merge from upstream 20240515

.env.example

@@ -2,11 +2,9 @@
 #                       LibreChat Configuration                       #
 #=====================================================================#
 # Please refer to the reference documentation for assistance          #
-# with configuring your LibreChat environment. The guide is           #
-# available both online and within your local LibreChat               #
-# directory:                                                          #
-# Online: https://docs.librechat.ai/install/configuration/dotenv.html #
-# Locally: ./docs/install/configuration/dotenv.md                     #
+# with configuring your LibreChat environment.                        #
+#                                                                     #
+# https://www.librechat.ai/docs/configuration/dotenv                  #
 #=====================================================================#
 
 #==================================================#
@@ -62,7 +60,7 @@ PROXY=
 #===================================#
 # Known Endpoints - librechat.yaml  #
 #===================================#
-# https://docs.librechat.ai/install/configuration/ai_endpoints.html
+# https://www.librechat.ai/docs/configuration/librechat_yaml/ai_endpoints
 
 # ANYSCALE_API_KEY=
 # APIPIE_API_KEY=
@@ -118,10 +116,10 @@ GOOGLE_KEY=user_provided
 # GOOGLE_REVERSE_PROXY=
 
 # Gemini API
-# GOOGLE_MODELS=gemini-1.0-pro,gemini-1.0-pro-001,gemini-1.0-pro-latest,gemini-1.0-pro-vision-latest,gemini-1.5-pro-latest,gemini-pro,gemini-pro-vision
+# GOOGLE_MODELS=gemini-1.5-flash-latest,gemini-1.0-pro,gemini-1.0-pro-001,gemini-1.0-pro-latest,gemini-1.0-pro-vision-latest,gemini-1.5-pro-latest,gemini-pro,gemini-pro-vision
 
 # Vertex AI
-# GOOGLE_MODELS=gemini-1.5-pro-preview-0409,gemini-1.0-pro-vision-001,gemini-pro,gemini-pro-vision,chat-bison,chat-bison-32k,codechat-bison,codechat-bison-32k,text-bison,text-bison-32k,text-unicorn,code-gecko,code-bison,code-bison-32k
+# GOOGLE_MODELS=gemini-1.5-flash-preview-0514,gemini-1.5-pro-preview-0409,gemini-1.0-pro-vision-001,gemini-pro,gemini-pro-vision,chat-bison,chat-bison-32k,codechat-bison,codechat-bison-32k,text-bison,text-bison-32k,text-unicorn,code-gecko,code-bison,code-bison-32k
 
 # Google Gemini Safety Settings
 # NOTE (Vertex AI): You do not have access to the BLOCK_NONE setting by default.
@@ -142,7 +140,7 @@ GOOGLE_KEY=user_provided
 #============#
 
 OPENAI_API_KEY=user_provided
-# OPENAI_MODELS=gpt-3.5-turbo-0125,gpt-3.5-turbo-0301,gpt-3.5-turbo,gpt-4,gpt-4-0613,gpt-4-vision-preview,gpt-3.5-turbo-0613,gpt-3.5-turbo-16k-0613,gpt-4-0125-preview,gpt-4-turbo-preview,gpt-4-1106-preview,gpt-3.5-turbo-1106,gpt-3.5-turbo-instruct,gpt-3.5-turbo-instruct-0914,gpt-3.5-turbo-16k
+# OPENAI_MODELS=gpt-4o,gpt-3.5-turbo-0125,gpt-3.5-turbo-0301,gpt-3.5-turbo,gpt-4,gpt-4-0613,gpt-4-vision-preview,gpt-3.5-turbo-0613,gpt-3.5-turbo-16k-0613,gpt-4-0125-preview,gpt-4-turbo-preview,gpt-4-1106-preview,gpt-3.5-turbo-1106,gpt-3.5-turbo-instruct,gpt-3.5-turbo-instruct-0914,gpt-3.5-turbo-16k
 
