Commit Graph

371 Commits

Author SHA1 Message Date
Sean Hatfield
948ac8a3dd
[FIX] Validate messages schema for gemini provider (#1351)
validate messages schema for gemini provider
2024-05-10 17:33:25 -07:00
Timothy Carambat
7b18a36288
prevent accidental lockout from restricted chars in single pass mode (#1352)
* prevent accidental lockout from restrict chars in single pass mode

* update error message
2024-05-10 17:29:49 -07:00
Timothy Carambat
98953d70b7
Fix typo leading to agent history in threads not being unique in same workspace (#1350) 2024-05-10 16:09:34 -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
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
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
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
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
Sean Hatfield
d02013fd71
[FIX] Document pinning does not count in query mode (#1250)
* if document is pinned, do not give queryRefusalResponse message

* forgot embed.js patch

---------

Co-authored-by: timothycarambat <rambat1010@gmail.com>
2024-05-02 10:27:09 -07:00
Timothy Carambat
244ce2e307
Prevent concurrent downloads on first-doc upload (#1267) 2024-05-02 10:15:11 -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
9feaad79cc
[CHORE] Remove sendChat and streamChat in all LLM providers (#1260)
* remove sendChat and streamChat functions/references in all LLM providers

* remove unused imports

---------

Co-authored-by: timothycarambat <rambat1010@gmail.com>
2024-05-01 16:52:28 -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
Timothy Carambat
894f727903
Remove restrictions on pinned documents to use more context (#1248)
* Remove restrictions on pinned documents to use more contet

* update comment
2024-05-01 13:32:52 -07:00
Timothy Carambat
e61dfd80a5
Prevent i-framing of frontend UI to prevent unsafe embedding and/or clickjacking (#1200)
Prevent iframing of frontend UI to prevent unsafe embedding and/or clickjacking
2024-05-01 13:02:08 -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
Timothy Carambat
94017e2b51
bump langchain deps (#1231)
* bump langchain deps

* patch native and ollama providers remove deprecated deps

---------

Co-authored-by: shatfield4 <seanhatfield5@gmail.com>
2024-04-30 12:04:24 -07:00
Timothy Carambat
bf435b2861
Adjust how text is split depending on input type (#1238)
resolves #1230
2024-04-30 10:11:56 -07:00
Timothy Carambat
ca63012c0f
bump lancedb dep (#1229) 2024-04-29 09:52:22 -07:00
timothycarambat
5ae20d50ea patch agent invocation regression
resolves #1211
2024-04-27 12:39:45 -07:00
Timothy Carambat
1b35bcbeab
Strengthen field validations on user Updates (#1201)
* Strengthen field validations on user Updates

* update writables
2024-04-26 16:46:04 -07:00
timothycarambat
df2c01b176 patch OpenRouter model fetcher when key is not present 2024-04-26 15:58:30 -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
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
dfaaf1680f update perplexity models
resolves #1188
2024-04-25 07:34:28 -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
Timothy Carambat
9c00db7d3b
patch agent invocation rule (#1175) 2024-04-23 09:59:00 -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
37f4db36a6 resolves #1156
Fixed prisma command response on api workspace update-embeddings
2024-04-21 11:45:34 -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
e28c0469f4 bump togetherai models Apr 18, 2024
resolves #1126
2024-04-18 16:28:43 -07:00
Timothy Carambat
91ea37d17a
Patch model selection for openai (#1128)
prevent rerenders of web-browsing for agents
update openai latest pkg name
2024-04-18 13:32:50 -07:00
Timothy Carambat
9655880cf0
Update all vector dbs to filter duplicate source documents that may be pinned (#1122)
* Update all vector dbs to filter duplicate parents

* cleanup
2024-04-17 18:04:39 -07:00
Timothy Carambat
41978765bc
Improve document summarizer by being able to reference by direct name versus ID, which sometimes models fail to chain (#1121) 2024-04-17 14:34:58 -07:00
Timothy Carambat
81fd82e133
model specific summarization (#1119)
* model specific summarization

* update guard functions

* patch model picker and key inputs
2024-04-17 14:04:51 -07:00
Timothy Carambat
9449fcd737
Add Anthropic agent support with new API and tool_calling (#1116)
* Add Anthropic agent support with new API and tool_calling

* patch useProviderHook to unset default models on provider change
2024-04-17 11:54:58 -07:00
Timothy Carambat
8ebe1a515b
Gracefully handle bad agent auth (#1115)
use provider that is set
2024-04-16 16:42:06 -07:00
Timothy Carambat
f9ac27e9a4
Handle Anthropic streamable errors (#1113) 2024-04-16 16:25:32 -07:00
Timothy Carambat
661563408a
Enable dynamic GPT model dropdown (#1111)
* Enable dynamic GPT model dropdown
2024-04-16 14:54:39 -07:00
Timothy Carambat
a5bb77f97a
Agent support for @agent default agent inside workspace chat (#1093)
V1 of agent support via built-in `@agent` that can be invoked alongside normal workspace RAG chat.
2024-04-16 10:50:10 -07:00
Timothy Carambat
8306098b08
Bump all static model providers (#1101) 2024-04-14 12:55:21 -07:00
Timothy Carambat
6fde5570b3
remove unneeded answerKey for Anthropic (#1100)
resolves #1096
2024-04-14 12:04:38 -07:00
Timothy Carambat
a8e731f548
Add ability for owner to reset just the workspace vector DB (#1094)
* Add ability for owner to reset just the workspace vector DB

