* fix astra not showing similarity score in citations ui
* fix qdrant not showing similarity score in citations ui
* fix weaviate not showing similarity score in citations ui
* Support Gitee AI(LLM Provider)
* refactor(server): 重构 GiteeAI 模型窗口限制功能,暂时将窗口限制硬编码,计划使用外部 API 数据和缓存
* updates for Gitee AI
* use legacy lookup since gitee does not enable getting token context windows
* add more missing records
* reorder imports
---------
Co-authored-by: 方程 <fangcheng@oschina.cn>
Co-authored-by: timothycarambat <rambat1010@gmail.com>
* implemented openrouter embedding model support
* ran yarn lint
* data handling entry
---------
Co-authored-by: timothycarambat <rambat1010@gmail.com>
* feat: add base64 document attachment support to API chat endpoints
* remove parsed documents from api chat process
linting for simplicity
fix logic issues with flow of data through the pipeline
documentiation
* change var scope
---------
Co-authored-by: timothycarambat <rambat1010@gmail.com>
* Add Default System Prompt Management
- Introduced a new route for fetching and updating the default system prompt in the backend.
- Added a new Admin page for managing the default system prompt, including a form for editing and saving changes.
- Updated the SettingsSidebar to include a link to the new Default System Prompt page.
- Implemented fetching of available system prompt variables for use in the prompt editor.
- Enhanced the ChatSettings and ChatPromptSettings components to support the new default system prompt functionality.
This commit lays the groundwork for improved management of system prompts across workspaces.
* Remove validation for system prompt in ChatSettings component
* Add comment for system prompt in workspaces model
* linting, simplify logic for default assumption
* dev build
---------
Co-authored-by: timothycarambat <rambat1010@gmail.com>
* prompt caching for anthropic llm and agent providers
* add UI for control of ENV
simplify implementation
---------
Co-authored-by: Timothy Carambat <rambat1010@gmail.com>
* feat: add AWS Bedrock API Key option to settings panel
* feat: Bedrock API key auth method
* fix: hide IAM note when using bedrock api key
* move to camcelCase identifier for bedrock api key use
linting
---------
Co-authored-by: timothycarambat <rambat1010@gmail.com>
* fix: Use eval_duration for output TPS calculations and add as a metric field
* refactor usage of eval_duration from ollama metrics
* move eval_duration to usage
* overwrite duration in ollama provider wip measureAsyncFunction optional param
* allow for overloaded duration in measureAsyncFunction
* simplify flow for duration tracking
---------
Co-authored-by: shatfield4 <seanhatfield5@gmail.com>
Co-authored-by: Timothy Carambat <rambat1010@gmail.com>
* paperless ngx data connector
* wip resync paperless ngx
* fix generateChunkSource for resyncing paperless ngx
* lint
* Refactor Paperless-NGX connector
Fix issue with date rendering in tooltip + extended width
Move tooltip details to be column for more space
---------
Co-authored-by: Timothy Carambat <rambat1010@gmail.com>
* add option to disable swagger docs via env
* update .example.env for docker and server
---------
Co-authored-by: Timothy Carambat <rambat1010@gmail.com>
* feat: add web app manifest and mobile PWA meta tags
* feat: serve dynamic manifest.json with custom branding for pwa
* feat: add ios status bar theming for pwa
* fix: prevent overscroll behavior for mobile
* fix: prevent ios safari auto-zoom on chat input
* fix: remove theme-color meta tags conflicting with ios status bar
* fix: add missing apple-mobile-web-app-capable meta tag for ios pwa
* fix: move catch-all route after manifest endpoint to prevent interception
* feat: add pwa detection helper and conditional styling for standalone mode
* PWA refactor
* undo changes to native CSS
* class fix
* proper response obj
* fix patch for import
* fix manifest errors
---------
Co-authored-by: Christian De Santis <christian.constantino98@gmail.com>
* fix(server): correct Qdrant batching logic for large uploads
Closes#4544
* modify O(3N) process to O(N)
---------
Co-authored-by: timothycarambat <rambat1010@gmail.com>
* Migrate gemini agents away from `Untooled`
* disable agents for gemma models as they are not supported for tool calling
* Dev build
resolve#4452 via function name prefix and then stripping within provider
* Reimplement Cohere models
- Redo LLM implementation to grab models from endpoint and pre-filter
- Migrate embedding models to also grab from remote
- Add records for easy context window lookup'
* fix comment
* auto model context limit detection for ollama llm provider
* auto model context limit detection for lmstudio llm provider
* Patch Ollama to function and sync context windows like Foundry
* normalize how model context windows are cached from endpoint service
todo: move this into global utility class with MODEL_MAP
eager load models on boot to pre-cache them
add performance model improvements into ollama agent as well as apply n_ctx
* remove debug log
---------
Co-authored-by: Timothy Carambat <rambat1010@gmail.com>
* add microsoft foundry local llm and agent providers
* minor change to fix early stop token + overloading of context window
always use user defined window _unless_ it is larger than the models real contenxt window
cache the context windows when we can from the API (0.7.*)+
Unload model forcefully on model change to prevent resource hogging
* add back token preference since some models have very large windows and can crash a machine
normalize cases
---------
Co-authored-by: Timothy Carambat <rambat1010@gmail.com>
* WIP agentic tool call streaming
- OpenAI
- Anthropic
- Azure OpenAI
* WIP rest of providers EXCLUDES Bedrock and GenericOpenAI
* patch untooled complete/streaming to use chatCallback provider from provider class and not assume OpenAI client struct
example: Ollama
* modify ollama to function with its own overrides
normalize completion/stream outputs across providers/untooled
* dev build
* fix message sanization for anthropic agent streaming
* wip fix anthropic agentic streaming sanitization
* patch gemini, webgenui, generic aibitat providers + disable providers unable to test
* refactor anthropic aibitat provider for empty message and tool call formatting
* Add frontend missing prop check
update Azure for streaming support
update Gemini to streamting support on gemini-* models
generic OpenAI disable streaming
verify localAI support
verify NVIDIA Nim support
* DPAIS, remove temp from call, support streaming'
* remove 0 temp to remove possibility of bad temp error/500s/400s
* Patch condition where model is non-streamable and no tools are present or called resulting in the provider `handleFunctionCallChat` being called - which returns a string.
This would then fail in Untooled.complete since response would be a string and not the expected `response.choices?.[0]?.message`
Modified this line to handle both conditions for stream/non-streaming and tool presence or lack thereof
* Allow generic Openai to be streamable since using untooled it should work fine
honor disabled streaming for provider where that concern may apply for regular chats
* rename function and more gemini-specific function to gemini provider
* add comments for readability
.complete on azure should be non-streaming as this is the sync response
* migrate CometAPI, but disable as we cannot test
---------
Co-authored-by: shatfield4 <seanhatfield5@gmail.com>
