* 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>
* 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
* 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
* 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>
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>
* 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
* 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
* feat: add status handling and visual indicators for file statuses
* refactor: comment out status field and related rendering logic in SearchPage
* format
* add timeout on mutation delete document
* make file fields be optional
* fetch task files and display them on knowledge page
* add tasks to files inside task context
* added failed to status badge
* added files on get all tasks on backend
* Changed models to get parameters by settings if not existent
* changed settings page to get models when is no ajth mode
* fixed openai allowing validation even when value is not present
* removed unused console log
---------
Co-authored-by: Lucas Oliveira <lucas.edu.oli@hotmail.com>
Co-authored-by: Mike Fortman <michael.fortman@datastax.com>