 DEBUG_OPENAI=false
 
@@ -164,7 +162,7 @@ DEBUG_OPENAI=false
 
 ASSISTANTS_API_KEY=user_provided
 # ASSISTANTS_BASE_URL=
-# ASSISTANTS_MODELS=gpt-3.5-turbo-0125,gpt-3.5-turbo-16k-0613,gpt-3.5-turbo-16k,gpt-3.5-turbo,gpt-4,gpt-4-0314,gpt-4-32k-0314,gpt-4-0613,gpt-3.5-turbo-0613,gpt-3.5-turbo-1106,gpt-4-0125-preview,gpt-4-turbo-preview,gpt-4-1106-preview
+# ASSISTANTS_MODELS=gpt-4o,gpt-3.5-turbo-0125,gpt-3.5-turbo-16k-0613,gpt-3.5-turbo-16k,gpt-3.5-turbo,gpt-4,gpt-4-0314,gpt-4-32k-0314,gpt-4-0613,gpt-3.5-turbo-0613,gpt-3.5-turbo-1106,gpt-4-0125-preview,gpt-4-turbo-preview,gpt-4-1106-preview
 
 #============#
 # OpenRouter #
@@ -176,7 +174,7 @@ ASSISTANTS_API_KEY=user_provided
 # Plugins    #
 #============#
 
-# PLUGIN_MODELS=gpt-4,gpt-4-turbo-preview,gpt-4-0125-preview,gpt-4-1106-preview,gpt-4-0613,gpt-3.5-turbo,gpt-3.5-turbo-0125,gpt-3.5-turbo-1106,gpt-3.5-turbo-0613
+# PLUGIN_MODELS=gpt-4o,gpt-4,gpt-4-turbo-preview,gpt-4-0125-preview,gpt-4-1106-preview,gpt-4-0613,gpt-3.5-turbo,gpt-3.5-turbo-0125,gpt-3.5-turbo-1106,gpt-3.5-turbo-0613
 
 DEBUG_PLUGINS=true
 

.github/ISSUE_TEMPLATE/FEATURE-REQUEST.yml

@@ -43,7 +43,7 @@ body:
     id: terms
     attributes:
       label: Code of Conduct
-      description: By submitting this issue, you agree to follow our [Code of Conduct](https://github.com/danny-avila/LibreChat/blob/main/CODE_OF_CONDUCT.md)
+      description: By submitting this issue, you agree to follow our [Code of Conduct](https://github.com/danny-avila/LibreChat/blob/main/.github/CODE_OF_CONDUCT.md)
       options:
         - label: I agree to follow this project's Code of Conduct
           required: true

.github/ISSUE_TEMPLATE/QUESTION.yml

@@ -44,7 +44,7 @@ body:
     id: terms
     attributes:
       label: Code of Conduct
-      description: By submitting this issue, you agree to follow our [Code of Conduct](https://github.com/danny-avila/LibreChat/blob/main/CODE_OF_CONDUCT.md)
+      description: By submitting this issue, you agree to follow our [Code of Conduct](https://github.com/danny-avila/LibreChat/blob/main/.github/CODE_OF_CONDUCT.md)
       options:
         - label: I agree to follow this project's Code of Conduct
           required: true

.github/pull_request_template.md

@@ -1,7 +1,10 @@
 # Pull Request Template
 
+⚠️ Before Submitting a PR, Please Review:
+- Please ensure that you have thoroughly read and understood the [Contributing Docs](https://github.com/danny-avila/LibreChat/blob/main/.github/CONTRIBUTING.md) before submitting your Pull Request.
 
-### ⚠️ Before Submitting a PR, read the [Contributing Docs](https://github.com/danny-avila/LibreChat/blob/main/.github/CONTRIBUTING.md) in full!
+⚠️ Documentation Updates Notice:
+- Kindly note that documentation updates are managed in this repository: [librechat.ai](https://github.com/LibreChat-AI/librechat.ai)
 
 ## Summary
 
@@ -16,8 +19,6 @@ Please delete any irrelevant options.
 - [ ] Breaking change (fix or feature that would cause existing functionality to not work as expected)
 - [ ] This change requires a documentation update
 - [ ] Translation update
-- [ ] Documentation update
-
 
 ## Testing
 
@@ -37,4 +38,4 @@ Please delete any irrelevant options.
 - [ ] I have written tests demonstrating that my changes are effective or that my feature works
 - [ ] Local unit tests pass with my changes
 - [ ] Any changes dependent on mine have been merged and published in downstream modules.
-- [ ] New documents have been locally validated with mkdocs
+- [ ] A pull request for updating the documentation has been submitted.

