendants(messageId);
-	// 	await updateChatById(localStorage.token, chatId, { history });
-	// 	await chats.set(await getChatList(localStorage.token));
-	// };
-
 	const messageDeleteHandler = async (messageId) => {
-		if (history.messages[messageId]) {
-			history.messages[messageId].deleted = true;
-
-			for (const childId of history.messages[messageId].childrenIds) {
-				history.messages[childId].deleted = true;
+		const messageToDelete = history.messages[messageId];
+		const messageParentId = messageToDelete.parentId;
+		const messageChildrenIds = messageToDelete.childrenIds ?? [];
+		const hasSibling = messageChildrenIds.some(
+			(childId) => history.messages[childId]?.childrenIds?.length > 0
+		);
+		messageChildrenIds.forEach((childId) => {
+			const child = history.messages[childId];
+			if (child && child.childrenIds) {
+				if (child.childrenIds.length === 0 && !hasSibling) {
+					// if last prompt/response pair
+					history.messages[messageParentId].childrenIds = [];
+					history.currentId = messageParentId;
+				} else {
+					child.childrenIds.forEach((grandChildId) => {
+						if (history.messages[grandChildId]) {
+							history.messages[grandChildId].parentId = messageParentId;
+							history.messages[messageParentId].childrenIds.push(grandChildId);
+						}
+					});
+				}
 			}
-		}
-		await updateChatById(localStorage.token, chatId, { history });
+			// remove response
+			history.messages[messageParentId].childrenIds = history.messages[
+				messageParentId
+			].childrenIds.filter((id) => id !== childId);
+		});
+		// remove prompt
+		history.messages[messageParentId].childrenIds = history.messages[
+			messageParentId
+		].childrenIds.filter((id) => id !== messageId);
+		await updateChatById(localStorage.token, chatId, {
+			messages: messages,
+			history: history
+		});
 	};
+
+	// const messageDeleteHandler = async (messageId) => {
+	// 	const message = history.messages[messageId];
+	// 	const parentId = message.parentId;
+	// 	const childrenIds = message.childrenIds ?? [];
+	// 	const grandchildrenIds = [];
+
+	// 	// Iterate through childrenIds to find grandchildrenIds
+	// 	for (const childId of childrenIds) {
+	// 		const childMessage = history.messages[childId];
+	// 		const grandChildrenIds = childMessage.childrenIds ?? [];
+
+	// 		for (const grandchildId of grandchildrenIds) {
+	// 			const childMessage = history.messages[grandchildId];
+	// 			childMessage.parentId = parentId;
+	// 		}
+	// 		grandchildrenIds.push(...grandChildrenIds);
+	// 	}
+
+	// 	history.messages[parentId].childrenIds.push(...grandchildrenIds);
+	// 	history.messages[parentId].childrenIds = history.messages[parentId].childrenIds.filter(
+	// 		(id) => id !== messageId
+	// 	);
+
+	// 	// Select latest message
+	// 	let currentMessageId = grandchildrenIds.at(-1);
+	// 	if (currentMessageId) {
+	// 		let messageChildrenIds = history.messages[currentMessageId].childrenIds;
+	// 		while (messageChildrenIds.length !== 0) {
+	// 			currentMessageId = messageChildrenIds.at(-1);
+	// 			messageChildrenIds = history.messages[currentMessageId].childrenIds;
+	// 		}
+	// 		history.currentId = currentMessageId;
+	// 	}
+
+	// 	await updateChatById(localStorage.token, chatId, { messages, history });
+	// };
 </script>
 
 {#if messages.length == 0}
@@ -258,103 +309,58 @@
 	<div class=" pb-10">
 		{#key chatId}
 			{#each messages as message, messageIdx}
-				{#if !message.deleted}
-					<div class=" w-full">
-						<div
-							class="flex flex-col justify-between px-5 mb-3 {$settings?.fullScreenMode ?? null
-								? 'max-w-full'
-								: 'max-w-3xl'} mx-auto rounded-lg group"
-						>
-							{#if message.role === 'user'}
-								<UserMessage
-									on:delete={() => messageDeleteHandler(message.id)}
-									user={$user}
-									{message}
-									isFirstMessage={messageIdx === 0}
-									siblings={message.parentId !== null
-										? history.messages[message.parentId]?.childrenIds ?? []
-										: Object.values(history.messages)
-												.filter((message) => message.parentId === null)
-												.map((message) => message.id) ?? []}
-									{confirmEditMessage}
-									{showPreviousMessage}
-									{showNextMessage}
-									{copyToClipboard}
-								/>
+				<div class=" w-full">
+					<div
+						class="flex flex-col justify-between px-5 mb-3 {$settings?.fullScreenMode ?? null
+							? 'max-w-full'
+							: 'max-w-3xl'} mx-auto rounded-lg group"
+					>
+						{#if message.role === 'user'}
+							<UserMessage
+								on:delete={() => messageDeleteHandler(message.id)}
+								user={$user}
+								{readOnly}
+								{message}
+								isFirstMessage={messageIdx === 0}
+								siblings={message.parentId !== null
+									? history.messages[message.parentId]?.childrenIds ?? []
+									: Object.values(history.messages)
+											.filter((message) => message.parentId === null)
+											.map((message) => message.id) ?? []}
+								{confirmEditMessage}
+								{showPreviousMessage}
+								{showNextMessage}
+								{copyToClipboard}
+							/>
+						{:else}
+							<ResponseMessage
+								{message}
+								modelfiles={selectedModelfiles}
+								siblings={history.messages[message.parentId]?.childrenIds ?? []}
+								isLastMessage={messageIdx + 1 === messages.length}
+								{readOnly}
+								{updateChatMessages}
+								{confirmEditResponseMessage}
+								{showPreviousMessage}
+								{showNextMessage}
+								{rateMessage}
+								{copyToClipboard}
+								{continueGeneration}
+								{regenerateResponse}
+								on:save={async (e) => {
+									console.log('save', e);
 
