Skip to content

Commit c4e20dd

Browse files
paullizerPatrick-Davis-MSFTnadoylemsftcjackson202Bionic711
authored
Update to v0.235.001 (#589)
* creating workflows * support agents * update * fix * updated demo * Swagger lite (#469) * Development (#467) * upgrade to v0.229.060 (#459) * Update release notes to show support for GPT-5 * Documented support for gpt-image-1 * Update config.py * remove documentation folder * Documentation and message table support (#444) * Develop demo docs and import markdown table support * fixed enhanced citations for groups and public workspaces * Updated to support showing public workspaces in scope * Update config.py * fix docs * Updated RELEASE_NOTES * docs demos for public workspaces * V0.229 bug fixes (v0.229.019) (#448) * Development (#445) * Update release notes to show support for GPT-5 * Documented support for gpt-image-1 * Update config.py * remove documentation folder * Documentation and message table support (#444) * Develop demo docs and import markdown table support * fixed enhanced citations for groups and public workspaces * Updated to support showing public workspaces in scope * Update config.py * fix docs * Updated RELEASE_NOTES * video indexer config details, doc intel test button fix, move multimedia configs to search and extract * improved header security * updated versions * moved * Update EXTERNAL_HEALTH_CHECK_DUPLICATION_FIX.md * added pdfs * v0.229.019 bug fixes upgrade to v0.229.058 (#452) * all urls in chat open in new tabs * consolidated admin settings for improved navigation * added left hand nav admin settings menus * added left hand menu options for workspaces * Added debug logging to video indexer processes * readme and functional test * Workspace Scope in Chat affects Prompts * Create WORKSPACE_SCOPE_PROMPTS_FIX.md * time based turn off for debug and file process logging * improve saving in admin settings * update to v0.229.058 * Update RELEASE_NOTES.md * Update RELEASE_NOTES.md * Popup modal for Health Check config * Added Health Check config guide * Chat page top nav bug (#458) * initial fix * fixed top nav chat up bug * notes for v0.229.060 * file location fix * Update config.py * Update RELEASE_NOTES.md * moved to correct location * Fixed enhanced citations CSP bug Simple Chat implemented improved security which negatively impacted enhanced citations. * Updated release notes * updated version and tests * swagger support for all endpoints and added swagger search * added wide screen support for chats when collapsing side bar * v0.230.001 features * adding support for xlsm, Macro Excel files. * moved into features * initial * added readme * removed html code * Update config.py (#477) Updated else if for AUTHORITY * Initial Setup for Pages documentation (#479) * setup folders and base files * setting up files * architecture diagrams * updated to libdoc * libdoc updates * updating side bar * removed loops * editing side bar * Created Simple Chat Jekyll theme * Update config.py (#477) (#478) Updated else if for AUTHORITY Co-authored-by: Patrick C Davis <82388365+Patrick-Davis-MSFT@users.noreply.github.com> * Updating architectures * Update README.md --------- Co-authored-by: Patrick C Davis <82388365+Patrick-Davis-MSFT@users.noreply.github.com> * initial * added to base * adding real data endpoints * Update route_backend_control_center.py * added individual charts * fix for bug 485 * added document metrics * added links to control center * debug * added date * fixed bugs due to branch descrepancies * added Azure SQL Driver Docker File * added documentation for docker_fileSession updates * Redis Managed Identity Azure Government Support Changes * Stop tracking ignored folders * updated gitignore * added sort by to table for user management * storage account size processing * Front end now shows storage account sizing * export user management list to csv * adding group management * fixing swagger generation * fix * Added inline dynamic property generation * added YAML support * Improved muiltform vs app/json detection * added Control Center Admin role ControlCenterAdmin * ai search sizing is working for groups * group refresh fixed * added group data fix * group table refresh * updated export to include group docs * adding public workspace management * removed sample data and consolidated row generators * Changed both caching helper functions to use the existing update_document() function from functions_documents.py instead of direct upsert. * removed workflow, will work on that in different branch * Document Set Fingerprinting, Scope-Aware Cache Key Generation, Event-Based Invalidation I've successfully implemented Document Set Fingerprint + Event-Based Cache Invalidation with deterministic sorting and Score Normalization. * added debug logging * setup cache feature and ttl time to admin app settings * removed cosmos level ttl * Keyvault for secrets (#492) * add crude keyvault base impl * upd actions for MAG * add settings to fix * upd secret naming convention * upd auth types to include conn string/basic(un/pw) * fix method name * add get agent helper * add ui trigger word and get agent helper * upd function imports * upd agents call * add desc of plugins * fix for admin modal loading * upd default agent handling * rmv unneeded file * rmv extra imp statements * add new cosmos container script * upd instructions for consistency of code * adds safe calls for akv functions * adds akv to personal agents * fix for user agents boot issue * fix global set * upd azure function plugin to super init * upd to clean imports * add keyvault to global actions loading * add plugin loading docs * rmv secret leak via logging * rmv displaying of token in logs * fix not loading global actions for personal agents * rmv unsupported characters from logging * fix chat links in dark mode * chg order of css for links in dark mode * fix chat color * add default plugin print logging * rmv default check for nonsql plugins * upd requirements * add keyvault and dynamic addsetting ui * fix for agents/plugins with invalid akv chars * add imp to appins logging * add security tab UI + key vault UI * add keyvault settings * fix for copilot findings. * fix for resaving plugin without changing secret --------- Co-authored-by: Bionic711 <nadoyle@microsoft.com> * Feature/remove abp for pr (#510) * add crude keyvault base impl * upd secret naming convention * upd auth types to include conn string/basic(un/pw) * add ui trigger word and get agent helper * adds safe calls for akv functions * add keyvault to global actions loading * rmv secret leak via logging * fix chat links in dark mode * chg order of css for links in dark mode * fix chat color * add keyvault and dynamic addsetting ui * fix for agents/plugins with invalid akv chars * add security tab UI + key vault UI * fix for resaving plugin without changing secret * init azure billing plugin * add app settings cache * upd to azure billing plugin * upd to msgraph plugin * init