### Local Development Setup

Source: https://github.com/librechat-ai/librechat.ai/blob/main/content/docs/features/admin_panel.mdx

Instructions for cloning the repository, setting up the environment, installing dependencies, and running the admin panel locally for development.

```bash
git clone https://github.com/ClickHouse/librechat-admin-panel.git
cd librechat-admin-panel
cp .env.example .env    # then edit
bun install
bun dev                 # http://localhost:3000
```

--------------------------------

### Copy Example librechat.yaml

Source: https://github.com/librechat-ai/librechat.ai/blob/main/content/docs/configuration/librechat_yaml/index.mdx

Copy the example configuration file to use as a starting point for your custom setup.

```bash
cp librechat.example.yaml librechat.yaml
```

--------------------------------

### Build and Start Project

Source: https://github.com/librechat-ai/librechat.ai/blob/main/content/blog/2024-04-17_blog_guide.mdx

Commands to build the project for production and then start the application.

```bash
pnpm build
pnpm start
```

--------------------------------

### Example MCP Settings Configuration

Source: https://github.com/librechat-ai/librechat.ai/blob/main/content/docs/configuration/librechat_yaml/object_structure/mcp_settings.mdx

This example demonstrates the structure of the mcpSettings configuration, showing commented-out options for allowedDomains and an active example for allowedAddresses.

```yaml
mcpSettings:
  # Strict whitelist mode:
  # allowedDomains:
  #   - "example.com"                    # Specific domain
  #   - "*.example.com"                  # All subdomains using wildcard
  #   - "https://api.example.com:8443"   # With protocol and port
  #   - "http://mcp-server:3000"         # Internal service, explicitly whitelisted

  # Default SSRF mode with private service exemptions:
  allowedAddresses:
    - "host.docker.internal:8080"        # Permit one private host on one port
    - "10.0.0.5:8000"                    # Permit one private IP on one port
```

--------------------------------

### Clone and Run LibreChat.ai

Source: https://github.com/librechat-ai/librechat.ai/blob/main/README.md

Steps to clone the repository, set up environment variables, install dependencies, and start the development server.

```bash
git clone https://github.com/LibreChat-AI/librechat.ai.git
cd librechat.ai

# (Optional) create a local env file for Ask AI, rate limiting, etc.
cp .env.template .env.local

# Install dependencies
pnpm install

# Start the dev server
pnpm dev
```

--------------------------------

### Standalone Admin Panel Setup

Source: https://github.com/librechat-ai/librechat.ai/blob/main/content/docs/features/admin_panel.mdx

Steps to set up the admin panel as a standalone service using Docker Compose. This involves creating an environment file and starting the service.

```bash
# 1. Create an env file
cp .env.example .env

# 2. Edit .env and set at minimum:
#    SESSION_SECRET=<random string, min 32 characters>
#    VITE_API_BASE_URL=http://host.docker.internal:3080

# 3. Start it
docker compose up -d   # http://localhost:3000
docker compose down    # stop
```

--------------------------------

### Install Helm Chart

Source: https://github.com/librechat-ai/librechat.ai/blob/main/content/docs/local/helm_chart.mdx

Install the LibreChat Helm chart from the official OCI registry.

```bash
helm install <deployment-name> oci://ghcr.io/danny-avila/librechat-chart/librechat
```

--------------------------------

### Interface Configuration Example

Source: https://github.com/librechat-ai/librechat.ai/blob/main/content/docs/configuration/librechat_yaml/object_structure/interface.mdx

This snippet shows a comprehensive example of the `interface` configuration block, demonstrating various settings for UI elements and functionalities.

```yaml
interface:
  mcpServers:
    placeholder: 'MCP Servers'
    use: true
    create: true
    share: false
    public: false
    configureObo: false
    trustCheckbox:
      label: 'I trust this server'
      subLabel: 'Only enable servers you trust'
  privacyPolicy:
    externalUrl: 'https://example.com/privacy'
    openNewTab: true
  termsOfService:
    externalUrl: 'https://example.com/terms'
    openNewTab: true
    modalAcceptance: true
    modalTitle: 'Terms of Service'
    modalContent: |
      # Terms of Service
      ## Introduction
      Welcome to LibreChat!
  modelSelect: false
  parameters: true
  contextUsage: true
  contextCost: true
  currency:
    code: EUR
    rate: 0.92
  presets: false
  prompts:
    use: true
    create: true
    share: true
    public: false
  bookmarks: true
  multiConvo: true
  agents:
    use: true
    create: true
    share: true
    public: false
  skills:
    use: true
    create: true
    share: false
    public: false
    defaultActiveOnShare: false
  sharedLinks:
    create: true
    share: true
    public: false
    snapshotFiles: true
  customWelcome: 'Hey {{user.name}}! Welcome to LibreChat'
  runCode: true
  webSearch: true
  fileSearch: true
  fileCitations: true
  defaultPinnedTools:
    - artifacts
    - execute_code
    - mcp

```

--------------------------------

### Successful Connection Example

Source: https://github.com/librechat-ai/librechat.ai/blob/main/content/docs/configuration/mongodb/mongodb_auth.mdx