-								{#if messages.length - 1 === messageIdx && processing !== ''}
-									<div class="flex my-2.5 ml-12 items-center w-fit space-x-2.5">
-										<div class=" dark:text-blue-100">
-											<svg
-												class=" w-4 h-4 translate-y-[0.5px]"
-												fill="currentColor"
-												viewBox="0 0 24 24"
-												xmlns="http://www.w3.org/2000/svg"
-												><style>
-													.spinner_qM83 {
-														animation: spinner_8HQG 1.05s infinite;
-													}
-													.spinner_oXPr {
-														animation-delay: 0.1s;
-													}
-													.spinner_ZTLf {
-														animation-delay: 0.2s;
-													}
-													@keyframes spinner_8HQG {
-														0%,
-														57.14% {
-															animation-timing-function: cubic-bezier(0.33, 0.66, 0.66, 1);
-															transform: translate(0);
-														}
-														28.57% {
-															animation-timing-function: cubic-bezier(0.33, 0, 0.66, 0.33);
-															transform: translateY(-6px);
-														}
-														100% {
-															transform: translate(0);
-														}
-													}
-												</style><circle class="spinner_qM83" cx="4" cy="12" r="2.5" /><circle
-													class="spinner_qM83 spinner_oXPr"
-													cx="12"
-													cy="12"
-													r="2.5"
-												/><circle class="spinner_qM83 spinner_ZTLf" cx="20" cy="12" r="2.5" /></svg
-											>
-										</div>
-										<div class=" text-sm font-medium">
-											{processing}
-										</div>
-									</div>
-								{/if}
-							{:else}
-								<ResponseMessage
-									{message}
-									modelfiles={selectedModelfiles}
-									siblings={history.messages[message.parentId]?.childrenIds ?? []}
-									isLastMessage={messageIdx + 1 === messages.length}
-									{confirmEditResponseMessage}
-									{showPreviousMessage}
-									{showNextMessage}
-									{rateMessage}
-									{copyToClipboard}
-									{continueGeneration}
-									{regenerateResponse}
-									on:save={async (e) => {
-										console.log('save', e);
-
-										const message = e.detail;
-										history.messages[message.id] = message;
-										await updateChatById(localStorage.token, chatId, {
-											messages: messages,
-											history: history
-										});
-									}}
-								/>
-							{/if}
-						</div>
+									const message = e.detail;
+									history.messages[message.id] = message;
+									await updateChatById(localStorage.token, chatId, {
+										messages: messages,
+										history: history
+									});
+								}}
+							/>
+						{/if}
 					</div>
-				{/if}
+				</div>
 			{/each}
 
 			{#if bottomPadding}

src/lib/components/chat/Messages/Placeholder.svelte

@@ -1,6 +1,9 @@
 <script lang="ts">
 	import { WEBUI_BASE_URL } from '$lib/constants';
-	import { onMount } from 'svelte';
+	import { user } from '$lib/stores';
+	import { onMount, getContext } from 'svelte';
+
+	const i18n = getContext('i18n');
 
 	export let models = [];
 	export let modelfiles = [];
@@ -30,7 +33,7 @@
 							<img
 								src={modelfiles[model]?.imageUrl ?? `${WEBUI_BASE_URL}/static/favicon.png`}
 								alt="modelfile"
-								class=" w-14 rounded-full border-[1px] border-gray-200 dark:border-none"
+								class=" size-12 rounded-full border-[1px] border-gray-200 dark:border-none"
 								draggable="false"
 							/>
 						{:else}
@@ -38,7 +41,7 @@
 								src={models.length === 1
 									? `${WEBUI_BASE_URL}/static/favicon.png`
 									: `${WEBUI_BASE_URL}/static/favicon.png`}
-								class=" w-14 rounded-full border-[1px] border-gray-200 dark:border-none"
+								class=" size-12 rounded-full border-[1px] border-gray-200 dark:border-none"
 								alt="logo"
 								draggable="false"
 							/>
@@ -47,7 +50,7 @@
 				{/each}
 			</div>
 		</div>
-		<div class=" mt-2 text-2xl text-gray-800 dark:text-gray-100 font-semibold">
+		<div class=" mt-2 mb-5 text-2xl text-gray-800 dark:text-gray-100 font-semibold">
 			{#if modelfile}
 				<span class=" capitalize">
 					{modelfile.title}
@@ -63,7 +66,9 @@
 					</div>
 				{/if}
 			{:else}
-				How can I help you today?
+				<div class=" line-clamp-1">{$i18n.t('Hello, {{name}}', { name: $user.name })}</div>
+
+				<div>{$i18n.t('How can I help you today?')}</div>
 			{/if}
 		</div>
 	</div>

