Commit graph

1864 commits

Author SHA1 Message Date
Danny Avila
e42709bd1f
🔍 feat: Show Messages from Search Result (#2699)
* refactor(Nav): delegate Search-specific variables/hooks to SearchContext

* fix: safely determine firstTodayConvoId if convo is undefined

* chore: remove empty line

* feat: initial render of search messages

* feat: SearchButtons

* update Ko.ts

* update localizations with new key phrases

* chore: localization comparisons

* fix: clear conversation state on searchQuery navigation

* style: search messages view styling

* refactor(Convo): consolidate logic to navigateWithLastTools from useNavigateToConvo

* fix(SearchButtons): styling and correct navigation logic

* fix(SearchBar): invalidate all message queries and invoke `clearText` if onChange value is empty

* refactor(NewChat): consolidate new chat button logic to NewChatButtonIcon

* chore: localizations for Nav date groups

* chore: update comparisons

* fix: early return from sendRequest to avoid quick searchQuery reset

* style: Link Icon

* chore: bump tiktoken, use o200k_base for gpt-4o
2024-05-14 11:00:01 -04:00
Danny Avila
638ac5bba6
🚀 feat: gpt-4o (#2692)
* 🚀 feat: gpt-4o

* update readme.md

* feat: Add new test case for getMultiplier function

* feat: Refactor getMultiplier function to use valueKey variable
2024-05-13 14:25:02 -04:00
Christian Köberl
5920672a8c
🐋 ci: create smaller Docker images (#2691)
- create fewer layers
- install only prod dependencies for final build
- clean npm cache
- fix layering in multi-image build
2024-05-13 10:47:18 -04:00
Danny Avila
a0d1e2a5f8
🪶 docs: Update README.md Icon 2024-05-13 10:42:09 -04:00
Danny Avila
4ffc1414a8
Revert "🐋 refactor(docker-compose): use "HOST" in ports field (#2654)"
This reverts commit df6183db0f.
2024-05-13 10:36:36 -04:00
nidasfly
df6183db0f
🐋 refactor(docker-compose): use "HOST" in ports field (#2654) 2024-05-13 10:31:13 -04:00
Fuegovic
3816219936
🧹 chore: remove old docs (#2684)
* delete docs folder

* delete mkdocs

* update .env.example

* update compose.override

* update librechat.yaml

* update pr template

* update librechat.yaml

* update README.md

* update missing custom config error msg

* update loadCustomConfig.js

* update check.js

* update .env.example

* update replit reference

* update README.md

* prevent logger URL truncation

* fix broken link in templates

---------

Co-authored-by: Danny Avila <danny@librechat.ai>
2024-05-13 10:15:30 -04:00
Danny Avila
6fc664e4a3
⚙️ feat: includedTools and script changes (#2690)
* chore: add email to npm scripts (user-stats and list-balances)

* feat: included tools

* chore: update console terminal links

* chore: add back typing
2024-05-13 10:07:10 -04:00
Danny Avila
89899164ed
👮 fix(enforceModelSpec): handle nested objects (#2681) 2024-05-12 18:20:53 -04:00
Danny Avila
c83d9d61d4
🧹 chore(/config/): add tsconfig.json & linting (#2680) 2024-05-12 16:24:13 -04:00
Danny Avila
bcdddaed72
🎨 style(MentionItem): update active bg-color (#2675) 2024-05-12 09:20:59 -04:00
Marco Beretta
a4de635719
🎨 style(MentionItem): update hover color (#2670)
* style(MentionItem): update hover color

* remove unused className
2024-05-11 21:12:22 -04:00
Danny Avila
4a32d7466a
v0.7.2 (#2667)
* v0.7.2

* chore: uninstall hnswlib-node

* bump package provider

* bump librechat-data-provider in lockfile

* README: ross index

* chore: center star history
2024-05-10 16:29:27 -04:00
Danny Avila
2ec821ea4c
🌍 : Updated Translations & AI Generation Scripts (#2666)
* chore: bun scripts

