Commit graph

1820 commits

Author SHA1 Message Date
Neelesh Kumar
463ca5d613
📄 docs: Update apipie fetch.py in ai_endpoints.md (#2547)
* Update apipie fetch.py in ai_endpoints.md

Made the python code more pythonic

* fix bug that caused duplicate model_ids
2024-04-27 18:37:33 -04:00
Neelesh Kumar
039c7ae880
📄 docs: update GOOGLE_MODELS in .env.example (#2506)
* update GOOGLE_MODELS in .env.example

* Update .env.example

* Update .env.example

* Update .env.example

* Update .env.example

---------

Co-authored-by: Danny Avila <danacordially@gmail.com>
2024-04-27 18:36:54 -04:00
Danny Avila
63ef15ab63
🦙 feat: Fetch list of Ollama Models (#2565)
* 🦙 feat: Fetch list of Ollama Models

* style: better Tag text styling for light mode
2024-04-27 18:27:04 -04:00
Ventz Petkov
8a78500fe2
🚅 docs: update LiteLLM config with more models (#2553)
Added all OpenAI, Azure OpenAI, Amazon Bedrock, and Google GCP models available.

Specifically latest: Llama3; Google Gemini 1.5 Pro Preview; Claude Opus.

Here are all of the models:
  - model_name: claude-3-haiku
  - model_name: claude-3-sonnet
  - model_name: claude-3-opus
  - model_name: claude-v2
  - model_name: claude-instant
  - model_name: llama2-13b
  - model_name: llama2-70b
  - model_name: llama3-8b
  - model_name: llama3-70b
  - model_name: mistral-7b-instruct
  - model_name: mixtral-8x7b-instruct
  - model_name: mixtral-large
  - model_name: cohere-command-v14
  - model_name: cohere-command-light-v14
  - model_name: ai21-j2-mid
  - model_name: ai21-j2-ultra
  - model_name: amazon-titan-lite
  - model_name: amazon-titan-express
  - model_name: azure-gpt-4-turbo-preview
  - model_name: azure-gpt-3.5-turbo
  - model_name: azure-gpt-4
  - model_name: azure-gpt-3.5-turbo-16k
  - model_name: azure-gpt-4-32k
  - model_name: gpt-4-turbo
  - model_name: old-gpt-4-turbo-preview
  - model_name: gpt-3.5-turbo
  - model_name: gpt-4
  - model_name: gpt-3.5-turbo-16k
  - model_name: gpt-4-32k
  - model_name: gpt-4-vision-preview
  - model_name: google-chat-bison
  - model_name: google-chat-bison-32k
  - model_name: google-gemini-pro-1.0
  - model_name: google-gemini-pro-1.5-preview
2024-04-27 06:46:20 -04:00
Fuegovic
144fd5f6aa
⚙️ docs: update dotenv.md (#2551)
* ⚙️ docs: update dotenv.md

* Update dotenv.md - formatting
2024-04-26 14:34:50 -04:00
Danny Avila
2720327aa1
👩‍💻 fix: Minor UI fixes (#2548)
* fix(useMessageHelpers): define iconEndpoint

* fix: rely on Assistant Switcher effect for defining `assistant_id`, ensure ChatRoute `newConversation` only fires once
2024-04-26 10:27:49 -04:00
Martin Dahlö
4d0806d3e8
📋 refactor: allow paste in confirm field when resetting passwords (#2542)
* Disabled paste prevention in the confirm password field when resetting passwords.

* chore(ResetPassword): remove comments

---------

Co-authored-by: Danny Avila <danacordially@gmail.com>
2024-04-25 20:26:33 -04:00
Neelesh Kumar
5b5f9b950b
🐋 refactor: Update docker-compose.yml (#2507) 2024-04-25 20:25:51 -04:00
いしかず
3ccff19821
🌍: Update Japanese translation (#2519)
* Update japanese translation

* translate japanese

* Added 5 Japanese translations

---------

Co-authored-by: k-ishii1020 <40662914+8492GitKaz@users.noreply.github.com>
2024-04-25 13:55:59 -04:00
Marco Beretta
11d5e232b3
🧪 refactor(isDomainAllowed): change directory, add tests (#2539) 2024-04-25 13:14:07 -04:00
Danny Avila
099aa9dead
feat: Stop Sequences for Conversations & Presets (#2536)
* feat: `stop` conversation parameter

* feat: Tag primitive

* feat: dynamic tags

* refactor: update tag styling

* feat: add stop sequences to OpenAI settings

* fix(Presentation): prevent `SidePanel` re-renders that flicker side panel

* refactor: use stop placeholder

* feat: type and schema update for `stop` and `TPreset` in generation param related types