src/lib/components/chat/Messages/RateComment.svelte

@@ -0,0 +1,117 @@
+<script lang="ts">
+	import { toast } from 'svelte-sonner';
+
+	import { createEventDispatcher, onMount } from 'svelte';
+
+	const dispatch = createEventDispatcher();
+
+	export let show = false;
+	export let message;
+
+	const LIKE_REASONS = [
+		`Accurate information`,
+		`Followed instructions perfectly`,
+		`Showcased creativity`,
+		`Positive attitude`,
+		`Attention to detail`,
+		`Thorough explanation`,
+		`Other`
+	];
+
+	const DISLIKE_REASONS = [
+		`Don't like the style`,
+		`Not factually correct`,
+		`Didn't fully follow instructions`,
+		`Refused when it shouldn't have`,
+		`Being Lazy`,
+		`Other`
+	];
+
+	let reasons = [];
+	let selectedReason = null;
+	let comment = '';
+
+	$: if (message.annotation.rating === 1) {
+		reasons = LIKE_REASONS;
+	} else if (message.annotation.rating === -1) {
+		reasons = DISLIKE_REASONS;
+	}
+
+	onMount(() => {
+		selectedReason = message.annotation.reason;
+		comment = message.annotation.comment;
+	});
+
+	const submitHandler = () => {
+		console.log('submitHandler');
+
+		message.annotation.reason = selectedReason;
+		message.annotation.comment = comment;
+
+		dispatch('submit');
+
+		toast.success('Thanks for your feedback!');
+		show = false;
+	};
+</script>
+
+<div class=" my-2.5 rounded-xl px-4 py-3 border dark:border-gray-850">
+	<div class="flex justify-between items-center">
+		<div class=" text-sm">Tell us more:</div>
+
+		<button
+			on:click={() => {
+				show = false;
+			}}
+		>
+			<svg
+				xmlns="http://www.w3.org/2000/svg"
+				fill="none"
+				viewBox="0 0 24 24"
+				stroke-width="1.5"
+				stroke="currentColor"
+				class="size-4"
+			>
+				<path stroke-linecap="round" stroke-linejoin="round" d="M6 18 18 6M6 6l12 12" />
+			</svg>
+		</button>
+	</div>
+
+	{#if reasons.length > 0}
+		<div class="flex flex-wrap gap-2 text-sm mt-2.5">
+			{#each reasons as reason}
+				<button
+					class="px-3.5 py-1 border dark:border-gray-850 dark:hover:bg-gray-850 {selectedReason ===
+					reason
+						? 'dark:bg-gray-800'
+						: ''} transition rounded-lg"
+					on:click={() => {
+						selectedReason = reason;
+					}}
+				>
+					{reason}
+				</button>
+			{/each}
+		</div>
+	{/if}
+
+	<div class="mt-2">
+		<textarea
+			bind:value={comment}
+			class="w-full text-sm px-1 py-2 bg-transparent outline-none resize-none rounded-xl"
+			placeholder="Feel free to add specific details"
+			rows="2"
+		/>
+	</div>
+
+	<div class="mt-2 flex justify-end">
+		<button
+			class=" bg-emerald-700 text-white text-sm font-medium rounded-lg px-3.5 py-1.5"
+			on:click={() => {
+				submitHandler();
+			}}
+		>
+			Submit
+		</button>
+	</div>
+</div>

src/lib/components/chat/Messages/ResponseMessage.svelte

@@ -1,20 +1,28 @@
 <script lang="ts">
-	import toast from 'svelte-french-toast';
+	import { toast } from 'svelte-sonner';
 	import dayjs from 'dayjs';
 	import { marked } from 'marked';
 	import tippy from 'tippy.js';
 	import auto_render from 'katex/dist/contrib/auto-render.mjs';
 	import 'katex/dist/katex.min.css';
 
+	import { fade } from 'svelte/transition';
 	import { createEventDispatcher } from 'svelte';
-	import { onMount, tick } from 'svelte';
+	import { onMount, tick, getContext } from 'svelte';
+
+	const i18n = getContext('i18n');
 
 	const dispatch = createEventDispatcher();
 
 	import { config, settings } from '$lib/stores';
 	import { synthesizeOpenAISpeech } from '$lib/apis/openai';
 	import { imageGenerations } from '$lib/apis/images';
-	import { extractSentences } from '$lib/utils';
+	import {
+		approximateToHumanReadable,
+		extractSentences,
+		revertSanitizedResponseContent,
+		sanitizeResponseContent
+	} from '$lib/utils';
 
 	import Name from './Name.svelte';
 	import ProfileImage from './ProfileImage.svelte';
@@ -22,6 +30,8 @@
 	import CodeBlock from './CodeBlock.svelte';
 	import Image from '$lib/components/common/Image.svelte';
 	import { WEBUI_BASE_URL } from '$lib/constants';
+	import Tooltip from '$lib/components/common/Tooltip.svelte';
+	import RateComment from './RateComment.svelte';
 
 	export let modelfiles = [];
 	export let message;
@@ -29,6 +39,9 @@
 
 	export let isLastMessage = true;
 
+	export let readOnly = false;
+
+	export let updateChatMessages: Function;
 	export let confirmEditResponseMessage: Function;
 	export let showPreviousMessage: Function;
 	export let showNextMessage: Function;
@@ -40,7 +53,7 @@
 
 	let edit = false;
 	let editedContent = '';
-
+	let editTextAreaElement: HTMLTextAreaElement;
 	let tooltipInstance = null;
 
 	let sentencesAudio = {};
@@ -50,7 +63,9 @@
 	let loadingSpeech = false;
 	let generatingImage = false;
 
-	$: tokens = marked.lexer(message.content);
+	let showRateComment = false;
+
+	$: tokens = marked.lexer(sanitizeResponseContent(message.content));
 
 	const renderer = new marked.Renderer();
 
@@ -108,7 +123,10 @@
                     eval_count: ${message.info.eval_count ?? 'N/A'}<br/>
                     eval_duration: ${
 											Math.round(((message.info.eval_duration ?? 0) / 1000000) * 100) / 100 ?? 'N/A'
-										}ms</span>`,
+										}ms<br/>
+                    approximate_total: ${approximateToHumanReadable(
+											message.info.total_duration
+										)}</span>`,
 				allowHTML: true
 			});
 		}
@@ -124,7 +142,7 @@
 				// • auto-render specific keys, e.g.:
 				delimiters: [
 					{ left: '$$', right: '$$', display: false },
-					{ left: '$', right: '$', display: false },
+					{ left: '$ ', right: ' $', display: false },
 					{ left: '\\(', right: '\\)', display: false },
 					{ left: '\\[', right: '\\]', display: false },
 					{ left: '[ ', right: ' ]', display: false }
@@ -247,10 +265,9 @@
 		editedContent = message.content;
 
 		await tick();
-		const editElement = document.getElementById(`message-edit-${message.id}`);
 
