Commit graph

361 commits

Author SHA1 Message Date
Timothy Carambat
446164d7b9
Add Groq vision preview support ()
Adds support for only the llama3.2 vision models on groq. This comes with many conditionals and nuances to handle as Groqs vision implemention is quite bad right now
2024-10-21 12:37:39 -07:00
Timothy Carambat
7342839e77
Passthrough agentModel for LMStudio () 2024-10-18 11:44:48 -07:00
Timothy Carambat
93d7ce6d34
Handle Bedrock models that cannot use system prompts () 2024-10-16 12:31:04 -07:00
Timothy Carambat
3dc0f3f490
Tts open ai compatible endpoints ()
* Update OpenAI TTS config to allow a custom BaseURL

* uncheck config file

* break openai generic TTS into its own provider

* add space

* hide TTS on user msg

---------

Co-authored-by: Adam <phazei@gmail.com>
2024-10-15 21:39:31 -07:00
Sean Hatfield
fa528e0cf3
OpenAI o1 model support ()
* support openai o1 models

* Prevent O1 use for agents
getter for isO1Model;

---------

Co-authored-by: timothycarambat <rambat1010@gmail.com>
2024-10-15 19:42:13 -07:00
Sean Hatfield
6674e5aab8
Support free-form input for workspace model for providers with no /models endpoint ()
* support generic openai workspace model

* Update UI for free form input for some providers

---------

Co-authored-by: Timothy Carambat <rambat1010@gmail.com>
2024-10-15 15:24:44 -07:00
Timothy Carambat
c3723ce2ff
Add backfilling on query for chat widget to improve UX () 2024-10-15 14:37:44 -07:00
Sean Hatfield
cb4b0a878e
LiteLLM agent support ()
* litellm agent support

* lint

* add LiteLLM provider config

---------

Co-authored-by: Timothy Carambat <rambat1010@gmail.com>
2024-10-15 12:43:14 -07:00
Timothy Carambat
bce7988683
Integrate Apipie support directly ()
resolves 
resolves 
Note: Streaming not supported
2024-10-15 12:36:06 -07:00
Sean Hatfield
5ac6020480
Tavily search web search agent support ()
* support tavily search web search agent

* lint

* remove unneeded comments
2024-10-01 14:52:57 -07:00
Blazej Owczarczyk
e07535471f
Added voyage-3 and voyage-3-lite. () 2024-09-30 09:37:25 -07:00
a4v2d4
cadc09d71a
[FEAT] Add Llama 3.2 models to Fireworks AI's LLM selection dropdown ()
Add Llama 3.2 3B and 1B models to Fireworks AI LLM selection
2024-09-28 15:30:56 -07:00
Sean Hatfield
7390bae6f6
Support DeepSeek ()
* add deepseek support

* lint

* update deepseek context length

* add deepseek to onboarding

---------

Co-authored-by: Timothy Carambat <rambat1010@gmail.com>
2024-09-26 12:55:12 -07:00
Timothy Carambat
44dddcd4af
1417 completion timeout ()
* Refactor handleDefaultStreamResponseV2 function for better error handling

* run yarn lint

* small error handling changes

* update error handling flow and scope of vars

* add back space

---------

Co-authored-by: Roman <rrojaski@gmail.com>
2024-09-25 14:00:19 -07:00
Sean Hatfield
e6c4eb3f1c
Support attachments in developer API ()
* support attachments in developer api

* lint

---------

Co-authored-by: Timothy Carambat <rambat1010@gmail.com>
2024-09-25 13:44:26 -07:00
Sean Hatfield
e2195a96d1
Workspace agent autoselection ()
* refactor agent to add fallback to workspace, then to chat provider/model

* commenting
update logic for bedrock and fireworks fallbacks

---------

Co-authored-by: timothycarambat <rambat1010@gmail.com>
2024-09-25 13:30:20 -07:00
Sean Hatfield
4ebc37b4e3
Export embedded chat history ()
export embedded chat history

Co-authored-by: Timothy Carambat <rambat1010@gmail.com>
2024-09-24 16:05:34 -07:00
Timothy Carambat
b44889a843
PR#2355 Continued + expanded scope ()
*  Fetch pinned documents once per folder to reduce the number of queries.