Example log output indicating a successful connection and server listening status after applying the new configuration.

```text
LibreChat         | 2024-02-04 20:59:43 info: Server listening on all interfaces at port 3080. Use http://localhost:3080 to access it
chat-mongodb      | {"t":{"$date":"2024-02-04T20:59:53.880+00:00"},"s":"I",  "c":"NETWORK",  "id":22943,   "ctx":"listener","msg":"Connection accepted","attr":{"remote":"192.168.160.4:58114","uuid":{"uuid":{" $uuid":"027bdc7b-a3f4-429a-80ee-36cd172058ec"}},"connectionId":17,"connectionCount":10}}
```

--------------------------------

### Balance Configuration Example

Source: https://github.com/librechat-ai/librechat.ai/blob/main/content/docs/configuration/librechat_yaml/object_structure/balance.pl.mdx

This snippet shows a complete example of the balance configuration object, demonstrating how to enable or disable various balance management features.

```yaml
balance:
  enabled: false
  startBalance: 20000
  autoRefillEnabled: false
  refillIntervalValue: 30
  refillIntervalUnit: "days"
  refillAmount: 10000
```

--------------------------------

### Verify Git, Node.js, and npm Installation

Source: https://github.com/librechat-ai/librechat.ai/blob/main/content/docs/remote/docker_linux.mdx

Confirms that Git, Node.js, and npm have been installed successfully by displaying their respective versions.

```bash
git --version
node -v
npm -v
```

--------------------------------

### Start Deployed Docker Container

Source: https://github.com/librechat-ai/librechat.ai/blob/main/content/docs/remote/docker_linux.mdx

Use this command to start the deployed Docker container.

```bash
npm run start:deployed
```

--------------------------------

### Example Traversaal Prompts

Source: https://github.com/librechat-ai/librechat.ai/blob/main/content/docs/configuration/tools/traversaal.mdx

Use these example prompts to test the Traversaal tool's search capabilities.

```text
Find recent reporting about open source AI coding agents.
```

```text
Search for sources comparing renewable energy adoption in Europe and North America.
```

--------------------------------

### Install LibreChat Components as Systemd Services

Source: https://github.com/librechat-ai/librechat.ai/blob/main/content/blog/2023-08-18_podman.mdx

These commands use the previously defined './install.sh' script to register LibreChat's MongoDB, MeiliSearch, and the main application as systemd user services, enabling them to start on boot.

```bash
./install.sh librechat-mongodb 

```

```bash
./install.sh librechat-meilisearch 

```

```bash
./install.sh librechat 

```

--------------------------------

### Start Meilisearch Process (npm)

Source: https://github.com/librechat-ai/librechat.ai/blob/main/content/docs/configuration/meilisearch.mdx

Start the Meilisearch process with your generated master key. It will listen on port 7700 by default.

```bash
./meilisearch --master-key=<your_master_key>
```

--------------------------------

### Web Search Configuration Example

Source: https://github.com/librechat-ai/librechat.ai/blob/main/content/docs/configuration/librechat_yaml/object_structure/web_search.mdx

Configure web search providers, scrapers, and rerankers using environment variables. This example shows how to set API keys and select providers for Serper, SearxNG, Tavily, Firecrawl, Jina, and Cohere.

```yaml
webSearch:
  # Search Provider Configuration
  serperApiKey: "${SERPER_API_KEY}"
  searxngInstanceUrl: "${SEARXNG_INSTANCE_URL}"
  searxngApiKey: "${SEARXNG_API_KEY}"
  searchProvider: "serper" # Options: "serper", "searxng", "tavily"

  # Tavily Configuration (search and/or scraper)
  tavilyApiKey: "${TAVILY_API_KEY}"
  # Optional: custom Tavily-compatible endpoints
  tavilySearchUrl: "${TAVILY_SEARCH_URL}"
  tavilyExtractUrl: "${TAVILY_EXTRACT_URL}"

  # Scraper Configuration
  firecrawlApiKey: "${FIRECRAWL_API_KEY}"
  firecrawlApiUrl: "${FIRECRAWL_API_URL}"
  firecrawlVersion: "${FIRECRAWL_VERSION}"
  scraperProvider: "firecrawl" # Options: "firecrawl", "serper", "tavily"

  # Reranker Configuration
  jinaApiKey: "${JINA_API_KEY}"
  jinaApiUrl: "${JINA_API_URL}"
  cohereApiKey: "${COHERE_API_KEY}"
  rerankerType: "jina" # Options: "jina", "cohere", "none"

  # General Settings
  scraperTimeout: 7500 # Timeout in milliseconds for scraper requests (default: 7500)
  safeSearch: 1 # Options: 0 (OFF), 1 (MODERATE - default), 2 (STRICT)
```

--------------------------------

### Start MongoDB Server with Configuration File

Source: https://github.com/librechat-ai/librechat.ai/blob/main/content/docs/configuration/mongodb/mongodb_community.mdx