-		editElement.style.height = '';
-		editElement.style.height = `${editElement.scrollHeight}px`;
+		editTextAreaElement.style.height = '';
+		editTextAreaElement.style.height = `${editTextAreaElement.scrollHeight}px`;
 	};
 
 	const editMessageConfirmHandler = async () => {
@@ -276,13 +293,15 @@
 
 	const generateImage = async (message) => {
 		generatingImage = true;
-		const res = await imageGenerations(localStorage.token, message.content);
+		const res = await imageGenerations(localStorage.token, message.content).catch((error) => {
+			toast.error(error);
+		});
 		console.log(res);
 
 		if (res) {
-			message.files = res.images.map((image) => ({
+			message.files = res.map((image) => ({
 				type: 'image',
-				url: `data:image/png;base64,${image}`
+				url: `${image.url}`
 			}));
 
 			dispatch('save', message);
@@ -313,7 +332,7 @@
 
 				{#if message.timestamp}
 					<span class=" invisible group-hover:visible text-gray-400 text-xs font-medium">
-						{dayjs(message.timestamp * 1000).format('DD/MM/YYYY HH:mm')}
+						{dayjs(message.timestamp * 1000).format($i18n.t('DD/MM/YYYY HH:mm'))}
 					</span>
 				{/if}
 			</Name>
@@ -334,16 +353,18 @@
 				{/if}
 
 				<div
-					class="prose chat-{message.role} w-full max-w-full dark:prose-invert prose-headings:my-0 prose-p:m-0 prose-p:-mb-6 prose-pre:my-0 prose-table:my-0 prose-blockquote:my-0 prose-img:my-0 prose-ul:-my-4 prose-ol:-my-4 prose-li:-my-3 prose-ul:-mb-6 prose-ol:-mb-8 prose-li:-mb-4 whitespace-pre-line"
+					class="prose chat-{message.role} w-full max-w-full dark:prose-invert prose-headings:my-0 prose-p:m-0 prose-p:-mb-6 prose-pre:my-0 prose-table:my-0 prose-blockquote:my-0 prose-img:my-0 prose-ul:-my-4 prose-ol:-my-4 prose-li:-my-3 prose-ul:-mb-6 prose-ol:-mb-8 prose-ol:p-0 prose-li:-mb-4 whitespace-pre-line"
 				>
 					<div>
 						{#if edit === true}
 							<div class=" w-full">
 								<textarea
 									id="message-edit-{message.id}"
+									bind:this={editTextAreaElement}
 									class=" bg-transparent outline-none w-full resize-none"
 									bind:value={editedContent}
 									on:input={(e) => {
+										e.target.style.height = '';
 										e.target.style.height = `${e.target.scrollHeight}px`;
 									}}
 								/>
@@ -355,7 +376,7 @@
 											editMessageConfirmHandler();
 										}}
 									>
-										Save
+										{$i18n.t('Save')}
 									</button>
 
 									<button
@@ -364,7 +385,7 @@
 											cancelEditMessage();
 										}}
 									>
-										Cancel
+										{$i18n.t('Cancel')}
 									</button>
 								</div>
 							</div>
@@ -396,8 +417,10 @@
 								{:else}
 									{#each tokens as token}
 										{#if token.type === 'code'}
-											<!-- {token.text} -->
-											<CodeBlock lang={token.lang} code={token.text} />
+											<CodeBlock
+												lang={token.lang}
+												code={revertSanitizedResponseContent(token.text)}
+											/>
 										{:else}
 											{@html marked.parse(token.raw, {
 												...defaults,
@@ -462,189 +485,133 @@
 											</div>
 										{/if}
 
