mirror of
https://github.com/danny-avila/LibreChat.git
synced 2025-12-17 00:40:14 +01:00
422 commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
Danny Avila
|
458dc9c88e
|
🛡️ feat: Optimize and Improve Anonymity of SharedLinks (#3543)
* ci: add spec for validateImageRequest * chore: install nanoid and run npm audit fix * refactor: optimize and further anonymize shared links data * ci: add SharedLink specs * feat: anonymize asst_id's * ci: tests actually failing, to revisit later * fix: do not anonymize authenticated shared links query * refactor: Update ShareView component styling * refactor: remove nested ternary * refactor: no nested ternaries * fix(ShareView): eslint warnings * fix(eslint): remove nested terns |
||
|
Danny Avila
|
5baa95bd9a
|
🖼️ fix: correct image extraction (#3538)
* fix: regex issue extracting text with images in markdown * fix: update addImages function to include only the first observed image path in the response message * ci: tests for addImages function: correct image extraction * fix(GoogleClient): linting --------- Co-authored-by: Dongwoo Jeong <dongwoo.jeong@lge.com> Co-authored-by: Dongwoo Jeong <dongwoo@duck.com> |
||
|
Oliver Faust
|
433d8f832a
|
🛠️fix: apply safety settings to Gemini API (#3533)
- Introduce getSafetySettings method for centralized safety settings - Apply safety settings uniformly in sendCompletion for all models, including Gemini - Ensure consistent safety settings application in getCompletion - Update .env.example to clarify safety settings usage for both APIs |
||
|
Danny Avila
|
b8a6efa649
|
👷♂️ chore: pass Tavily Response error and revert test commit on userSchema.js (#3496)
* chore: revert test commit * chore: make sure tavily error gets passed |
||
|
Danny Avila
|
422d1a2c91
|
🤖 feat: new Anthropic Default Settings / Increased Output Tokens for 3.5-Sonnet (#3407)
* chore: bump data-provider * feat: Add anthropicSettings to endpointSettings The commit adds the `anthropicSettings` object to the `endpointSettings` in the `schemas.ts` file. This allows for the configuration of settings specific to the `anthropic` model endpoint. * chore: adjust maxoutputtokens localization * feat: Update AnthropicClient to use anthropicSettings for default model options and increased output beta header * ci: new anthropic tests |
||
|
Danny Avila
|
2ad097647c
|
⌚ fix: Wait for Initial Message Save & Correct Latest Message (#3399)
* chore: assistants, unsupported assistant, better logging * chore: remove unnecessary logger in validateAssistant middleware * fix: resolve initial conversation save/promise before saving response * chore: Import and organize dependencies in Speech component * fix: conversation statefulness - Latest Message (at index 0) should not be reset if existing convo - add debugging context for clearAllLatestMessages - Added logging concerning latest Message updates (dev mode only) - update latest message Set logic, also checks for change in conversation Id - consolidated latest message helpers to client/src/utils/messages.ts |
||
|
Danny Avila
|
f6125ccd59
|
🌿 fix: Message Route Improvements pt. 2 (#3379)
* fix: edge case with debugTraverse function in parsers.js * chore: Update error message in audio stream processing * refactor: Add ONE_MINUTE and THIRTY_SECONDS options to Time enum * fix: logging |
||
|
Danny Avila
|
5d40d0a37a
|
⚙️ feat: Adjust Rate of Stream Progress (#3244)
* chore: bump data-provider and add MESSAGES CacheKey * refactor: avoid saving messages while streaming, save partial text to cache instead * fix(ci): processChunks * chore: logging aborted request to debug * feat: set stream rate for token processing * chore: specify default stream rate * fix(ci): Update AppService.js to use optional chaining for endpointLocals assignment * refactor: abstract the error handler * feat: streamRate for assistants; refactor: update default rate for token * refactor: update error handling in assistants/errors.js * refactor: update error handling in assistants/errors.js |
||
|
Danny Avila
|
d5d188eebf
|
🔐 fix: Enhance Message & Image Access Security (#3363)
* chore: slight refactor * fix: prevent message updates unless explicitly owned * refactor: rethrow errors, update deleteMessagesSince (not used), add basic tests * fix: Add path normalization and validation to image request middleware * fix: image validation path security |
||
|
Marco Beretta
|
1aad315de6
|
🎤 feat: add custom speech config, browser TTS/STT features, and dynamic speech tab settings (#2921)