community customizations * add module * add key vault config modal * add logging and functions to math * rmv extra telemetry, add appcache * upd billing plugin * add/upd key vault, admin settings, agents, max tokens * Remove abp for pr * disable static logging for development * rmv dup import * add note on pass * added notes * rmv dup decl * add semicolon * rmv unused variable add agent name to log * add actions migration back in * add notes and copilot fixes --------- Co-authored-by: Bionic711 <nadoyle@microsoft.com> * Feature/group agents actions (#521) * add crude keyvault base impl * upd actions for MAG * add settings to fix * upd secret naming convention * upd auth types to include conn string/basic(un/pw) * fix method name * add get agent helper * add ui trigger word and get agent helper * upd function imports * upd agents call * add desc of plugins * fix for admin modal loading * upd default agent handling * rmv unneeded file * rmv extra imp statements * add new cosmos container script * upd instructions for consistency of code * adds safe calls for akv functions * adds akv to personal agents * fix for user agents boot issue * fix global set * upd azure function plugin to super init * upd to clean imports * add keyvault to global actions loading * add plugin loading docs * rmv secret leak via logging * rmv displaying of token in logs * fix not loading global actions for personal agents * rmv unsupported characters from logging * fix chat links in dark mode * chg order of css for links in dark mode * fix chat color * add default plugin print logging * rmv default check for nonsql plugins * upd requirements * add keyvault and dynamic addsetting ui * fix for agents/plugins with invalid akv chars * add imp to appins logging * add security tab UI + key vault UI * add keyvault settings * fix for copilot findings. * fix for resaving plugin without changing secret * init azure billing plugin * add app settings cache * upd to azure billing plugin * upd to msgraph plugin * init community customizations * add module * add key vault config modal * add logging and functions to math * rmv extra telemetry, add appcache * upd billing plugin * add/upd key vault, admin settings, agents, max tokens * Remove abp for pr * disable static logging for development * rmv dup import * add note on pass * added notes * rmv dup decl * add semicolon * rmv unused variable add agent name to log * add actions migration back in * add notes and copilot fixes * add group agents/actions * add branch for testing/rmv old branch * bug fixes, group agent modifications, rmv client validation * rmv ajv * upd from copilot --------- Co-authored-by: Bionic711 <nadoyle@microsoft.com> * Add cosmos activity logs container configuration * incorporate branch updates Add 372 fix 489 * Support deployment via AZD UP (#530) * Update devcontainer configuration for support of AZD * Move to module based bicep files * Add Azure deployment configuration and update Bicep modules for service outputs * Enhance Azure deployment process by adding predeploy hooks for Docker image management and updating Bicep modules to include managed identity client ID and container registry outputs. * Add deployment script for creating and storing Azure AD client secret in Key Vault * Update Azure Dev CLI feature version to latest in devcontainer configuration * Remove deprecated Bicep files and parameter configurations for cleaner deployment structure * Refactor Bicep modules for improved diagnostics and role assignments - Updated appService.bicep to conditionally import diagnostic settings based on enableDiagLogging parameter. - Changed Azure Cosmos DB authentication type to managed identity and removed key-based authentication settings. - Enhanced appServiceAuthentication.bicep by removing unnecessary parameters and configuring Key Vault reference for client secret. - Modified appServicePlan.bicep to conditionally import diagnostic settings. - Refactored azureContainerRegistry-existing.bicep to deploy role assignment to the ACR's resource group. - Updated azureContainerRegistry.bicep to conditionally import diagnostic settings. - Enhanced contentSafety.bicep with conditional diagnostic settings import. - Updated cosmosDb.bicep to include a new database and container, and added role assignments for managed identity. - Refactored documentIntelligence.bicep to conditionally import diagnostic settings. - Enhanced enterpriseApplication.bicep by adding additional required resource access scopes. - Updated keyVault.bicep to conditionally import diagnostic settings and adjusted enterprise app parameters. - Refactored openAI.bicep to conditionally import diagnostic settings. - Enhanced redisCache.bicep with conditional diagnostic settings import. - Updated search.bicep to conditionally import diagnostic settings. - Refactored speechService.bicep to conditionally import diagnostic settings. - Enhanced storageAccount.bicep with conditional diagnostic settings import. - Added main.parameters.json for parameter management. - Introduced azureContainerRegistry-roleAssignment.bicep for managing ACR role assignments. * Add custom subdomain names for document intelligence, OpenAI, and speech services * Fix casing for hostingMode property in search service configuration * Enhance storage account configuration by enabling hierarchical namespace and setting public access to 'None' for document containers * Add enterprise app permissions module for resource access management * Fixed ExternalApi configuration to valid guid and set value to a unique name * Add Init Script to Configure Entra Application * Fix spelling error * fix failure in hostingMode value * configure managed identity for contentSafety * update readme to support new AZD deployment solution * Video Indexer, Multi-Modal Enhancements, Scope Bug ## PR Summary: Video Indexer Multi-Modal Enhancements ### Overview This PR introduces significant enhancements to video processing and image analysis capabilities, focusing on multi-modal AI features and improved metadata handling. **Version updated from 0.233.167 to 0.233.172**. ### 🎯 Key Features #### 1. **Multi-Modal Vision Analysis for Images** - Added AI-powered vision analysis for uploaded images using GPT-4 Vision or similar models - Extracts comprehensive image insights including: - AI-generated descriptions - Object detection - Text extraction from images (OCR) - Detailed visual analysis - New admin setting: `enable_multimodal_vision` to control feature availability - Vision analysis results stored in document metadata and included in AI Search indexing - Connection testing endpoint added for vision model validation #### 2. **Enhanced Document Metadata Citations** - Implemented metadata-based citations that surface document keywords, abstracts, and vision analysis - New citation types displayed with distinct visual indicators: - **Keywords**: Tagged with `bi-tags` icon, labeled as "Metadata" - **Abstract**: Document summaries included