### Local Development Setup

Source: https://www.librechat.ai/docs/features/admin_panel

Clone the repository, set up environment variables, install dependencies, and start the development server for local administration panel 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
```

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

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

Source: https://www.librechat.ai/docs/remote/docker_linux

Installs Git, Node.js, and npm, which are useful for managing projects and dependencies, though not strictly required for Docker-based setups.

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

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

### Copy Example librechat.yaml

Source: https://www.librechat.ai/docs/configuration/librechat_yaml

Copy the example configuration file to `librechat.yaml` as a starting point for your custom configuration.

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

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

### Copy Environment Example

Source: https://www.librechat.ai/docs/local

Copy the example environment file to create your own configuration.

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

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

### Build and Start LibreChat

Source: https://www.librechat.ai/docs/local/npm

Perform a clean dependency install and build LibreChat using 'npm run reinstall'. Then, start the backend server with 'npm run backend'.

```bash
npm run reinstall
```

```bash
npm run backend
```

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

### Allowed Domains - Full Example

Source: https://www.librechat.ai/docs/configuration/librechat_yaml/object_structure/actions

A comprehensive example showing various allowed domain configurations, including internal services.

```yaml
allowedDomains:
  - "swapi.dev"
  - "librechat.ai"
  - "google.com"
  - "https://secure-api.example.com:443"
  - "192.168.1.50"  # Internal service (explicitly allowed)

```

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

### Standalone Admin Panel Setup

Source: https://www.librechat.ai/docs/features/admin_panel

Deploy the admin panel using its published image from GHCR. This involves creating an environment file and starting the Docker container.

```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 and Use Node.js Version

Source: https://www.librechat.ai/docs/development/get_started

Use nvm to install and switch to the recommended Node.js version. Ensure npm is also updated to the specified version.

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

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

### Copy Environment Example

Source: https://www.librechat.ai/docs/development/testing

Copy the example environment file to be used for local testing. Ensure this is done before setting NODE_ENV.

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

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

### Install Dependencies and Build with Turborepo

Source: https://www.librechat.ai/docs/development/architecture

Use `smart-reinstall` to install dependencies and build the project via Turborepo, especially if the lockfile has changed. `reinstall` is a clean install option.

```bash
npm run smart-reinstall
```

```bash
npm run reinstall
```

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

### Create Docker Compose Override File

Source: https://www.librechat.ai/docs/configuration/docker_override

Copy the example override file to start customizing your Docker Compose setup. Docker Compose automatically detects this file.

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

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

### Summarization Configuration Example

Source: https://www.librechat.ai/docs/configuration/librechat_yaml/object_structure/summarization

Configure the summarization provider, model, token limits, and context pruning settings. This setup replaces per-endpoint summarization fields.

```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]'
```

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

### Example MCP Settings Configuration

Source: https://www.librechat.ai/docs/configuration/librechat_yaml/object_structure/mcp_settings

This example demonstrates how to configure mcpSettings, showing both strict domain whitelisting and default SSRF protection with private service exemptions.

```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
```

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

### Interactive Banner Creation Prompts

Source: https://www.librechat.ai/docs/configuration/banner

Example of the interactive prompts guiding the user through banner creation, including date formats and visibility options.

```bash
--------------------------
Update the banner!
--------------------------
Display From (Format: yyyy-mm-ddTHH:MM:SSZ, Default: now):
> 2025-12-02T09:00:00Z

Display To (Format: yyyy-mm-ddTHH:MM:SSZ, Default: not specified):
> 2025-12-31T23:59:59Z

Enter your message (Enter a single dot "." on a new line to finish):
> 🎉 Welcome to LibreChat! Check out our new features.
> .

Is public (y/N):
> n

Is persistable (cannot be dismissed) (y/N):
> n
```

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

### Example Traversaal Prompts

Source: https://www.librechat.ai/docs/configuration/tools/traversaal

Use these example prompts to query Traversaal for specific information. Ensure your query is a complete sentence.

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

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

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

### Copy Environment Example File

Source: https://www.librechat.ai/docs/local/npm

Copy the example environment file to create a new environment file. Note: Use 'copy' instead of 'cp' on Windows 10.

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

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

### Install Dependencies and Build Workspaces

Source: https://www.librechat.ai/docs/development

Use this command to install dependencies and build compiled workspaces. It's recommended when needed or after significant changes.

```bash
npm run smart-reinstall
```

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

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

Source: https://www.librechat.ai/docs/remote/docker_linux

Confirms the successful installation of Git, Node.js, and npm by displaying their respective version numbers.

