Commit Graph

80 Commits

Author SHA1 Message Date
Timothy Carambat
f1fc2d90fa
Readme updates (#475)
* wip

* btn links

* button updates

* update dev instructions

* typo
2023-12-19 13:24:50 -08:00
timothycarambat
2def9a67a1 docs: update default storage path to just write to user home dir for docker instructions 2023-12-17 15:48:56 -08:00
Ikko Eltociear Ashimine
4fe25cebe3
Update README.md (#454)
proprotional -> proportional
2023-12-17 10:44:27 -08:00
Timothy Carambat
719521c307
Document Processor v2 (#442)
* wip: init refactor of document processor to JS

* add NodeJs PDF support

* wip: partity with python processor
feat: add pptx support

* fix: forgot files

* Remove python scripts totally

* wip:update docker to boot new collector

* add package.json support

* update dockerfile for new build

* update gitignore and linting

* add more protections on file lookup

* update package.json

* test build

* update docker commands to use cap-add=SYS_ADMIN so web scraper can run
update all scripts to reflect this
remove docker build for branch
2023-12-14 15:14:56 -08:00
Timothy Carambat
cc3343ba79
add Docker internal URL to READMEs (#441)
add Docker internal URL
2023-12-13 11:59:14 -08:00
Ikko Eltociear Ashimine
fef5169ca4
chore: update README.md (#420)
standlone -> standalone
2023-12-11 11:32:26 -08:00
timothycarambat
48dd99b028 chore: update docker boot script for storage location export 2023-12-07 15:11:48 -08:00
Timothy Carambat
655ebd9479
[Feature] AnythingLLM use locally hosted Llama.cpp and GGUF files for inferencing (#413)
* 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
timothycarambat
ce52f54cda Documentation update 2023-12-06 11:38:40 -08:00
Timothy Carambat
1a6f599971
update docker build instructions (#412)
* update docker build instructions

* cleanup
2023-12-06 11:27:38 -08:00
timothycarambat
c6f0e4cdc4 update docker instructions 2023-11-17 20:15:11 -08:00
Francisco Bischoff
f499f1ba59
Using OpenAI API locally (#335)
* 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>
2023-11-09 12:33:21 -08:00
Timothy Carambat
d34ec68702
Add support for gpt-4-turbo 128K model (#340)
resolves #336
Add support for gpt-4-turbo 128K model
2023-11-06 14:22:19 -08:00
timothycarambat
4233d1a240 Update screenshots of new UI
Update README to point to updated YT video
2023-10-25 11:31:58 -07:00
timothycarambat
bfa5c75fe4 update discord badge 2023-10-03 17:42:10 -07:00
timothycarambat
79e3faa82d Update readme to not prefer Pinecone 2023-09-12 14:58:14 -07:00
Timothy Carambat
defe6054b3
Full developer api (#221)
* Autodocument Swagger API with JSDocs on /v1/ endpoints for API access
implement single-player API keys
WIP Admin API Keys

* Create new api keys as both single and multi-user

* Add boot and telem

* Complete Admin API

* Complete endpoints
dark mode swagger

* update docs

* undo debug

* update docs and readme
2023-08-23 19:15:07 -07:00
timothycarambat
8af817e2d5 update local dev docs 2023-08-16 15:34:03 -07:00
Timothy Carambat
122f29069c
Enable optional Telemetry integration via posthog (#190)
* Enable optional Telemetry integration via posthog
2023-08-14 17:42:17 -07:00
timothycarambat
6e56c51a53 add feedback form, hosting link, update readme, show promo image 2023-08-11 17:28:30 -07:00
timothycarambat
ab7837068b Update Readme Thumbnail 2023-07-26 18:39:13 -07:00
Timothy Carambat
91f5f94200
[FEATURE] Enable the ability to have multi user instances (#158)
* multi user wip

* WIP MUM features

* invitation mgmt

* suspend or unsuspend users

* workspace mangement

* manage chats

* manage chats

* add Support for admin system settings for users to delete workspaces and limit chats per user

* fix issue ith system var
update app to lazy load invite page

* cleanup and bug fixes

* wrong method

* update readme

* update readme

* update readme

* bump version to 0.1.0
2023-07-25 10:37:04 -07:00
timothycarambat
c6f69fc0a6 add Docker setup to Readme.md 2023-06-13 13:25:56 -07:00
frasergr
9f33b3dfcb
Docker support (#34)
* Updates for Linux for frontend/server

* frontend/server docker

* updated Dockerfile for deps related to node vectordb

* updates for collector in docker

* docker deps for ODT processing

* ignore another collector dir

* storage mount improvements; run as UID

* fix pypandoc version typo

* permissions fixes
2023-06-13 11:26:11 -07:00
Tim Asp
ebd3a62866
update readme with build instructions (#41) 2023-06-12 21:56:29 -07:00
Matt Farmer
9092b0b55b
Fix link to Vector Caching in README.md (#38) 2023-06-12 21:48:10 -07:00
Timothy Carambat
ad15e1f9b6
Lancedb support (#6)
* add start of lanceDB support

* lancedb initial support

* add null method for deletion of documents from namespace since LanceDB does not support
show warning modal on frontend for this

* update .env.example and lancedb methods for sourcing

* change export method

* update readme
2023-06-08 18:40:29 -07:00
Timothy Carambat
6d01970df2
Implement Chroma Support (#1) 2023-06-07 21:31:35 -07:00
timothycarambat
b093ef711e update README 2023-06-06 16:00:39 -07:00
timothycarambat
27c58541bd inital commit 2023-06-03 19:28:07 -07:00