as contextual citations - **Vision Analysis**: AI-generated image insights labeled as "AI Vision" - Metadata content passed to AI models as additional context for more informed responses - Special modal view for metadata citations (separate from standard document citations) #### 3. **Image Message UI Improvements** - Enhanced display for user-uploaded images vs AI-generated images - Added "View Text" button for uploaded images with extracted content or vision analysis - Collapsible info sections showing: - Extracted OCR text from Document Intelligence - AI Vision Analysis results - Proper avatar distinction between uploaded and generated images - Improved metadata tracking with `is_user_upload` flag #### 4. **Video Indexer Configuration Updates** - **BREAKING CHANGE**: Removed API key authentication support - Now exclusively uses **Managed Identity authentication** for Video Indexer - Updated admin UI documentation to guide managed identity setup: - Enable system-assigned managed identity on App Service - Assign "Video Indexer Restricted Viewer" role - Configure required ARM settings (subscription ID, resource group, account name) - Improved validation for required Video Indexer settings - Enhanced error messaging for missing configuration #### 5. **Search Scope Improvements** - Fixed search behavior when `document_scope='all'` to properly include group documents - Added `active_group_id` to search context when document scope is 'all' and groups are enabled - Conditional group index searching - only queries group index when `active_group_id` is present - Prevents unnecessary searches and potential errors when groups aren't in use #### 6. **Image Context in Conversation History** - Enhanced conversation history to include rich image context for AI models - Extracts and includes: - OCR text from Document Intelligence (up to max content length) - AI Vision analysis (description, objects, text) - Structured prompt formatting for multimodal understanding - **Important**: Base64 image data excluded from conversation history to prevent token overflow - Only metadata and extracted insights passed to models for efficient token usage ### 🔧 Technical Improvements #### Backend Changes - **route_backend_chats.py**: - Added metadata citation extraction logic (~150 lines) - Enhanced conversation history building for image uploads - Improved search argument handling for group contexts - **functions_documents.py**: - New `analyze_image_with_vision_model()` function for AI vision analysis - Enhanced `get_document_metadata_for_citations()` integration - Vision analysis now runs BEFORE chunk saving to include insights in AI Search indexing - Removed redundant blob storage for vision JSON (stored in document metadata) - **route_backend_settings.py**: - New `_test_multimodal_vision_connection()` endpoint for testing vision models - Supports both APIM and direct Azure OpenAI endpoints - Test uses 1x1 pixel sample image for validation - **functions_search.py**: - Added conditional logic for group search execution - Prevents empty `active_group_id` from causing search errors #### Frontend Changes - **chat-messages.js** (~275 lines changed): - Enhanced `appendMessage()` to handle uploaded image metadata - New `toggleImageInfo()` functionality for expandable image details - Improved citation rendering with metadata type indicators - Debug logging for image message processing - **chat-citations.js** (~70 lines added): - New `showMetadataModal()` function for displaying keywords/abstracts/vision analysis - Enhanced citation click handling to detect metadata citations - Separate modal styling and behavior for metadata vs document citations - **admin_settings.html**: - Complete redesign of Video Indexer configuration section - Removed all API key references - Added managed identity setup instructions with step-by-step guidance - Updated configuration display to show resource group and subscription ID - **_video_indexer_info.html**: - Updated modal content to clarify managed identity requirement - Added warning banner about authentication type - Enhanced configuration display with ARM resource details ### 📊 Files Changed - **16 files** modified - **+1,063 insertions**, **-412 deletions** - Net change: **+651 lines** ### 🧪 Testing Considerations - Test multi-modal vision analysis with various image types - Validate metadata citations appear correctly in chat responses - Verify Video Indexer works with managed identity authentication - Test search scope behavior with and without groups enabled - Validate image upload UI shows extracted text and vision analysis - Confirm conversation history properly handles image context without token overflow ### 🔐 Security & Performance - Managed identity authentication improves security posture (no stored API keys) - Image base64 data excluded from conversation history prevents token exhaustion - Metadata citations add minimal overhead while providing rich context - Vision analysis runs efficiently during document processing pipeline ### 📝 Configuration Required Admins must configure: 1. Enable `enable_multimodal_vision` in admin settings 2. Select vision-capable model (e.g., `gpt-4o`, `gpt-4-vision-preview`) 3. For Video Indexer: Configure managed identity and ARM resource details 4. Enable `enable_extract_meta_data` to surface metadata citations --- This PR significantly enhances the application's multi-modal capabilities, providing users with richer context from images and documents while maintaining efficient token usage and robust security practices. * Conversation Management Features (#532) New Features 1. Pin Conversations Users can pin important conversations to keep them at the top of the list Pinned conversations display a pin icon (📌) in the conversation header and details modal Pin icon appears before the conversation title Bulk pin/unpin operations available in multi-select mode Pinned conversations always appear first, sorted by most recent activity 2. Hide Conversations Users can hide conversations to declutter their workspace without deleting them Hidden conversations display an eye-slash icon (👁️‍🗨️) in the conversation header and details modal Eye-slash icon appears next to the pin icon (if pinned) Bulk hide/unhide operations available in multi-select mode Toggle visibility of hidden conversations using the eye icon in the sidebar 3. Two-Tier Conversation Search Quick Search (Sidebar) Instant title-based filtering of conversations Search icon in sidebar activates inline search input Real-time filtering as you type Clear button to reset search Expand button to open advanced search modal Advanced Search (Modal) Full-text search across all message content Multiple filter options: Date range (from/to) Chat type (personal/group/public) Classifications (multi-select) Has uploaded files Has generated images Pagination (20 results per page) Message snippets with highlighted search terms (50 chars before/after match) Click to navigate