Commit Graph

334 Commits

Author SHA1 Message Date
timothycarambat
6c1b5477e0 Merge branch 'master' of github.com:Mintplex-Labs/anything-llm into render 2024-05-10 15:03:10 -07:00
timothycarambat
5eec5cbb9e update agent modal 2024-05-10 15:02:59 -07:00
Sean Hatfield
0a6a9e40c1
[FIX] Add max tokens field to generic OpenAI LLM connector (#1345)
* add max tokens field to generic openai llm connector

* add max_tokens property to generic openai agent provider
2024-05-10 14:49:02 -07:00
Sean Hatfield
734c5a9e96
[FEAT] Implement regenerate response button (#1341)
* implement regenerate response button

* wip on rerenders

* remove function that was duplicate

* update delete-chats function

---------

Co-authored-by: timothycarambat <rambat1010@gmail.com>
2024-05-10 14:47:29 -07:00
timothycarambat
2345424b03 linting 2024-05-10 14:10:07 -07:00
timothycarambat
8f068b80d7 chat history performance improvements with memo 2024-05-10 14:09:25 -07:00
Sean Hatfield
d36c3ff8b2
[FEAT] Slash templates (#1314)
* WIP slash presets

* WIP slash command customization CRUD + validations complete

* backend slash command support

* fix permission setting on new slash commands
rework form submit and pattern on frontend

* Add field updates for hooks,
required=true to field
add user<>command constraint to keep them unique
enforce uniquness via teritary uid field on table for multi and non-multi user

* reset migration

---------

Co-authored-by: timothycarambat <rambat1010@gmail.com>
2024-05-10 12:35:33 -07:00
timothycarambat
0f981abd40 remove unused import 2024-05-08 16:23:13 -07:00
timothycarambat
2da0d39b51 update todo comment 2024-05-08 16:04:45 -07:00
Timothy Carambat
81bc16cc39
More agent providers (#1316)
* add OpenRouter support

* add mistral agents
add perplexity agents
add textwebgenui agents
2024-05-08 16:04:18 -07:00
Sean Hatfield
8422f92542
Agent support for LLMs with no function calling (#1295)
* add LMStudio agent support (generic) support
"work" with non-tool callable LLMs, highly dependent on system specs

* add comments

* enable few-shot prompting per function for OSS models

* Add Agent support for Ollama models

* azure, groq, koboldcpp agent support complete + WIP togetherai

* WIP gemini agent support

* WIP gemini blocked and will not fix for now

* azure fix

* merge fix

* add localai agent support

* azure untooled agent support

* merge fix

* refactor implementation of several agent provideers

* update bad merge comment

---------

Co-authored-by: timothycarambat <rambat1010@gmail.com>
2024-05-08 15:17:54 -07:00
timothycarambat
8aba28b02e Merge branch 'master' of github.com:Mintplex-Labs/anything-llm into render 2024-05-08 14:12:33 -07:00
Sean Hatfield
b2b41db110
[FEAT] Implement width and height resizing options for embed chat widget (#1278)
* WIP embed app window size

* fix UI when resizing window and add text size customization option

* update stylying for dims

* publish new embed

---------

Co-authored-by: timothycarambat <rambat1010@gmail.com>
2024-05-08 14:11:55 -07:00
Sean Hatfield
977a07db86
[FEAT] Text Generation Web UI LLM provider support (#1279)
* add text gen web ui LLM provider support

* update README

* README typo

* update TextWebUI display name
patch workspace<>model support for provider

---------

Co-authored-by: timothycarambat <rambat1010@gmail.com>
2024-05-08 11:56:30 -07:00
Imtiaz Mehmood
ad778dd36d
Feat/quick delete chat (#1302)
* feat:quick delete chat thread

* update:pull request template

* refactor bulk-deletion implementation

* unset pull_request_changes

* add border none for desktop support

* unset marks when toggling bulk mode

---------

Co-authored-by: timothycarambat <rambat1010@gmail.com>
2024-05-08 11:10:00 -07:00
Timothy Carambat
331d3741c9
Ollama agents (#1270)
* add LMStudio agent support (generic) support
"work" with non-tool callable LLMs, highly dependent on system specs

* add comments

* enable few-shot prompting per function for OSS models

* Add Agent support for Ollama models

* improve json parsing for ollama text responses
2024-05-07 18:06:31 -07:00
Timothy Carambat
1b4559f57f
Add LMStudio agent support (generic) support (#1246)
* add LMStudio agent support (generic) support
"work" with non-tool callable LLMs, highly dependent on system specs