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

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

### Start MongoDB Community Server

Source: https://www.librechat.ai/docs/configuration/mongodb/mongodb_community

Use this command to start the MongoDB server, specifying the data directory. Ensure the path is correct for your system.

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

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

### Full Speech Configuration Example

Source: https://www.librechat.ai/docs/configuration/librechat_yaml/object_structure/speech

This example demonstrates how to configure multiple TTS providers (OpenAI, ElevenLabs) and an STT provider (OpenAI), along with default UI settings for speech features.

```yaml
speech:
  tts:
    openai:
      apiKey: "${TTS_API_KEY}"
      model: "tts-1"
      voices: ["alloy", "echo", "fable", "onyx", "nova", "shimmer"]
    elevenlabs:
      apiKey: "${ELEVENLABS_API_KEY}"
      model: "eleven_multilingual_v2"
      voices: ["voice-id-1", "voice-id-2"]
  stt:
    openai:
      apiKey: "${STT_API_KEY}"
      model: "whisper-1"
  speechTab:
    conversationMode: true
    advancedMode: false
    speechToText: true
    textToSpeech: true
```

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

### MCP Servers Configuration Example

Source: https://www.librechat.ai/docs/configuration/librechat_yaml/object_structure/config

This example demonstrates how to configure various MCP servers with different connection types, timeouts, and instructions. It covers 'sse', 'stdio', and 'streamable-http' connection types, along with custom user variables for authentication.

```yaml
mcpServers:
  everything:
    # type: sse # type can optionally be omitted
    url: http://localhost:3001/sse
    timeout: 30000
    initTimeout: 10000
    serverInstructions: true # Use server-provided instructions
  puppeteer:
    type: stdio
    command: npx
    args:
      - -y
      - '@modelcontextprotocol/server-puppeteer'
    timeout: 30000
    initTimeout: 10000
    serverInstructions: 'Do not access any local files or local/internal IP addresses'
  filesystem:
    # type: stdio
    command: npx
    args:
      - -y
      - '@modelcontextprotocol/server-filesystem'
      - /home/user/LibreChat/
    iconPath: /home/user/LibreChat/client/public/assets/logo.svg
  mcp-obsidian:
    command: npx
    args:
      - -y
      - 'mcp-obsidian'
      - /path/to/obsidian/vault
  streamable-http-example:
    type: streamable-http
    url: https://example.com/mcp
    headers:
      Authorization: 'Bearer ${API_TOKEN}'
    timeout: 30000
  per-user-crendentials-example:
    type: sse
    url: 'https//some.mcp/sse'
    headers:
      X-Custom-Auth-Token: '{{USER_API_KEY}}' # Placeholder for the user-provided API key, defined in `customUserVars` below.
    customUserVars:
      USER_API_KEY:
        title: 'Service API Key'
        description: "Your personal API key for this service. You can get it <a href='https://example.com/api-keys' target='_blank'>here</a>."
    serverInstructions: true
```

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

### Install LibreChat Helm Chart (OCI)

Source: https://www.librechat.ai/docs/local/helm_chart

Install the official LibreChat Helm chart from the OCI registry. Replace `<deployment-name>` with your desired release name.

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

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

### Install and Run Azurite using npm

Source: https://www.librechat.ai/docs/configuration/cdn/azure

Install the Azurite package globally and run it with specified silent, location, and debug options for local Azure Storage emulation.

```bash
npm install -g azurite
azurite --silent --location /path/to/azurite/workspace --debug /path/to/debug/log
```

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

### Example MCP Servers Object Structure

Source: https://www.librechat.ai/docs/configuration/librechat_yaml/object_structure/mcp_servers