* refactor: pass conversation to dynamic settings

* refactor(OpenAIClient): remove default handling for `modelOptions.stop`

* docs: fix Google AI Setup formatting

* feat: current_model

* docs: WIP update

* fix(ChatRoute): prevent default preset override before `hasSetConversation.current` becomes true by including latest conversation state as template

* docs: update docs with more info on `stop`

* chore: bump config_version

* refactor: CURRENT_MODEL handling
2024-04-25 11:40:17 -04:00
Danny Avila
4121818124
✍️ fix(useTextarea): Rich Text Format paste from MS Word (#2530) 2024-04-25 00:10:41 -04:00
Fuegovic
ca9a0fe629
🥧 feat: APIpie support (#2524) 2024-04-24 20:32:18 -04:00
Danny Avila
bde6bb0152
🔀 fix: Remove use of Mongo Transactions (#2525)
* fix: remove use of transactions

* fix: remove use of transactions

* refactor(actions): perform OpenAI API operation first, before attempting database updates
2024-04-24 16:04:46 -04:00
ilsubyeega
667f5f91fe
👤 fix: Use user?.username if user?.name is undefined (#2511)
* Use `user?.username` if `user?.name` is undefined

* Add useLocalize hook to Icon component
2024-04-24 12:34:01 -04:00
Mathieu Breton
75da75be08
🛂 feat(oauth): add domain restriction on social login (#2512) 2024-04-24 12:14:27 -04:00
Danny Avila
cdab1e9cda
🔒 fix: package-lock file for cross-compatibility (#2515) 2024-04-24 10:42:18 -04:00
Danny Avila
3df4fac118
v0.7.1 (#2502)
* chore: make openai package definition explicit

*  v0.7.1

* chore: gpt-4-vision correct context length

* add `llava` to vision models list
2024-04-23 08:57:20 -04:00
Danny Avila
0ae98ff011
🧪 ci: Add .env.test for backend-review.yml (#2501)
* 🧪 ci: Add `.env.test` for `backend-review.yml`

* chore: touch example file
2024-04-23 08:21:12 -04:00
Walber Cardoso
4d05e5b79a
👟 style: WrenchIcon and ImageGen SVG Animations (#2382)
* refactor(WrenchIcon, ImageGen SVG)

* refactor(WrenchIcon SVG)

* refactor(ImageGen SVG)

* refactor(ImageGen SVG) - add CSS
2024-04-23 08:14:28 -04:00
Danny Avila
199f9f32e6
🐋 fix(Dockerfile.multi): Resolve OpenAI SDK @ Latest for Assistants v1 2024-04-22 20:23:28 -04:00
Danny Avila
f94a782b4f
💻 fix(client): Allow Code Filetypes and Suppress Known Vite Warnings (#2492)
* refactor(vite): suppress known warnings

* fix: allow known code filetypes if there is a mismatch of expected type, or originalFile.type is empty

* refactor(useFileHandling): naming, use variable
2024-04-22 20:08:34 -04:00
Fuegovic
738207de50
✏️docs: remove "copilot-gpt4-service" (#2491)
removed "copilot-gpt4-service", the repository has been disabled
2024-04-22 16:35:05 -04:00
Danny Avila
c96f067689
🔧 fix: Resolve Proper Dependencies to fix Application Error (#2488)
* chore: bump data-provider

* feat: script to check recent dependency updates

* fix: override vite/rollup version for vite build fix
- also remove unused vite-plugin-html
- add vite build to file output command

* chore: bump rollup override to last known working version (v4.16.0 is breaking)

* chore(vite): increase file size cache for workbox

* fix: resolve openai to last known version using assistants v1 latest features and default header

* chore: update openrouter examples
2024-04-22 12:52:30 -04:00
Danny Avila
3bfd185cab
feat: Added PWA Setup & Manual Chunks via Vite (#2477)
* added pwa setup via vite config

Added apple status bar meta data

added maskable 512 icon for chrome and android devices

added vite-plugin-pwa

updated vite config to setup the pwa service worker and manifest upon build

* fix(vite): avoid pre-caching generated images

* chore: add manual chunking of larger vendor package

* chore: remove comments

---------

Co-authored-by: davecrab <65996799+davecrab@users.noreply.github.com>
2024-04-21 10:39:15 -04:00
Danny Avila
c937b8cd07
🧑‍💻 refactor: Display Client-facing Errors (#2476)
* fix(Google): allow presets to configure expected maxOutputTokens

* refactor: standardize client-facing errors

* refactor(checkUserKeyExpiry): pass endpoint instead of custom message

* feat(UserService): JSDocs and getUserKeyValues

* refactor: add NO_BASE_URL error type, make use of getUserKeyValues, throw user-specific errors