-										<button
-											class="{isLastMessage
-												? 'visible'
-												: 'invisible group-hover:visible'} p-1 rounded dark:hover:text-white hover:text-black transition"
-											on:click={() => {
-												editMessageHandler();
-											}}
-										>
-											<svg
-												xmlns="http://www.w3.org/2000/svg"
-												fill="none"
-												viewBox="0 0 24 24"
-												stroke-width="1.5"
-												stroke="currentColor"
-												class="w-4 h-4"
-											>
-												<path
-													stroke-linecap="round"
-													stroke-linejoin="round"
-													d="M16.862 4.487l1.687-1.688a1.875 1.875 0 112.652 2.652L6.832 19.82a4.5 4.5 0 01-1.897 1.13l-2.685.8.8-2.685a4.5 4.5 0 011.13-1.897L16.863 4.487zm0 0L19.5 7.125"
-												/>
-											</svg>
-										</button>
-
-										<button
-											class="{isLastMessage
-												? 'visible'
-												: 'invisible group-hover:visible'} p-1 rounded dark:hover:text-white hover:text-black transition copy-response-button"
-											on:click={() => {
-												copyToClipboard(message.content);
-											}}
-										>
-											<svg
-												xmlns="http://www.w3.org/2000/svg"
-												fill="none"
-												viewBox="0 0 24 24"
-												stroke-width="1.5"
-												stroke="currentColor"
-												class="w-4 h-4"
-											>
-												<path
-													stroke-linecap="round"
-													stroke-linejoin="round"
-													d="M15.666 3.888A2.25 2.25 0 0013.5 2.25h-3c-1.03 0-1.9.693-2.166 1.638m7.332 0c.055.194.084.4.084.612v0a.75.75 0 01-.75.75H9a.75.75 0 01-.75-.75v0c0-.212.03-.418.084-.612m7.332 0c.646.049 1.288.11 1.927.184 1.1.128 1.907 1.077 1.907 2.185V19.5a2.25 2.25 0 01-2.25 2.25H6.75A2.25 2.25 0 014.5 19.5V6.257c0-1.108.806-2.057 1.907-2.185a48.208 48.208 0 011.927-.184"
-												/>
-											</svg>
-										</button>
-
-										<button
-											class="{isLastMessage
-												? 'visible'
-												: 'invisible group-hover:visible'} p-1 rounded {message.rating === 1
-												? 'bg-gray-100 dark:bg-gray-800'
-												: ''} dark:hover:text-white hover:text-black transition"
-											on:click={() => {
-												rateMessage(message.id, 1);
-											}}
-										>
-											<svg
-												stroke="currentColor"
-												fill="none"
-												stroke-width="2"
-												viewBox="0 0 24 24"
-												stroke-linecap="round"
-												stroke-linejoin="round"
-												class="w-4 h-4"
-												xmlns="http://www.w3.org/2000/svg"
-												><path
-													d="M14 9V5a3 3 0 0 0-3-3l-4 9v11h11.28a2 2 0 0 0 2-1.7l1.38-9a2 2 0 0 0-2-2.3zM7 22H4a2 2 0 0 1-2-2v-7a2 2 0 0 1 2-2h3"
-												/></svg
-											>
-										</button>
-										<button
-											class="{isLastMessage
-												? 'visible'
-												: 'invisible group-hover:visible'} p-1 rounded {message.rating === -1
-												? 'bg-gray-100 dark:bg-gray-800'
-												: ''} dark:hover:text-white hover:text-black transition"
-											on:click={() => {
-												rateMessage(message.id, -1);
-											}}
-										>
-											<svg
-												stroke="currentColor"
-												fill="none"
-												stroke-width="2"
-												viewBox="0 0 24 24"
-												stroke-linecap="round"
-												stroke-linejoin="round"
-												class="w-4 h-4"
-												xmlns="http://www.w3.org/2000/svg"
-												><path
-													d="M10 15v4a3 3 0 0 0 3 3l4-9V2H5.72a2 2 0 0 0-2 1.7l-1.38 9a2 2 0 0 0 2 2.3zm7-13h2.67A2.31 2.31 0 0 1 22 4v7a2.31 2.31 0 0 1-2.33 2H17"
-												/></svg
-											>
-										</button>
-
-										<button
-											id="speak-button-{message.id}"
-											class="{isLastMessage
-												? 'visible'
-												: 'invisible group-hover:visible'} p-1 rounded dark:hover:text-white hover:text-black transition"
-											on:click={() => {
-												if (!loadingSpeech) {
-													toggleSpeakMessage(message);
-												}
-											}}
-										>
-											{#if loadingSpeech}
-												<svg
-													class=" w-4 h-4"
-													fill="currentColor"
-													viewBox="0 0 24 24"
-													xmlns="http://www.w3.org/2000/svg"
-													><style>
-														.spinner_S1WN {
-															animation: spinner_MGfb 0.8s linear infinite;
-															animation-delay: -0.8s;
-														}
-														.spinner_Km9P {
-															animation-delay: -0.65s;
-														}
-														.spinner_JApP {
-															animation-delay: -0.5s;
-														}
-														@keyframes spinner_MGfb {
-															93.75%,
-															100% {
-																opacity: 0.2;
-															}
-														}
-													</style><circle class="spinner_S1WN" cx="4" cy="12" r="3" /><circle
-														class="spinner_S1WN spinner_Km9P"
-														cx="12"
-														cy="12"
-														r="3"
-													/><circle class="spinner_S1WN spinner_JApP" cx="20" cy="12" r="3" /></svg
+										{#if !readOnly}
+											<Tooltip content="Edit" placement="bottom">
+												<button
+													class="{isLastMessage
+														? 'visible'
+														: 'invisible group-hover:visible'} p-1 rounded dark:hover:text-white hover:text-black transition"
+													on:click={() => {
+														editMessageHandler();
+													}}
 												>
-											{:else if speaking}
-												<svg
-													xmlns="http://www.w3.org/2000/svg"
-													fill="none"
-													viewBox="0 0 24 24"
-													stroke-width="1.5"
-													stroke="currentColor"
-													class="w-4 h-4"
-												>
-													<path
-														stroke-linecap="round"
-														stroke-linejoin="round"
-														d="M17.25 9.75 19.5 12m0 0 2.25 2.25M19.5 12l2.25-2.25M19.5 12l-2.25 2.25m-10.5-6 4.72-4.72a.75.75 0 0 1 1.28.53v15.88a.75.75 0 0 1-1.28.53l-4.72-4.72H4.51c-.88 0-1.704-.507-1.938-1.354A9.009 9.009 0 0 1 2.25 12c0-.83.112-1.633.322-2.396C2.806 8.756 3.63 8.25 4.51 8.25H6.75Z"
-													/>
-												</svg>
-											{:else}
-												<svg
-													xmlns="http://www.w3.org/2000/svg"
-													fill="none"
-													viewBox="0 0 24 24"
-													stroke-width="1.5"
-													stroke="currentColor"
-													class="w-4 h-4"
-												>
-													<path
-														stroke-linecap="round"
-														stroke-linejoin="round"
-														d="M19.114 5.636a9 9 0 010 12.728M16.463 8.288a5.25 5.25 0 010 7.424M6.75 8.25l4.72-4.72a.75.75 0 011.28.53v15.88a.75.75 0 01-1.28.53l-4.72-4.72H4.51c-.88 0-1.704-.507-1.938-1.354A9.01 9.01 0 012.25 12c0-.83.112-1.633.322-2.396C2.806 8.756 3.63 8.25 4.51 8.25H6.75z"
-													/>
-												</svg>
-											{/if}
-										</button>
+													<svg
+														xmlns="http://www.w3.org/2000/svg"
+														fill="none"
+														viewBox="0 0 24 24"
+														stroke-width="2"
+														stroke="currentColor"
+														class="w-4 h-4"
+													>
+														<path
+															stroke-linecap="round"
+															stroke-linejoin="round"
+															d="M16.862 4.487l1.687-1.688a1.875 1.875 0 112.652 2.652L6.832 19.82a4.5 4.5 0 01-1.897 1.13l-2.685.8.8-2.685a4.5 4.5 0 011.13-1.897L16.863 4.487zm0 0L19.5 7.125"
+														/>
+													</svg>
+												</button>
+											</Tooltip>
+										{/if}
 