Dockerfile

@@ -1,10 +1,8 @@
 # v0.7.2
 
 # Base node image
-FROM node:18-alpine3.18 AS node
+FROM node:20-alpine AS node
 
-RUN apk add g++ make py3-pip
-RUN npm install -g node-gyp
 RUN apk --no-cache add curl
 
 RUN mkdir -p /app && chown node:node /app
@@ -14,20 +12,20 @@ USER node
 
 COPY --chown=node:node . .
 
-# Allow mounting of these files, which have no default
-# values.
-RUN touch .env
-RUN npm config set fetch-retry-maxtimeout 600000
-RUN npm config set fetch-retries 5
-RUN npm config set fetch-retry-mintimeout 15000
-RUN npm install --no-audit
+RUN \
+    # Allow mounting of these files, which have no default
+    touch .env ; \
+    # Create directories for the volumes to inherit the correct permissions
+    mkdir -p /app/client/public/images /app/api/logs ; \
+    npm config set fetch-retry-maxtimeout 600000 ; \
+    npm config set fetch-retries 5 ; \
+    npm config set fetch-retry-mintimeout 15000 ; \
+    npm install --no-audit; \
+    # React client build
+    NODE_OPTIONS="--max-old-space-size=2048" npm run frontend; \
+    npm prune --production; \
+    npm cache clean --force
 
-# React client build
-ENV NODE_OPTIONS="--max-old-space-size=2048"
-RUN npm run frontend
-
-# Create directories for the volumes to inherit
-# the correct permissions
 RUN mkdir -p /app/client/public/images /app/api/logs
 
 # Node API setup

Dockerfile.multi

@@ -7,32 +7,31 @@ FROM node:20-alpine AS base
 FROM base AS data-provider-build
 WORKDIR /app/packages/data-provider
 COPY ./packages/data-provider ./
-RUN npm install
+RUN npm install; npm cache clean --force
 RUN npm run build
+RUN npm prune --production
 
 # React client build
-FROM data-provider-build AS client-build
+FROM base AS client-build
 WORKDIR /app/client
 COPY ./client/package*.json ./
 # Copy data-provider to client's node_modules
-RUN mkdir -p /app/client/node_modules/librechat-data-provider/
-RUN cp -R /app/packages/data-provider/* /app/client/node_modules/librechat-data-provider/
-RUN npm install
+COPY --from=data-provider-build /app/packages/data-provider/ /app/client/node_modules/librechat-data-provider/
+RUN npm install; npm cache clean --force
 COPY ./client/ ./
 ENV NODE_OPTIONS="--max-old-space-size=2048"
 RUN npm run build
 
 # Node API setup
-FROM data-provider-build AS api-build
+FROM base AS api-build
 WORKDIR /app/api
 COPY api/package*.json ./
 COPY api/ ./
 # Copy helper scripts
 COPY config/ ./
 # Copy data-provider to API's node_modules
-RUN mkdir -p /app/api/node_modules/librechat-data-provider/
-RUN cp -R /app/packages/data-provider/* /app/api/node_modules/librechat-data-provider/
-RUN npm install
+COPY --from=data-provider-build /app/packages/data-provider/ /app/api/node_modules/librechat-data-provider/
+RUN npm install --include prod; npm cache clean --force
 COPY --from=client-build /app/client/dist /app/client/dist
 EXPOSE 3080
 ENV HOST=0.0.0.0

README.md

@@ -1,6 +1,6 @@
 <p align="center">
   <a href="https://librechat.ai">
-    <img src="docs/assets/LibreChat.svg" height="256">
+    <img src="client/public/assets/logo.svg" height="256">
   </a>
   <h1 align="center">
     <a href="https://librechat.ai">LibreChat</a>
@@ -43,14 +43,14 @@
 - 🖥️ UI matching ChatGPT, including Dark mode, Streaming, and latest updates
 - 🤖 AI model selection:
   - OpenAI, Azure OpenAI, BingAI, ChatGPT, Google Vertex AI, Anthropic (Claude), Plugins, Assistants API (including Azure Assistants)
-- ✅ Compatible across both **[Remote & Local AI services](https://docs.librechat.ai/install/configuration/ai_endpoints.html#intro):**
+- ✅ Compatible across both **[Remote & Local AI services](https://www.librechat.ai/docs/configuration/librechat_yaml/ai_endpoints):**
   - groq, Ollama, Cohere, Mistral AI, Apple MLX, koboldcpp, OpenRouter, together.ai, Perplexity, ShuttleAI, and more
 - 💾 Create, Save, & Share Custom Presets
 - 🔀 Switch between AI Endpoints and Presets, mid-chat
 - 🔄 Edit, Resubmit, and Continue Messages with Conversation branching
 - 🌿 Fork Messages & Conversations for Advanced Context control
 - 💬 Multimodal Chat:
-    - Upload and analyze images with Claude 3, GPT-4, and Gemini Vision 📸
+    - Upload and analyze images with Claude 3, GPT-4 (including `gpt-4o`), and Gemini Vision 📸
     - Chat with Files using Custom Endpoints, OpenAI, Azure, Anthropic, & Google. 🗃️
     - Advanced Agents with Files, Code Interpreter, Tools, and API Actions 🔦
       - Available through the [OpenAI Assistants API](https://platform.openai.com/docs/assistants/overview) 🌤️
@@ -69,56 +69,56 @@
 - 📖 Completely Open-Source & Built in Public
 - 🧑‍🤝‍🧑 Community-driven development, support, and feedback
 