* ci: update tests with recent changes
2024-04-21 08:31:54 -04:00
Passerby1011
6db91978ca
🎨 style: update CodeSherpa icon (#2417)
The icon address error leads to the icon not displaying.
2024-04-20 15:09:59 -04:00
Danny Avila
8c22bb1d3d
🛠️ fix(Azure/Assistants): Handle Long Domain Names & Other Minor chores (#2475)
* chore: replace violation cache accessors with enum

* chore: fix test

* chore(fileSchema): index timestamps

* fix(ActionService): use encoding/caching strategy for handling assistant function character length limit

* refactor(actions): async `domainParser` also resolve retrieved model (which is deployment name) to user-defined model

* style(AssistantAction): add `whitespace-nowrap` for ellipsis

* refactor(ActionService): if domain is less than or equal to encoded domain fixed length, return domain with replacement of separator

* refactor(actions): use sessions/transactions for updating Assistant Action database records

* chore: remove TTL from ENCODED_DOMAINS cache

* refactor(domainParser): minor optimization and add tests

* fix(spendTokens): use txData.user for token usage logging

* refactor(actions): add helper function `withSession` for database operations with sessions/transactions

* fix(PluginsClient): logger debug `message` field edge case
2024-04-20 15:02:56 -04:00
Noah Ispas
5d642d0187
📙 docs: Remove duplicate information (#2451) 2024-04-19 22:57:40 -04:00
Fuegovic
4196a86fa9
🦙 doc update: llama3 (#2470)
* docs: update breaking_changes.md

* docs: update ai_endpoints.md -> llama3 for Ollama and groq

* librechat.yaml: update groq models

* Update breaking_changes.md

logs location

* Update breaking_changes.md

---------

Co-authored-by: Danny Avila <danny@librechat.ai>
2024-04-19 21:40:12 -04:00
Danny Avila
e6310c806a
🤖 fix: Minor Assistants Endpoint Fixes (#2472)
* fix(useCreateAssistantMutation): force re-render of assistants map by avoiding use shallow reference of listRes.data

* fix(AppService): regression by not including azure assistant defaults when no assistant endpoint values are set
2024-04-19 19:05:25 -04:00
Danny Avila
3d1dec62a4
🧼 refactor(AppService): Consolidate Logic & Issue more Warnings (#2468)
* chore: bump example config version

* refactor(AppService): issue warnings from separate modules where possible

* refactor(AppService): consolidate AppService logic to separate modules as much as possible

* chore: bump data-provider

* chore: remove unn. variable definition

* chore: warning wording
2024-04-19 12:05:39 -04:00
Danny Avila
de3987cbaf
🛂 refactor(openidStrategy): Use Strategy Functions for Avatars (#2467) 2024-04-19 09:12:55 -04:00
Fuegovic
f406a85633
🖥️ docs: env changes v0.6.10→v0.7.0+ (#2442)
* docs: env changes v0.6.10→v0.7.0+ | update railway referral

* docs: env changes v0.6.10→v0.7.0+
2024-04-18 08:27:52 -04:00
Danny Avila
692ce3b346
🛠️ fix: Merge Textarea Ref with Form for Simplified Handling (#2456)
* share ref correctly

* chore: remove extraneous textarea handlers and add excel text data
2024-04-18 08:19:52 -04:00
Fuegovic
26ea990045
📘 docs: update docker_compose_install.md (#2447)
* Update docker_compose_install.md

* Update docker_compose_install.md
2024-04-18 07:31:44 -04:00
Fuegovic
265abbc1c8
⚙️ docs: Update .env.example (#2449) 2024-04-18 07:30:46 -04:00
marlonka
0b7da72be6
🌍 : Update German Translations (#2409)
* Improved and additional German translations

* Improved and added german translations and removed language translations here

* Spelling error fixed

* Use single quotes instead of double

* Use single quotes instead of double
2024-04-18 07:26:44 -04:00
Danny Avila
3c184e9410
🛠️ fix: Ensure imageOutputType is Always Defined (#2438)
* avatar fix

* chore: ensure `imageOutputType` is always defined

* ci(AppService): extra test for default value

* chore: replace default value for `desiredFormat` with `EImageOutputType` enum
2024-04-16 16:34:19 -04:00
Danny Avila
bf4e64ce63
🪙 fix(Google): Update maxOutputTokens Condition (#2434)
- generalize condition to fix max output tokens for gemini-1.5
2024-04-16 10:23:13 -04:00
Danny Avila
9d854dac07
🤖 feat: Gemini 1.5 Support (+Vertex AI) (#2383)
* WIP: gemini-1.5 support

* feat: extended vertex ai support

* fix: handle possibly undefined modelName

* fix: gpt-4-turbo-preview invalid vision model

* feat: specify `fileConfig.imageOutputType` and make PNG default image conversion type