* feat: comparisons

* refactor: move scripts to own folder

* feat: generated prompts script and Es output

* feat: generated prompts

* created prompts

* feat: Russian localization prompts

* translation setup

* additional ES translations

* additional ES translations

* translation services

* feat: additional translations

* fix regex for parseParamPrompt

* RU translations

* remove stores from git

* update gitignore

* update gitignore

* ZH translations

* move gen prompt output location

* ZH traditional translations

* AR translations

* chore: rename

* JP

* cleanup scripts

* add additional instruction prompts

* fix translation prompt and add DE

* FR translations (rate limited so not complete)

* chore: update translation comparisons

* chore: remove unused AnthropicClient changes

* refactor: use compositional styling for archive/delete buttons, fix manage archive table styling
2024-05-10 15:56:25 -04:00
Marco Beretta
978009787c
📝 docs(ai_endpoints): update HF key link (#2664) 2024-05-10 12:48:39 -04:00
Danny Avila
27e7621b6a
🪟 fix: Windows Vite Build Issue (#2663)
* fix: Windows CSS VITE build issue: peer-focus:dark => dark:peer-focus

* ci: add windows env step for frontend ci/cd
2024-05-10 12:44:43 -04:00
Danny Avila
2b37a44b8d
🔧 fix: Preset Dialog Styling and Values (#2657)
* style: preset dialog styling

* refactor: coerce number input for convo schema

* refactor: replace dynamic input number with static component
2024-05-10 03:05:45 -04:00
Danny Avila
98c96cd020
🦙 fix: Ollama System Message order (#2655) 2024-05-10 00:50:02 -04:00
Anirudh
8f20fb28e5
🪟 fix+feat: General UI Enhancements (#2619)
* feat: Minor design changes to mimic OpenAI's latest login page

* fix: Optimize ThemeSelector for mobile

* fix: Use a svg for the logo for transperency in dark mode

* feat: Update styles for Registration

* feat: Update error colors for login & registration

* fix: remove medium font

* wip: Dropdown menu

* feat: Update dropdown to match ChatGPT

* feat: Improve rounding and padding

* feat: Add UI Updates to RequestPasswordReset, PasswordRest and increase width for theme dropdown

* fix: Modify the My Files modal's width to not touch the screen

* feat: fix scrolling for dropdown, and make border width lighter

* feat: Match popup menu design to OpenAI (p1/2)

* fix+feat: fix dark mode, add user email, add lighter borders

* fix: Add border color on focus of chat input.

* feat: Move Export Conversation to a seperate button (testing)

* fix: Properly center Login, Registration, Reset Password Flow

* fix: Border colors on dark mode for settings modal

* feat: Improve wording for settings menu

* fix: Optimize settings modal for mobile and fix height for modal

* feat: Optimize for desktop

* fix: make TooltipTrigger asChild of button, improve settings mobile responsiveness

* feat: Handle dropdowns properly
TODO: Make height dynamic, fix dark mode colors

* fix: input styles
fix: make endpoint icon smaller

* feat: Update UI to Match ChatGPT Style

- Updated the dropdown styles to match the aesthetic of ChatGPT.
- Decreased spacing within the conversation area for cleanliness.
- Replaced the current archive icon with the ChatGPT's icon.

* fix: fix colors for EditMenuButton & ArchiveButton for dark mode and light mode

* fix: ui fixes

* fix: Fix Conversation UI Bugs

* fix: transparency of HoverToggle to make buttons not visible

* fix: dark mode HoverToggle & compress menu item spacing

* fix: responsiveness of export icon

* fix: first mentionitem is set to always be highlighted

* fix: improve hover state to text instead of bg

* feat: Update icons to ChatGPT Style

* fix: dark mode hover for PanelFileCell

* fix: change navlinks z-index to 100

* fix: hover states for DataTable

* feat: Move ExportButton to seperate component

* chore: remove unused imports
2024-05-09 17:46:16 -04:00
Fuegovic
d73ea8e1f2
🤗 feat: Known Endpoints: HuggingFace (#2646)
* endpoints: huggingface

