Commit Graph

156 Commits

Author SHA1 Message Date
Sean Hatfield
31c7bd2838
[REFACTOR] Refactor UserMenu component for readability (#767)
* refactor UserMenu component for readability

* revisit hook

---------

Co-authored-by: timothycarambat <rambat1010@gmail.com>
2024-02-21 11:20:36 -08:00
Timothy Carambat
755df4dbba
auto highlight slash command on typing (#743) 2024-02-19 10:32:53 -08:00
Sean Hatfield
17c1913ccc
[FEAT]: Allow user to set support email (#726)
* implement custom support email for usermenu support button

* small refactor

---------

Co-authored-by: timothycarambat <rambat1010@gmail.com>
2024-02-19 10:30:41 -08:00
Timothy Carambat
51dbff0dcb
Breakout Chat/Query mode as a workspace setting (#734)
Remove useless icons in prompt bar
Add chatMode column to workspaces that defaults to chat
Add UI for toggle of chat mode with hint
Update UI for workspace settings to match designs
2024-02-16 14:50:40 -08:00
Sean Hatfield
858b2fcedb
[FEAT] New Workspace Settings Layout (#718)
* WIP new settings layout

* add suggested messages to general & appearance and clean up/make more user friendly

* lazy load workspace settings pages

* css fix on X button for document picker where button is barely clickable

* remove additional workspace settings page

* fix thread selection action when on thread

* refactor inputs into sub-components
remove unused paths

---------

Co-authored-by: timothycarambat <rambat1010@gmail.com>
2024-02-14 15:29:49 -08:00
Timothy Carambat
dbb865f6f3
design QA (#724) 2024-02-14 13:16:52 -08:00
Timothy Carambat
161dc5f901
Implement thread UI update (#722)
* Implement thread UI update

* remove comment
2024-02-14 12:31:43 -08:00
Timothy Carambat
ee3a79fdcf
Remove custom tooltip implementation (#716) 2024-02-13 14:26:56 -08:00
Timothy Carambat
d52f8aafd4
689 links in citation (#715)
* Include links in citations
force ChunkSource key to retain this information
old links will be unsupported

* show special icons depending on source

* remove console log

* reset server documents writeTo
2024-02-13 14:11:57 -08:00
Sean Hatfield
f4b09a8c79
[FEAT] RLHF on response messages (#708)
* WIP RLHF works on historical messages

* refactor Actions component

* completed RLHF up and down votes for chats

* add defaults for HistoricalMessage params

* refactor RLHF implmenation
remove forwardRef on history items to prevent rerenders

* remove dup id

* Add rating to CSV output

---------

Co-authored-by: timothycarambat <rambat1010@gmail.com>
2024-02-13 11:33:05 -08:00
Timothy Carambat
229757bef9
Fix sidebar hiding options on small height viewport (#704) 2024-02-09 11:44:33 -08:00
Timothy Carambat
406732830f
Implement workspace threading that is backwards compatible (#699)
* Implement workspace thread that is compatible with legacy versions

* last touches

* comment on chat qty enforcement
2024-02-08 18:37:22 -08:00
Sean Hatfield
b985524901
[FEAT] Customizable footer icon links in Appearance Settings (#694)
* WIP custom footer icons

* UI for updating footer icons complete and backend to save/modify

* add backend for unprotected footer fetch

* break out footer into separate component and render footer items using a cache for 1 hour

* wip review

* refactor & cleanup

* Optimize footer form component
Optimize caching for footer icons
Add validation on SystemSetting upserts
Normalize fallback items for footer_data

* Adjust max icons to 3

* fix success message on remove

* fix success message on remove

---------

Co-authored-by: timothycarambat <rambat1010@gmail.com>
2024-02-08 12:17:01 -08:00
timothycarambat
a01d4b847e drop temp loading state on workspace modal 2024-02-07 12:48:59 -08:00
Sean Hatfield
f402ef4c3c
[CHORE] Hide security tab on Settings Sidebar/Refactor SettingsSidebar component (#683)
* hide security setting in settings sidebar when in multiusermode

* refactor sidebar to handle mobile view inside SettingsSidebar component

* forgot eventlogs on sidebar
move footer on settingSidebar to component

---------

Co-authored-by: timothycarambat <rambat1010@gmail.com>
2024-02-07 08:17:48 -08:00
Sean Hatfield
d789920a19
[FEAT] Automated audit logging (#667)
* WIP event logging - new table for events and new settings view for viewing

* WIP add logging

* UI for log rows

* rename files to Logging to prevent getting gitignore

* add metadata for all logging events and colored badges in logs page

* remove unneeded comment

* cleanup namespace for logging

* clean up backend calls

* update logging to show to => from settings changes

* add logging for invitations, created, deleted, and accepted

* add logging for user created, updated, suspended, or removed

* add logging for workspace deleted

* add logging for chat logs exported

* add logging for API keys, LLM, embedder, vector db, embed chat, and reset button

* modify event logs

* update to event log types

* simplify rendering of event badges

---------

Co-authored-by: timothycarambat <rambat1010@gmail.com>
2024-02-06 15:21:40 -08:00
Sean Hatfield
b94da205a5
fix truncate function to handle Chinese characters (#677)
* fix truncate function to handle Chinese characters

* revert changes to truncate function and cut off title using css

* add CSS ellipse on long file name

* fix uploaded middleTruncation as well as directory

---------

Co-authored-by: timothycarambat <rambat1010@gmail.com>
2024-02-06 11:30:49 -08:00
Sean Hatfield
608f28d745
[FEAT] create custom prompt suggestions per workspace (#664)
* create custom suggested chat messages per workspace

* update how suggestedChats are passed to chat window

* update mobile styles

* update edit change handler

---------

Co-authored-by: timothycarambat <rambat1010@gmail.com>
2024-02-06 11:24:33 -08:00
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
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
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
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
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
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
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