-[For a thorough review of our features, see our docs here](https://docs.librechat.ai/features/plugins/introduction.html) 📚
+[For a thorough review of our features, see our docs here](https://docs.librechat.ai/) 📚
 
 ## 🪶 All-In-One AI Conversations with LibreChat
 
 LibreChat brings together the future of assistant AIs with the revolutionary technology of OpenAI's ChatGPT. Celebrating the original styling, LibreChat gives you the ability to integrate multiple AI models. It also integrates and enhances original client features such as conversation and message search, prompt templates and plugins.
 
 With LibreChat, you no longer need to opt for ChatGPT Plus and can instead use free or pay-per-call APIs. We welcome contributions, cloning, and forking to enhance the capabilities of this advanced chatbot platform.
 
-<!-- https://github.com/danny-avila/LibreChat/assets/110412045/c1eb0c0f-41f6-4335-b982-84b278b53d59 -->
-
-[![Watch the video](https://img.youtube.com/vi/pNIOs1ovsXw/maxresdefault.jpg)](https://youtu.be/pNIOs1ovsXw)
+[![Watch the video](https://img.youtube.com/vi/YLVUW5UP9N0/maxresdefault.jpg)](https://www.youtube.com/watch?v=YLVUW5UP9N0)
 Click on the thumbnail to open the video☝️
 
 ---
 
-## 📚 Documentation
+## 🌐 Resources
+
+**GitHub Repo:**
+  - **RAG API:** [github.com/danny-avila/rag_api](https://github.com/danny-avila/rag_api)
+  - **Website:** [github.com/LibreChat-AI/librechat.ai](https://github.com/LibreChat-AI/librechat.ai)
 
-For more information on how to use our advanced features, install and configure our software, and access our guidelines and tutorials, please check out our documentation at [docs.librechat.ai](https://docs.librechat.ai)
+**Other:**
+  - **Website:** [librechat.ai](https://librechat.ai)
+  - **Documentation:** [docs.librechat.ai](https://docs.librechat.ai)
+  - **Blog:** [blog.librechat.ai](https://docs.librechat.ai)
 
 ---
 
 ## 📝 Changelog
 
-Keep up with the latest updates by visiting the releases page - [Releases](https://github.com/danny-avila/LibreChat/releases)
+Keep up with the latest updates by visiting the releases page and notes:
+- [Releases](https://github.com/danny-avila/LibreChat/releases)
+- [Changelog](https://www.librechat.ai/changelog) 
 
-**⚠️ [Breaking Changes](docs/general_info/breaking_changes.md)**
-Please consult the breaking changes before updating.
+**⚠️ Please consult the [changelog](https://www.librechat.ai/changelog) for breaking changes before updating.**
 
