Removes the unused `/litellm/config` endpoint, the corresponding `downloadLiteLLMConfig` frontend API function, and the unused import from the `Database.svelte` component. This code was identified as dead code as it was not being used in the UI.
This commit introduces a new setting in the Interface settings that allows users to control whether the chat title is used as the browser's tab title.
The following changes were made:
- Added `useChatTitleAsTabTitle` to the `Settings` type in `src/lib/stores/index.ts`.
- Added a toggle switch in `src/lib/components/chat/Settings/Interface.svelte` to manage this new setting.
- Updated `src/lib/components/chat/Chat.svelte` to conditionally set the document title based on the `useChatTitleAsTabTitle` setting.
This change introduces a visual warning in the group settings page. The warning appears when an admin attempts to disable a permission for a group that is already enabled in the default 'user' group. This is necessary because permissions are additive, and disabling a permission in a specific group will not revoke it if it's enabled in the default group.
To achieve this, the following changes were made:
- A new `PermissionSwitch.svelte` component was created to encapsulate the permission switch and its warning logic, avoiding redundant code.
- The `Groups.svelte` component was updated to correctly fetch the default user group's permissions.
- The `Permissions.svelte` component was refactored to use the new `PermissionSwitch.svelte` component, making the code cleaner and more maintainable.
When creating a new user group, the permissions for the new group will now be pre-populated with the same permissions as the "default user group".
This is achieved by removing the separate `AddGroupModal` and instead using the `EditGroupModal` for both creating and editing groups. When creating a new group, the `EditGroupModal` is now pre-populated with the default permissions, saving administrators from having to manually configure them each time.
This change simplifies the codebase by removing a redundant component and directly addresses the user's request to streamline the group creation process.
This commit introduces a new permission toggle that allows administrators to control whether users can publicly share their notes.
- Adds a new environment variable `USER_PERMISSIONS_NOTES_ALLOW_PUBLIC_SHARING` to control the default setting.
- Adds a `public_notes` permission to the `sharing` section of the user permissions.
- Adds a toggle switch to the admin panel for managing this permission.
- Implements backend logic to enforce the permission when a user attempts to share a note publicly.
This commit introduces support for the DISKANN index type in the Milvus vector database integration.
Changes include:
- Added `MILVUS_DISKANN_MAX_DEGREE` and `MILVUS_DISKANN_SEARCH_LIST_SIZE` configuration variables.
- Updated the Milvus client to recognize and configure the DISKANN index type during collection creation.
The pymilvus library expects -1 for unlimited queries, but the code was passing None, which caused a TypeError. This commit changes the default value of the limit parameter in the query method from None to -1. It also updates the call site in the get method to pass -1 instead of None and updates the type hint and a comment to reflect this change.
This commit fixes an issue where Retrieval-Augmented Generation (RAG)
queries were still being generated even when all attached files were set
to 'full context' mode. This was inefficient as the full content of the
files was already available to the model.
The `chat_completion_files_handler` in `backend/open_webui/utils/middleware.py`
has been updated to:
- Check if all attached files have the `context: 'full'` property.
- Skip the `generate_queries` step if all files are in full context mode.
- Pass a `full_context=True` flag to the `get_sources_from_items`
function to ensure it fetches the entire document content instead of
performing a vector search.
This change ensures that RAG queries are only generated when necessary,
improving the efficiency of the system.
This commit fixes a bug where hidden models were still visible and selectable in the notes section. The following changes were made:
- The model dropdown in the chat section of the note editor is now filtered to exclude hidden models.
- The default model selection logic in the note editor is now filtered to exclude hidden models.
Previously, when downloading a generated image, the filename was set to the AI's response text. This was not ideal as the response text could be long and contain characters that are not suitable for filenames.
This commit changes the behavior to use a generic, translatable filename for downloaded images. The new filename is 'ai_generated_image' (or its translation), which is more user-friendly and consistent.
Adds the ability to enable the Code Interpreter feature by appending
`code-interpreter=true` to the chat URL.
The `Chat.svelte` component's `initNewChat` function has been updated
to parse this URL parameter. If present, it sets the
`codeInterpreterEnabled` state variable to true.
This change leverages the existing mechanisms for:
- Saving and restoring `codeInterpreterEnabled` state to/from localStorage.
- Displaying and toggling the Code Interpreter state via the existing UI
button in the `MessageInput` component.
No new UI elements were added as the existing UI correctly reflects
the feature's state.
google-labs-jules[bot]