Commit graph

12 commits

Author SHA1 Message Date
Timothy Carambat
d8ca92df88
Onboarding V2 ()
* WIP onboarding v2

* Welcome screen for onboarding complete

* fix home page and WIP create skeleton for llm preference search/options

* render llms as options

* add search functionality to llm preference & add survey step

* fix openai settings undefined & create custom logo onboarding page

* add user setup UI

* add data handling & privacy onboarding screen

* add create workspace onboarding screen

* fix survey width in onboarding

* create vector database connection onboarding page

* add workspace image & all skeleton ui complete

* fix navigation buttons and ui tweaks to fit on screen

* WIP LLMPreference

* LLM Preference screen fully functional

* create components for vector db options and fix styling of azure options

* remove unneeded comment

* vector db connection onboarding screen complete

* minor ui tweak to searchbar

* user setup page fully working

* create workspace onboarding page fully working

* useNavigate for navigation between pages

* mobile layout, cleanup old files, survey functionality implemented

* fix default logo appearing when should be blank & password setup bug fix

* Modify flow of onboarding
todo: embedding set up

* Add embedder setup screen & insert into flow

* update embedding back button
auto-dismiss toasts on each step

* move page defs under imports
fix bg color on mobile styling

---------

Co-authored-by: shatfield4 <seanhatfield5@gmail.com>
2024-01-04 15:54:31 -08:00
Timothy Carambat
e0a0a8976d
Add Ollama as LLM provider option ()
* Add support for Ollama as LLM provider
resolves 
2023-12-27 17:21:47 -08:00
Timothy Carambat
24227e48a7
Add LLM support for Google Gemini-Pro ()
resolves 
2023-12-27 17:08:03 -08:00
Timothy Carambat
a84333901a
feat: implement questionnaire during onboarding (optional) ()
fix: PFP url check
2023-12-12 13:11:32 -08:00
Timothy Carambat
655ebd9479
[Feature] AnythingLLM use locally hosted Llama.cpp and GGUF files for inferencing ()
* 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
2023-12-07 14:48:27 -08:00
Timothy Carambat
f48e6b1a3e
chore: add @ as alias for frontend root ()
* chore: add @ as alias for frontend root

* fix: remove bad tag
2023-12-07 09:09:01 -08:00
Timothy Carambat
88cdd8c872
Add built-in embedding engine into AnythingLLM ()
* 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

* Update to progress output for embedder

* move embedder selection options to component

* forgot import

* add Data privacy alert updates for local embedder
2023-12-06 10:36:22 -08:00
Sean Hatfield
064e0c3408
Fix modal sizes to fit smaller screens & bug fixes ()
* fix sizing of onboarding modals & lint

* fix extra scrolling on mobile onboarding flow

* added message to use desktop for onboarding

* linting

* change mobile alert copy

* fix div with bullet points to use list-disc instead

---------

Co-authored-by: timothycarambat <rambat1010@gmail.com>
2023-12-04 13:23:45 -08:00
Sean Hatfield
5ad8a5f2d0
Allow use of any embedder for any llm/update data handling modal ()
* 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>
2023-11-16 15:19:49 -08:00
Timothy Carambat
4bb99ab4bf
Support LocalAi as LLM provider by @tlandenberger ()
* 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>
2023-11-14 12:31:44 -08:00
timothycarambat
6e72519caf patch onboarding 2023-11-09 15:19:52 -08:00
Sean Hatfield
458ffed0c7
added onboarding data handling modal ()
* added onboarding data handling modal

* adding data handling modal component

* update element to list
Update copy

* remove useEffect dep

* refactor onboarding navigation using history

---------

Co-authored-by: timothycarambat <rambat1010@gmail.com>
2023-11-08 19:00:12 -08:00