Start the MongoDB server using a configuration file to apply network settings for remote access. Ensure the --config path is correct.

```yaml
./mongod --config /path/to/mongodb/config/mongodb.conf
```

--------------------------------

### Complete Speech Configuration Example

Source: https://github.com/librechat-ai/librechat.ai/blob/main/content/docs/configuration/librechat_yaml/object_structure/speech.mdx

A comprehensive example demonstrating the configuration of multiple TTS providers (OpenAI, ElevenLabs), STT, and speech tab defaults within the LibreChat YAML file.

```yaml
version: 1.3.10
cache: true

speech:
  tts:
    openai:
      apiKey: "${TTS_API_KEY}"
      model: "tts-1-hd"
      voices: ["alloy", "echo", "fable", "onyx", "nova", "shimmer"]
    elevenlabs:
      apiKey: "${ELEVENLABS_API_KEY}"
      model: "eleven_multilingual_v2"
      voices: ["21m00Tcm4TlvDq8ikWAM", "AZnzlk1XvdvUeBnXmlld"]
      voice_settings:
        stability: 0.5
        similarity_boost: 0.75
  stt:
    openai:
      apiKey: "${STT_API_KEY}"
      model: "whisper-1"
  speechTab:
    conversationMode: false
    advancedMode: false
    speechToText: true
    textToSpeech:
      engineTTS: "openai"
      voice: "nova"
      automaticPlayback: false
```

--------------------------------

### Start Backend Server in Development Mode

Source: https://github.com/librechat-ai/librechat.ai/blob/main/content/docs/development/get_started.mdx

Starts the backend server with hot-reloading enabled, monitoring for changes. Access the backend at http://localhost:3080/.

```sh
npm run backend:dev
```

--------------------------------

### Summarization Configuration Example

Source: https://github.com/librechat-ai/librechat.ai/blob/main/content/docs/configuration/librechat_yaml/object_structure/summarization.mdx

Configure the summarization provider, model, token limits, and context pruning behavior. This example shows how to set up OpenAI for summarization with specific token ratios and pruning strategies.

```yaml
summarization:
  provider: 'openAI'
  model: 'gpt-4o-mini'
  maxSummaryTokens: 4096
  reserveRatio: 0.05
  trigger:
    type: 'token_ratio'
    value: 0.8
  contextPruning:
    enabled: true
    keepLastAssistants: 3
    softTrimRatio: 0.3
    hardClearRatio: 0.5
    minPrunableToolChars: 50000
    softTrim:
      maxChars: 4000
      headChars: 1500
      tailChars: 1500
    hardClear:
      enabled: true
      placeholder: '[Old tool result content cleared]'
```

--------------------------------

### Install Development Version of Helm Chart

Source: https://github.com/librechat-ai/librechat.ai/blob/main/content/docs/local/helm_chart.mdx

Install the development version of the Helm chart from the local repository.

```bash
helm install <deployment-name> ./helm/librechat
```

--------------------------------

### Registration Object Structure Example

Source: https://github.com/librechat-ai/librechat.ai/blob/main/content/docs/configuration/librechat_yaml/object_structure/registration.mdx

An example demonstrating the overall structure of the registration object, including social logins and allowed domains.

```yaml
# Example Registration Object Structure
registration:
  socialLogins: ["google", "facebook", "github", "discord", "openid"]
  allowedDomains:
    - "gmail.com"
    - "protonmail.com"
```

--------------------------------

### Copy Example Override File

Source: https://github.com/librechat-ai/librechat.ai/blob/main/content/docs/configuration/docker_override.mdx

Create a local docker-compose.override.yml file by copying the example provided in the repository. This file is automatically detected by Docker Compose.

```bash
cp docker-compose.override.yml.example docker-compose.override.yml
```

--------------------------------

### Production Redirect URI Example

Source: https://github.com/librechat-ai/librechat.ai/blob/main/content/docs/mcp_servers/google_workspace.mdx

Provides an example of a redirect URI for a production environment. Replace `chat.example.com` with your actual LibreChat domain.

```text
https://chat.example.com/api/mcp/gmail/oauth/callback
```

--------------------------------

### MCP Servers Configuration Example

Source: https://github.com/librechat-ai/librechat.ai/blob/main/content/docs/configuration/librechat_yaml/object_structure/interface.mdx

This snippet provides a specific example for configuring `mcpServers`, including internationalized labels for the trust checkbox.

```yaml
interface:
  mcpServers:
    placeholder: 'Select MCP Server'
    use: true
    create: true
    share: false
    configureObo: false
    trustCheckbox:
      label:
        en: 'I trust this server'
        es: 'Confío en este servidor'
      subLabel:
        en: 'Only enable servers you trust'
        es: 'Solo habilite servidores en los que confíe'

```

--------------------------------

### Example Prompts for OpenWeather Tool

Source: https://github.com/librechat-ai/librechat.ai/blob/main/content/docs/configuration/tools/openweather.mdx

These example prompts demonstrate how to query different types of weather information using the OpenWeather tool. They cover current conditions, historical data, summaries, and unit preferences.

```text
What's the current weather in London?
What was the weather like in Paris on 2023-01-01?
Give me a weather summary for Tokyo.
What's the temperature in New York in Fahrenheit?
```