directly to specific messages Search history tracking (last 20 searches) Clickable search history to repeat searches 4. Message Highlighting & Navigation Search results highlight matched text in yellow (amber in dark mode) Smooth scroll animation to navigate to specific messages Pulse animation draws attention to the target message Highlights persist for 30 seconds before auto-clearing Works across conversation switches 5. Multi-Select Mode Select multiple conversations for bulk operations Visual checkboxes appear when entering selection mode Bulk actions available: Pin/unpin selected conversations Hide/unhide selected conversations Delete selected conversations Selection mode accessible from conversation dropdown menu Auto-exit after 30 seconds of inactivity 6. Enhanced Conversation Details Modal Displays pin icon if conversation is pinned Displays eye-slash icon if conversation is hidden Shows both icons at the top of the modal (next to title) Status section shows visual badges for pinned/hidden state Comprehensive metadata display Technical Implementation Frontend Changes chat-conversations.js: Core conversation management, quick search, pin/hide functionality chat-search-modal.js (NEW): Advanced search modal implementation chat-sidebar-conversations.js: Sidebar search synchronization, hidden conversation handling chat-messages.js: Message highlighting, smooth scroll, search highlight persistence chat-conversation-details.js: Updated to show pin/hidden icons in modal chats.css: Styles for search highlights and message pulse animations HTML Templates: Added search modal, updated navigation icons Backend Changes route_backend_conversations.py: /api/search_conversations - Full-text search with filters and pagination /api/conversations/classifications - Get unique classification values /api/user-settings/search-history - GET/POST/DELETE endpoints for search history /api/conversations/{id}/pin - Toggle pin status /api/conversations/{id}/hide - Toggle hide status Bulk operations for pin/hide/delete functions_settings.py: Search history management functions * Message management (#553) * added message masking mask selected content of message or an entire message * fixed citation border * enabled streaming * image gen with streaming * added reasoning support * added reasoning to agents * agent support * fixed key bug * disable group create and fixed model fetch * updated config * fixed support for workspace search for streaming * fix bug with sidebar update * fixed gpt-5 vision processing bug * metadata works with all messages now * fixed debug_print bug * added reasoning effort to agents and fixed agent validation * fixed file metadata loading bug * fixed llm streaming when working with group workspace data * fixed cosmos container config error * added delete message and fixed message threading * retry bug fixes * fixed message threading order * moved message buttons to menu * fixed bug for conversation history that included inactive threads * added css styling for urls for dark mode * fixed bug with newly created messages not showing metadata or deleting * improved search times by 100x * added token collect to messages supports models and agents * added streaming for agents along with token collection * added embedding token tracking * added document creation/deletion and token tracking to activity log * adding conversations to activity logs * added activity log viewer with filters, search, and export * added support for agents in edit and retry messages * Configure Application from AZD Up command (#548) * Add Cosmos DB post-configuration script and update requirements - Initial POC * post deploy configure services in cosmosdb * refactor to prevent post deploy configuration + begin support of key based auth. * Add additional parameter validation for creating entra app * Refactor Bicep modules for improved authentication and key management - Added keyVault-Secrets.bicep module for storing secrets in Key Vault. - Modified keyVault.bicep to remove enterprise app client secret handling and commented out managed identity role assignments. - Removed openAI-existing.bicep and refactored openAI.bicep to handle model deployments dynamically. - Added setPermissions.bicep for managing role assignments for various resources. - Updated postconfig.py to reflect changes in environment variable handling for authentication type. * Refactor Bicep modules to conditionally add settings based on authentication type and enable resource declarations for services * initial support for VideoIndexer service * Refactor Bicep modules to enhance VideoIndexer service integration and update diagnostic settings configurations * move from using chainguard-dev builder image to python slim image. * Updates to support post deployment app config * Add post-deployment permissions script for CosmosDB and update authentication type handling * fix typo in enhanced citation deployment config * Refactor Dockerfile to use Python 3.13-slim and streamline build process * restart web application after deployment settings applied * remove setting for disableLocalAuth * update to latest version of bicep deployment * remove dead code * code cleanup / formatting * removed unnecessary content from readme.md * fix token scope for commericial search service * set permission correctly for lookup of openAI models * fixes required to configure search with managed identity * Adds Azure Billing Plugin in Community Customizations (#546) * add crude keyvault base impl * upd actions for MAG * add settings to fix * upd secret naming convention * upd auth types to include conn string/basic(un/pw) * fix method name * add get agent helper * add ui trigger word and get agent helper * upd function imports * upd agents call * add desc of plugins * fix for admin modal loading * upd default agent handling * rmv unneeded file * rmv extra imp statements * add new cosmos container script * upd instructions for consistency of code * adds safe calls for akv functions * adds akv to personal agents * fix for user agents boot issue * fix global set * upd azure function plugin to super init * upd to clean imports * add keyvault to global actions loading * add plugin loading docs * rmv secret leak via logging * rmv displaying of token in logs * fix not loading global actions for personal agents * rmv unsupported characters from logging * fix chat links in dark mode * chg order of css for links in dark mode * fix chat color * add default plugin print logging * rmv default check for nonsql plugins * upd requirements * add keyvault and dynamic addsetting ui * fix for agents/plugins with invalid akv chars * add imp to appins logging * add security tab UI + key vault UI * add keyvault settings * fix for copilot findings. * fix for resaving plugin without changing secret * init azure billing plugin * add app settings cache * upd to azure billing plugin * upd to msgraph plugin * init community customizations * add module * add key vault config