-										{#if $config.images}
+										<Tooltip content="Copy" placement="bottom">
 											<button
+												class="{isLastMessage
+													? 'visible'
+													: 'invisible group-hover:visible'} p-1 rounded dark:hover:text-white hover:text-black transition copy-response-button"
+												on:click={() => {
+													copyToClipboard(message.content);
+												}}
+											>
+												<svg
+													xmlns="http://www.w3.org/2000/svg"
+													fill="none"
+													viewBox="0 0 24 24"
+													stroke-width="2"
+													stroke="currentColor"
+													class="w-4 h-4"
+												>
+													<path
+														stroke-linecap="round"
+														stroke-linejoin="round"
+														d="M15.666 3.888A2.25 2.25 0 0013.5 2.25h-3c-1.03 0-1.9.693-2.166 1.638m7.332 0c.055.194.084.4.084.612v0a.75.75 0 01-.75.75H9a.75.75 0 01-.75-.75v0c0-.212.03-.418.084-.612m7.332 0c.646.049 1.288.11 1.927.184 1.1.128 1.907 1.077 1.907 2.185V19.5a2.25 2.25 0 01-2.25 2.25H6.75A2.25 2.25 0 014.5 19.5V6.257c0-1.108.806-2.057 1.907-2.185a48.208 48.208 0 011.927-.184"
+													/>
+												</svg>
+											</button>
+										</Tooltip>
+
+										{#if !readOnly}
+											<Tooltip content="Good Response" placement="bottom">
+												<button
+													class="{isLastMessage
+														? 'visible'
+														: 'invisible group-hover:visible'} p-1 rounded {message?.annotation
+														?.rating === 1
+														? 'bg-gray-100 dark:bg-gray-800'
+														: ''} dark:hover:text-white hover:text-black transition"
+													on:click={() => {
+														rateMessage(message.id, 1);
+														showRateComment = true;
+													}}
+												>
+													<svg
+														stroke="currentColor"
+														fill="none"
+														stroke-width="2"
+														viewBox="0 0 24 24"
+														stroke-linecap="round"
+														stroke-linejoin="round"
+														class="w-4 h-4"
+														xmlns="http://www.w3.org/2000/svg"
+														><path
+															d="M14 9V5a3 3 0 0 0-3-3l-4 9v11h11.28a2 2 0 0 0 2-1.7l1.38-9a2 2 0 0 0-2-2.3zM7 22H4a2 2 0 0 1-2-2v-7a2 2 0 0 1 2-2h3"
+														/></svg
+													>
+												</button>
+											</Tooltip>
+
+											<Tooltip content="Bad Response" placement="bottom">
+												<button
+													class="{isLastMessage
+														? 'visible'
+														: 'invisible group-hover:visible'} p-1 rounded {message?.annotation
+														?.rating === -1
+														? 'bg-gray-100 dark:bg-gray-800'
+														: ''} dark:hover:text-white hover:text-black transition"
+													on:click={() => {
+														rateMessage(message.id, -1);
+														showRateComment = true;
+													}}
+												>
+													<svg
+														stroke="currentColor"
+														fill="none"
+														stroke-width="2"
+														viewBox="0 0 24 24"
+														stroke-linecap="round"
+														stroke-linejoin="round"
+														class="w-4 h-4"
+														xmlns="http://www.w3.org/2000/svg"
+														><path
+															d="M10 15v4a3 3 0 0 0 3 3l4-9V2H5.72a2 2 0 0 0-2 1.7l-1.38 9a2 2 0 0 0 2 2.3zm7-13h2.67A2.31 2.31 0 0 1 22 4v7a2.31 2.31 0 0 1-2.33 2H17"
+														/></svg
+													>
+												</button>
+											</Tooltip>
+										{/if}
+
+										<Tooltip content="Read Aloud" placement="bottom">
+											<button
+												id="speak-button-{message.id}"
 												class="{isLastMessage
 													? 'visible'
 													: 'invisible group-hover:visible'} p-1 rounded dark:hover:text-white hover:text-black transition"
 												on:click={() => {
-													if (!generatingImage) {
-														generateImage(message);
+													if (!loadingSpeech) {
+														toggleSpeakMessage(message);
 													}
 												}}
 											>
-												{#if generatingImage}
+												{#if loadingSpeech}
 													<svg
 														class=" w-4 h-4"
 														fill="currentColor"
@@ -679,108 +646,206 @@
 															r="3"
 														/></svg
 													>
-												{:else}
+												{:else if speaking}
 													<svg
 														xmlns="http://www.w3.org/2000/svg"
 														fill="none"
 														viewBox="0 0 24 24"
-														stroke-width="1.5"
+														stroke-width="2"
 														stroke="currentColor"
 														class="w-4 h-4"
 													>
 														<path
 															stroke-linecap="round"
 															stroke-linejoin="round"
-															d="m2.25 15.75 5.159-5.159a2.25 2.25 0 0 1 3.182 0l5.159 5.159m-1.5-1.5 1.409-1.409a2.25 2.25 0 0 1 3.182 0l2.909 2.909m-18 3.75h16.5a1.5 1.5 0 0 0 1.5-1.5V6a1.5 1.5 0 0 0-1.5-1.5H3.75A1.5 1.5 0 0 0 2.25 6v12a1.5 1.5 0 0 0 1.5 1.5Zm10.5-11.25h.008v.008h-.008V8.25Zm.375 0a.375.375 0 1 1-.75 0 .375.375 0 0 1 .75 0Z"
+															d="M17.25 9.75 19.5 12m0 0 2.25 2.25M19.5 12l2.25-2.25M19.5 12l-2.25 2.25m-10.5-6 4.72-4.72a.75.75 0 0 1 1.28.53v15.88a.75.75 0 0 1-1.28.53l-4.72-4.72H4.51c-.88 0-1.704-.507-1.938-1.354A9.009 9.009 0 0 1 2.25 12c0-.83.112-1.633.322-2.396C2.806 8.756 3.63 8.25 4.51 8.25H6.75Z"
+														/>
+													</svg>
+												{:else}
+													<svg
+														xmlns="http://www.w3.org/2000/svg"
+														fill="none"
+														viewBox="0 0 24 24"
+														stroke-width="2"
+														stroke="currentColor"
+														class="w-4 h-4"
+													>
+														<path
+															stroke-linecap="round"
+															stroke-linejoin="round"
+															d="M19.114 5.636a9 9 0 010 12.728M16.463 8.288a5.25 5.25 0 010 7.424M6.75 8.25l4.72-4.72a.75.75 0 011.28.53v15.88a.75.75 0 01-1.28.53l-4.72-4.72H4.51c-.88 0-1.704-.507-1.938-1.354A9.01 9.01 0 012.25 12c0-.83.112-1.633.322-2.396C2.806 8.756 3.63 8.25 4.51 8.25H6.75z"
 														/>
 													</svg>
 												{/if}
 											</button>
+										</Tooltip>
+
+										{#if $config.images && !readOnly}
+											<Tooltip content="Generate Image" placement="bottom">
+												<button
+													class="{isLastMessage
+														? 'visible'
+														: 'invisible group-hover:visible'} p-1 rounded dark:hover:text-white hover:text-black transition"
+													on:click={() => {
+														if (!generatingImage) {
+															generateImage(message);
+														}
+													}}
+												>
+													{#if generatingImage}
+														<svg
+															class=" w-4 h-4"
+															fill="currentColor"
+															viewBox="0 0 24 24"
+															xmlns="http://www.w3.org/2000/svg"
+															><style>
+																.spinner_S1WN {
+																	animation: spinner_MGfb 0.8s linear infinite;
+																	animation-delay: -0.8s;
+																}
+																.spinner_Km9P {
+																	animation-delay: -0.65s;
+																}
+																.spinner_JApP {
+																	animation-delay: -0.5s;
+																}
+																@keyframes spinner_MGfb {
+																	93.75%,
+																	100% {
+																		opacity: 0.2;
+																	}
+																}
+															</style><circle class="spinner_S1WN" cx="4" cy="12" r="3" /><circle
+																class="spinner_S1WN spinner_Km9P"
+																cx="12"
+																cy="12"
+																r="3"
+															/><circle
+																class="spinner_S1WN spinner_JApP"
+																cx="20"
+																cy="12"
+																r="3"
+															/></svg
+														>
+													{:else}
+														<svg
+															xmlns="http://www.w3.org/2000/svg"
+															fill="none"
+															viewBox="0 0 24 24"
+															stroke-width="2"
+															stroke="currentColor"
+															class="w-4 h-4"
+														>
+															<path
+																stroke-linecap="round"
+																stroke-linejoin="round"
+																d="m2.25 15.75 5.159-5.159a2.25 2.25 0 0 1 3.182 0l5.159 5.159m-1.5-1.5 1.409-1.409a2.25 2.25 0 0 1 3.182 0l2.909 2.909m-18 3.75h16.5a1.5 1.5 0 0 0 1.5-1.5V6a1.5 1.5 0 0 0-1.5-1.5H3.75A1.5 1.5 0 0 0 2.25 6v12a1.5 1.5 0 0 0 1.5 1.5Zm10.5-11.25h.008v.008h-.008V8.25Zm.375 0a.375.375 0 1 1-.75 0 .375.375 0 0 1 .75 0Z"
+															/>
+														</svg>
+													{/if}
+												</button>
+											</Tooltip>
 										{/if}
 