* explicit border none
2024-04-12 14:50:39 -07:00
Timothy Carambat
d54e1c1f2d
expand support for non-US azure deployments (#1080)
* expand support for non-US azure deployments

* update conditional
2024-04-10 09:34:14 -07:00
Timothy Carambat
24b523d5eb
append missing import for some vectordb providers (#1066) 2024-04-07 14:40:23 -07:00
Timothy Carambat
ce98ff4653
Enable customization of chunk length and overlap (#1059)
* Enable customization of chunk length and overlap

* fix onboarding link
show max limit in UI and prevent overlap >= chunk size
2024-04-06 16:38:07 -07:00
Timothy Carambat
1c11a47f93
Check ollama alive for embedder (#1057) 2024-04-06 12:16:30 -07:00
Timothy Carambat
6f52a2b729
Embedder download - fallback URL (#1056)
* Embedder download - fallback URL

* improve logging for native embedder
2024-04-06 11:49:15 -07:00
Timothy Carambat
94b58249a3
Enable per-workspace provider/model combination (#1042)
* Enable per-workspace provider/model combination

* cleanup

* remove resetWorkspaceChatModels and wipeWorkspaceModelPreference to prevent workspace from resetting model

* add space

---------

Co-authored-by: shatfield4 <seanhatfield5@gmail.com>
2024-04-05 10:58:36 -07:00
Timothy Carambat
8c7379cda1
persist provider keys between toggle providers (#1041) 2024-04-04 13:47:33 -07:00
timothycarambat
0b454016cf patch comkey path to fallback 2024-04-04 10:47:26 -07:00
timothycarambat
718062d033 patch milvus/zilliz auto-generated collection name
resolves #1027
2024-04-03 12:34:23 -07:00
Sean Hatfield
41fe20f2e0
[FEAT] Implement new workspace members settings and admin users UI updates (#990)
* members workspace settings menu and admin users UI updates

* change copy/fix admin and managers in workspace when not showing in UI

* remove existing workspace user mgmt modal

---------

Co-authored-by: timothycarambat <rambat1010@gmail.com>
2024-04-02 14:53:35 -07:00
Timothy Carambat
df2aac9f3c
useMLock for Ollama API chats (#1014) 2024-04-02 10:43:04 -07:00
Ivan Skodje
e9199bac12
[FEAT] Check port access in docker before showing a default error (#961)
* [FEAT] Added port checks in updateENV.validDockerizedUrl to prevent docker from assuming it cannot access localhost URLs

* [CHORE] Updated error message to include Linux URL

* Patch port checking for general loopbacks

* typo

---------

Co-authored-by: timothycarambat <rambat1010@gmail.com>
2024-04-02 10:34:50 -07:00
Timothy Carambat
f4088d9348
RSA-Signing on server<->collector communication via API (#1005)
* WIP integrity check between processes

* Implement integrity checking on document processor payloads
2024-04-01 13:56:35 -07:00
timothycarambat
200bd7f061 patch prisma query expansion on threads 2024-04-01 13:09:37 -07:00
timothycarambat
b1a2fa6385 Stringify username/pass 2024-04-01 12:11:46 -07:00
Timothy Carambat
b8d37d9f43
Handle no-mutli-part form data error (#1004) 2024-04-01 12:06:47 -07:00
timothycarambat
49f30e051c security: patch footer icon self-xss from privledged user 2024-03-29 13:39:11 -07:00
timothycarambat
bfedfebfab security: force sanitize env string set by user 2024-03-29 13:03:05 -07:00
timothycarambat
2374939ffb security: patch primsa expansion on token request 2024-03-29 11:47:30 -07:00
Timothy Carambat
52fac84422
Patch ability to update multi-user-flag once set (#993)
* Patch ability to update multi-user-flag once set

* update logo function to safe update key values
2024-03-29 10:56:32 -07:00
timothycarambat
bf8df60c02 move vector db debug endpoint to dev only 2024-03-27 13:19:28 -07:00
timothycarambat
99cfee1e70 sec: fix enable-multi-user preflight check to prevent error loop 2024-03-27 12:20:53 -07:00
Sean Hatfield
fa4adb1e56
[FIX] User messages not saving due to empty message check (#978)
fix user messages not saving due to empty message check
2024-03-27 10:45:20 -07:00
Timothy Carambat
0dd6001fa6
Patch Gemini/Google AI errors (#977) 2024-03-26 17:20:12 -07:00
Timothy Carambat
efe9dfa5e3
handle expired token being null and prevent constant rerender (#956)
* handle expired token being null and prevent constant rerender