modal * add logging and functions to math * rmv extra telemetry, add appcache * upd billing plugin * add/upd key vault, admin settings, agents, max tokens * Remove abp for pr * disable static logging for development * rmv dup import * add note on pass * added notes * rmv dup decl * add semicolon * rmv unused variable add agent name to log * add actions migration back in * add notes and copilot fixes * add abp back in * upd abp/seperate graph from query * rmv missed merge lines * fix for AL * upd for consistency testing * upd abp to community * fix copilot findings #1 * fix plotting conflict * fix exception handling * fix static max function invokes * rmv unneeded decl * rmv unneeded imports * fix grouping dimensions * fix abp copilot suggestions #2 * simplify methods for message reload * upd dockerfile to google distroless * add pipelines * add modifications to container * upd to build * add missing arg * add arg for major/minor/patch python version * upd python paths and pip install * add perms to /app for user * chg back to root * rmv python3 * rmv not built python * add shared * add path and home * upd for stdlib paths * fix user input filesystem path vulns * fix to consecutive dots * upd pipeline to include branch name in image * add abp to deploy * upd instructions name/rmv abp from deploy * fix pipeline * mov back to Comm Cust for main inclusion --------- Co-authored-by: Bionic711 <nadoyle@microsoft.com> * Security/container build (#549) * upd dockerfile to google distroless * add pipelines * add modifications to container * upd to build * add missing arg * add arg for major/minor/patch python version * upd python paths and pip install * add perms to /app for user * chg back to root * rmv python3 * rmv not built python * add shared * add path and home * upd for stdlib paths * fix user input filesystem path vulns * fix to consecutive dots --------- Co-authored-by: Bionic711 <nadoyle@microsoft.com> * Feature/speech managed identity (#543) * Bugfix - deleted duplicate enable_external_healthcheck entry * Feature - updated Speech Service to use Managed Identity in addition to the key, added MAG functionality via Azure Speech SDK since the Fast Transcription API is not available in MAG, updated Admin Setup Walkthrough so it goes to the right place in the settings when Next is clicked, updated Speech requirements in Walkthrough, rewrote Admin Configuration docs, updated/corrected Managed Identity roles in Setup Instructions Special docs. * Update application/single_app/templates/admin_settings.html Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Update application/single_app/functions_settings.py Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Update application/single_app/functions_documents.py Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Update application/single_app/functions_documents.py Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> --------- Co-authored-by: Paul Lizer <paullizer@microsoft.com> Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Banner text color picker from Vivien (#555) * Classification text color picker * Line endings * Remove opencensus * Add flask instrumentation * Add troubleshooting doc * Add troubleshooting doc * Control center (#567) * added group status (active, locked, upload disabled, and inactive) Adds Azure Billing Plugin in Community Customizations * added bulk member upload via csv for groups * add document metadata modified activity log tracking * activity logging for members deleted from groups * added group activity timeline * added notification system * added notifications for document upload to workspaces * fixed badge sizing * fixed url link * fixed badge to not show with zero notifications * Updated notification system * Updated approval system * updated approval workflow * updated notification workflow * Fixed set active bug on my public workspace page * Added user retention policy, updated user profile page with dashboards, retention config, and more. * adding speed to text for chat UI * updated the speech wave form and input field * updated to transcribe entire recording * fixed bug creating new conversation with auto-send * add mic permissions * added stream token tracking * Added public workspace reporting * Updated AI search sizing analysis * added management for public workspaces * improved public workspace management includes stats and bulk actions * updated groups dashboard for owners and admins with stats and bulk actions * added voice for ai to talk with users in chats * Auto Voice Response * for speech service, added 429 randomized response pattern to prevent thunder herding * updated admin settings for speech services and fixed dark mode for raw log viewing * updated video extraction card * Added Control Center Admin and Dashboard Reader roles * updated feedback and safety decorators so admins work unless required then those roles must be used * Updated and Validated logic for admin roles; control center, safety, and feedback * added support for control center admin and dashboard reader * Development (#566) * Banner text color picker from Vivien (#555) * Classification text color picker * Line endings * Remove opencensus * Add flask instrumentation * Add troubleshooting doc * Add troubleshooting doc --------- Co-authored-by: Ed Clark <107473135+clarked-msft@users.noreply.github.com> Co-authored-by: Ed Clark <clarked@microsoft.com> Co-authored-by: Bionic711 <13358952+Bionic711@users.noreply.github.com> * updated tool tip to better inform user on status of ai response * improve query parameters detection for swagger * updated visual cue showing the ai is talking to the user * moved duplicates to shared js * replaced alert with toast. * fixed and added log_event to exceptions * added @user_required and improved swagger generation * Update route_frontend_profile.py * fixed swagger generation bug on affecting two apis * returned keyvault to admin settings ui * Fixed bug when running local js --------- Co-authored-by: Ed Clark <107473135+clarked-msft@users.noreply.github.com> Co-authored-by: Ed Clark <clarked@microsoft.com> Co-authored-by: Bionic711 <13358952+Bionic711@users.noreply.github.com> * Adding release notes * fixed debug_debug_print * Updated README * Update README.md * accepted changes --------- Co-authored-by: Patrick C Davis <82388365+Patrick-Davis-MSFT@users.noreply.github.com> Co-authored-by: Bionic711 <nadoyle@microsoft.com> Co-authored-by: cjackson202 <134412115+cjackson202@users.noreply.github.com> Co-authored-by: Bionic711 <ndoyle001@gmail.com> Co-authored-by: Bionic711 <13358952+Bionic711@users.noreply.github.com> Co-authored-by: Steve Carroll <37545884+SteveCInVA@users.noreply.github.com> Co-authored-by: Xeelee33 <Xeelee33@users.noreply.github.com> Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> Co-authored-by: Ed Clark <107473135+clarked-msft@users.noreply.github.com> Co-authored-by: Ed Clark <clarked@microsoft.com>
1 parent 297e646 commit c4e20dd

