* Improve DMR support
- Autodetect models installed
- Grab all models from hub.docker to show available
- UI to handle render,search, install, and management of models
- Support functionality for chat, stream, and agentic calls
* forgot files
* fix loader circle being too large
fix tooltip width command
adjust location of docker installer open for web platform
* adjust imports
* 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>
* 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>
* 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>
* feat: Implement CometAPI integration for chat completions and model management
- Added CometApiLLM class for handling chat completions using CometAPI.
- Implemented model synchronization and caching mechanisms.
- Introduced streaming support for chat responses with timeout handling.
- Created CometApiProvider class for agent interactions with CometAPI.
- Enhanced error handling and logging throughout the integration.
- Established a structure for managing function calls and completions.
* linting
---------
Co-authored-by: timothycarambat <rambat1010@gmail.com>
* add chroma cloud as new vector db provider
* update docker example env
* extend chroma class to chroma cloud
* update readme
---------
Co-authored-by: timothycarambat <rambat1010@gmail.com>
* Added exa-search case to the search provider switch in web-browsing.js
* Added ExaSearchOptions component for API key input
* update
* Patch missing image crashing UI
Fix issue where ENV key did not exist or was saved on click
Update copy for provider
Add Docs for ENV keys for manual placements
update systemssettings for returning key saved to UI
---------
Co-authored-by: timothycarambat <rambat1010@gmail.com>
* WIP on embedder selection
TODO: apply splitting and query prefixes (if applicable)
* wip on upsert
* Support base model
support nomic-text-embed-v1
support multilingual-e5-small
Add prefixing for both embedding and query for RAG tasks
Add chunking prefix to all vector dbs to apply prefix when possible
Show dropdown and auto-pull on new selection
* norm translations
* move supported models to constants
handle null seelction or invalid selection on dropdown
update comments
* dev
* patch text splitter maximums for now
* normalize translations
* add tests for splitter functionality
* normalize
---------
Co-authored-by: shatfield4 <seanhatfield5@gmail.com>
* PGVector support for vector db storage
* forgot files
* comments
* dev build
* Add ENV connection and table schema validations for vector table
add .reset call to drop embedding table when changing the AnythingLLM embedder
update instrutions
Add preCheck error reporting in UpdateENV
add timeout to pg connection
* update setup
* update README
* update doc
* feat: implement iam role auth for bedrock
* fix: make client refreshes properly when switching between iam_user and iam_role
* checkout agent flow
* fix aiprovider for bedrock in agent use
---------
Co-authored-by: timothycarambat <rambat1010@gmail.com>
* Fixed two primary issues discovered while using AWS Bedrock with Anthropic Claude Sonnet models:
- Context Window defaults to 8192 maximum, which isn't correct
- Multimodal stopped working when removing langchain, which was transparently handling image_url to a format sonnet expects.
* Ran `yarn lint`
* Updated .env.example to have aws bedrock examples too
* Refactor for readability
move utils for AWS specific functionality to subfile
add token output max to ENV so setting persits
---------
Co-authored-by: Tristan Stahnke <tristan.stahnke+gpsec@guidepointsecurity.com>
Co-authored-by: Timothy Carambat <rambat1010@gmail.com>
* Enable bypass of ip limitations via ENV in collector startup
resolves#3625
connect #3626
* dev build
* bump dockerx build action
* enable runtime setting config of collector requests
* comments and linting for option passing
* unset
* unset
* update docs link
* linting and docs
* Add multilingual support for ocr mudule
* Add OCR langauge as server var that is passed into Collector
Support all valid tesseract language codes
Filter and parse only valid codes with fallbacks'
* persist TARGET_OCR_LANG
* update docker example env
---------
Co-authored-by: Timothy Carambat <rambat1010@gmail.com>
* feat: add new model provider PPIO
* fix: fix ppio model fetching
* fix: code lint
* reorder LLM
update interface for streaming and chats to use valid keys
linting
---------
Co-authored-by: timothycarambat <rambat1010@gmail.com>
* add claude 3-7 sonnet
* made all the changes everywhere
* add 3-7-sonnet-latest model
* lint
---------
Co-authored-by: shatfield4 <seanhatfield5@gmail.com>
* Add support for Google Generative AI (Gemini) embedder
* Add missing example in docker
Fix UI key elements in options
Add Gemini to data handling section
Patch issues with chunk handling during embedding
* remove dupe in env
---------
Co-authored-by: timothycarambat <rambat1010@gmail.com>
* Add support for gemini authenticated models endpoint
add customModels entry
add un-authed fallback to default listing
separate models by expiermental status
resolves#2866
* add back improved logic for apiVersion decision making
* wip remove all docs clear vector db on embedder/vector db change
* purge all cached docs and remove docs from workspaces on vectordb/embedder change
* lint
* remove unneeded console log
* remove reset vector stores endpoint and move to server side updateENV with postUpdate check
* reset embed module
* remove unused import
* simplify deletion process
rescoped document deletion to be more general for speed, everything needs to be reset anyway
fixed issue where unembedded docs not in any workspaces, but cached, were not removed
* add back missing readme file
update warning text modals
---------
Co-authored-by: timothycarambat <rambat1010@gmail.com>