* reset defaults
2024-03-26 16:47:25 -07:00
Timothy Carambat
1ecefe8bed
Add ability to add invitee to workspaces automatically (#975) 2024-03-26 16:38:32 -07:00
timothycarambat
1cd255c1ec deprecate /migrate endpoint 2024-03-26 15:32:07 -07:00
timothycarambat
7de23dbb2d norm path logo 2024-03-26 15:25:46 -07:00
Timothy Carambat
1135853740
Patch LMStudio Inference server bug integration (#957) 2024-03-22 14:39:30 -07:00
Sean Hatfield
35a155d3ac
Workspace prompt changes (#949)
* track workspace prompt change

* refactor

* modify arg order

---------

Co-authored-by: timothycarambat <rambat1010@gmail.com>
2024-03-21 15:25:42 -07:00
timothycarambat
373c833aad path API document mgmt with STORAGE_DIR 2024-03-21 15:10:44 -07:00
timothycarambat
22ef2c287d folder mgmt, use STORAGE_DIR 2024-03-21 15:03:52 -07:00
timothycarambat
2ce77b943e filter null folders 2024-03-21 14:47:45 -07:00
Sean Hatfield
4f268dfeb6
[FEAT] Document picker folders for organization (#902)
* implement alternating color rows for file picker

* implement alternating colors for workspace directory

* remove unneeded props/variables

* remove unused border classes

* WIP new folder UI

* remove unneeded expanded prop from filerow component

* folder creation UI and files object manipulation WIP

* folder creation & moving files complete

* add developer API support for creating folders and moving files

* update alternating row css for file picker

* remove unneeded props from merge

* normalize paths for folders
priority to custom docs folder
silently fail on duplicate folders

* update folder icon to custom svg

* linting and move FolderIcon to JSX

---------

Co-authored-by: timothycarambat <rambat1010@gmail.com>
2024-03-20 16:10:30 -07:00
Timothy Carambat
7e7e957e32
Enable privacy and handling to be reviewed and modified (#910) 2024-03-14 16:56:15 -07:00
Timothy Carambat
0ada882991
Support external transcription providers (#909)
* Support External Transcription providers

* patch files

* update docs

* fix return data
2024-03-14 15:43:26 -07:00
Sean Hatfield
ac0e62d490
[FEAT] Anthropic Haiku model support (#901)
add Haiku model support
2024-03-13 17:32:02 -07:00
Timothy Carambat
0e46a11cb6
Stop generation button during stream-response (#892)
* Stop generation button during stream-response

* add custom stop icon

* add stop to thread chats
2024-03-12 15:21:27 -07:00
Sean Hatfield
04399b1328
[FEAT] Ability to set workspace profile image (#847)
* WIP workspace pfp, CRUD functions complete

* implement fetching workspace pfp in UserIcon component

* update UI for workspace settings pfp

* minor css refactor

* WIP fixes to workspace pfp

* create responseCache for workspace pfp blob to improve performance

* fix cache not clearing when removing workspace pfp and remove unneeded util

* load workspace image once, dont reload

---------

Co-authored-by: timothycarambat <rambat1010@gmail.com>
2024-03-12 11:36:59 -07:00
timothycarambat
0117589bbf pin prisma versions to be the same 2024-03-08 12:51:58 -08:00
timothycarambat
31d9268ed4 Merge branch 'master' of github.com:Mintplex-Labs/anything-llm 2024-03-06 17:14:26 -08:00
timothycarambat
273d824df4 patch: do not block response if user password check failed 2024-03-06 17:14:17 -08:00
Sean Hatfield
e0d5d8039a
[FEAT] Claude 3 support and implement new version of Anthropic SDK (#863)
* implement new version of anthropic sdk and support new models

* remove handleAnthropicStream and move to handleStream inside anthropic provider

* update useGetProvidersModels for new anthropic models
2024-03-06 14:57:47 -08:00
Sean Hatfield
0634013788
[FEAT] Groq LLM support (#865)
* Groq LLM support complete

* update useGetProvidersModels for groq models

* Add definiations
update comments and error log reports
add example envs

---------

Co-authored-by: timothycarambat <rambat1010@gmail.com>
2024-03-06 14:48:38 -08:00
Gabriel Koo
4731ec8be8
[FIX] : missing import for parseAuthHeader in server/utils/vectorDbProviders/chroma/index.js (#869)
fix: import parseAuthHeader in chroma/index.js
2024-03-06 09:14:36 -08:00
Sean Hatfield
fde905aac1
[FEAT] JSON export append all metadata fields to workspace chats (#845)
have JSON export append all metadata fields
2024-02-29 17:04:59 -08:00