File tree

1 file changed

+0
-161
lines changed

1 file changed

+0
-161
lines changed

‎application/single_app/functions_documents.py‎

Lines changed: 0 additions & 161 deletions
Original file line numberDiff line numberDiff line change
@@ -3087,21 +3087,15 @@ def analyze_image_with_vision_model(image_path, user_id, document_id, settings):
30873087
'analysis': 'detailed analysis'
30883088
} or None if vision analysis is disabled or fails
30893089
"""
3090-
<<<<<<< HEAD
30913090
debug_print(f"[VISION_ANALYSIS_V2] Function entry - document_id: {document_id}, user_id: {user_id}")
30923091

3093-
=======
3094-
if not settings.get('enable_multimodal_vision', False):
3095-
return None
3096-
>>>>>>> origin/main
30973092

30983093
try:
30993094
# Convert image to base64
31003095
with open(image_path, 'rb') as img_file:
31013096
image_bytes = img_file.read()
31023097
base64_image = base64.b64encode(image_bytes).decode('utf-8')
31033098

3104-
<<<<<<< HEAD
31053099
image_size = len(image_bytes)
31063100
base64_size = len(base64_image)
31073101
debug_print(f"[VISION_ANALYSIS] Image conversion for {document_id}:")
@@ -3116,21 +3110,13 @@ def analyze_image_with_vision_model(image_path, user_id, document_id, settings):
31163110
# Get vision model settings
31173111
vision_model = settings.get('multimodal_vision_model', 'gpt-4o')
31183112
debug_print(f"[VISION_ANALYSIS] Vision model selected: {vision_model}")
3119-
=======
3120-
# Determine image mime type
3121-
mime_type = mimetypes.guess_type(image_path)[0] or 'image/jpeg'
3122-
3123-
# Get vision model settings
3124-
vision_model = settings.get('multimodal_vision_model', 'gpt-4o')
3125-
>>>>>>> origin/main
31263113

31273114
if not vision_model:
31283115
print(f"Warning: Multi-modal vision enabled but no model selected")
31293116
return None
31303117

31313118
# Initialize client (reuse GPT configuration)
31323119
enable_gpt_apim = settings.get('enable_gpt_apim', False)
3133-
<<<<<<< HEAD
31343120
debug_print(f"[VISION_ANALYSIS] Using APIM: {enable_gpt_apim}")
31353121

31363122
if enable_gpt_apim:
@@ -3143,19 +3129,11 @@ def analyze_image_with_vision_model(image_path, user_id, document_id, settings):
31433129
gpt_client = AzureOpenAI(
31443130
api_version=api_version,
31453131
azure_endpoint=endpoint,
3146-
=======
3147-
3148-
if enable_gpt_apim:
3149-
gpt_client = AzureOpenAI(
3150-
api_version=settings.get('azure_apim_gpt_api_version'),
3151-
azure_endpoint=settings.get('azure_apim_gpt_endpoint'),
3152-
>>>>>>> origin/main
31533132
api_key=settings.get('azure_apim_gpt_subscription_key')
31543133
)
31553134
else:
31563135
# Use managed identity or key
31573136
auth_type = settings.get('azure_openai_gpt_authentication_type', 'key')
3158-
<<<<<<< HEAD
31593137
api_version = settings.get('azure_openai_gpt_api_version')
31603138
endpoint = settings.get('azure_openai_gpt_endpoint')
31613139

@@ -3164,39 +3142,26 @@ def analyze_image_with_vision_model(image_path, user_id, document_id, settings):
31643142
debug_print(f" API Version: {api_version}")
31653143
debug_print(f" Auth Type: {auth_type}")
31663144

3167-
=======
3168-
>>>>>>> origin/main
31693145
if auth_type == 'managed_identity':
31703146
token_provider = get_bearer_token_provider(
31713147
DefaultAzureCredential(),
31723148
cognitive_services_scope
31733149
)
31743150
gpt_client = AzureOpenAI(
3175-
<<<<<<< HEAD
31763151
api_version=api_version,
31773152
azure_endpoint=endpoint,
3178-
=======
3179-
api_version=settings.get('azure_openai_gpt_api_version'),
3180-
azure_endpoint=settings.get('azure_openai_gpt_endpoint'),
3181-
>>>>>>> origin/main
31823153
azure_ad_token_provider=token_provider
31833154
)
31843155
else:
31853156
gpt_client = AzureOpenAI(
3186-
<<<<<<< HEAD
31873157
api_version=api_version,
31883158
azure_endpoint=endpoint,
3189-
=======
3190-
api_version=settings.get('azure_openai_gpt_api_version'),
3191-
azure_endpoint=settings.get('azure_openai_gpt_endpoint'),
3192-
>>>>>>> origin/main
31933159
api_key=settings.get('azure_openai_gpt_key')
31943160
)
31953161