* Update ai_endpoints.md

* huggingface: update icon
2024-05-09 14:26:47 -04:00
Marco Beretta
83bae9e9d9
🔧 fix: android keyboard @ popover issue (#2647) 2024-05-09 13:31:55 -04:00
Danny Avila
6ba7f60eec
🪙 feat: Configure Max Context and Output Tokens (#2648)
* chore: make frequent 'error' log into 'debug' log

* feat: add maxContextTokens as a conversation field

* refactor(settings): increase popover height

* feat: add DynamicInputNumber and maxContextTokens to all endpoints that support it (frontend), fix schema

* feat: maxContextTokens handling (backend)

* style: revert popover height

* feat: max tokens

* fix: Ollama Vision firebase compatibility

* fix: Ollama Vision, use message_file_map to determine multimodal request

* refactor: bring back MobileNav and improve title styling
2024-05-09 13:27:13 -04:00
Danny Avila
5293b73b6d
🤖 feat(google): Add safety settings configuration (#2644)
* 🤖 feat(google): Add safety settings configuration

- Implement safety settings configuration in GoogleClient.js
- Add safety settings variables in .env.example
- Update documentation to explain safety settings and clarify model usage

* fix(google): Apply safety settings only to Gemini models

Previously, the safety settings were being applied to all models, regardless of whether they were Gemini models or not. This commit ensures that the safety settings are only applied to models that contain the "gemini" string in their name.

The changes include:

- Extracting the model name from `payload.parameters.model`
- Checking if the model name exists and contains the "gemini" string
- Only applying the safety settings if the model name contains "gemini"
- Ignoring the safety settings for non-Gemini models

This fix ensures that the safety settings are only used for the intended Gemini models, and not applied to other models where they may not be applicable.

* Update GoogleClient.js

* fix(google): Apply safety settings only to Gemini models

---------

Co-authored-by: Oliver Faust <oliver@f4ust.de>
2024-05-08 21:32:23 -04:00
Walber Cardoso
b6d1f5fa53
🎨 style: Convo fade effect (#2642)
* style: Improve fade effect into convos

* style: Improve fade effect into convos. WIP code

* 🔧 fix: Convo fade effect

* 🔧 fix: Convo fade effect: removed listeners
2024-05-08 21:21:55 -04:00
Danny Avila
c94278be85
🦙 feat: Ollama Vision Support (#2643)
* refactor: checkVisionRequest, search availableModels for valid vision model instead of using default

* feat: install ollama-js, add typedefs

* feat: Ollama Vision Support

* ci: fix test
2024-05-08 20:24:40 -04:00
Danny Avila
3c5fa40435
📶 fix: Mobile Stylings (#2639)
* chore: remove unused mobile nav

* fix: mobile nav fix for 'more' and 'archive' buttons div

* refactor(useTextarea): rewrite handleKeyUp for backwards compatibility

refactor(useTextarea): rewrite handleKeyUp for backwards compatibility

* experimental: add processing delay to azure streams for better performance/UX

* experiemental: adjust gpt-3 azureDelay

* fix: perplexity titles
2024-05-08 16:40:20 -04:00
Danny Avila
b6d6343f54
📧 feat: Mention "@" Command Popover (#2635)
* feat: initial mockup

* wip: activesetting, may use or not use

* wip: mention with useCombobox usage

* feat: connect textarea to new mention popover

* refactor: consolidate icon logic for Landing/convos

* refactor: cleanup URL logic

* refactor(useTextarea): key up handler

* wip: render desired mention options

* refactor: improve mention detection

* feat: modular chat the default option

* WIP: first pass mention selection

* feat: scroll mention items with keypad

* chore(showMentionPopoverFamily): add typing to atomFamily

* feat: removeAtSymbol

* refactor(useListAssistantsQuery): use defaultOrderQuery as default param

* feat: assistants mentioning

* fix conversation switch errors

* filter mention selections based on startup settings and available endpoints

* fix: mentions model spec icon URL

* style: archive icon

* fix: convo renaming behavior on click

* fix(Convo): toggle hover state

* style: EditMenu refactor

* fix: archive chats table

* fix: errorsToString import

* chore: remove comments

* chore: remove comment

* feat: mention descriptions

* refactor: make sure continue hover button is always last, add correct fork button alt text
2024-05-07 13:13:55 -04:00
Yuichi Ohneda
89b1e33be0
🚀feat: Archive conversations (#2590)
* 🔧chore: add internationalization labels for archive feature