--------------------------------

### Install Git, Node.js, and npm

Source: https://github.com/librechat-ai/librechat.ai/blob/main/content/docs/remote/docker_linux.mdx

Installs Git, Node.js, and npm on Debian/Ubuntu systems. These tools are useful for managing the LibreChat project and its dependencies.

```bash
sudo apt install git nodejs npm
```

--------------------------------

### USD Spend Calculation Example

Source: https://github.com/librechat-ai/librechat.ai/blob/main/content/docs/configuration/token_usage.mdx

Demonstrates the calculation of USD spend using the provided token values and rate. This practical example helps in verifying the accuracy of the formulas and understanding the real-world cost.

```math
\frac{205.5}{1,000,000} = \$0.0002055 \text{ USD}
```

--------------------------------

### Azure OpenAI Configuration Example

Source: https://github.com/librechat-ai/librechat.ai/blob/main/content/docs/configuration/librechat_yaml/ai_endpoints/azure.mdx

An example librechat.yaml configuration demonstrating endpoint, group, and model-level settings for Azure OpenAI, including multiple regions and deployments.

```yaml
endpoints:
  azureOpenAI:
    # Endpoint-level configuration
    titleModel: "llama-70b-chat"
    plugins: true
    assistants: true
    groups:
    # Group-level configuration
    - group: "my-resource-westus"
      apiKey: "${WESTUS_API_KEY}"
      instanceName: "my-resource-westus"
      version: "2024-03-01-preview"
      # Model-level configuration
      models:
        gpt-4-vision-preview:
          deploymentName: gpt-4-vision-preview
          version: "2024-03-01-preview"
        gpt-3.5-turbo:
          deploymentName: gpt-35-turbo
        gpt-4-1106-preview:
          deploymentName: gpt-4-1106-preview
    # Group-level configuration
    - group: "mistral-inference"
      apiKey: "${AZURE_MISTRAL_API_KEY}"
      baseURL: "https://Mistral-large-vnpet-serverless.region.inference.ai.azure.com/v1/chat/completions"
      serverless: true
      # Model-level configuration
      models:
        mistral-large: true
    # Group-level configuration
    - group: "my-resource-sweden"
      apiKey: "${SWEDEN_API_KEY}"
      instanceName: "my-resource-sweden"
      deploymentName: gpt-4-1106-preview
      version: "2024-03-01-preview"
      assistants: true
      # Model-level configuration
      models:
        gpt-4-turbo: true

```

--------------------------------

### Set Node.js and npm Versions

Source: https://github.com/librechat-ai/librechat.ai/blob/main/content/docs/local/npm.mdx

Use nvm to install and select Node.js v24.16.0, then install npm v11.16.0 globally. Verify the versions using `node -v` and `npm -v`.

```bash
nvm install 24.16.0
nvm use 24.16.0
npm install -g npm@11.16.0
node -v
npm -v
```

--------------------------------

### Start MongoDB Server with Data Directory

Source: https://github.com/librechat-ai/librechat.ai/blob/main/content/docs/configuration/mongodb/mongodb_community.mdx

Use this command to start the MongoDB server, specifying the directory for data storage. Ensure the --dbpath points to your created data directory.

```sh
./mongod --dbpath=/path/to/data/directory
```

--------------------------------

### mcpSettings Configuration Example

Source: https://github.com/librechat-ai/librechat.ai/blob/main/content/docs/configuration/librechat_yaml/object_structure/config.mdx

Demonstrates how to configure mcpSettings in the LibreChat YAML file. It shows examples for both strict allowedDomains whitelisting and the default SSRF mode with allowedAddresses exemptions for private services.

```yaml
mcpSettings:
  # Strict whitelist mode:
  # allowedDomains:
  #   - "example.com"           # Specific domain
  #   - "*.example.com"         # All subdomains
  #   - "http://mcp-server:3000" # Internal service, explicitly whitelisted

  # Default SSRF mode with private service exemptions:
  allowedAddresses:
    - 'host.docker.internal:8080' # Permit one private host on one port
    - '10.0.0.5:8000' # Permit one private IP on one port
```

--------------------------------

### Actions Object Structure Example

Source: https://github.com/librechat-ai/librechat.ai/blob/main/content/docs/configuration/librechat_yaml/object_structure/actions.mdx

Demonstrates the basic structure of the Actions object, showing commented-out examples for strict whitelist mode (`allowedDomains`) and default SSRF mode with private service exemptions (`allowedAddresses`).

```yaml
# Example Actions Object Structure
actions:
  # Strict whitelist mode:
  # allowedDomains:
  #   - "swapi.dev"
  #   - "librechat.ai"
  #   - "google.com"
  #   - "https://api.example.com:8443"  # With protocol and port

  # Default SSRF mode with private service exemptions:
  allowedAddresses:
    - "host.docker.internal:11434"    # Permit one private host on one port
    - "10.0.0.5:8080"                 # Permit one private IP on one port
```