* feat: better truncation for errors including base64 strings

* fix: gemini inlineData formatting

* feat: RAG augmented prompt for gemini-1.5

* feat: gemini-1.5 rates and token window

* chore: adjust tokens, update docs, update vision Models

* chore: add back `ChatGoogleVertexAI` for chat models via vertex ai

* refactor: ask/edit controllers to not use `unfinished` field for google endpoint

* chore: remove comment

* chore(ci): fix AppService test

* chore: remove comment

* refactor(GoogleSearch): use `GOOGLE_SEARCH_API_KEY` instead, issue warning for old variable

* chore: bump data-provider to 0.5.4

* chore: update docs

* fix: condition for gemini-1.5 using generative ai lib

* chore: update docs

* ci: add additional AppService test for `imageOutputType`

* refactor: optimize new config value `imageOutputType`

* chore: bump CONFIG_VERSION

* fix(assistants): avatar upload
2024-04-16 08:32:40 -04:00
Danny Avila
fce7246ac1
🔓 refactor: Make Image URL Security Optional (#2415) 2024-04-14 19:34:13 -04:00
Danny Avila
2cc580ba52
*️⃣ refactor(DeleteButton): Conversation List Behavior after Deletion (#2414)
* Refactor DeleteButton component in client/src/components/Conversations/DeleteButton.tsx

* chore: bump data-provider package

* chore: remove console.log
2024-04-14 19:11:55 -04:00
Danny Avila
d2d9ac0280
feat: Add 'EnterToSend' Option & Update Br. Translation 🇧🇷 (#2413)
* chore: Add EnterToSend, Translation Portuguese Brazilian Update

* Inverted selection and corrected translation

* fix: removed Trailing spaces not allowed

* feat: Refactor key event handler & updated translations

* fix: removed return; & updated files translations

* fix: duplicate switchs on General.tsx

* fix: added again switch

* refactor(useTextarea): limit refactoring of handleKeyDown

* refactor: correct keyDown handler and add English localization

---------

Co-authored-by: Raí Santos <140329135+itzraiss@users.noreply.github.com>
Co-authored-by: Raí Santos <raimorningstarchristus@gmail.com>
2024-04-14 19:06:20 -04:00
Ventz Petkov
f380f261a5
🛂 fix: OIDC Username Array Edge Case (#2394)
* Patch for OpenID username

`username` is generally based on email, rather than `given_name`. The challenge with `given_name` is that it can be a multi-value array (ex: "Nick, Fullname"), which completely breaks the system with: 

```
LibreChat      | ValidationError: User validation failed: username: Cast to string failed for value "[ 'Nickname', 'Firstname' ]" (type Array) at path "username"
LibreChat      |     at Document.invalidate (/app/node_modules/mongoose/lib/document.js:3200:32)
LibreChat      |     at model.$set (/app/node_modules/mongoose/lib/document.js:1459:12)
LibreChat      |     at model.set [as username] (/app/node_modules/mongoose/lib/helpers/document/compile.js:205:19)
LibreChat      |     at OpenIDConnectStrategy._verify (/app/api/strategies/openidStrategy.js:127:27)
LibreChat      |     at process.processTicksAndRejections (node:internal/process/task_queues:95:5)
```

* Update openidStrategy.js

* refactor(openidStrategy): add helper function for stringy username

---------

Co-authored-by: Danny Avila <danny@librechat.ai>
2024-04-12 12:39:11 -04:00
jp789
9d137ce42f
📑 docs: Add claude haiku to example anthropic models (#2391)
Co-authored-by: juliaanp <juliaan.posaratnanathan@zafin.com>
2024-04-11 15:31:04 -04:00
Melaton
25f92dd1c3
🌎 : Update chinese localization (#2384)
* 🌍 Update Chinese Translation

Update Simplified Chinese Translation

* Update Chinese Translation

Formatting file, adding new translations, delete unused translations
2024-04-11 11:23:23 -04:00
Danny Avila
9277e2a0c5
🔒 feat: Authenticated Image Requests (#2389)
* 🔒 feat: Authenticated Image Requests

* fix: reserved keyword `static`
2024-04-11 02:50:57 -04:00
Danny Avila
c19dfddd0f
👷 fix: Minor Fixes and Refactors (#2388)
* refactor(useTextarea): set Textarea disabled message due to key higher in priority

* fix(SidePanel): intended behavior for non-user provided keys

* fix: generate specs

* style: update combobox styling as before, with better dynamic height

* chore: remove unused import
2024-04-11 02:12:48 -04:00
Danny Avila
0fe47cf1f8
🤖 feat: Update Context Limit for gpt-3.5-turbo (#2381) 2024-04-10 15:10:21 -04:00