* add comments

* enable few-shot prompting per function for OSS models
2024-05-07 16:35:47 -07:00
David Holmlund
0b61ef6383
[FIX] Add scrollbar when new invite modal overflows (#1301)
fix: Add scrollbar when new invite modal overflows
2024-05-07 09:17:32 -07:00
timothycarambat
c60077a078 merge with master 2024-05-03 10:02:53 -07:00
Sean Hatfield
fc77b46800
[FEAT] KoboldCPP LLM Support (#1268)
* koboldcpp LLM support

* update .env.examples for koboldcpp support

* update LLM preference order
update koboldcpp comments

---------

Co-authored-by: timothycarambat <rambat1010@gmail.com>
2024-05-02 12:12:44 -07:00
Sean Hatfield
3caebc47b4
[FEAT] Cohere LLM and embedder support (#1233)
* getChatCompletion working WIP streaming

* WIP

* working streaming WIP abort stream

* implement cohere embedder support

* remove inputType option from cohere embedder

* fix cohere LLM from not aborting stream when canceled by user

* Patch Cohere implemention

* add cohere to onboarding

---------

Co-authored-by: timothycarambat <rambat1010@gmail.com>
2024-05-02 10:35:50 -07:00
timothycarambat
c2277906ad turn off HTML for renderer 2024-05-02 09:55:06 -07:00
Timothy Carambat
47b7df4fc3
Clear chat window on /reset (#1261)
clear chat window on /reset
2024-05-01 20:39:58 -07:00
Sean Hatfield
a156a1e58c
[FEAT] Remove custom logo onboarding screen (#1252)
remove custom logo onboarding screen
2024-05-01 16:26:14 -07:00
Sean Hatfield
43e54a19dc
[FEAT] Workspace settings gear icon UX improvement (#1254)
take user back to workspace chat from gear icon
2024-05-01 16:22:10 -07:00
timothycarambat
b69bf7cc27 Clearing of events does not reload anymore
updating workspace name does not result in reload anymore
set event log page size to 10
fix css issues with charts
2024-05-01 16:13:20 -07:00
timothycarambat
6150ff41ea Merge branch 'master' of github.com:Mintplex-Labs/anything-llm into render 2024-05-01 13:33:07 -07:00
Timothy Carambat
42e1d8e8ce
Customize refusal response for query mode (#1243)
* Customize refusal response for `query` mode

* remove border for desktop
2024-04-30 16:14:30 -07:00
Timothy Carambat
547d4859ef
Bump openai package to latest (#1234)
* Bump `openai` package to latest
Tested all except localai

* bump LocalAI support with latest image

* add deprecation notice

* linting
2024-04-30 12:33:42 -07:00
timothycarambat
d0f5eafce6 fix: Always fetch workspace documents on tab-nav in uploader 2024-04-29 09:49:51 -07:00
Timothy Carambat
d72f1af361
Improve uploader experience (#1205)
* Improve uploader expierence
- Wipe upload container (fadeout) after uploading
- debounce fetchKeys by 1s

* patch unneded exports
2024-04-26 17:41:42 -07:00
Sean Hatfield
360f17cd58
[FIX] Move to Workspace popup UI bug fix (#1204)
fix for popup menu transparent container
2024-04-26 17:38:41 -07:00
Sean Hatfield
8eda75d624
[FIX] Loading message in document picker bug (#1202)
* fix loading message in document picker bug

* linting

---------

Co-authored-by: timothycarambat <rambat1010@gmail.com>
2024-04-26 17:08:10 -07:00
Timothy Carambat
2e813846dc
Agent skill: chart generation (#1103)
* WIP agent support

* move agent folder

* wip frontend socket

* checkpoint

* fix schema

* Checkpoint for plugins and AgentHandler

* refactor plugins and agent arch

* agent error reporting and handling

* add frontend elements for agents in prompt input

* WIP integrations for agents

* enable web-search agent config from frontend

* persist chat history

* update alert

* update migration
remove console logs
update close state for agent invocations

* add examples to dockerignore
Extract statusResponse to its own component

* update close method

* wrap scraping rejections

* add RAG search as funciton

* Add telem and link highlight

* chat support

* patch memory

* Add rechart as a plugin option

* Toggles for abilites of default agent (system wide)
Validate values for agent skills
Enable dynamic loading of skills
UI for toggle of skills

* add UI for toggle of configs for agent

* toggle WS or WSS protocol

* update NGNIX proxy pass

* move components around and capture failed websocket creation

* fix name

* tmp docker image

* reset workflow

* safety mark functions

* telem on tool calls

* remove hardcode short circuit

* separate web-browser from scrape

* extract summarizer to util
add abort handlers and controller for langchain stuff so socket close kills process