This snippet shows a comprehensive example of how to configure various MCP servers within the LibreChat YAML configuration. It includes examples for different server types, authentication methods, and custom parameters.

```yaml
# Example MCP Servers Object Structure
mcpServers:
  everything:
    # type: sse # type can optionally be omitted
    url: http://localhost:3001/sse
  googlesheets:
    type: sse
    url: https://mcp.composio.dev/googlesheets/some-endpoint
    requiresOAuth: true
    headers:
      X-User-ID: '{{LIBRECHAT_USER_ID}}'
      X-API-Key: '${SOME_API_KEY}'
    serverInstructions: true # Use server-provided instructions
  puppeteer:
    type: stdio
    command: npx
    args:
      - -y
      - '@modelcontextprotocol/server-puppeteer'
    serverInstructions: 'Do not access any local files or local/internal IP addresses'
  filesystem:
    # type: stdio
    command: npx
    args:
      - -y
      - '@modelcontextprotocol/server-filesystem'
      - /home/user/LibreChat/
    iconPath: /home/user/LibreChat/client/public/assets/logo.svg
    # The “wrench” icon shows up if no icon is provided as it is the default rendering.
  mcp-obsidian:
    command: npx
    args:
      - -y
      - 'mcp-obsidian'
      - /path/to/obsidian/vault
  streamable-http-server:
    type: streamable-http
    url: https://example.com/api/
    proxy: '${MCP_PROXY_URL}'
  per-user-credentials-example:
    type: streamable-http
    url: 'https://example.com/api/'
    headers:
      X-Auth-Token: '{{MY_SERVICE_API_KEY}}'
    customUserVars:
      MY_SERVICE_API_KEY:
        title: 'My Service API Key'
        description: "Enter your personal API key for the service. You can generate one at <a href='https://myservice.example.com/developer/keys' target='_blank'>Service Developer Portal</a>."
        sensitive: true
      MY_SERVICE_PROJECT:
        title: 'Project ID'
        description: 'Enter the project ID used by this service.'
        sensitive: false
  oauth-example:
    type: streamable-http
    url: https://api.example.com/mcp/
    oauth:
      authorization_url: https://example.com/oauth/authorize
      token_url: https://example.com/oauth/token
      client_id: your_client_id
      client_secret: your_client_secret
      redirect_uri: http://localhost:3080/api/mcp/oauth-example/oauth/callback
      scope: 'read execute'
  obo-example:
    type: streamable-http
    url: https://api.example.com/mcp/
    obo:
      scopes: 'api://mcp-server-id/Mcp.Tools.ReadWrite'
```

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

### Example SAML Certificate File Content

Source: https://www.librechat.ai/docs/configuration/authentication/SAML

This is an example of the content expected in a SAML certificate file (PEM format).

```text
-----BEGIN CERTIFICATE-----
MIIDazCCAlOgAwIBAgIUKhXaFJGJJPx466rl...
-----END CERTIFICATE-----
```

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

### Example Registration Object Structure

Source: https://www.librechat.ai/docs/configuration/librechat_yaml/object_structure/registration

This is a complete example of the registration object structure, showing how to define social login providers and allowed email domains.

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

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

### Start Docker Compose Services

Source: https://www.librechat.ai/docs/remote/docker_linux

Starts the Docker services defined in the deploy-compose.yml file. This command may rebuild images if necessary.

```bash
docker compose -f ./deploy-compose.yml up
```

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

### Install and Build LibreChat

Source: https://www.librechat.ai/docs/development/get_started

Run the smart reinstall command for dependencies and then build the project. If Node.js or npm versions were recently changed, use `npm run reinstall` for a clean installation.

```bash
npm run smart-reinstall
npm run build
```

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

### Calculate Token Value Example

Source: https://www.librechat.ai/docs/configuration/token_usage

Example calculation demonstrating how to compute the token value using the provided raw amount and rate.

```plaintext
137 \times 1.5 = 205.5
```

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

### Clean Install Dependencies

Source: https://www.librechat.ai/docs/development

Perform a clean installation of dependencies. Use this after changing Node/npm versions or if the dependency state becomes suspect.

```bash
npm run reinstall
```

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

### Combined AWS Bedrock Configuration Example

Source: https://www.librechat.ai/docs/configuration/librechat_yaml/object_structure/aws_bedrock

A comprehensive example demonstrating the configuration of Bedrock models and their corresponding inference profiles, including cross-region model IDs and environment variable interpolation.

```yaml
endpoints:
  bedrock:
    models:
      - 'us.anthropic.claude-sonnet-4-20250514-v1:0'
      - 'us.anthropic.claude-haiku-4-20250514-v1:0'
    inferenceProfiles:
      'us.anthropic.claude-sonnet-4-20250514-v1:0': '${BEDROCK_CLAUDE_SONNET_PROFILE}'
      'us.anthropic.claude-haiku-4-20250514-v1:0': '${BEDROCK_CLAUDE_HAIKU_PROFILE}'
```

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

### Install LibreChat Helm Chart (Local Development)

Source: https://www.librechat.ai/docs/local/helm_chart

Install the LibreChat Helm chart from a local directory, typically used during development. Navigate to the repo's root directory first.

