Commit Graph

166 Commits

Author SHA1 Message Date
Timothy Carambat
2bc11d3f1a
Implement support for HuggingFace Inference Endpoints (#680) 2024-02-06 09:17:51 -08:00
Sean Hatfield
1846a99b93
[FEAT] Embedded AnythingLLM (#656)
* WIP embedded app

* WIP got response from backend in embedded app

* WIP streaming prints to embedded app

* implemented streaming and tailwind min for styling into embedded app

* WIP embedded app history functional

* load params from script tag into embedded app

* rough in modularization of embed chat
cleanup dev process for easier dev support
move all chat to components
todo: build process
todo: backend support

* remove eslint config

* Implement models and cleanup embed chat endpoints
Improve build process for embed
prod minification and bundle size awareness
WIP

* forgot files

* rename to embed folder

* introduce chat modal styles

* add middleware validations on embed chat

* auto open param and default greeting

* reset chat history

* Admin embed config page

* Admin Embed Chats mgmt page

* update embed

* nonpriv

* more style support
reopen if chat was last opened

* update comments

* remove unused imports

* allow change of workspace for embedconfig

* update failure to lookup message

* update reset script

* update instructions

* Add more styling options
Add sponsor text at bottom
Support dynamic container height
Loading animations

* publish new embed script

* Add back syntax highlighting and keep bundle small via dynamic script build

* add hint

* update readme

* update copy model for snippet with link to styles

---------

Co-authored-by: timothycarambat <rambat1010@gmail.com>
2024-02-05 14:21:34 -08:00
Sean Hatfield
9d41ff58e2
[FEAT] add support for new openai embedding models (#653)
* add support for new openai models

* QOL changes/improve logic for adding new openai embedding models

* add example file inputs for Openai embedding ENV selection;

* Fix if stmt conditional

---------

Co-authored-by: timothycarambat <rambat1010@gmail.com>
2024-01-29 08:48:27 -08:00
Hakeem Abbas
5614e2ed30
feature: Integrate Astra as vectorDBProvider (#648)
* feature: Integrate Astra as vectorDBProvider

feature: Integrate Astra as vectorDBProvider

* Update .env.example

* Add env.example to docker example file
Update spellcheck fo Astra
Update Astra key for vector selection
Update order of AstraDB options
Resize Astra logo image to 330x330
Update methods of Astra to take in latest vectorDB params like TopN and more
Update Astra interface to support default methods and avoid crash errors from 404 collections
Update Astra interface to comply to max chunk insertion limitations
Update Astra interface to dynamically set dimensionality from chunk 0 size on creation

* reset workspaces

---------

Co-authored-by: timothycarambat <rambat1010@gmail.com>
2024-01-26 13:07:53 -08:00
Sean Hatfield
21653b09fc
[FEAT] add gpt-4-turbo-preview (#651)
* add gpt-4-turbo-preview

* add gpt-4-turbo-preview to valid models
2024-01-26 13:03:50 -08:00
timothycarambat
09a0fe1c81 Add prisma reset dev command
Patch background color for fullscreen loader
2024-01-23 14:22:50 -08:00
Sean Hatfield
62da5c9933
[REFACTOR] remove all <dialog> modals and replace with custom ModalWrapper component (#641)
* add useModal hook and ModalWrapper component that will be used to replace all <dialog> modals for better browser support

* implement useModal hook and ModalWrapper component to replace all exisiting <dialog>
2024-01-23 14:19:08 -08:00
Sean Hatfield
2f3db0e63a
[FEAT] support pinecone serverless (#639)
* migrate pinecone package to latest version and migrate pinecone vectordb provider class

* remove pinecone environment name env variable and update docs to reflect removal & serverless support complete

* migrate query for pinecone db

* typo in log

---------

Co-authored-by: timothycarambat <rambat1010@gmail.com>
2024-01-22 16:41:20 -08:00
Timothy Carambat
9a237db3d1
Implement total permission overhaul (#629)
* Implement total permission overhaul
Add explicit permissions on each flex and strict route
Patch issues with role escalation and CRUD of users
Patch permissions on all routes for coverage
Improve middleware to accept role array for clarity

* update comments

* remove permissions to API-keys for manager. Manager could generate API-key and using high-privelege api-key give themselves admin

* update sidebar permissions for multi-user and single user

* update options for mobile sidebar
2024-01-22 14:14:01 -08:00
Sean Hatfield
62cea07599
add gpt-3.5-turbo-1106 model for openai LLM (#636)
* add gpt-3.5-turbo-1106 model for openai LLM