* langchain summarize verbose when in dev

* chart styling improvements + add title to chart

* fix legend from being cutoff in chart downloads

* remove cursor blink

---------

Co-authored-by: shatfield4 <seanhatfield5@gmail.com>
2024-04-26 11:18:55 -07:00
timothycarambat
331423f864 patch Citation 2024-04-25 17:54:14 -07:00
Sean Hatfield
348b36bf85
[FEAT] Confluence data connector (#1181)
* WIP Confluence data connector backend

* confluence data connector complete

* confluence citations

* fix citation for confluence

* Patch confulence integration

* fix Citation Icon for confluence

---------

Co-authored-by: timothycarambat <rambat1010@gmail.com>
2024-04-25 17:53:38 -07:00
Sean Hatfield
11f6419c3c
[FEAT] Implement new login screen UI & multi-user password reset (#1074)
* WIP new login screen UI

* update prisma schema/create new models for pw recovery

* WIP password recovery backend

* WIP reset password flow

* WIP pw reset flow

* password reset logic complete & functional UI

* WIP login screen redesign for single and multi user

* create placeholder modal to display recovery codes

* implement UI for recovery code modals/download recovery codes

* multiuser desktop password reset UI/functionality complete

* support single user mode for pw reset

* mobile styles for all password reset/login flows complete

* lint

* remove single user password recovery

* create PasswordRecovery util file to make more readable

* do not drop-replace users table in migration

* review pr

---------

Co-authored-by: timothycarambat <rambat1010@gmail.com>
2024-04-25 16:52:30 -07:00
timothycarambat
d25933930b merge with master 2024-04-25 07:35:55 -07:00
Sean Hatfield
ff5d7d8372
[FEAT] Chat UI font size (#1172)
* WIP text font size change feature

* store text size settings in localstorage and improve styles of popup menu
2024-04-23 16:22:37 -07:00
Timothy Carambat
323c080b5e
Support single-model providers for workspace LLMs (#1179) 2024-04-23 13:18:28 -07:00
Timothy Carambat
df17fbda36
Add generic OpenAI endpoint support (#1178)
* Add generic OpenAI endpoint support

* allow any input for model in case provider does not support models endpoint
2024-04-23 13:06:07 -07:00
Timothy Carambat
ac6ca13f60
1173 dynamic cache openrouter (#1176)
* patch agent invocation rule

* Add dynamic model cache from OpenRouter API for context length and available models
2024-04-23 11:10:54 -07:00
Sean Hatfield
2543e8df40
[FEAT] Remove vectordb and embedder settings in onboarding flow (#1138)
* default to AnythingLLM embedder and LanceDB on onboarding for simpler setup

* remove unused onboarding flow components

* add text telling user settings can be reconfigured later

* remove space

* update copy
patch back-path navigation on onboarding

---------

Co-authored-by: timothycarambat <rambat1010@gmail.com>
2024-04-22 16:22:14 -07:00
Sean Hatfield
b50f1e7479
[FEAT] Improve autoscroll during message streaming (#1139)
emulate chatgpt autoscroll to not always force autoscroll when streaming responses
2024-04-22 15:06:48 -07:00
Sean Hatfield
897e168fd1
[FEAT] Add support for more groq models (Llama 3 and Gemma) (#1143)
add support for more groq models
2024-04-22 13:14:27 -07:00
timothycarambat
e1372a81d4 Merge branch 'master' of github.com:Mintplex-Labs/anything-llm into render 2024-04-20 18:22:41 -07:00
Timothy Carambat
c65f890afc
Add LMStudio embedding endpoint support (#1141)
* Add LMStudio embedding endpoint support

* update alive path check for HEAD
remove commented JSX

* update comment
2024-04-19 15:36:07 -07:00
Timothy Carambat
b3c7c002db
Warn user when changing embedder with current progress already (#1135)
* Warn user when changing embedder with current progress already

* update comment
2024-04-19 09:51:58 -07:00
Timothy Carambat
58b744771f
Add support for Gemini-1.5 Pro (#1134)
* Add support for Gemini-1.5 Pro
bump @google/generative-ai pkg
Toggle apiVersion if beta model selected
resolves #1109

* update API messages due to package change
2024-04-19 08:59:46 -07:00
timothycarambat
bd5b3f5d00 Merge branch 'master' of github.com:Mintplex-Labs/anything-llm into render 2024-04-18 14:54:05 -07:00