* 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>
* 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
* Changed flows and components to support different models
* Changed onboarding to redirect automatically
* Added new components and ids to settings
* Changed flows service to change llm text components as well
* changed models service to not remove : on ollama
* fix edge not connecting on nudges flow
- Implemented bulk selection and deletion functionality in the Knowledge page.
- Added a confirmation dialog for bulk deletions, providing user feedback on success or failure.
- Updated AgGrid configuration to support multiple row selection and checkbox functionality.
- Styled checkboxes for better visibility and user experience.
- Refactored related components to accommodate new bulk actions.
This commit modifies the AppClients class to remove the Content-Type header if it is explicitly set to None, particularly for file uploads. This change enhances the robustness of the async code by ensuring proper header management during API requests, aligning with the project's focus on well-documented and maintainable code.
This commit updates the settings for LANGFLOW_INGEST_FLOW_ID to remove reliance on a deprecated environment variable. It introduces a new Langflow HTTP client for making API requests and adds a centralized method for handling Langflow API requests, improving code organization and maintainability. The changes enhance the robustness of the async code while ensuring proper documentation practices are followed.