* feat: update useTextToSpeech and useSpeechToText hooks to support external audio endpoints This commit updates the useTextToSpeech and useSpeechToText hooks in the Input directory to support external audio endpoints. It introduces the useGetExternalTextToSpeech and useGetExternalSpeechToText hooks, which determine whether the audio endpoints should be set to 'browser' or 'external' based on the value of the endpointTTS and endpointSTT Recoil states. The useTextToSpeech and useSpeechToText hooks now use these new hooks to determine whether to use external audio endpoints * feat: add userSelect style to ConversationModeSwitch label * fix: remove unused updateTokenWebsocket function and import The updateTokenWebsocket function and its import are no longer used in the OpenAIClient module. This commit removes the function and import to clean up the codebase * feat: support external audio endpoints in useTextToSpeech and useSpeechToText hooks This commit updates the useTextToSpeech and useSpeechToText hooks in the Input directory to support external audio endpoints. It introduces the useGetExternalTextToSpeech and useGetExternalSpeechToText hooks, which determine whether the audio endpoints should be set to 'browser' or 'external' based on the value of the endpointTTS and endpointSTT Recoil states. The useTextToSpeech and useSpeechToText hooks now use these new hooks to determine whether to use external audio endpoints * feat: update AutomaticPlayback component to AutomaticPlaybackSwitch; tests: added AutomaticPlaybackSwitch.spec > > This commit renames the AutomaticPlayback component to AutomaticPlaybackSwitch in the Speech directory. The new name better reflects the purpose of the component and aligns with the naming convention used in the codebase. * feat: update useSpeechToText hook to include interimTranscript This commit updates the useSpeechToText hook in the client/src/components/Chat/Input/AudioRecorder.tsx file to include the interimTranscript state. This allows for real-time display of the speech-to-text transcription while the user is still speaking. The interimTranscript is now used to update the text area value during recording. * feat: Add customConfigSpeech API endpoint for retrieving custom speech configuration This commit adds a new API endpoint in the file under the directory. This endpoint is responsible for retrieving the custom speech configuration using the function from the module * feat: update store var and ; fix: getCustomConfigSpeech * fix: client tests, removed unused import * feat: Update useCustomConfigSpeechQuery to return an array of custom speech configurations This commit modifies the useCustomConfigSpeechQuery function in the client/src/data-provider/queries.ts file to return an array of custom speech configurations instead of a single object. This change allows for better handling and manipulation of the data in the application * feat: Update useCustomConfigSpeechQuery to return an array of custom speech configurations * refactor: Update variable name in speechTab schema * refactor: removed unused and nested code * fix: using recoilState * refactor: Update Speech component to use useCallback for setting settings * fix: test * fix: tests * feature: ensure that the settings don't change after modifying then through the UI * remove comment * fix: Handle error gracefully in getCustomConfigSpeech and getVoices endpoints * fix: Handle error * fix: backend tests * fix: invalid custom config logging * chore: add back custom config info logging * chore: revert loadCustomConfig spec --------- Co-authored-by: Danny Avila <danny@librechat.ai> |
||
|
Danny Avila
|
5d985746cb
|
🛠️ fix: Tool Filtering in PluginsClient (#3266)
* feat(plugins): implement tool filtering in PluginsClient Add functionality to filter tools based on filteredTools and includedTools arrays in the request's app locals. This allows for dynamic tool selection on a per-request basis, enhancing the flexibility of the plugin system. * test(plugins): add unit tests for tool filtering in PluginsClient Introduce comprehensive test suite for the new tool filtering feature in PluginsClient. Cover scenarios including filtering out tools, including specific tools, prioritization of includedTools over filteredTools, and behavior when no filters are provided. * chore: Remove unused legacy Conversation component and update imports |
||
|
Danny Avila
|
a2fd975cd5
|
🚤 refactor: Optimize Request Lifecycle Speeds (#3222)