--------------------------------

### Start MongoDB Container

Source: https://github.com/librechat-ai/librechat.ai/blob/main/content/docs/configuration/mongodb/mongodb_auth.mdx

Start only the MongoDB container in detached mode to prepare for authentication setup. The `-d` flag runs the container in the background.

```bash
docker compose up -d mongodb
```

--------------------------------

### Start ngrok HTTP Tunnel on Windows

Source: https://github.com/librechat-ai/librechat.ai/blob/main/content/docs/remote/ngrok.mdx

Start an ngrok HTTP tunnel to expose your local server running on port 3080. This command is used after ngrok is installed and configured on Windows.

```bash
ngrok http 3080
```

--------------------------------

### Create Banner (Direct Command Examples)

Source: https://github.com/librechat-ai/librechat.ai/blob/main/content/docs/configuration/banner.mdx

These examples demonstrate how to create banners with specific configurations using direct command-line arguments. They cover different scenarios like welcome messages, maintenance notices, and security alerts, specifying display times, messages, public visibility, and persistence.

```bash
npm run update-banner "" "" "👋 Welcome to LibreChat!" "false" "false"
```

```bash
npm run update-banner "2025-12-20T00:00:00Z" "2025-12-21T06:00:00Z" "⚠️ Scheduled maintenance on Dec 20th, 2-6 AM UTC" "true" "true"
```

```bash
npm run update-banner "" "" "🔒 Please update your password by January 1st" "true" "true"
```

--------------------------------

### Start Development Server

Source: https://github.com/librechat-ai/librechat.ai/blob/main/content/blog/2024-04-17_blog_guide.mdx

Use this command to launch the local development server for real-time previewing of changes.

```bash
pnpm dev
```

--------------------------------

### Build Compiled Code

Source: https://github.com/librechat-ai/librechat.ai/blob/main/content/docs/development/get_started.mdx

Compiles all necessary code for the LibreChat project. This command should be run after installing dependencies and before starting the development servers.

```sh
npm run build
```

--------------------------------

### Groq API Key Setup

Source: https://github.com/librechat-ai/librechat.ai/blob/main/content/docs/configuration/librechat_yaml/ai_endpoints/groq.mdx

Add your Groq API key to the `.env` file for authentication.

```bash
GROQ_API_KEY=your-api-key
```

--------------------------------

### MCP Server Configuration Example

Source: https://github.com/librechat-ai/librechat.ai/blob/main/content/docs/configuration/librechat_yaml/object_structure/mcp_servers.mdx

Demonstrates a basic configuration for an MCP server using the 'stdio' type, including command and arguments.

```yaml
mcpServers:
  myServer:
    type: "stdio"
    command: "npx"
    args: ["-y", "@modelcontextprotocol/server-puppeteer"]
```

--------------------------------

### Example AWS Bedrock Object Structure

Source: https://github.com/librechat-ai/librechat.ai/blob/main/content/docs/configuration/librechat_yaml/object_structure/aws_bedrock.mdx

This configuration sets up an AWS Bedrock endpoint, specifying the title model, stream rate, available regions, and guardrail settings. It demonstrates a comprehensive setup for Bedrock integration.

```yaml
endpoints:
  bedrock:
    titleModel: 'anthropic.claude-3-haiku-20240307-v1:0'
    streamRate: 35
    availableRegions:
      - 'us-east-1'
      - 'us-west-2'
    guardrailConfig:
      guardrailIdentifier: 'your-guardrail-id'
      guardrailVersion: '1'
      trace: 'enabled'
      streamProcessingMode: 'sync'
```

--------------------------------

### Install pnpm Globally

Source: https://github.com/librechat-ai/librechat.ai/blob/main/content/blog/2024-04-17_blog_guide.mdx

If pnpm is not installed globally, you can install it using npm. This is a prerequisite for installing project dependencies.

```bash
npm install -g pnpm
```

--------------------------------

### Install Project Dependencies

Source: https://github.com/librechat-ai/librechat.ai/blob/main/content/blog/2024-04-17_blog_guide.mdx

Install project dependencies using pnpm. Ensure Node.js and pnpm are installed globally.

```bash
pnpm install
```

--------------------------------

### Create /api/.env File

Source: https://github.com/librechat-ai/librechat.ai/blob/main/content/docs/development/testing.mdx

Copy the example environment file to create a local .env file for the API. This is a prerequisite for running local tests.

```bash
cp .env.example ./api/.env
```

--------------------------------

### Install and Use Node.js Version 24

Source: https://github.com/librechat-ai/librechat.ai/blob/main/content/docs/development/get_started.mdx

Installs and sets the Node.js version to 24.16.0 and globally installs npm version 11.16.0. Use this when a specific Node.js version is required.

```sh
nvm install 24.16.0
nvm use 24.16.0
npm install -g npm@11.16.0
```

--------------------------------

### Copy Environment File

Source: https://github.com/librechat-ai/librechat.ai/blob/main/content/docs/remote/docker_linux.mdx

Copies the example environment file (`.env.example`) to `.env`. This file will store sensitive credentials and configuration settings.

```bash
# Copies the example file as your global env file
cp .env.example .env
```