*  feat: Add function to useArchiveConversationMutation()

This commit adds a new mutation function `useArchiveConversationMutation()` for archiving conversations. This function takes the ID string of the conversation to be archived and returns a mutation result object. Upon successful archiving, it removes and refreshes the conversation from the query data cache.
While ChatGPT PATCHes the archived status by sending `{is_archived: true}` to the URL `/backend-api/conversation/$conversation_id`, this implementation uses the `dataService.updateConversation(payload)` with a POST method, aligning with the existing code conventions.

*  feat(api): add is_archived field to Conversation schema and update getConvosByPage method

This commit adds a new field `is_archived` with a default value of false to the Conversation schema. It also modifies the `getConvosByPage` method within the Conversation API to adjust the query to only target conversations where `is_archived` is set to false or where the `is_archived` field does not exist. The function `getConvosQueried`, which returns conversations for a specified Conversation ID, was determined not to require consideration of whether `is_archived` is true or false, and thus was not modified.

* ♻️ refactor: add className prop to DotsIcon component

To enhance the versatility of the DotsIcon component, this commit introduces the ability to specify a className prop, allowing for greater customization.

*  feat(ui): add Edit Button to group Title change and Conversation delete buttons

Added a new Edit Button to the conversations, similar to the ChatGPT UI, which groups options for editing the conversation title and deleting conversations. This grouping is accessible through a dialogue that appears when the three-dot icon is clicked.

* ♻️ refactor(ui): enhance Delete Button to accept className and label options

Enhanced the Delete Button component to accept a `className` for customization and an optional `appendLabel`. The DeleteButton component is used by both `Convo.tsx` and `Conversation.tsx`, but currently only `Convo.tsx` is active and `Conversation.tsx `is apparently not used; removing `Conversation.tsx` may eliminate the need for the `appendLabel` property in the future.

* ♻️ refactor(ui): enhance RenameButton to accept label options

Added the ability to optionally display labels; the Rename Button component is used by both `Convo.tsx` and `Conversation.tsx`, but currently only `Convo.tsx` is active and `Conversation.tsx `is apparently not used; removing `Conversation.tsx` may eliminate the need for the `appendLabel` property in the future.

* 🔧 chors: additional localization labels

* ♻️  refactor: change is_archived property of conversation to camelCase

* Refactor the is_archived property of conversation to camelCase (isArchived) to adhere to the existing code conventions
* Modify the function that retrieves conversations to accept the isArchived parameter

* ♻️ refactor: add archiveConversation mutation

I thought I could divert dataService.updateConversation, but added a new archiveConversation because the request types are different. It might be better to make them common, but to avoid side effects, I added a new function this time.
Added process to deleteConversationMutation to delete archived conversations

*  feat: Add the function to hide a cancel button in DialogTemplate component

The Cancel button is not needed when displaying the archive list, so I made the Cancel button optional.

* ♻️ refactor: Add support for filtering archived conversations in Nav component

This commit modifies the Nav component to add the ability to filter out archived conversations when fetching data. This is done by adding `isArchived: false` to the query parameters for both the `useConversationsInfiniteQuery()` and `useSearchInfiniteQuery()` hooks, effectively excluding any archived conversations from the results returned.

* ♻️ refactor: add Tooltip to DeleteButton

* Add Tooltip to DeleteButton component
* Display Tooltip when DeleteButton only shows an Icon without text

*  feat(ui): add ArchiveButton component for archiving conversations

To be compatible with the ChatGPT UI, no confirmation dialog is displayed when ArchiveButton is clicked. The basic behavior conforms to DeleteButton and RenameButton.

*  feat(ui): add Archive button to list of conversations

Modify the Nav of the conversation list to include a dropdown that contains the Rename and Delete options, similar to the ChatGPT UI. Additionally, an Archive button has been added adjacent to the dropdown menu.

*  feat: Add ArchivedChatsTable component

Adds the `ArchivedChatsTable` component, which displays a table of archived chats. It has been implemented to be as compatible with the ChatGPT UI as possible.