* add gpt-3.5-turbo-1106 as valid model for backend and per workspace model selection
2024-01-22 13:19:47 -08:00
Sean Hatfield
288ff0d18c
fix vector cache not deleting cache after unembedding items with folders (#630) 2024-01-22 13:03:05 -08:00
Sean Hatfield
7fb76cfef0
add support for exporting to json and csv in workspace chats (#622)
* add support for exporting to json and csv in workspace chats

* safety encode URL options

* remove message about openai fine tuning on export success

* all defaults to jsonl
2024-01-18 17:59:51 -08:00
Sean Hatfield
08d33cfd8f
Merge pull request from GHSA-xmj6-g32r-fc5q
* remove support for import export anythingllm data

* remove unused imports
remove unused dep
update lockfile

---------

Co-authored-by: timothycarambat <rambat1010@gmail.com>
2024-01-18 13:57:23 -08:00
Sean Hatfield
56fa17caf2
create configurable topN per workspace (#616)
* create configurable topN per workspace

* Update TopN UI text
Fix fallbacks for all providers
Add SQLite CHECK to TOPN value

* merge with master
Update zilliz provider for variable TopN

---------

Co-authored-by: timothycarambat <rambat1010@gmail.com>
2024-01-18 12:34:20 -08:00
Timothy Carambat
683cd69a97
Display readable error message in chat failure (#621) 2024-01-18 12:01:53 -08:00
Timothy Carambat
658e7fa390
chore: Better VectorDb and Embedder error messages (#620)
* chore: propogate embedder and vectordb errors during document mutations

* add default value for errors on addDocuments
2024-01-18 11:40:48 -08:00
Timothy Carambat
0df86699e7
feat: Add support for Zilliz Cloud by Milvus (#615)
* feat: Add support for Zilliz Cloud by Milvus

* update placeholder text
update data handling stmt

* update zilliz descriptor
2024-01-17 18:00:54 -08:00
Sean Hatfield
3fe7a25759
add token context limit for native llm settings (#614)
Co-authored-by: timothycarambat <rambat1010@gmail.com>
2024-01-17 16:25:30 -08:00
Sean Hatfield
56dc49966d
add copy feature to assistant chat message (#611)
* add copy feature to assistant chat message

* fix tooltip not hiding on mobile

* fix: add tooltips
chore: breakout actions to extendable component + memoize
add CopyText to hook we can reuse
fix: Copy on code snippets broken, moved to event listener
fix: highlightjs patch for new API support
feat: add copy response support

---------

Co-authored-by: timothycarambat <rambat1010@gmail.com>
2024-01-17 16:22:06 -08:00
Sean Hatfield
c2c8fe9756
add support for mistral api (#610)
* 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>
2024-01-17 14:42:05 -08:00
Sean Hatfield
90df37582b
Per workspace model selection (#582)
* 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>
2024-01-17 12:59:25 -08:00
Timothy Carambat
c61cbd1502
Add support for fetching single document in documents folder (#607) 2024-01-16 14:58:49 -08:00
Timothy Carambat
e973c1edbf
Preload onboarding (#606)
* no lazy onboarding

* no lazy onboarding steps

* Do not lazy load onboarding to prevent lazy-load white flash
2024-01-16 14:15:46 -08:00
Sean Hatfield
8b11288764
truncate title to shorter length so x button is not hidden for longer… (#603)
* truncate title to shorter length so x button is not hidden for longer title names in the citation modal

* absolutely position x button on citation modal
2024-01-16 13:43:32 -08:00
Timothy Carambat
bd158ce7b1
[Feat] Query mode to return no-result when no context found (#601)
* Query mode to return no-result when no context found

* update default error for sync chat

* remove unnecessary type conversion
2024-01-16 09:32:51 -08:00
Shuyoou
6faa0efaa8
Issue #543 support milvus vector db (#579)
* issue #543 support milvus vector db

* migrate Milvus to use MilvusClient instead of ORM
normalize env setup for docs/implementation
feat: embedder model dimension added

* update comments

---------

Co-authored-by: timothycarambat <rambat1010@gmail.com>
2024-01-12 13:23:57 -08:00
Timothy Carambat
3c859ba303
Change pwd check to O(1) check to prevent timing attacks - single user mode (#575)
Change pwd check to O(1) check to prevent timing attacks
2024-01-11 10:54:55 -08:00
Timothy Carambat
a4ace56a40
Patch minor XSS opportunity where user can self-XSS themselves. (#574)
Patch minor XSS opportunity where user can self-XSS themselvess. There is not real vuln here as any instance is not public facing
2024-01-11 09:57:59 -08:00
timothycarambat
4af9b9d5cc fix: relative/absolute url patch for vector count
connect #516
2024-01-10 19:27:39 -08:00
Timothy Carambat
4e2c0f04b4
Dynamic vector count on workspace settings (#567)
* Dynamic vector count on workspace settings
Add count to be workspace specific, fallback to system count
Update layout of data in settings
Update OpenAI per-token embedding price