--------------------------------

### Create .env File

Source: https://github.com/librechat-ai/librechat.ai/blob/main/content/docs/local/npm.mdx

Copy the example environment file to create your active .env file. Note: Windows users may need to use `copy` instead of `cp`.

```bash
cp .env.example .env
```

--------------------------------

### File Configuration Example

Source: https://github.com/librechat-ai/librechat.ai/blob/main/content/docs/configuration/librechat_yaml/object_structure/file_config.mdx

Demonstrates the structure of the fileConfig object, including endpoint-specific settings for assistants, OpenAI, and custom endpoints, as well as global limits for server file size, avatar size, file token limits, image generation, and file processing for OCR, text, and STT.

```yaml
fileConfig:
  endpoints:
    assistants:
      fileLimit: 5
      fileSizeLimit: 10
      totalSizeLimit: 50
      supportedMimeTypes:
        - "image/.*"
        - "application/pdf"
    openAI:
      disabled: true
    default:
      totalSizeLimit: 20
    YourCustomEndpointName:
      fileLimit: 5
      fileSizeLimit: 1000
      supportedMimeTypes:
        - "image/.*"
  serverFileSizeLimit: 1000
  avatarSizeLimit: 2
  fileTokenLimit: 100000
  imageGeneration:
    percentage: 100
    px: 1024
  ocr:
    supportedMimeTypes:
      - "^image/(jpeg|gif|png|webp|heic|heif)$"
      - "^application/pdf$"
      - "^application/vnd\.openxmlformats-officedocument\.(wordprocessingml\.document|presentationml\.presentation|spreadsheetml\.sheet)$"
      - "^application/vnd\.ms-(word|powerpoint|excel)$"
      - "^application/epub\+zip$"
  text:
    supportedMimeTypes:
      - "^text/(plain|markdown|csv|json|xml|html|css|javascript|typescript|x-python|x-java|x-csharp|x-php|x-ruby|x-go|x-rust|x-kotlin|x-swift|x-scala|x-perl|x-lua|x-shell|x-sql|x-yaml|x-toml)$"
  stt:
    supportedMimeTypes:
      - "^audio/(mp3|mpeg|mpeg3|wav|wave|x-wav|ogg|vorbis|mp4|x-m4a|flac|x-flac|webm)$"
```

--------------------------------

### Install Docker Dependencies

Source: https://github.com/librechat-ai/librechat.ai/blob/main/content/docs/remote/docker_linux.mdx

Installs essential packages required for Docker to function correctly on Ubuntu.

```bash
sudo apt install apt-transport-https ca-certificates curl software-properties-common gnupg lsb-release
```

--------------------------------

### Install Certbot for CentOS

Source: https://github.com/librechat-ai/librechat.ai/blob/main/content/docs/remote/nginx.mdx

Installs Certbot and the Nginx plugin on CentOS systems for managing SSL/TLS certificates.

```bash
sudo yum install certbot python2-certbot-nginx
```

--------------------------------

### Install Certbot for Ubuntu

Source: https://github.com/librechat-ai/librechat.ai/blob/main/content/docs/remote/nginx.mdx

Installs Certbot and the Nginx plugin on Ubuntu systems for managing SSL/TLS certificates.

```bash
sudo apt-get install certbot python3-certbot-nginx
```

--------------------------------

### Configure Environment Variables

Source: https://github.com/librechat-ai/librechat.ai/blob/main/content/blog/2023-08-18_podman.mdx

Copies the example environment file to the root directory and updates specific configuration keys required for container networking.

```bash
cp ./LibreChat/.env.example .env
```

```sh
HOST=0.0.0.0
MONGO_URI=mongodb://librechat-mongodb:27017/LibreChat
MEILI_HOST=http://librechat-meilisearch:7700
MEILI_NO_ANALYTICS=true
```

--------------------------------

### Example LibreChat URL

Source: https://github.com/librechat-ai/librechat.ai/blob/main/content/docs/remote/huggingface.mdx

An example of a fully formed URL for accessing a LibreChat deployment, based on the template.

```text
https://cooluser-librechat.hf.space/
```

--------------------------------

### MCP Server with Custom Instructions

Source: https://github.com/librechat-ai/librechat.ai/blob/main/content/docs/configuration/librechat_yaml/object_structure/mcp_servers.mdx

Demonstrates how to provide custom instructions for an MCP server to be injected into the agent context.

```yaml
mcpServers:
  customInstructionsServer:
    serverInstructions: "Custom instructions for this server."
```

--------------------------------

### Make Installation Script Executable

Source: https://github.com/librechat-ai/librechat.ai/blob/main/content/blog/2023-08-18_podman.mdx

This command changes the permissions of the installation script to make it executable, allowing it to be run directly.

```bash
chmod +x ./install.sh
```

--------------------------------

### Start LibreChat Docker Services

Source: https://github.com/librechat-ai/librechat.ai/blob/main/content/docs/local/docker.mdx

Starts the LibreChat services using Docker Compose after pulling the latest changes and images.

```bash
docker compose up
```