 										{#if message.info}
-											<button
-												class=" {isLastMessage
-													? 'visible'
-													: 'invisible group-hover:visible'} p-1 rounded dark:hover:text-white hover:text-black transition whitespace-pre-wrap"
-												on:click={() => {
-													console.log(message);
-												}}
-												id="info-{message.id}"
-											>
-												<svg
-													xmlns="http://www.w3.org/2000/svg"
-													fill="none"
-													viewBox="0 0 24 24"
-													stroke-width="1.5"
-													stroke="currentColor"
-													class="w-4 h-4"
+											<Tooltip content="Generation Info" placement="bottom">
+												<button
+													class=" {isLastMessage
+														? 'visible'
+														: 'invisible group-hover:visible'} p-1 rounded dark:hover:text-white hover:text-black transition whitespace-pre-wrap"
+													on:click={() => {
+														console.log(message);
+													}}
+													id="info-{message.id}"
 												>
-													<path
-														stroke-linecap="round"
-														stroke-linejoin="round"
-														d="M11.25 11.25l.041-.02a.75.75 0 011.063.852l-.708 2.836a.75.75 0 001.063.853l.041-.021M21 12a9 9 0 11-18 0 9 9 0 0118 0zm-9-3.75h.008v.008H12V8.25z"
-													/>
-												</svg>
-											</button>
+													<svg
+														xmlns="http://www.w3.org/2000/svg"
+														fill="none"
+														viewBox="0 0 24 24"
+														stroke-width="2"
+														stroke="currentColor"
+														class="w-4 h-4"
+													>
+														<path
+															stroke-linecap="round"
+															stroke-linejoin="round"
+															d="M11.25 11.25l.041-.02a.75.75 0 011.063.852l-.708 2.836a.75.75 0 001.063.853l.041-.021M21 12a9 9 0 11-18 0 9 9 0 0118 0zm-9-3.75h.008v.008H12V8.25z"
+														/>
+													</svg>
+												</button>
+											</Tooltip>
 										{/if}
 