* refactor: optimize backend operations for client requests * fix: message styling * refactor: Improve handleKeyUp logic in StreamRunManager.js and handleText.js * refactor: Improve handleKeyUp logic in StreamRunManager.js and handleText.js * fix: clear new convo messages on clear all convos * fix: forgot to pass userId to getConvo * refactor: update getPartialText to send basePayload.text |
||
|
Danny Avila
|
156c52e293
|
🌿 feat: Multi-response Streaming (#3191)
* chore: comment back handlePlusCommand * chore: ignore .git dir * refactor: pass newConversation to `useSelectMention` refactor: pass newConversation to Mention component refactor: useChatFunctions for modular use of `ask` and `regenerate` refactor: set latest message only for the first index in useChatFunctions refactor: pass setLatestMessage to useChatFunctions refactor: Pass setSubmission to useChatFunctions for submission handling refactor: consolidate event handlers to separate hook from useSSE WIP: additional response handlers feat: responsive added convo, clears on new chat/navigating to chat, assistants excluded feat: Add conversationByKeySelector to select any conversation by index WIP: handle second submission with messages paired to root * style: surface-primary-contrast * refactor: remove unnecessary console.log statement in useChatFunctions * refactor: Consolidate imports in ChatForm and Input hooks * refactor: compositional usage of useSSE for multiple streams * WIP: set latest 'multi' message * WIP: first pass, added response streaming * pass: performant multi-message stream * fix: styling and message render * second pass: modular, performant multi-stream * fix: align parentMessageId of multiMessage * refactor: move resetting latestMultiMessage * chore: update footer text in Chat component * fix: stop button styling * fix: handle abortMessage request for multi-response * clear messages but bug with latest message reset present * fix: add delay for additional message generation * fix: access LAST_CONVO_SETUP by index * style: add div to prevent layout shift before hover buttons render * chore: Update Message component styling for card messages * chore: move hook use order * fix: abort middleware using unsent field from req.body * feat: support multi-response stream from initial message * refactor: buildTree function to improve readability and remove unused code * feat: add logger for frontend dev * refactor: use depth to track if message is really last in its branch * fix(buildTree): default export * fix: share parent message Id and avoid duplication error for multi-response streams * fix: prevent addedConvo reset to response convo * feat: allow setting multi message as latest message to control which to respond to * chore: wrap setSiblingIdxRev with useCallback * chore: styling and allow editing messages * style: styling fixes * feat: Add "AddMultiConvo" component to Chat Header * feat: prevent clearing added convos on endpoint, preset, mention, or modelSpec switch * fix: message styling fixes, mainly related to code blocks * fix: stop button visibility logic * fix: Handle edge case in abortMiddleware for non-existant `abortControllers` * refactor: optimize/memoize icons * chore(GoogleClient): change info to debug logs * style: active message styling * style: prevent layout shift due to placeholder row * chore: remove unused code * fix: Update BaseClient to handle optional request body properties * fix(ci): `onStart` now accepts 2 args, the 2nd being responseMessageId * chore: bump data-provider |
||
|
berat reha sönmez
|
e2867eecc9
|
🧹 chore: clean commented code (#3160) | ||
|
Matthew Unrath
|
b5081bfe86
|
🤖 feat: Add titling to Google client (#2983)
* feat: Add titling to Google client * feat: Add titling to Google client * PR feedback changes |
||
|
Danny Avila
|
0294cfc881
|
✨ v0.7.3 (#3067)
* refactor: revert BaseClient to use node-fetch instead of undici * chore: bump version * chore: update npm dependencies to latest versions * chore: fix custom footer |
||
|
Danny Avila
|
4416f69a9b
|
🚀 refactor: Use Undici Instead of Node-Fetch, prevent Event Close, add Index (#3052)
* feat: Add index to conversationId field in messageSchema * refactor: prevent immediate event close on error * refactor: use undici instead of node-fetch in non-Bun environment |
||
|
Danny Avila
|
084cf266a2
|
🗃️ fix: revise RAG prompt (#3006) | ||
|
Danny Avila
|
08d6bea359
|
🛠️ refactor: Improve Logging and Error Handling in ToolService and useSSE (#2922)