--------------------------------

### Run Frontend in Development Mode

Source: https://github.com/librechat-ai/librechat.ai/blob/main/content/docs/development/get_started.mdx

Starts the frontend development server with hot-reloading, monitoring for changes. Ensure the backend is running. View the frontend at http://localhost:3090/.

```sh
npm run frontend:dev
```

--------------------------------

### Install Docker Compose Plugin

Source: https://github.com/librechat-ai/librechat.ai/blob/main/content/docs/remote/docker_linux.mdx

Installs the Docker Compose plugin on Debian/Ubuntu-based systems. This is required for managing Docker containers for LibreChat.

```bash
sudo apt install docker-compose-plugin
```

--------------------------------

### Install Helm Chart with Values Override

Source: https://github.com/librechat-ai/librechat.ai/blob/main/content/docs/local/helm_chart.mdx

Install the Helm chart using a custom values file to override default settings.

```bash
helm install librechat oci://ghcr.io/danny-avila/librechat-chart/librechat --values <values-override-filel>
```

--------------------------------

### Shared Endpoint Configuration Example

Source: https://github.com/librechat-ai/librechat.ai/blob/main/content/docs/configuration/librechat_yaml/object_structure/shared_endpoint_settings.mdx

Demonstrates how to configure shared settings for multiple endpoints, including individual endpoint overrides and global defaults using the 'all' key. Headers are merged, with endpoint-specific headers taking precedence.

```yaml
endpoints:
  # Individual endpoint configurations
  openAI:
    streamRate: 25
    titleModel: 'gpt-4o-mini'
    titleMethod: 'completion'
    titleTiming: 'immediate'
    titlePrompt: "Create a concise title for this conversation:\n\n{convo}"
    headers:
      X-Gateway-Metadata: '{"user_email":"{{LIBRECHAT_USER_EMAIL}}"}'

  azureOpenAI:
    streamRate: 35
    titleModel: 'grok-3'
    titleMethod: 'structured'
    titlePrompt: |
      Analyze this conversation and provide:
      1. A concise title in the detected language (5 words or less, no punctuation or quotation)
      2. Always provide a relevant emoji at the start of the title

      {convo}
    titleConvo: true

  anthropic:
    streamRate: 25
    titleModel: 'claude-3-5-haiku-20241022'
    titleMethod: 'completion'
    headers:
      X-Conversation-Id: '{{LIBRECHAT_BODY_CONVERSATIONID}}'

  bedrock:
    streamRate: 25
    titleModel: 'us.amazon.nova-lite-v1:0'
    titleEndpoint: 'anthropic'

  google:
    streamRate: 1
    titleModel: 'gemini-2.0-flash-lite'
    titlePromptTemplate: "Human: {input}\nAssistant: {output}"
    headers:
      X-Gateway-Metadata: '{"user_id":"{{LIBRECHAT_USER_ID}}"}'

  assistants:
    streamRate: 30

  azureAssistants:
    streamRate: 30

  # Global configuration using 'all' - this applies shared settings across endpoints.
  # Most defined values override endpoint defaults; headers are merged and endpoint values win on collisions.
  all:
    headers:
      X-App: 'librechat'
    titleConvo: true
    titleModel: 'gpt-4.1-nano'
    titleTiming: 'immediate'
    titlePrompt: |
      Analyze this conversation and provide:
      1. The detected language of the conversation
      2. A concise title in the detected language (5 words or less, no punctuation or quotation)
      3. Always provide a relevant emoji at the start of the title
      {convo}
```

--------------------------------

### Enable Marketplace Access in Interface Configuration

Source: https://github.com/librechat-ai/librechat.ai/blob/main/content/docs/configuration/librechat_yaml/object_structure/interface.mdx

Example of how to enable marketplace access by setting `use` to `true` within the interface configuration.

```yaml
interface:
  marketplace:
    use: true # Enable marketplace access
```

--------------------------------

### Install Docker CE

Source: https://github.com/librechat-ai/librechat.ai/blob/main/content/docs/remote/docker_linux.mdx

Installs the Docker Community Edition (docker-ce) from the official Docker repository, which is preferred over distribution-provided packages for up-to-date versions.

```bash
sudo apt install docker-ce
```

--------------------------------

### Configure Stable Diffusion URL for Local Install

Source: https://github.com/librechat-ai/librechat.ai/blob/main/content/docs/configuration/tools/stable_diffusion.mdx

Set the SD_WEBUI_URL environment variable in your .env file or directly in the webui for local installations.

```env
SD_WEBUI_URL=http://127.0.0.1:7860
```

--------------------------------

### Complete LibreChat YAML Configuration Example

Source: https://github.com/librechat-ai/librechat.ai/blob/main/content/docs/configuration/librechat_yaml/example.mdx

