* WIP openrouter integration
* add OpenRouter options to onboarding flow and data handling
* add todo to fix headers for rankings
* OpenRouter LLM support complete
* Fix hanging response stream with OpenRouter
update tagline
update comment
* update timeout comment
* wait for first chunk to start timer
* sort OpenRouter models by organization
* uppercase first letter of organization
* sort grouped models by org
---------
Co-authored-by: timothycarambat <rambat1010@gmail.com>
* add LLM support for perplexity
* update README & example env
* fix ENV keys in example env files
* slight changes for QA of perplexity support
* Update Perplexity AI name
---------
Co-authored-by: timothycarambat <rambat1010@gmail.com>
* update HOW_TO_USE_DOCKER to help with Ollama setup using docker
* update HOW_TO_USE_DOCKER
* styles update
* create separate README for ollama and link to it in HOW_TO_USE_DOCKER
* styling update
* Enable ability to do full-text query on documents
Show alert modal on first pin for client
Add ability to use pins in stream/chat/embed
* typo and copy update
* simplify spread of context and sources
* refactor stream/chat/embed-stram to be a single execution logic path so that it is easier to maintain and build upon
* no thread in sync chat since only api uses it
adjust import locations
* add support for mistral api
* update docs to show support for Mistral
* add default temp to all providers, suggest different results per provider
---------
Co-authored-by: timothycarambat <rambat1010@gmail.com>
* WIP model selection per workspace (migrations and openai saves properly
* revert OpenAiOption
* add support for models per workspace for anthropic, localAi, ollama, openAi, and togetherAi
* remove unneeded comments
* update logic for when LLMProvider is reset, reset Ai provider files with master
* remove frontend/api reset of workspace chat and move logic to updateENV
add postUpdate callbacks to envs
* set preferred model for chat on class instantiation
* remove extra param
* linting
* remove unused var
* refactor chat model selection on workspace
* linting
* add fallback for base path to localai models
---------
Co-authored-by: timothycarambat <rambat1010@gmail.com>
* add Together AI LLM support
* update readme to support together ai
* Patch togetherAI implementation
* add model sorting/option labels by organization for model selection
* linting + add data handling for TogetherAI
* change truthy statement
patch validLLMSelection method
---------
Co-authored-by: timothycarambat <rambat1010@gmail.com>
* Implement use of native embedder (all-Mini-L6-v2)
stop showing prisma queries during dev
* Add native embedder as an available embedder selection
* wrap model loader in try/catch
* print progress on download
* add built-in LLM support (expiermental)
* Update to progress output for embedder
* move embedder selection options to component
* saftey checks for modelfile
* update ref
* Hide selection when on hosted subdomain
* update documentation
hide localLlama when on hosted
* saftey checks for storage of models
* update dockerfile to pre-build Llama.cpp bindings
* update lockfile
* add langchain doc comment
* remove extraneous --no-metal option
* Show data handling for private LLM
* persist model in memory for N+1 chats
* update import
update dev comment on token model size
* update primary README
* chore: more readme updates and remove screenshots - too much to maintain, just use the app!
* remove screeshot link
* allow use of any embedder for any llm/update data handling modal
* Apply embedder override and fallback to OpenAI and Azure models
---------
Co-authored-by: timothycarambat <rambat1010@gmail.com>
* feature: add LocalAI as llm provider
* update Onboarding/mgmt settings
Grab models from models endpoint for localai
merge with master
* update streaming for complete chunk streaming
update localAI LLM to be able to stream
* force schema on URL
---------
Co-authored-by: timothycarambat <rambat1010@gmail.com>
Co-authored-by: tlandenberger <tobiaslandenberger@gmail.com>
* Using OpenAI API locally
* Infinite prompt input and compression implementation (#332)
* WIP on continuous prompt window summary
* wip
* Move chat out of VDB
simplify chat interface
normalize LLM model interface
have compression abstraction
Cleanup compressor
TODO: Anthropic stuff
* Implement compression for Anythropic
Fix lancedb sources
* cleanup vectorDBs and check that lance, chroma, and pinecone are returning valid metadata sources
* Resolve Weaviate citation sources not working with schema
* comment cleanup
* disable import on hosted instances (#339)
* disable import on hosted instances
* Update UI on disabled import/export
---------
Co-authored-by: timothycarambat <rambat1010@gmail.com>
* Add support for gpt-4-turbo 128K model (#340)
resolves#336
Add support for gpt-4-turbo 128K model
* 315 show citations based on relevancy score (#316)
* settings for similarity score threshold and prisma schema updated
* prisma schema migration for adding similarityScore setting
* WIP
* Min score default change
* added similarityThreshold checking for all vectordb providers
* linting
---------
Co-authored-by: shatfield4 <seanhatfield5@gmail.com>
* rename localai to lmstudio
* forgot files that were renamed
* normalize model interface
* add model and context window limits
* update LMStudio tagline
* Fully working LMStudio integration
---------
Co-authored-by: Francisco Bischoff <984592+franzbischoff@users.noreply.github.com>
Co-authored-by: Timothy Carambat <rambat1010@gmail.com>
Co-authored-by: Sean Hatfield <seanhatfield5@gmail.com>
* WIP on continuous prompt window summary
* wip
* Move chat out of VDB
simplify chat interface
normalize LLM model interface
have compression abstraction
Cleanup compressor
TODO: Anthropic stuff
* Implement compression for Anythropic
Fix lancedb sources
* cleanup vectorDBs and check that lance, chroma, and pinecone are returning valid metadata sources
* Resolve Weaviate citation sources not working with schema
* comment cleanup
* WIP Anythropic support for chat, chat and query w/context
* Add onboarding support for Anthropic
* cleanup
* fix Anthropic answer parsing
move embedding selector to general util
Limit is due to POST body max size. Sufficiently large requests will abort automatically
We should report that error back on the frontend during embedding
Update vectordb providers to return on failed
* Remove LangchainJS for chat support chaining
Implement runtime LLM selection
Implement AzureOpenAI Support for LLM + Emebedding
WIP on frontend
Update env to reflect the new fields
* Remove LangchainJS for chat support chaining
Implement runtime LLM selection
Implement AzureOpenAI Support for LLM + Emebedding
WIP on frontend
Update env to reflect the new fields
* Replace keys with LLM Selection in settings modal
Enforce checks for new ENVs depending on LLM selection