* refactor(ToolService): streamline logging and tool error handling, also ensure generated outputs always have `output` field * refactor(useSSE): error message for server connection issue * refactor: add back capture group of sensitive information.js * hotfix: cohere chinese character unicode issue, return aggregated reply |
||
|
Danny Avila
|
40685f6eb4
|
🚀 refactor: Enhance Custom Endpoints, Message Logic, and Payload Handling (#2895)
* chore: use node-fetch for OpenAIClient fetch key for non-crashing usage of AbortController in Bun runtime * chore: variable order * fix(useSSE): prevent finalHandler call in abortConversation to update messages/conversation after user navigated away * chore: params order * refactor: organize intermediate message logic and ensure correct variables are passed * fix: Add stt and tts routes before upload limiters, prevent bans * fix(abortRun): temp fix to delete unfinished messages to avoid message thread parent relationship issues * refactor: Update AnthropicClient to use node-fetch for fetch key and add proxy support * fix(gptPlugins): ensure parentMessageId/messageId relationship is maintained * feat(BaseClient): custom fetch function to analyze/edit payloads just before sending (also prevents abortController crash on Bun runtime) * feat: `directEndpoint` and `titleMessageRole` custom endpoint options * chore: Bump version to 0.6.6 in data-provider package.json |
||
|
Danny Avila
|
2b7a973a33
|
😎 fix: Azure Bug, short default max_tokens response using gpt-4-vision-preview (#2885)
|
||
|
nidasfly
|
795bb9c568
|
🌏 refactor: Improve Title Prompt for Multilingual Titles (#2832) | ||
|
Danny Avila
|
b3e03b75d0
|
🔉 feat: Speech-to-text / Text-to-speech (initial support) (#2836)
* Update TextChat.jsx * Update SubmitButton.jsx * Update TextChat.jsx * Update SubmitButton.jsx * Create ListeningIcon.tsx * Update index.ts * Update SubmitButton.jsx * Update TextChat.jsx * Update ListeningIcon.tsx * Update ListeningIcon.tsx * Create SpeechRecognition.tsx * Update TextChat.jsx * Update TextChat.jsx * Update SpeechRecognition.tsx * Update TextChat.jsx * Update SpeechRecognition.tsx * Update SpeechRecognition.tsx * Update SpeechRecognition.tsx * Update SpeechRecognition.tsx * Update SubmitButton.jsx * Update TextChat.jsx * Update SpeechRecognition.tsx * Create SpeechSynthesis.tsx * Update index.jsx * Update SpeechSynthesis.tsx * Update SpeechRecognition.tsx * Update TextChat.jsx * Update SpeechRecognition.tsx * Update SpeechRecognition.tsx * Update SpeechRecognition.tsx * Update TextChat.jsx * Squashed commit of the following: commit |
||
|
Danny Avila
|
f00a8f87f7
|
🔧 fix(StableDiffusion): Temporarily Remove sampler_index (#2815)
|
||
|
Danny Avila
|
1a452121fa
|
🤖 feat: OpenAI Assistants v2 (initial support) (#2781)
* 🤖 Assistants V2 Support: Part 1 - Separated Azure Assistants to its own endpoint - File Search / Vector Store integration is incomplete, but can toggle and use storage from playground - Code Interpreter resource files can be added but not deleted - GPT-4o is supported - Many improvements to the Assistants Endpoint overall data-provider v2 changes copy existing route as v1 chore: rename new endpoint to reduce comparison operations and add new azure filesource api: add azureAssistants part 1 force use of version for assistants/assistantsAzure chore: switch name back to azureAssistants refactor type version: string | number Ensure assistants endpoints have version set fix: isArchived type issue in ConversationListParams refactor: update assistants mutations/queries with endpoint/version definitions, update Assistants Map structure chore: FilePreview component ExtendedFile type assertion feat: isAssistantsEndpoint helper chore: remove unused useGenerations chore(buildTree): type issue chore(Advanced): type issue (unused component, maybe in future) first pass for multi-assistant endpoint rewrite fix(listAssistants): pass params correctly feat: list separate assistants by endpoint fix(useTextarea): access assistantMap correctly fix: assistant endpoint switching, resetting ID fix: broken during rewrite, selecting assistant mention fix: set/invalidate assistants endpoint query data correctly feat: Fix issue with assistant ID not being reset correctly getOpenAIClient helper function feat: add toast for assistant deletion fix: assistants delete right after create issue for azure fix: assistant patching refactor: actions to use getOpenAIClient refactor: consolidate