* Reorder the lines to keeps const declarations together.

* Add some comments to functions
move pinned document fetch for folder to function
move watched documents per-folder to also function the same
remove unused function in documents model

---------

Co-authored-by: Błażej Owczarczyk <blazeyy@gmail.com>
2024-09-24 15:55:54 -07:00
timothycarambat
48c9c2e212 Dont overwrite content in input on paste
linting
2024-09-23 11:07:56 -05:00
Jaid
12b8af4654
Added JSONSchema for plugin.json files ()
Added JSONSchema for agent skill plugin manifest files

Signed-off-by: Jaid <6216144+Jaid@users.noreply.github.com>
2024-09-23 10:25:29 -05:00
Timothy Carambat
a781345a0d
Enable Mistral Multimodal ()
* Enable Mistral Multimodal

* remove console
2024-09-21 16:17:17 -05:00
Sean Hatfield
b7c7c0db98
Add more verbose error messages in embed chat ()
* publish embed updates

* server sided error messages

* publish embed chat widget

* sync submodule

* unset change

* update embed to merged changes for error

---------

Co-authored-by: timothycarambat <rambat1010@gmail.com>
2024-09-19 11:28:45 -05:00
Timothy Carambat
a30fa9b2ed
1943 add fireworksai support ()
* Issue : Add support for LLM provider - Fireworks AI

* Update UI selection boxes
Update base AI keys for future embedder support if needed
Add agent capabilites for FireworksAI

* class only return

---------

Co-authored-by: Aaron Van Doren <vandoren96+1@gmail.com>
2024-09-16 12:10:44 -07:00
Timothy Carambat
b557a289fe
Support @agent custom skills ()
* Support `@agent` custom skills

* move import
2024-09-13 14:35:10 -07:00
Timothy Carambat
906eb70ca1
bump Perplexity models () 2024-09-12 13:13:47 -07:00
Timothy Carambat
f5565dd6c9
Patch missing folder autogenerate for plugins () 2024-09-12 09:48:53 -07:00
Timothy Carambat
43b6ece0a5
Update OpenAI models and prices ()
* Update OpenAI models

* Sort OpenAI models by created timestamp in ascending order

* Update OpenAI models price

* uncheck fallback listing (even if old)
closes 

* linting

---------

Co-authored-by: Yaner <1468275133@qq.com>
2024-09-11 13:08:10 -07:00
Timothy Carambat
c612239ecb
Add Gemini exp models ()
Add Gemini  models
resolves 
2024-09-11 13:03:14 -07:00
Timothy Carambat
d1103e2b71
Add support for custom agent skills via plugins ()
* Add support for custom agent skills via plugins
Update Admin.systemPreferences to updated endpoint (legacy has deprecation notice

* lint

* dev build

* patch safeJson
patch label loading

* allow plugins with no config options

* lint

* catch invalid setupArgs in frontend

* update link to docs page for agent skills

* remove unneeded files

---------

Co-authored-by: shatfield4 <seanhatfield5@gmail.com>
2024-09-10 17:06:02 -07:00
Sean Hatfield
a58f271149
Milvus bug fix ()
* patch no text results for milvus chunks

* wrap addDocumentToNamespace in try catch for handling milvus errors

* lint

* revert milvus db changes

* add try catch to handle grpc error from milvus
2024-09-09 15:32:08 -07:00
Mr Simon C
cf6928fd5d
match user prompts exactly not partially () 2024-09-09 14:40:06 -07:00
Timothy Carambat
20135835d0
Ollama sequential embedding ()
* ollama: Switch from parallel to sequential chunk embedding

* throw error on empty embeddings

---------

Co-authored-by: John Blomberg <john.jb.blomberg@gmail.com>
2024-09-06 10:06:46 -07:00
Timothy Carambat
b8b55b5899
Feature/add searchapi web browsing ()
* Add SearchApi to web browsing