31963162
# Create vision prompt
31973163
print(f"Analyzing image with vision model: {vision_model}")
31983164

3199-
<<<<<<< HEAD
32003165
# Determine which token parameter to use based on model type
32013166
# o-series and gpt-5 models require max_completion_tokens instead of max_tokens
32023167
vision_model_lower = vision_model.lower()
@@ -3222,17 +3187,6 @@ def analyze_image_with_vision_model(image_path, user_id, document_id, settings):
32223187
Ensure your entire response is valid JSON. Include all four keys even if some are empty strings or empty arrays."""
32233188
else:
32243189
prompt_text = """Analyze this image and provide:
3225-
=======
3226-
response = gpt_client.chat.completions.create(
3227-
model=vision_model,
3228-
messages=[
3229-
{
3230-
"role": "user",
3231-
"content": [
3232-
{
3233-
"type": "text",
3234-
"text": """Analyze this image and provide:
3235-
>>>>>>> origin/main
32363190
1. A detailed description of what you see
32373191
2. List any objects, people, or notable elements
32383192
3. Extract any visible text (OCR)
@@ -3245,7 +3199,6 @@ def analyze_image_with_vision_model(image_path, user_id, document_id, settings):
32453199
"text": "...",
32463200
"analysis": "..."
32473201
}"""
3248-
<<<<<<< HEAD
32493202

32503203
api_params = {
32513204
"model": vision_model,
@@ -3256,8 +3209,6 @@ def analyze_image_with_vision_model(image_path, user_id, document_id, settings):
32563209
{
32573210
"type": "text",
32583211
"text": prompt_text
3259-
=======
3260-
>>>>>>> origin/main
32613212
},
32623213
{
32633214
"type": "image_url",
@@ -3267,7 +3218,6 @@ def analyze_image_with_vision_model(image_path, user_id, document_id, settings):
32673218
}
32683219
]
32693220
}
3270-
<<<<<<< HEAD
32713221
]
32723222
}
32733223

@@ -3305,16 +3255,10 @@ def analyze_image_with_vision_model(image_path, user_id, document_id, settings):
33053255
# Check finish reason
33063256
if hasattr(response.choices[0], 'finish_reason'):
33073257
debug_print(f" Finish reason: {response.choices[0].finish_reason}")
3308-
=======
3309-
],
3310-
max_tokens=1000
3311-
)
3312-
>>>>>>> origin/main
33133258

33143259
# Parse response
33153260
content = response.choices[0].message.content
33163261

3317-
<<<<<<< HEAD
33183262
# Handle None content
33193263
if content is None:
33203264
print(f"[VISION_ANALYSIS_V2] ⚠️ Response content is None!")
@@ -3344,14 +3288,10 @@ def analyze_image_with_vision_model(image_path, user_id, document_id, settings):
33443288
has_code_fence = '```' in content
33453289
debug_print(f" Starts with JSON bracket: {is_json_like}")
33463290
debug_print(f" Contains code fence: {has_code_fence}")
3347-
=======
3348-
debug_print(f"[VISION_ANALYSIS] Raw response for {document_id}: {content[:500]}...")
3349-
>>>>>>> origin/main
33503291

33513292
# Try to parse as JSON, fallback to raw text
33523293
try:
33533294
# Clean up potential markdown code fences
3354-
<<<<<<< HEAD
33553295
debug_print(f"[VISION_ANALYSIS] Attempting to clean JSON code fences...")
33563296
content_cleaned = clean_json_codeFence(content)
33573297
debug_print(f" Cleaned length: {len(content_cleaned)} characters")
@@ -3376,23 +3316,10 @@ def analyze_image_with_vision_model(image_path, user_id, document_id, settings):
33763316
'parse_failed': True
33773317
}
33783318
debug_print(f"[VISION_ANALYSIS] Created fallback structure with raw response")
3379-
=======
3380-
content_cleaned = clean_json_codeFence(content)
3381-
vision_analysis = json.loads(content_cleaned)
3382-
debug_print(f"[VISION_ANALYSIS] Parsed JSON successfully for {document_id}")
3383-
except Exception as parse_error:
3384-
debug_print(f"[VISION_ANALYSIS] Vision response not valid JSON: {parse_error}")
3385-
print(f"Vision response not valid JSON, using raw text")
3386-
vision_analysis = {
3387-
'description': content,
3388-
'raw_response': content
3389-
}
3390-
>>>>>>> origin/main
33913319

33923320
# Add model info to analysis
33933321
vision_analysis['model'] = vision_model
33943322

3395-
<<<<<<< HEAD
33963323
debug_print(f"[VISION_ANALYSIS] Final analysis structure for {document_id}:")
33973324
debug_print(f" Model: {vision_model}")
33983325
debug_print(f" Has 'description': {'description' in vision_analysis}")
@@ -3414,13 +3341,6 @@ def analyze_image_with_vision_model(image_path, user_id, document_id, settings):
34143341
txt = vision_analysis['text']
34153342
debug_print(f" Text length: {len(txt) if txt else 0} chars")
34163343
debug_print(f" Text preview: {txt[:100] if txt else 'None'}...")
3417-
=======
3418-
debug_print(f"[VISION_ANALYSIS] Complete analysis for {document_id}:")
3419-
debug_print(f" Model: {vision_model}")
3420-
debug_print(f" Description: {vision_analysis.get('description', 'N/A')[:200]}...")
3421-
debug_print(f" Objects: {vision_analysis.get('objects', [])}")
3422-
debug_print(f" Text: {vision_analysis.get('text', 'N/A')[:100]}...")
3423-
>>>>>>> origin/main
34243344

