* added telemetry utils
* added telemetry to openrag
* fixed http timeout
* Added OS and GPU logging
* Track task fail and cancel
* Updated messages to be more readable
* Changed backend to mount config at volume
* update lock
* Changed backend to reapply settings after detecting that flow is reset
* Added periodic backup for flows, make better reset
* tui warning
* Changed settings page to alert user that he has to disable lock flow
* Changed flows to be locked
* Do periodic backup only if onboarding is done
* Change backup function to only back up flows if flow lock is disabled
* Added session manager to reapply all settings
---------
Co-authored-by: Sebastián Estévez <estevezsebastian@gmail.com>
Introduces a 'fail_safe_mode' option to the Embedding Model and OpenSearch (Multi-Model Multi-Embedding) components, allowing errors to be logged and None returned instead of raising exceptions. Refactors embedding model fetching logic for better error handling and updates component metadata, field order, and dependencies. Also adds 'className' fields and updates frontend node folder IDs for improved UI consistency.
Replaces all references to 'OpenSearchHybrid-Ve6bS' with 'OpenSearchVectorStoreComponentMultimodalMultiEmbedding-By9U4' in main.py, processors, and file service. Adds a utility for injecting provider credentials into Langflow request headers and integrates it into chat and file services for improved credential handling.
Replaced imports from config_manager with settings in chat_service.py and langflow_file_service.py to use get_openrag_config from config.settings. This change ensures consistency with the updated configuration structure.
Introduces SELECTED_EMBEDDING_MODEL as a global environment variable in docker-compose files and ensures it is passed in API headers for Langflow-related services. Updates settings and onboarding logic to set this variable without triggering flow updates, improving embedding model configuration consistency across services.
* Fixed models service to try api key with first available model
* fixed ibm onboarding to not disable query when no data is available
* make ibm query disabled when not configured
* enable ollama query only when configured or endpoint present
* enable get openai models query when already configured
* just enable get from env when not configured
* Simplify ollama models validation
* fix max_tokens error on gpt 4o
* Added flows with new components
* commented model provider assignment
* Added agent component display name
* commented provider assignment, assign provider on the generic component, assign custom values
* fixed ollama not showing loading steps, fixed loading steps never being removed
* made embedding and llm model optional on onboarding call
* added isEmbedding handling on useModelSelection
* added isEmbedding on onboarding card, separating embedding from non embedding card
* Added one additional step to configure embeddings
* Added embedding provider config
* Changed settings.py to return if not embedding
* Added editing fields to onboarding
* updated onboarding and flows_service to change embedding and llm separately
* updated templates that needs to be changed with provider values
* updated flows with new components
* Changed config manager to not have default models
* Changed flows_service settings
* Complete steps if not embedding
* Add more onboarding steps
* Removed one step from llm steps
* Added Anthropic as a model for the language model on the frontend
* Added anthropic models
* Added anthropic support on Backend
* Fixed provider health and validation
* Format settings
* Change anthropic logo
* Changed button to not jump
* Changed flows service to make anthropic work
* Fixed some things
* add embedding specific global variables
* updated flows
* fixed ingestion flow
* Implemented anthropic on settings page
* add embedding provider logo
* updated backend to work with multiple provider config
* update useUpdateSettings with new settings type
* updated provider health banner to check for health with new api
* changed queries and mutations to use new api
* changed embedding model input to work with new api
* Implemented provider based config on the frontend
* update existing design
* fixed settings configured
* fixed provider health query to include health check for both the providers
* Changed model-providers to show correctly the configured providers
* Updated prompt
* updated openrag agent
* Fixed settings to allow editing providers and changing llm and embedding models
* updated settings
* changed lf ver
* bump openrag version
* added more steps
* update settings to create the global variables
* updated steps
* updated default prompt
---------
Co-authored-by: Sebastián Estévez <estevezsebastian@gmail.com>
* Removed upload start message
* Made onboarding upload refetch nudges and only finish when document is ingested
* Implemented query filters on nudges
* changed get to post
* Implemented filtering for documents that are not sample data on nudges
---------
Co-authored-by: Sebastián Estévez <estevezsebastian@gmail.com>
* Updated ollama components
* Changed ollama display name to be correct
* Changed prompt of provider validation
* removed event dispatched from file upload
* Changed onboarding to upload the entire knowledge
* Changed default models for ollama
OWNER_NAME is now wrapped in double quotes to prevent issues with spaces and special characters when used in headers. This change improves reliability when passing user names containing spaces.
Introduces the CONNECTOR_TYPE_URL environment variable to docker-compose files and assets, updates the OpenRAG URL ingestion flow to use it, and ensures it is set in the auth service global variables. This enables explicit configuration and handling of URL-based connectors in the OpenRAG system.
Replaces the File component with a new OpenSearch hybrid search component in the ingestion flow, adds support for document metadata, and updates flow edges for DataFrame operations. Updates OpenSearch component implementation with advanced authentication, metadata handling, and vector store features. Docker Compose files and related service references are also updated to support the new OpenSearch integration.
Changed the handling of original filenames in Langflow upload tasks to use a mapping from file paths to original filenames instead of a list. Updated both the API router and TaskService to support this change, improving reliability when associating uploaded files with their original names.
* hard-coded openai models
* ensure index if disable ingest with langflow is active
* update backend to not update embedding model when flag is disabled
* initialize index on startup when feature flag is enabled
* put config.yaml on docker compose
* add container utils
* added localhost url to settings
* added localhost_url as a constant
* added localhost_url to get settings query
* make ollama onboarding have localhost url by default
* make endpoint be changed in models service and in onboarding backend instead of onboarding screen
* fixed embedding dimensions to get stripped model
* make config come as localhost but global variable be set as the transformed endpoint
* remove setting ollama url since it comes from the global variable
* use localhost again on ollama
---------
Co-authored-by: Lucas Oliveira <lucas.edu.oli@hotmail.com>