* 🚑 fix(tooltip): increase z-index to ensure visibility over Dialog

Resolve an issue where tooltips were not visible when displayed over a Dialog. The z-index of `DialogPrimitive.Portal` in `Dialog.tsx` is set to 999. Since the rationale for this value is unclear, the z-index of the tooltip has been increased to 1000 to guarantee its visibility above the Dialog component.

* 🔧 chors: add internationalization labels
2024-05-06 23:07:00 -04:00
Marco Beretta
436f7195b5
🌍: Update Italian translation (#2622) 2024-05-06 07:51:01 -04:00
Marco Beretta
2aec4a6250
🔄 refactor: improved RAG animations/messages (#2616)
* fix: warning slow process rag  message

* refactor: improved useProgress hook for Files
2024-05-05 15:35:51 -04:00
Marco Beretta
b77bd19092
🎨 style(Fork): update light/dark theme (#2621) 2024-05-05 15:35:16 -04:00
Danny Avila
446ffe0417
📝 docs: update README.md 2024-05-05 12:51:38 -04:00
Danny Avila
b9bcaee656
📝 docs: update README.md 2024-05-05 12:48:26 -04:00
Danny Avila
110c0535fb
Update README.md 2024-05-05 12:38:17 -04:00
Danny Avila
25fceb78b7
🌿 feat: Fork Messages/Conversations (#2617)
* typedef for ImportBatchBuilder

* feat: first pass, fork conversations

* feat: fork - getMessagesUpToTargetLevel

* fix: additional tests and fix getAllMessagesUpToParent

* chore: arrow function return

* refactor: fork 3 options

* chore: remove unused genbuttons

* chore: remove unused hover buttons code

* feat: fork first pass

* wip: fork remember setting

* style: user icon

* chore: move clear chats to data tab

* WIP: fork UI options

* feat: data-provider fork types/services/vars and use generic MutationOptions

* refactor: use single param for fork option, use enum, fix mongo errors, use Date.now(), add records flag for testing, use endpoint from original convo and messages, pass originalConvo to finishConversation

* feat: add fork mutation hook and consolidate type imports

* refactor: use enum

* feat: first pass, fork mutation

* chore: add enum for target level fork option

* chore: add enum for target level fork option

* show toast when checking remember selection

* feat: splitAtTarget

* feat: split at target option

* feat: navigate to new fork, show toasts, set result query data

* feat: hover info for all fork options

* refactor: add Messages settings tab

* fix(Fork): remember text info

* ci: test for single message and is target edge case

* feat: additional tests for getAllMessagesUpToParent

* ci: additional tests and cycle detection for getMessagesUpToTargetLevel

* feat: circular dependency checks for getAllMessagesUpToParent

* fix: getMessagesUpToTargetLevel circular dep. check

* ci: more tests for getMessagesForConversation

* style: hover text for checkbox fork items

* refactor: add statefulness to conversation import
2024-05-05 11:48:20 -04:00
Danny Avila
c8baceac76
🐛 fix: Prevent Empty File Uploads & Assistants Fixes (#2611)
* chore: update default models for openai/assistants

* fix: allows assistants models fetching

* change default models order, ensure assistant_id is defined if intended

* fix: prevent empty files from being uploaded
2024-05-03 12:49:26 -04:00
Kai Kreuzer
a0288f1c5c
🧾 docs: Fix Typo in librechat.example.yaml (#2606) 2024-05-02 16:27:11 -04:00
Danny Avila
5d3c90be26
📦 chore: update package.json/package-lock.json (#2600)
* 📦 chore: update package.json/package-lock.json

* 📦 chore: remove unused dependencies
2024-05-02 03:23:38 -04:00
Denis Palnitsky
ab6fbe48f1
📥 feat: Import Conversations from LibreChat, ChatGPT, Chatbot UI (#2355)
* Basic implementation of ChatGPT conversation import

