* models query combined
* make endpoint to handle provider health
* provider health banner
* update-pdf-to-include-provider-selection (#344)
* polishing the error fixing experience
* fix agent instructions and up char limit
* fix provider
* disable tracing in langflow
* improve docling serve banner remove false positives
* Changed pyproject.toml docling versions
* Added another uv lock revision
* version bump
* unused things and fix bad conflicts
* add isFetching to the hook
* put back settings for models queries to never cache results
* update banner refetching indicator
* validate provider settings when saving
* fix settings page layout issue
* Added retry as false on the get models, to not take a long time
---------
Co-authored-by: Mendon Kissling <59585235+mendonk@users.noreply.github.com>
Co-authored-by: Mike Fortman <michael.fortman@datastax.com>
Co-authored-by: phact <estevezsebastian@gmail.com>
Co-authored-by: Lucas Oliveira <lucas.edu.oli@hotmail.com>
* update settings update api to allow changing model provider config
* use react hook form
* make settings page small width
* re-use the onboarding forms instead of rolling a custom one
* issue
* remove test
* make custom forms with react-hook-form
* replace the updateFlow mutation with updateSettings
* show all the model providers
* revert changes to onboarding forms
* disabled state styles for providers
* break model selectors into their own file
* use existing selector component, use settings endpoint instead of onboarding, clean up form styles
* revert changes to openai onboarding
* small form changes
* Initial plan
* Implement dynamic Ollama embedding dimension resolution with probing
Co-authored-by: phact <1313220+phact@users.noreply.github.com>
* Fix Ollama probing
* raise instead of dims 0
* Show better error
* Run embedding probe before saving settings so that user can update
---------
Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: phact <1313220+phact@users.noreply.github.com>
Co-authored-by: Lucas Oliveira <lucas.edu.oli@hotmail.com>
Co-authored-by: phact <estevezsebastian@gmail.com>
* 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>
* changed tooltip stype
* added start on label wrapper
* changed switch to checkbox on openai onboarding and changed copies
* made border be red when api key is invalid
* Added embedding configuration after onboarding
* changed openrag ingest docling to have same embedding model component as other flows
* changed flows service to get flow by id, not by path
* modify reset_langflow to also put right embedding model
* added endpoint and project id to provider config
* added replacing the model with the provider model when resetting
* Moved consts to settings.py
* raise when flow_id is not found
* implement delete user conversation on agent
* format
* implement delete session endpoint
* implement delete session on persistence services
* added deletion of sessions and added fetch sessions with query instead of with useEffect
* removed unused texts
* implemented dropdown menu on conversations
This commit adds functionality to retrieve and set ingestion-specific defaults from the Langflow API based on the flow configuration. It includes error handling for the API call and updates the settings with values for chunk size, chunk overlap, separator, and embedding model based on the flow data. This enhancement improves the flexibility and robustness of the ingestion process.
This commit updates the settings retrieval function to include new flow IDs for chat and ingestion, replacing the deprecated FLOW_ID. It also improves the logic for exposing edit URLs based on the availability of public URLs, contributing to a more robust and well-documented codebase.