logic into helpers file fix: issue where conversation data was not initially available v1 chat support refactor(spendTokens): only early return if completionTokens isNaN fix(OpenAIClient): ensure spendTokens has all necessary params refactor: route/controller logic fix(assistants/initializeClient): use defaultHeaders field fix: sanitize default operation id chore: bump openai package first pass v2 action service feat: retroactive domain parsing for actions added via v1 feat: delete db records of actions/assistants on openai assistant deletion chore: remove vision tools from v2 assistants feat: v2 upload and delete assistant vision images WIP first pass, thread attachments fix: show assistant vision files (save local/firebase copy) v2 image continue fix: annotations fix: refine annotations show analyze as error if is no longer submitting before progress reaches 1 and show file_search as retrieval tool fix: abort run, undefined endpoint issue refactor: consolidate capabilities logic and anticipate versioning frontend version 2 changes fix: query selection and filter add endpoint to unknown filepath add file ids to resource, deleting in progress enable/disable file search remove version log * 🤖 Assistants V2 Support: Part 2 🎹 fix: Autocompletion Chrome Bug on Action API Key Input chore: remove `useOriginNavigate` chore: set correct OpenAI Storage Source fix: azure file deletions, instantiate clients by source for deletion update code interpret files info feat: deleteResourceFileId chore: increase poll interval as azure easily rate limits fix: openai file deletions, TODO: evaluate rejected deletion settled promises to determine which to delete from db records file source icons update table file filters chore: file search info and versioning fix: retrieval update with necessary tool_resources if specified fix(useMentions): add optional chaining in case listMap value is undefined fix: force assistant avatar roundedness fix: azure assistants, check correct flag chore: bump data-provider * fix: merge conflict * ci: fix backend tests due to new updates * chore: update .env.example * meilisearch improvements * localization updates * chore: update comparisons * feat: add additional metadata: endpoint, author ID * chore: azureAssistants ENDPOINTS exclusion warning |
||
|
Danny Avila
|
fc9368e0e7
|
⚡ feat: Gemini-1.5 Flash, gpt-4o imports, modelSpec greeting fix (#2729)
* fix: Gemini Flash stream fix * fix: correct `sender` field for gpt-4o imports from ChatGPT * add flash model examples and fix vertex streaming * style: modelSpec greeting fix |
||
|
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 |
||
|
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 |
||
|
Danny Avila
|
98c96cd020
|
🦙 fix: Ollama System Message order (#2655) | ||
|
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 |
||
|
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>
|
||
|
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 |
||
|
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 |
||
|
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 |
||
|
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 |
||
|
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 |
||
|
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 |
||
|
Passerby1011
|
6db91978ca
|
🎨 style: update CodeSherpa icon (#2417)
The icon address error leads to the icon not displaying. |
||
|
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 |
||
|
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 |
||
|
Danny Avila
|
6f0eb35365
|
🐞 fix: Balance and Token Usage Improvements (#2350)
* fix(processModelData): handle `openrouter/auto` edge case * fix(Tx.create): prevent negative multiplier edge case and prevent balance from becoming negative * fix(NavLinks): render 0 balance properly * refactor(NavLinks): show only up to 2 decimal places for balance * fix(OpenAIClient/titleConvo): fix cohere condition and record token usage for `this.options.titleMethod === 'completion'` |
||
|
Danny Avila
|
fb80af05be
|
🧠 fix(Cohere): map to expected SDK params (#2329) | ||
|
Danny Avila
|
cd7f3a51e1
|
🧠 feat: Cohere support as Custom Endpoint (#2328)
* chore: bump cohere-ai, fix firebase vulnerabilities by going down versions * feat: cohere rates and context windows * feat(createCoherePayload): transform openai payload for cohere compatibility * feat: cohere backend support * refactor(UnknownIcon): optimize icon render and add cohere * docs: add cohere to Compatible AI Endpoints * Update ai_endpoints.md |