34253345
print(f"Vision analysis completed for document: {document_id}")
34263346
return vision_analysis
@@ -5195,79 +5115,10 @@ def process_di_document(document_id, user_id, temp_file_path, original_filename,
51955115
# Don't fail the whole proc, total_embedding_tokens, embedding_model_nameess, just update status
51965116
update_callback(status=f"Processing complete (metadata extraction warning)")
51975117

5198-
<<<<<<< HEAD
51995118
# Note: Vision analysis now happens BEFORE save_chunks (moved earlier in the flow)
52005119
# This ensures vision_analysis is available in metadata when chunks are being saved
52015120

52025121
return total_final_chunks_processed, total_embedding_tokens, embedding_model_name
5203-
=======
5204-
# --- Multi-Modal Vision Analysis (for images only) ---
5205-
if is_image and enable_enhanced_citations:
5206-
enable_multimodal_vision = settings.get('enable_multimodal_vision', False)
5207-
if enable_multimodal_vision:
5208-
try:
5209-
update_callback(status="Performing AI vision analysis...")
5210-
5211-
vision_analysis = analyze_image_with_vision_model(
5212-
temp_file_path,
5213-
user_id,
5214-
document_id,
5215-
settings
5216-
)
5217-
5218-
if vision_analysis:
5219-
print(f"Vision analysis completed for image: {original_filename}")
5220-
5221-
# Update document with vision analysis results
5222-
update_fields = {
5223-
'vision_analysis': vision_analysis,
5224-
'vision_description': vision_analysis.get('description', ''),
5225-
'vision_objects': vision_analysis.get('objects', []),
5226-
'vision_extracted_text': vision_analysis.get('text', ''),
5227-
'status': "AI vision analysis completed"
5228-
}
5229-
update_callback(**update_fields)
5230-
5231-
# Save vision analysis as separate blob for citations
5232-
vision_json_path = temp_file_path + '_vision.json'
5233-
try:
5234-
with open(vision_json_path, 'w', encoding='utf-8') as f:
5235-
json.dump(vision_analysis, f, indent=2)
5236-
5237-
vision_blob_filename = f"{os.path.splitext(original_filename)[0]}_vision_analysis.json"
5238-
5239-
upload_blob_args = {
5240-
"temp_file_path": vision_json_path,
5241-
"user_id": user_id,
5242-
"document_id": document_id,
5243-
"blob_filename": vision_blob_filename,
5244-
"update_callback": update_callback
5245-
}
5246-
5247-
if is_public_workspace:
5248-
upload_blob_args["public_workspace_id"] = public_workspace_id
5249-
elif is_group:
5250-
upload_blob_args["group_id"] = group_id
5251-
5252-
upload_to_blob(**upload_blob_args)
5253-
print(f"Vision analysis saved to blob storage: {vision_blob_filename}")
5254-
5255-
finally:
5256-
if os.path.exists(vision_json_path):
5257-
os.remove(vision_json_path)
5258-
else:
5259-
print(f"Vision analysis returned no results for: {original_filename}")
5260-
update_callback(status="Vision analysis completed (no results)")
5261-
5262-
except Exception as e:
5263-
print(f"Warning: Error in vision analysis for {document_id}: {str(e)}")
5264-
import traceback
5265-
traceback.print_exc()
5266-
# Don't fail the whole process, just update status
5267-
update_callback(status=f"Processing complete (vision analysis warning)")
5268-
5269-
return total_final_chunks_processed
5270-
>>>>>>> origin/main
52715122

52725123
def _get_content_type(path: str) -> str:
52735124
ext = os.path.splitext(path)[1].lower()
@@ -5572,7 +5423,6 @@ def update_doc_callback(**kwargs):
55725423
args["group_id"] = group_id
55735424

55745425
if file_ext == '.txt':
5575-
<<<<<<< HEAD
55765426
result = process_txt(**{k: v for k, v in args.items() if k != "file_ext"})
55775427
# Handle tuple return (chunks, tokens, model_name)
55785428
if isinstance(result, tuple) and len(result) == 3:
@@ -5603,17 +5453,6 @@ def update_doc_callback(**kwargs):
56035453
total_chunks_saved, total_embedding_tokens, embedding_model_name = result
56045454
else:
56055455
total_chunks_saved = result
5606-
=======
5607-
total_chunks_saved = process_txt(**{k: v for k, v in args.items() if k != "file_ext"})
5608-
elif file_ext == '.xml':
5609-
total_chunks_saved = process_xml(**{k: v for k, v in args.items() if k != "file_ext"})
5610-
elif file_ext in ('.yaml', '.yml'):
5611-
total_chunks_saved = process_yaml(**{k: v for k, v in args.items() if k != "file_ext"})
5612-
elif file_ext == '.log':
5613-
total_chunks_saved = process_log(**{k: v for k, v in args.items() if k != "file_ext"})
5614-
elif file_ext in ('.doc', '.docm'):
5615-
total_chunks_saved = process_doc(**{k: v for k, v in args.items() if k != "file_ext"})
5616-
>>>>>>> origin/main
56175456
elif file_ext == '.html':
56185457
result = process_html(**{k: v for k, v in args.items() if k != "file_ext"})
56195458
if isinstance(result, tuple) and len(result) == 3:

0 commit comments

Comments
 (0)