 ---
 
 ## ⭐ Star History
 
 <p align="center">
-<a href="https://trendshift.io/repositories/4685" target="_blank"><img src="https://trendshift.io/api/badge/repositories/4685" alt="danny-avila%2FLibreChat | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
-<a
-     href="https://runacap.com/ross-index/q1-24/"
-     target="_blank"
-     rel="noopener"
->
-    <img
-        style="width: 260px; height: 56px"
-        src="https://runacap.com/wp-content/uploads/2024/04/ROSS_badge_white_Q1_2024.svg"
-        alt="ROSS Index - Fastest Growing Open-Source Startups in Q1 2024 | Runa Capital"
-        width="260"
-        height="56"
-    />
-</a>
-<a href="https://star-history.com/#danny-avila/LibreChat&Date">
-  <img alt="Star History Chart" src="https://api.star-history.com/svg?repos=danny-avila/LibreChat&type=Date&theme=dark" onerror="this.src='https://api.star-history.com/svg?repos=danny-avila/LibreChat&type=Date'" />
-</a>
+  <a href="https://star-history.com/#danny-avila/LibreChat&Date">
+    <img alt="Star History Chart" src="https://api.star-history.com/svg?repos=danny-avila/LibreChat&type=Date&theme=dark" onerror="this.src='https://api.star-history.com/svg?repos=danny-avila/LibreChat&type=Date'" />
+  </a>
+</p>
+<p align="center">
+  <a href="https://trendshift.io/repositories/4685" target="_blank" style="padding: 10px;">
+    <img src="https://trendshift.io/api/badge/repositories/4685" alt="danny-avila%2FLibreChat | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/>
+  </a>
+  <a href="https://runacap.com/ross-index/q1-24/" target="_blank" rel="noopener" style="margin-left: 20px;">
+    <img style="width: 260px; height: 56px" src="https://runacap.com/wp-content/uploads/2024/04/ROSS_badge_white_Q1_2024.svg" alt="ROSS Index - Fastest Growing Open-Source Startups in Q1 2024 | Runa Capital" width="260" height="56"/>
+  </a>
 </p>
 
 ---

api/app/clients/GoogleClient.js

@@ -683,11 +683,12 @@ class GoogleClient extends BaseClient {
       const safetySettings = _payload.safetySettings;
       requestOptions.safetySettings = safetySettings;
 
+      const delay = modelName.includes('flash') ? 8 : 14;
       const result = await client.generateContentStream(requestOptions);
       for await (const chunk of result.stream) {
         const chunkText = chunk.text();
-        this.generateTextStream(chunkText, onProgress, {
-          delay: 12,
+        await this.generateTextStream(chunkText, onProgress, {
+          delay,
         });
         reply += chunkText;
       }
@@ -701,10 +702,14 @@ class GoogleClient extends BaseClient {
       safetySettings: safetySettings,
     });
 
+    let delay = this.isGenerativeModel ? 12 : 8;
+    if (modelName.includes('flash')) {
+      delay = 5;
+    }
     for await (const chunk of stream) {
       const chunkText = chunk?.content ?? chunk;
-      this.generateTextStream(chunkText, onProgress, {
-        delay: this.isGenerativeModel ? 12 : 8,
+      await this.generateTextStream(chunkText, onProgress, {
+        delay,
       });
       reply += chunkText;
     }

api/app/clients/OpenAIClient.js

@@ -308,7 +308,7 @@ class OpenAIClient extends BaseClient {
     let tokenizer;
     this.encoding = 'text-davinci-003';
     if (this.isChatCompletion) {
-      this.encoding = 'cl100k_base';
+      this.encoding = this.modelOptions.model.includes('gpt-4o') ? 'o200k_base' : 'cl100k_base';
       tokenizer = this.constructor.getTokenizer(this.encoding);
     } else if (this.isUnofficialChatGptModel) {
       const extendSpecialTokens = {

api/models/tx.js

@@ -12,6 +12,7 @@ const tokenValues = {
   '4k': { prompt: 1.5, completion: 2 },
   '16k': { prompt: 3, completion: 4 },
   'gpt-3.5-turbo-1106': { prompt: 1, completion: 2 },
+  'gpt-4o': { prompt: 5, completion: 15 },
   'gpt-4-1106': { prompt: 10, completion: 30 },
   'gpt-3.5-turbo-0125': { prompt: 0.5, completion: 1.5 },
   'claude-3-opus': { prompt: 15, completion: 75 },
@@ -52,6 +53,8 @@ const getValueKey = (model, endpoint) => {
     return 'gpt-3.5-turbo-1106';
   } else if (modelName.includes('gpt-3.5')) {
     return '4k';
+  } else if (modelName.includes('gpt-4o')) {
+    return 'gpt-4o';
   } else if (modelName.includes('gpt-4-vision')) {
     return 'gpt-4-1106';
   } else if (modelName.includes('gpt-4-1106')) {