||
|
bsu3338
|
038063d4d1
|
🐞Fix: Stable Diffusion User Directory (#2270) | ||
|
Danny Avila
|
bb8a40dd98
|
🎨 fix: Optimize StableDiffusion API Tool and Fix for Assistants Usage (#2253)
* chore: update docs * fix(StableDiffusion): optimize API responses and file handling, return expected metadata for Assistants endpoint |
||
|
Danny Avila
|
a00756c469
|
⬇️ feat: Assistant File Downloads (#2234)
* WIP: basic route for file downloads and file strategy for generating readablestream to pipe as res * chore(DALLE3): add typing for OpenAI client * chore: add `CONSOLE_JSON` notes to dotenv.md * WIP: first pass OpenAI Assistants File Output handling * feat: first pass assistants output file download from openai * chore: yml vs. yaml variation to .gitignore for `librechat.yml` * refactor(retrieveAndProcessFile): remove redundancies * fix(syncMessages): explicit sort of apiMessages to fix message order on abort * chore: add logs for warnings and errors, show toast on frontend * chore: add logger where console was still being used |
||
|
Danny Avila
|
798e8763d0
|
👓 feat: Vision Support for Assistants (#2195)
* refactor(assistants/chat): use promises to speed up initialization, initialize shared variables, include `attachedFileIds` to streamRunManager * chore: additional typedefs * fix(OpenAIClient): handle edge case where attachments promise is resolved * feat: createVisionPrompt * feat: Vision Support for Assistants |
||
|
Danny Avila
|
1f0fb497f8
|
🎉 feat: Optimizations and Anthropic Title Generation (#2184)
* feat: add claude-3-haiku-20240307 to default anthropic list * refactor: optimize `saveMessage` calls mid-stream via throttling * chore: remove addMetadata operations and consolidate in BaseClient * fix(listAssistantsForAzure): attempt to specify correct model mapping as accurately as possible (#2177) * refactor(client): update last conversation setup with current assistant model, call newConvo again when assistants load to allow fast initial load and ensure assistant model is always the default, not the last selected model * refactor(cache): explicitly add TTL of 2 minutes when setting titleCache and add default TTL of 10 minutes to abortKeys cache * feat(AnthropicClient): conversation titling using Anthropic Function Calling * chore: remove extraneous token usage logging * fix(convos): unhandled edge case for conversation grouping (undefined conversation) * style: Improved style of Search Bar after recent UI update * chore: remove unused code, content part helpers * feat: always show code option |
||
|
Danny Avila
|
45a95acec2
|
📂 feat: RAG Improvements (#2169)
* feat: new vector file processing strategy * chore: remove unused client files * chore: remove more unused client files * chore: remove more unused client files and move used to new dir * chore(DataIcon): add className * WIP: Model Endpoint Settings Update, draft additional context settings * feat: improve parsing for augmented prompt, add full context option * chore: remove volume mounting from rag.yml as no longer necessary |
||
|
Danny Avila
|
f7761df52c
|
🗃️ feat: General File Support for OpenAI, Azure, Custom, Anthropic and Google (RAG) (#2143)
* refactor: re-purpose `resendImages` as `resendFiles` * refactor: re-purpose `resendImages` as `resendFiles` * feat: upload general files * feat: embed file during upload * feat: delete file embeddings on file deletion * chore(fileConfig): add epub+zip type * feat(encodeAndFormat): handle non-image files * feat(createContextHandlers): build context prompt from file attachments and successful RAG * fix: prevent non-temp files as well as embedded files to be deleted on new conversation * fix: remove temp_file_id on usage, prevent non-temp files as well as embedded files to be deleted on new conversation * fix: prevent non-temp files as well as embedded files to be deleted on new conversation * feat(OpenAI/Anthropic/Google): basic RAG support * fix: delete `resendFiles` only when true (Default) * refactor(RAG): update endpoints and pass JWT * fix(resendFiles): default values * fix(context/processFile): query unique ids only * feat: rag-api.yaml * feat: file upload improved ux for longer uploads * chore: await embed call and catch embedding errors * refactor: store augmentedPrompt in Client * refactor(processFileUpload): throw error if not assistant file upload * fix(useFileHandling): handle markdown empty mimetype issue * chore: necessary compose file changes |