* remove debug code

* Handle citations

* Fix updatedAt in import

* update default model

* Use job scheduler to handle import requests

* import job status endpoint

* Add wrapper around Agenda

* Rate limits for import endpoint

* rename import api path

* Batch save import to mongo

* Improve naming

* Add documenting comments

* Test for importers

* Change button for importing conversations

* Frontend changes

* Import job status endpoint

* Import endpoint response

* Add translations to new phrases

* Fix conversations refreshing

* cleanup unused functions

* set timeout for import job status polling

* Add documentation

* get extra spaces back

* Improve error message

* Fix translation files after merge

* fix translation files 2

* Add zh translation for import functionality

* Sync mailisearch index after import

* chore: add dummy uri for jest tests, as MONGO_URI should only be real for E2E tests

* docs: fix links

* docs: fix conversationsImport section

* fix: user role issue for librechat imports

* refactor: import conversations from json
- organize imports
- add additional jsdocs
- use multer with diskStorage to avoid loading file into memory outside of job
- use filepath instead of loading data string for imports
- replace console logs and some logger.info() with logger.debug
- only use multer for import route

* fix: undefined metadata edge case and replace ChatGtp -> ChatGpt

* Refactor importChatGptConvo function to handle undefined metadata edge case and replace ChatGtp with ChatGpt

* fix: chatgpt importer

* feat: maintain tree relationship for librechat messages

* chore: use enum

* refactor: saveMessage to use single object arg, replace console logs, add userId to log message

* chore: additional comment

* chore: multer edge case

* feat: first pass, maintain tree relationship

* chore: organize

* chore: remove log

* ci: add heirarchy test for chatgpt

* ci: test maintaining of heirarchy for librechat

* wip: allow non-text content type messages

* refactor: import content part object json string

* refactor: more content types to format

* chore: consolidate messageText formatting

* docs: update on changes, bump data-provider/config versions, update readme

* refactor(indexSync): singleton pattern for MeiliSearchClient

* refactor: debug log after batch is done

* chore: add back indexSync error handling

---------

Co-authored-by: jakubmieszczak <jakub.mieszczak@zendesk.com>
Co-authored-by: Danny Avila <danny@librechat.ai>
2024-05-02 02:48:26 -04:00
Yuichi Ohneda
3b44741cf9
🚑 fix(dialog): showCloseButton Prop Warning in DialogContent Component (#2597)
Fix DialogPrimitive.Content to not pass a showCloseButton property that does not exist in it to avoid outputting a warning.
2024-05-02 02:08:37 -04:00
Extremys
d21a05606e
🍎 feat: Apple MLX as Known Endpoint (#2580)
* add integration with Apple MLX

* fix: apple icon + image mkd link

---------

Co-authored-by: “Extremys” <“Extremys@email.com”>
Co-authored-by: Danny Avila <danny@librechat.ai>
2024-05-01 03:27:02 -04:00
Danny Avila
0e50c07e3f
🤖 feat: Model Specs & Save Tools per Convo/Preset (#2578)
* WIP: first pass ModelSpecs

* refactor(onSelectEndpoint): use `getConvoSwitchLogic`

* feat: introduce iconURL, greeting, frontend fields for conversations/presets/messages

* feat: conversation.iconURL & greeting in Landing

* feat: conversation.iconURL & greeting in New Chat button

* feat: message.iconURL

* refactor: ConversationIcon -> ConvoIconURL

* WIP: add spec as a conversation field

* refactor: useAppStartup, set spec on initial load for new chat, allow undefined spec, add localStorage keys enum, additional type fields for spec

* feat: handle `showIconInMenu`, `showIconInHeader`, undefined `iconURL` and no specs on initial load

* chore: handle undefined or empty modelSpecs

* WIP: first pass, modelSpec schema for custom config

* refactor: move default filtered tools definition to ToolService

* feat: pass modelSpecs from backend via startupConfig

* refactor: modelSpecs config, return and define list

* fix: react error and include iconURL in responseMessage

* refactor: add iconURL to responseMessage only

* refactor: getIconEndpoint

* refactor: pass TSpecsConfig

* fix(assistants): differentiate compactAssistantSchema, correctly resets shared conversation state with other endpoints

* refactor: assistant id prefix localStorage key

* refactor: add more LocalStorageKeys and replace hardcoded values

* feat: prioritize spec on new chat behavior: last selected modelSpec behavior (localStorage)

* feat: first pass, interface config

* chore: WIP, todo: add warnings based on config.modelSpecs settings.