* UI modifications for SearchAPI

---------

Co-authored-by: Sebastjan Prachovskij <sebastjan.prachovskij@gmail.com>
2024-09-05 10:36:46 -07:00
Sean Hatfield
86ba16acdc
Add new Voyage AI embedding models ()
new voyageai embedding models
2024-08-29 14:11:00 -07:00
timothycarambat
334fd9cdd0 pre-validate sessionID type for embed chats 2024-08-27 16:38:20 -07:00
timothycarambat
548da9ade3 Exception handler on embed chat middleware 2024-08-27 16:27:58 -07:00
Timothy Carambat
29df483a27
AnythingLLM Chrome Extension ()
* initial commit for chrome extension

* wip browser extension backend

* wip frontend browser extension settings

* fix typo for browserExtension route

* implement verification codes + frontend panel for browser extension keys

* reorganize + state management for all connection states

* implement embed to workspace

* add send page to anythingllm extension option + refactor

* refactor connection string auth + update context menus + organize background.js into models

* popup extension from main app and save if successful

* fix hebrew translation misspelling

* fetch custom logo inside chrome extension

* delete api keys on disconnect of extension

* use correct apiUrl constant in frontend + remove unneeded comments

* remove upload-link endpoint and send inner text html to raw text collector endpoint

* update readme

* fix readme link

* fix readme typo

* update readme

* handle deletion of browser keys with key id and DELETE endpoint

* move event string to constant

* remove tablename and writable fields from BrowserExtensionApiKey backend model

* add border-none to all buttons and inputs for desktop compatibility

* patch prisma injections

* update delete endpoints to delete keys by id

* remove unused prop

* add button to attempt browser extension connection + remove max active keys

* wip multi user mode support

* multi user mode support

* clean up backend + show created by in frotend browser extension page

* show multi user warning message on key creation + hide context menus when no workspaces

* show browser extension options to managers

* small backend changes and refactors

* extension cleanup

* rename submodule

* extension updates & docs

* dev docker build

---------

Co-authored-by: shatfield4 <seanhatfield5@gmail.com>
2024-08-27 14:58:47 -07:00
Timothy Carambat
b4651aff35
Support gpt-4o for Azure deployments () 2024-08-26 14:35:42 -07:00
Timothy Carambat
22ecb7cb39
Add RAG agent plugin to API agent () 2024-08-23 09:32:19 -07:00
Timothy Carambat
2de9e492ec
Enabled use of @agent (and skills) via dev API calls ()
* Use `@agent` via dev API

* Move EphemeralEventListener to same file as agent
2024-08-22 13:12:09 -07:00
Timothy Carambat
fdc3add53c
Api session id support ()
* Refactor api endpoint chat handler to its own function
remove legacy `chatWithWorkspace` and cleanup `index.js`

* Add `sessionId` in dev API to partition chats logically statelessly
2024-08-21 15:25:47 -07:00
timothycarambat
2d2e49bc00 fix missing export 2024-08-21 14:58:56 -07:00
Timothy Carambat
1f96b837b3
Refactor api endpoint chat handler to its own function ()
remove legacy `chatWithWorkspace` and cleanup `index.js`
2024-08-21 14:47:06 -07:00
timothycarambat
cb7cb2d976 Add 405B to perplexity 2024-08-19 12:26:22 -07:00
Timothy Carambat
a8d25c7dd3
Allow readable username passed in script widget () 2024-08-16 16:55:42 -07:00
Timothy Carambat
c8fe254d45
Omit invalid response.text values and prompts ()
* Omit invalid `response.text` values and `prompts`
resolves 

* remove import
2024-08-15 14:22:27 -07:00
Timothy Carambat
99f2c25b1c
Agent Context window + context window refactor. ()
* Enable agent context windows to be accurate per provider:model

* Refactor model mapping to external file
Add token count to document length instead of char-count
refernce promptWindowLimit from AIProvider in central location

* remove unused imports
2024-08-15 12:13:28 -07:00
Shahar
4365d69359
Fix TypeError by replacing this.openai.createChatCompletion with the correct function call ()
fixed new api syntax
2024-08-14 14:39:48 -07:00
Timothy Carambat
4430ddb059
Encryption in JWT for single-user password mode ()
* wip encrypting jwt value

* Encrypt/Decrypt pass in JWT value for verification in single-user password mode
2024-08-13 17:54:12 -07:00
PyKen
a2571024a9
Add prompt window limits for gpt-4o-* models () 2024-08-13 09:13:36 -07:00