librechat.yaml

# For more information, see the Configuration Guide:
# https://www.librechat.ai/docs/configuration/librechat_yaml

# Configuration version (required)
version: 1.2.1

# Cache settings: Set to true to enable caching
cache: true

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

  # Terms of service
  termsOfService:
    externalUrl: 'https://librechat.ai/tos'
    openNewTab: true
    modalAcceptance: true
    modalTitle: "Terms of Service for LibreChat"
    modalContent: |
      # Terms and Conditions for LibreChat

      Please do not use chatgpt , since librechat is better 😀

      Regards , Vaibhav 

      

  endpointsMenu: true
  modelSelect: true
  parameters: true
  sidePanel: true
  presets: true
  prompts: true
  bookmarks: true
  multiConvo: true
  agents: true

# Example Registration Object Structure (optional)
registration:
  socialLogins: ['github', 'google', 'discord', 'openid', 'facebook']
  # allowedDomains:
  # - "gmail.com"

# speech:
#   tts:
#     openai:
#       url: ''
#       apiKey: '${TTS_API_KEY}'
#       model: ''
#       voices: ['']

#  
#   stt:
#     openai:
#       url: ''
#       apiKey: '${STT_API_KEY}'
#       model: ''

# rateLimits:
#   fileUploads:
#     ipMax: 100
#     ipWindowInMinutes: 60  # Rate limit window for file uploads per IP
#     userMax: 50
#     userWindowInMinutes: 60  # Rate limit window for file uploads per user
#   conversationsImport:
#     ipMax: 100
#     ipWindowInMinutes: 60  # Rate limit window for conversation imports per IP
#     userMax: 50
#     userWindowInMinutes: 60  # Rate limit window for conversation imports per user

# Example Actions Object Structure
actions:
  allowedDomains:
    - "swapi.dev"
    - "librechat.ai"
    - "google.com"
    - "https://api.e2b.dev"
    - "api.e2b.dev"
# Example MCP Servers Object Structure
mcpServers:
  # everything:
  #   type: sse # type can optionally be omitted
  #   url: https://787d-182-69-182-121.ngrok-free.app/


  # memory:
  #  type: stdio
  #  command: npx
  #  args:
  #    - -y
  #    - "@modelcontextprotocol/server-memory"
  #  timeout: 60000000


  # apify:
  #   type: stdio
  #   command: npx
  #   args:
  #     - -y
  #     - "@apify/actors-mcp-server"
  #     - --actors
  #     - apify/screenshot-url,apify/website-content-crawler,apify/puppeteer-scraper,apify/rag-web-browser,jancurn/screenshot-taker,apify/cheerio-scraper,apify/playwright-scraper,apify/ai-web-agent,marco.gullo/page-printer,dz_omar/example-website-screenshot-crawler,apify/legacy-phantomjs-crawler,lukaskrivka/article-extractor-smart
  #   timeout: 60000000
  #   env:
  #     APIFY_TOKEN: "apify_api_M3vftXQILokc2NDlhsc3twMBa5e7Be282swR"
      # PATH: "/usr/local/bin:/usr/bin:/bin"
      # NODE_PATH: "/usr/local/lib/node_modules" 

  hfspace:
    type: stdio
    command: npx
    args:
      - -y
      - "@llmindset/mcp-hfspace"
      - --HF_TOKEN=${HF_TOKEN}
      - --work-dir=/app/uploads/temp/
      - Qwen/Qwen2.5-Max-Demo
      - evalstate/FLUX.1-schnell
    timeout: 60000000
  #   env:
  #    E2B_API_KEY: "e2b_6eb042e8d60248f71b0aadcc05f29a7dd353b3e2"
  #    PATH: "/usr/local/bin:/usr/bin:/bin"
  #    NODE_PATH: "/usr/local/lib/node_modules" 
  exa:
    type: stdio
    command: npx
    args:
      - -y
      - "/app/exa-mcp-server/build/index.js"
      # - --HF_TOKEN=${HF_TOKEN}
    timeout: 60000000
    env:
     EXA_API_KEY: "e4399980-1016-44ab-8789-1ef7f967a281"
     PATH: "/usr/local/bin:/usr/bin:/bin"
     NODE_PATH: "/usr/local/lib/node_modules" 
  arxiv:
    type: stdio
    command: python
    args:
      - -m
      - mcp_simple_arxiv
    timeout: 60000000
  pubmed:
    type: stdio
    command: python
    args:
      - -m
      - mcp_simple_pubmed
    env:
      PUBMED_EMAIL: "vaibhavarduino@gmail.com"
      PUBMED_API_KEY : "77ea72d89b98d279c1848389cd027a51c408"
      PATH: "/usr/local/bin:/usr/bin:/bin"
      NODE_PATH: "/usr/local/lib/node_modules" 
  memory:
   type: stdio
   command: npx
   args:
     - -y
     - "@modelcontextprotocol/server-memory"
   timeout: 60000000
  filesystem:
    # type: stdio
    command: npx
    args:
      - -y
      - "@modelcontextprotocol/server-filesystem"
      - /app/
  codesandbox:
    type: stdio
    command: python
    args:
      - tests.py
    timeout: 60000000
# Definition of custom endpoints
endpoints:
  agents:
    recursionLimit: 50
    disableBuilder: false
    capabilities:
      # - "execute_code"
      - "file_search"
      - "actions"
      - "tools"