* feat: enforce modelSpecs if configured

* feat: show config file yaml errors

* chore: delete unused legacy Plugins component

* refactor: set tools to localStorage from recoil store

* chore: add stable recoil setter to useEffect deps

* refactor: save tools to conversation documents

* style(MultiSelectPop): dynamic height, remove unused import

* refactor(react-query): use localstorage keys and pass config to useAvailablePluginsQuery

* feat(utils): add mapPlugins

* refactor(Convo): use conversation.tools if defined, lastSelectedTools if not

* refactor: remove unused legacy code using `useSetOptions`, remove conditional flag `isMultiChat` for using legacy settings

* refactor(PluginStoreDialog): add exhaustive-deps which are stable react state setters

* fix(HeaderOptions): pass `popover` as true

* refactor(useSetStorage): use project enums

* refactor: use LocalStorageKeys enum

* fix: prevent setConversation from setting falsy values in lastSelectedTools

* refactor: use map for availableTools state and available Plugins query

* refactor(updateLastSelectedModel): organize logic better and add note on purpose

* fix(setAgentOption): prevent reseting last model to secondary model for gptPlugins

* refactor(buildDefaultConvo): use enum

* refactor: remove `useSetStorage` and consolidate areas where conversation state is saved to localStorage

* fix: conversations retain tools on refresh

* fix(gptPlugins): prevent nullish tools from being saved

* chore: delete useServerStream

* refactor: move initial plugins logic to useAppStartup

* refactor(MultiSelectDropDown): add more pass-in className props

* feat: use tools in presets

* chore: delete unused usePresetOptions

* refactor: new agentOptions default handling

* chore: note

* feat: add label and custom instructions to agents

* chore: remove 'disabled with tools' message

* style: move plugins to 2nd column in parameters

* fix: TPreset type for agentOptions

* fix: interface controls

* refactor: add interfaceConfig, use Separator within Switcher

* refactor: hide Assistants panel if interface.parameters are disabled

* fix(Header): only modelSpecs if list is greater than 0

* refactor: separate MessageIcon logic from useMessageHelpers for better react rule-following

* fix(AppService): don't use reserved keyword 'interface'

* feat: set existing Icon for custom endpoints through iconURL

* fix(ci): tests passing for App Service

* docs: refactor custom_config.md for readability and better organization, also include missing values

* docs: interface section and re-organize docs

* docs: update modelSpecs info

* chore: remove unused files

* chore: remove unused files

* chore: move useSetIndexOptions

* chore: remove unused file

* chore: move useConversation(s)

* chore: move useDefaultConvo

* chore: move useNavigateToConvo

* refactor: use plugin install hook so it can be used elsewhere

* chore: import order

* update docs

* refactor(OpenAI/Plugins): allow modelLabel as an initial value for chatGptLabel

* chore: remove unused EndpointOptionsPopover and hide 'Save as Preset' button if preset UI visibility disabled

* feat(loadDefaultInterface): issue warnings based on values

* feat: changelog for custom config file

* docs: add additional changelog note

* fix: prevent unavailable tool selection from preset and update availableTools on Plugin installations

* feat: add `filteredTools` option in custom config

* chore: changelog

* fix(MessageIcon): always overwrite conversation.iconURL in messageSettings

* fix(ModelSpecsMenu): icon edge cases

* fix(NewChat): dynamic icon

* fix(PluginsClient): always include endpoint in responseMessage

* fix: always include endpoint and iconURL in responseMessage across different response methods

* feat: interchangeable keys for modelSpec enforcing
2024-04-30 22:11:48 -04:00
Ventz Petkov
a5cac03fa4
🚅 docs: load LiteLLM into LibreChat (#2573)
Documentation was missing one significant component, on loading librechat.yaml
2024-04-29 19:56:19 -04:00
Fuegovic
ba4fa6150e
🦙 docs: fix litellm.md (#2566) 2024-04-28 08:33:51 -04:00
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