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

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

### Enable Marketplace Access

Source: https://www.librechat.ai/docs/configuration/librechat_yaml/object_structure/interface.mdx

Example of how to enable access to the Agent Marketplace by setting 'use' to true.

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

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

### Rate Limits Configuration Example

Source: https://www.librechat.ai/docs/configuration/librechat_yaml/object_structure/config

This example demonstrates how to configure rate limits for various operations including file uploads, conversation imports, STT, and TTS. It shows settings for IP-based and user-based limits with specified time windows.

```yaml
rateLimits:
  fileUploads:
    ipMax: 100
    ipWindowInMinutes: 60
    userMax: 50
    userWindowInMinutes: 60
  conversationsImport:
    ipMax: 100
    ipWindowInMinutes: 60
    userMax: 50
    userWindowInMinutes: 60
  stt:
    ipMax: 100
    ipWindowInMinutes: 1
    userMax: 50
    userWindowInMinutes: 1
  tts:
    ipMax: 100
    ipWindowInMinutes: 1
    userMax: 50
    userWindowInMinutes: 1
```

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

### Huggingface API Key Setup

Source: https://www.librechat.ai/docs/configuration/librechat_yaml/ai_endpoints/huggingface

Set your Huggingface API token in the .env file for authentication.

```shell
HUGGINGFACE_TOKEN=your-api-key
```

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

### Example ngrok URL for Auth0 Callback

Source: https://www.librechat.ai/docs/configuration/authentication/OAuth2-OIDC/auth0

This is an example of an ngrok URL that can be used for local development and testing. Ensure this matches the 'Allowed Callback URLs' in your Auth0 application settings.

```bash
ngrok http 3080
# This will give you a URL like: https://abc123.ngrok.io
```

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

### Start Backend and Frontend Development Servers

Source: https://www.librechat.ai/docs/development/architecture

Start the backend server for API requests and the frontend development server with Hot Module Replacement (HMR). The frontend dev server requires the backend to be running.

```bash
npm run backend
```

```bash
npm run backend:dev
```

```bash
npm run frontend:dev
```

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

### Initialize Environment File

Source: https://www.librechat.ai/docs/remote/docker_linux

Copy the example environment file to `.env` and update sensitive values. This file holds application secrets and configurations.

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

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

### Azure OpenAI Group Configuration Example

Source: https://www.librechat.ai/docs/configuration/azure

Example of a group-level configuration for Azure OpenAI in the `librechat.yaml` file. This demonstrates setting up a group with API key, instance name, deployment details, custom headers, parameters, and model mappings.

```yaml
endpoints:
  azureOpenAI:
    # ... (endpoint-level configurations)
    groups:
      - group: "my-resource-group"
        apiKey: "${AZURE_API_KEY}"
        instanceName: "my-instance"
        deploymentName: "gpt-35-turbo"
        version: "2023-03-15-preview"
        baseURL: "https://my-instance.openai.azure.com/"
        additionalHeaders:
          CustomHeader: "HeaderValue"
        addParams:
          max_tokens: 2048
          temperature: 0.7
        dropParams:
          - "frequency_penalty"
          - "presence_penalty"
        models:
        # ... (model-level configurations)

```

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

### Perplexity API Key Setup

Source: https://www.librechat.ai/docs/configuration/librechat_yaml/ai_endpoints/perplexity

Add your Perplexity API key to your `.env` file for authentication.

```dotenv
PERPLEXITY_API_KEY=your-api-key
```

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

### Complete Balance Configuration Settings

Source: https://www.librechat.ai/docs/configuration/token_usage

Use this complete example to configure all aspects of the token credit balance system. Ensure your YAML file is correctly formatted.

```yaml
version: 1.3.5

# Balance settings
balance:
  enabled: true # Enable token credit balances for users
  startBalance: 20000 # Initial tokens credited upon registration
  autoRefillEnabled: false # Enable automatic token refills
  refillIntervalValue: 30 # Numerical value for refill interval
  refillIntervalUnit: 'days' # Time unit for refill interval (days, hours, etc.)
  refillAmount: 10000 # Tokens added during each refill
```

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

### Start Backend Development Server

Source: https://www.librechat.ai/docs/development

Launches the backend server with file watching enabled for rapid development cycles.

```bash
npm run backend:dev
```