-										{#if isLastMessage}
-											<button
-												type="button"
-												class="{isLastMessage
-													? 'visible'
-													: 'invisible group-hover:visible'} p-1 rounded dark:hover:text-white hover:text-black transition regenerate-response-button"
-												on:click={() => {
-													continueGeneration();
-												}}
-											>
-												<svg
-													xmlns="http://www.w3.org/2000/svg"
-													fill="none"
-													viewBox="0 0 24 24"
-													stroke-width="1.5"
-													stroke="currentColor"
-													class="w-4 h-4"
+										{#if isLastMessage && !readOnly}
+											<Tooltip content="Continue Response" placement="bottom">
+												<button
+													type="button"
+													class="{isLastMessage
+														? 'visible'
+														: 'invisible group-hover:visible'} p-1 rounded dark:hover:text-white hover:text-black transition regenerate-response-button"
+													on:click={() => {
+														continueGeneration();
+													}}
 												>
-													<path
-														stroke-linecap="round"
-														stroke-linejoin="round"
-														d="M21 12a9 9 0 1 1-18 0 9 9 0 0 1 18 0Z"
-													/>
-													<path
-														stroke-linecap="round"
-														stroke-linejoin="round"
-														d="M15.91 11.672a.375.375 0 0 1 0 .656l-5.603 3.113a.375.375 0 0 1-.557-.328V8.887c0-.286.307-.466.557-.327l5.603 3.112Z"
-													/>
-												</svg>
-											</button>
+													<svg
+														xmlns="http://www.w3.org/2000/svg"
+														fill="none"
+														viewBox="0 0 24 24"
+														stroke-width="2"
+														stroke="currentColor"
+														class="w-4 h-4"
+													>
+														<path
+															stroke-linecap="round"
+															stroke-linejoin="round"
+															d="M21 12a9 9 0 1 1-18 0 9 9 0 0 1 18 0Z"
+														/>
+														<path
+															stroke-linecap="round"
+															stroke-linejoin="round"
+															d="M15.91 11.672a.375.375 0 0 1 0 .656l-5.603 3.113a.375.375 0 0 1-.557-.328V8.887c0-.286.307-.466.557-.327l5.603 3.112Z"
+														/>
+													</svg>
+												</button>
+											</Tooltip>
 
-											<button
-												type="button"
-												class="{isLastMessage
-													? 'visible'
-													: 'invisible group-hover:visible'} p-1 rounded dark:hover:text-white hover:text-black transition regenerate-response-button"
-												on:click={regenerateResponse}
-											>
-												<svg
-													xmlns="http://www.w3.org/2000/svg"
-													fill="none"
-													viewBox="0 0 24 24"
-													stroke-width="1.5"
-													stroke="currentColor"
-													class="w-4 h-4"
+											<Tooltip content="Regenerate" placement="bottom">
+												<button
+													type="button"
+													class="{isLastMessage
+														? 'visible'
+														: 'invisible group-hover:visible'} p-1 rounded dark:hover:text-white hover:text-black transition regenerate-response-button"
+													on:click={regenerateResponse}
 												>
-													<path
-														stroke-linecap="round"
-														stroke-linejoin="round"
-														d="M16.023 9.348h4.992v-.001M2.985 19.644v-4.992m0 0h4.992m-4.993 0l3.181 3.183a8.25 8.25 0 0013.803-3.7M4.031 9.865a8.25 8.25 0 0113.803-3.7l3.181 3.182m0-4.991v4.99"
-													/>
-												</svg>
-											</button>
+													<svg
+														xmlns="http://www.w3.org/2000/svg"
+														fill="none"
+														viewBox="0 0 24 24"
+														stroke-width="2"
+														stroke="currentColor"
+														class="w-4 h-4"
+													>
+														<path
+															stroke-linecap="round"
+															stroke-linejoin="round"
+															d="M16.023 9.348h4.992v-.001M2.985 19.644v-4.992m0 0h4.992m-4.993 0l3.181 3.183a8.25 8.25 0 0013.803-3.7M4.031 9.865a8.25 8.25 0 0113.803-3.7l3.181 3.182m0-4.991v4.99"
+														/>
+													</svg>
+												</button>
+											</Tooltip>
 										{/if}
 									</div>
 								{/if}
+
+								{#if showRateComment}
+									<RateComment
+										bind:show={showRateComment}
+										bind:message
+										on:submit={() => {
+											updateChatMessages();
+										}}
+									/>
+								{/if}
 							</div>
 						{/if}
 					</div>