* linting
2024-01-10 13:18:48 -08:00
Sean Hatfield
1d39b8a2ce
add Together AI LLM support (#560)
* 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>
2024-01-10 12:35:30 -08:00
Sean Hatfield
5c3bb4b8cc
532 uiux add slash command modal (#555)
* WIP slash commands

* add slash command image

* WIP slash commands

* slash command menu feature complete

* move icons to slash command local

* update how slash command component works

* relint with new linter

* Finalize slash command input
Change empty workspace text layout
Patch dev unmount issues on Chatworkspace/index.jsx

---------

Co-authored-by: timothycarambat <rambat1010@gmail.com>
2024-01-09 13:07:09 -08:00
Sagar Jaglan
5172bceec3
#520 fixed unauthorized token error (#535) 2024-01-08 13:16:00 -08:00
Sean Hatfield
d95d1a9dfd
529 UI update llm embedder and vectordb selection pages (#533)
* move llm, embedder, vectordb items to components folder

* add backdrop blur to search in llm, embedder, vectordb preferences

* implement searchable llm preference in settings

* implement searchable embedder in settings

* remove unused useState from embedder preferences

* implement searchable vector database in settings

* fix save changes button not appearing on change for llm, embedder, and vectordb settings pages

* sort selected items in all settings and put selected item at top of list

* no auto-top for selection

---------

Co-authored-by: timothycarambat <rambat1010@gmail.com>
2024-01-04 18:20:58 -08:00
timothycarambat
a1b4ed43ba allow native when on embedder 2024-01-04 16:12:20 -08:00
Timothy Carambat
d8ca92df88
Onboarding V2 (#502)
* 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
timothycarambat
dc23961231 drop feeback path in paths 2024-01-03 15:44:26 -08:00
Timothy Carambat
e0a0a8976d
Add Ollama as LLM provider option (#494)
* Add support for Ollama as LLM provider
resolves #493
2023-12-27 17:21:47 -08:00
Timothy Carambat
24227e48a7
Add LLM support for Google Gemini-Pro (#492)
resolves #489
2023-12-27 17:08:03 -08:00
timothycarambat
7bee849c65 chore: Force VectorCache to always be on;
update file picker spacing for attributes
2023-12-20 10:45:03 -08:00
Timothy Carambat
ecf4295537
Add ability to grab youtube transcripts via doc processor (#470)
* Add ability to grab youtube transcripts via doc processor

* dynamic imports
swap out Github for Youtube in placeholder text
2023-12-18 17:17:26 -08:00
Timothy Carambat
452582489e
GitHub loader extension + extension support v1 (#469)
* feat: implement github repo loading
fix: purge of folders
fix: rendering of sub-files

* noshow delete on custom-documents

* Add API key support because of rate limits

* WIP for frontend of data connectors

* wip

* Add frontend form for GitHub repo data connector

* remove console.logs
block custom-documents from being deleted

* remove _meta unused arg

* Add support for ignore pathing in request
Ignore path input via tagging

* Update hint
2023-12-18 15:48:02 -08:00
Timothy Carambat
2d700b13f6
fix: patch middle truncation func (#465)
resolves #456
2023-12-17 16:04:50 -08:00
Timothy Carambat
1c549e2844
fix: clarify custom truncate from npm truncate (#464)
chore: add @ where we can for less long imports
2023-12-17 15:58:49 -08:00
Timothy Carambat
65c7c0a518
fix: patch api key not persisting when setting LLM/Embedder (#458) 2023-12-16 10:21:36 -08:00
timothycarambat
d2e3506bb9 fix: transition on LLM and embedding screen
linting
2023-12-15 12:40:11 -08:00
Timothy Carambat
61db981017
feat: Embed on-instance Whisper model for audio/mp4 transcribing (#449)
* feat: Embed on-instance Whisper model for audio/mp4 transcribing
resolves #329

* additional logging

* add placeholder for tmp folder in collector storage
Add cleanup of hotdir and tmp on collector boot to prevent hanging files
split loading of model and file conversion into concurrency

* update README

* update model size

* update supported filetypes
2023-12-15 11:20:13 -08:00
timothycarambat
b444171ef3 fix: Update copy code button on markdown to work with new highlightjs lib implementation 2023-12-12 16:25:22 -08:00
timothycarambat
7154f4f82b non-blocking send responses 2023-12-12 13:41:17 -08:00
Timothy Carambat
a84333901a
feat: implement questionnaire during onboarding (optional) (#429)
fix: PFP url check
2023-12-12 13:11:32 -08:00