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

### Delete User Script (Deploy Compose)

Source: https://www.librechat.ai/docs/configuration/authentication

Use this command to delete a user by email when using the deploy-compose.yml setup, as per the Ubuntu Docker Guide.

```bash
docker exec -it LibreChat-API /bin/sh -c "cd .. && npm run delete-user email@domain.com"
```

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

### Create User Script (Deploy Compose)

Source: https://www.librechat.ai/docs/configuration/authentication

Use this command to create a new user via the API when using the deploy-compose.yml setup, as per the Ubuntu Docker Guide.

```bash
docker exec -it LibreChat-API /bin/sh -c "cd .. && npm run create-user"
```

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

### Switch to New User

Source: https://www.librechat.ai/docs/remote/digitalocean

Log out of the root user and log in as the newly created user to continue with the setup using their permissions.

```bash
# example: su - danny
su - <yourusername>
```

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

### Configure Anthropic Claude Compatible Custom Endpoint

Source: https://www.librechat.ai/docs/configuration/librechat_yaml/object_structure/custom_endpoint

Example configuration for integrating an Anthropic Claude compatible model as a custom endpoint. This setup uses the native Messages API and specifies required headers.

```yaml
    # Example using the native Anthropic Messages API
    - name: 'Claude-Compatible'
      provider: 'anthropic'
      apiKey: '${ANTHROPIC_API_KEY}'
      baseURL: 'https://api.anthropic.com'
      headers:
        anthropic-version: '2023-06-01'
      models:
        default: ['claude-sonnet-4-5', 'claude-opus-4-5']
        fetch: false
      titleConvo: true
      titleModel: 'claude-sonnet-4-5'
      modelDisplayLabel: 'Claude (Compatible)'
```

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

### Configure Spotify MCP Server with OAuth Client Discovery and Refresh Tokens

Source: https://www.librechat.ai/docs/features/mcp

Example configuration for a self-hosted Spotify MCP server using streamable-http transport and OAuth Client Discovery. This setup automatically refreshes authentication tokens, providing a more seamless user experience.

```yaml
mcpServers:
  # Example self-hosted remote MCP server for Spotify, uses OAuth Client Discovery
  # ✅ Refresh Tokens: refreshes token for authentication automatically
  # Hosted on Cloudflare Workers, more info: https://github.com/LibreChat-AI/spotify-mcp
  spotify:
    type: 'streamable-http'
    initTimeout: 150000
    url: 'https://mcp-spotify-oauth-example.account.workers.dev/mcp'
```

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

### Verify Docker Compose Installation

Source: https://www.librechat.ai/docs/remote/docker_linux

Checks the installed version of Docker Compose to confirm successful installation.

```bash
docker compose version
```

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

### Start Meilisearch Process

Source: https://www.librechat.ai/docs/configuration/meilisearch

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

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

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

### Run Frontend in Development Mode

Source: https://www.librechat.ai/docs/development/get_started

Start the frontend development server to monitor changes. Ensure the backend is running first. The frontend is accessible at http://localhost:3090/.

```bash
npm run frontend:dev
```

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

### Anyscale API Key Setup

Source: https://www.librechat.ai/docs/configuration/librechat_yaml/ai_endpoints/anyscale

Add your Anyscale API key to your `.env` file for authentication.

```shell
ANYSCALE_API_KEY=your-api-key
```

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

### Install Node.js Dependencies

Source: https://www.librechat.ai/docs/local

Install all project dependencies for LibreChat using npm ci.

```bash
$npm ci
```

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

### Example Shared Endpoint Configuration

Source: https://www.librechat.ai/docs/configuration/librechat_yaml/object_structure/shared_endpoint_settings

Demonstrates how to configure shared settings for various endpoints like OpenAI, Azure OpenAI, Anthropic, Bedrock, and Google. Includes individual endpoint settings and a global 'all' configuration for overriding defaults.

```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}
```

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

### Start MongoDB Container

Source: https://www.librechat.ai/docs/configuration/mongodb/mongodb_auth

Stops all running containers and then starts only the MongoDB container in detached mode.

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

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

### Install Docker Dependencies

Source: https://www.librechat.ai/docs/remote/docker_linux

Installs necessary packages for Docker to function, including transport-https, curl, and software-properties-common.