This example configuration includes most documented endpoints and settings. It's useful for understanding the full scope of LibreChat's configuration options. Note that Azure, LiteLLM, MLX, and Ollama require additional specific configurations not shown here.

```yaml
version: 1.3.13

cache: true

# skillSync:
#   github:
#     enabled: false
#     intervalMinutes: 60
#     runOnStartup: true
#     sources:
#       - id: librechat-skills
#         owner: your-org
#         repo: your-skills-repo
#         ref: main
#         paths:
#           - skills
#         skillDiscoveryDepth: 2
#         token: '${GITHUB_SKILLS_TOKEN}'
#         # credentialKey: production-skills
#         # tenantId: your-tenant-id

interface:
  # MCP Servers UI configuration
  mcpServers:
    placeholder: 'MCP Servers'
    # configureObo: false # Permission to configure MCP On-Behalf-Of token exchange

  # Shared Links permissions
  # sharedLinks:
  #   create: true
  #   share: true
  #   public: false
  #   snapshotFiles: true

  # Skills permissions and activation defaults
  # skills:
  #   use: true
  #   create: true
  #   share: false
  #   public: false
  #   defaultActiveOnShare: false

  # Retention mode: "temporary" applies only to temporary chats; "all" applies to all retained data
  # retentionMode: "temporary"
  # retainAgentFiles: false # Keep persistent agent resource files when retentionMode is "all"

  # Privacy policy settings
  privacyPolicy:
    externalUrl: 'https://librechat.ai/privacy-policy'
    openNewTab: true

  # Terms of service
  termsOfService:
    externalUrl: 'https://librechat.ai/tos'
    openNewTab: true

  # Context usage and cost display
  # contextUsage: true
  # contextCost: true
  # currency:
  #   code: EUR
  #   rate: 0.92

  # Default prompt-bar pinned tools for users who have not customized pins
  # defaultPinnedTools:
  #   - artifacts
  #   - execute_code
  #   - mcp

registration:
  socialLogins: ['discord', 'facebook', 'github', 'google', 'openid']

endpoints:
  custom:
    # Anyscale
    - name: 'Anyscale'
      apiKey: '${ANYSCALE_API_KEY}'
      baseURL: 'https://api.endpoints.anyscale.com/v1'
      models:
        default: ['meta-llama/Llama-2-7b-chat-hf']
        fetch: true
      titleConvo: true
      titleModel: 'meta-llama/Llama-2-7b-chat-hf'
      summarize: false
      summaryModel: 'meta-llama/Llama-2-7b-chat-hf'
      modelDisplayLabel: 'Anyscale'

    # APIpie
    - name: 'APIpie'
      apiKey: '${APIPIE_API_KEY}'
      baseURL: 'https://apipie.ai/v1/'
      models:
        default:
          [
            'gpt-4',
            'gpt-4-turbo',
            'gpt-3.5-turbo',
            'claude-3-opus',
            'claude-3-sonnet',
            'claude-3-haiku',
            'llama-3-70b-instruct',
            'llama-3-8b-instruct',
            'gemini-pro-1.5',
            'gemini-pro',
            'mistral-large',
            'mistral-medium',
            'mistral-small',
            'mistral-tiny',
            'mixtral-8x22b',
          ]
        fetch: false
      titleConvo: true
      titleModel: 'gpt-3.5-turbo'
      dropParams: ['stream']

    #cohere
    - name: 'cohere'
      apiKey: '${COHERE_API_KEY}'
      baseURL: 'https://api.cohere.ai/v1'
      models:
        default:
          [
            'command-r',
            'command-r-plus',
            'command-light',
            'command-light-nightly',
            'command',
            'command-nightly',
          ]
        fetch: false
      modelDisplayLabel: 'cohere'
      titleModel: 'command'
      dropParams: ['stop', 'user', 'frequency_penalty', 'presence_penalty', 'temperature', 'top_p']

    # Fireworks
    - name: 'Fireworks'
      apiKey: '${FIREWORKS_API_KEY}'
      baseURL: 'https://api.fireworks.ai/inference/v1'
      models:
        default: ['accounts/fireworks/models/mixtral-8x7b-instruct']
        fetch: true
      titleConvo: true
      titleModel: 'accounts/fireworks/models/llama-v2-7b-chat'
      summarize: false
      summaryModel: 'accounts/fireworks/models/llama-v2-7b-chat'
      modelDisplayLabel: 'Fireworks'
      dropParams: ['user']

    # groq
    - name: 'groq'
      apiKey: '${GROQ_API_KEY}'
      baseURL: 'https://api.groq.com/openai/v1/'
      models:
        default:
          [
            'llama2-70b-4096',
            'llama3-70b-8192',
            'llama3-8b-8192',
            'mixtral-8x7b-32768',
            'gemma-7b-it',
          ]
        fetch: false
      titleConvo: true
      titleModel: 'mixtral-8x7b-32768'
      modelDisplayLabel: 'groq'

```

--------------------------------

### Enable and Configure User Token Balances

Source: https://github.com/librechat-ai/librechat.ai/blob/main/content/docs/configuration/dotenv.mdx

Enable token credit balances for OpenAI/Plugins endpoints and set an initial balance for new users upon registration. Defaults to false for CHECK_BALANCE and 20000 for START_BALANCE.

```bash
CHECK_BALANCE=false
START_BALANCE=20000
```