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

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

### Vertex AI Setup

Source: https://www.librechat.ai/docs/features/image_gen

Configure environment variables for Vertex AI, including the service account key file and optional cloud location.

```bash
GOOGLE_SERVICE_KEY_FILE=/path/to/service-account.json
GOOGLE_CLOUD_LOCATION=us-central1  # optional, default: global
```

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

### Install Certbot for CentOS

Source: https://www.librechat.ai/docs/remote/nginx

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

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

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

### Install Certbot for Ubuntu

Source: https://www.librechat.ai/docs/remote/nginx

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

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

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

### Example Actions Object Structure

Source: https://www.librechat.ai/docs/configuration/librechat_yaml/object_structure/actions

Demonstrates the configuration of allowed domains and addresses for agent actions. Use 'allowedDomains' for a strict whitelist or rely on default SSRF protection with specific '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 LibreChat with Docker Compose

Source: https://www.librechat.ai/docs/local

Start all necessary services for LibreChat using Docker Compose in detached mode.

```bash
$docker compose up -d
```

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

### Create a Dismissible Welcome Banner

Source: https://www.librechat.ai/docs/configuration/banner

Example of creating a simple welcome message banner that users can dismiss. Dates are left empty to use default 'now' and 'forever'.

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

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

### Start LibreChat with Updated Images

Source: https://www.librechat.ai/docs/local/docker

Start LibreChat services using Docker Compose, applying any newly pulled images.

```bash
docker compose up
```

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

### Start Backend Server

Source: https://www.librechat.ai/docs/development/get_started

Use `npm run backend` for normal operation or `npm run backend:dev` to enable watch mode for active development. The backend is accessible at http://localhost:3080/.

```bash
npm run backend
npm run backend:dev
```

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

### Enable Meilisearch in .env (Source Install)

Source: https://www.librechat.ai/docs/configuration/meilisearch

Configure LibreChat for a source installation by setting the Meilisearch host and master key in the .env file.

```env
SEARCH=true
MEILI_NO_ANALYTICS=true
MEILI_HOST=http://localhost:7700
MEILI_MASTER_KEY=<your_master_key>
```

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

### MongoDB Atlas Connection String Example

Source: https://www.librechat.ai/docs/configuration/mongodb/mongodb_atlas

This is an example of a MongoDB Atlas connection string. Replace placeholders with your actual credentials and cluster URL.

```text
mongodb+srv://username:password@cluster-url.mongodb.net/LibreChat?retryWrites=true
```

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

### Start Docker Service

Source: https://www.librechat.ai/docs/remote/docker_linux

Ensure the Docker service is running on your Linux system. This command starts the Docker daemon if it's not already active.

```bash
# should already be running, but just to be safe
sudo systemctl start docker

# confirm docker is running
docker info
```

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

### Install Docker CE

Source: https://www.librechat.ai/docs/remote/docker_linux

Installs the Docker Community Edition (CE) package. This is the recommended version for most users, providing up-to-date features and security patches.

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

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

### Docker Ngrok Installation

Source: https://www.librechat.ai/docs/remote/ngrok

Run ngrok as a Docker container to tunnel a local server. Ensure you replace '<your token>' with your actual ngrok auth token.

```bash
docker run -d -it -e NGROK_AUTHTOKEN=<your token> ngrok/ngrok http 80
```

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

### Production Redirect URI Example

Source: https://www.librechat.ai/docs/mcp_servers/google_workspace

Example of a production redirect URI for the OAuth 2.0 callback. Replace `https://chat.example.com` with your actual LibreChat domain.

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

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

### Calculate USD Spend Example

Source: https://www.librechat.ai/docs/configuration/token_usage

Example calculation showing the conversion of token value to USD. This illustrates the actual monetary cost of token usage.

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

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

### Development Redis Setup

Source: https://www.librechat.ai/docs/configuration/redis

Configure Redis for local development using a simple URI and a development-specific key prefix.

```env
USE_REDIS=true
REDIS_URI=redis://127.0.0.1:6379
REDIS_KEY_PREFIX=librechat-dev
```

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

### Azure OpenAI Endpoint Configuration Example

Source: https://www.librechat.ai/docs/configuration/azure

Example configuration for Azure OpenAI endpoints in `librechat.yaml`. This includes settings for title generation, plugins, and assistants.

```yaml
endpoints:
  azureOpenAI:
    titleModel: "gpt-3.5-turbo-1106"
    plugins: true
    assistants: true
    summarize: true
    summaryModel: "gpt-3.5-turbo-1106"
    titleConvo: true
    titleMethod: "functions"
    groups:
      # ... (group-level and model-level configurations)
```