  custom:
    # together.ai
    # https://api.together.ai/settings/api-keys
    # Model list: https://docs.together.ai/docs/inference-models
    - name: "together.ai"
      apiKey: '${MISTRAL_API_KEY}'
      baseURL: "https://api.together.xyz"
      models:
        default: [
          "Gryphe/MythoMax-L2-13b",
          "Gryphe/MythoMax-L2-13b-Lite",
          "NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO",
          "Qwen/QwQ-32B-Preview",
          "Qwen/Qwen2-72B-Instruct",
          "Qwen/Qwen2-VL-72B-Instruct",
          "Qwen/Qwen2.5-72B-Instruct-Turbo",
          "Qwen/Qwen2.5-7B-Instruct-Turbo",
          "Qwen/Qwen2.5-Coder-32B-Instruct",
          "databricks/dbrx-instruct",
          "deepseek-ai/DeepSeek-R1",
          "deepseek-ai/DeepSeek-V3",
          "deepseek-ai/deepseek-llm-67b-chat",
          "dev-vfs/Qwen2-VL-72B-Instruct",
          "devuser/test-lora-model-creation-1",
          "devuser/test-lora-model-creation-10",
          "devuser/test-lora-model-creation-2",
          "devuser/test-lora-model-creation-3",
          "devuser/test-lora-model-creation-4",
          "devuser/test-lora-model-creation-5",
          "devuser/test-lora-model-creation-6",
          "devuser/test-lora-model-creation-7",
          "devuser/test-lora-model-creation-8",
          "devuser/test-lora-model-creation-9",
          "google/gemma-2-27b-it",
          "google/gemma-2-9b-it",
          "google/gemma-2b-it",
          "jd/test-lora-model-creation-2",
          "jd/test-min-lora-model-creation-2",
          "justindriemeyer_tai/test-lora-model-creation-3",
          "justindriemeyer_tai/test-lora-model-creation-4",
          "justindriemeyer_tai/test-lora-model-creation-5",
          "justindriemeyer_tai/test-lora-model-creation-6",
          "justindriemeyer_tai/test-lora-model-creation-7",
          "llava-hf/llava-v1.6-mistral-7b-hf",
          "meta-llama/Llama-2-13b-chat-hf",
          "meta-llama/Llama-2-7b-chat-hf",
          "meta-llama/Llama-3-70b-chat-hf",
          "meta-llama/Llama-3-8b-chat-hf",
          "meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo",
          "meta-llama/Llama-3.2-3B-Instruct-Turbo",
          "meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo",
          "meta-llama/Llama-3.3-70B-Instruct-Turbo",
          "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free",
          "meta-llama/Llama-Vision-Free",
          "meta-llama/Meta-Llama-3-70B-Instruct-Lite",
          "meta-llama/Meta-Llama-3-70B-Instruct-Turbo",
          "meta-llama/Meta-Llama-3-8B-Instruct-Lite",
          "meta-llama/Meta-Llama-3-8B-Instruct-Turbo",
          "meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo",
          "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo",
          "meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo",
          "meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo-128K",
          "microsoft/WizardLM-2-8x22B",
          "mistralai/Mistral-7B-Instruct-v0.1",
          "mistralai/Mistral-7B-Instruct-v0.2",
          "mistralai/Mistral-7B-Instruct-v0.3",
          "mistralai/Mixtral-8x22B-Instruct-v0.1",
          "mistralai/Mixtral-8x7B-Instruct-v0.1",
          "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF",
          "salesforce/xgen-9b-instruct",
          "scb10x/llama-3-typhoon-v1.5-8b-instruct",
          "scb10x/scb10x-llama3-typhoon-v1-5-8b-instruct",
          "scb10x/scb10x-llama3-typhoon-v1-5x-4f316",
          "togethercomputer/Llama-3-8b-chat-hf-int4",
          "togethercomputer/Llama-3-8b-chat-hf-int8",
          "upstage/SOLAR-10.7B-Instruct-v1.0",
          "vfs/Qwen2-VL-72B-Instruct"
          ]
        fetch: false
      titleConvo: true
      titleModel: "openchat/openchat-3.5-1210"
      summarize: false
      summaryModel: "openchat/openchat-3.5-1210"
      forcePrompt: false
      modelDisplayLabel: "together.ai"
    - name: "OpenRouter"
      # For `apiKey` and `baseURL`, you can use environment variables that you define.
      # recommended environment variables:
      apiKey: "${OPENROUTER_KEY}" # NOT OPENROUTER_API_KEY
      baseURL: "https://openrouter.ai/api/v1"
      models:
        default: ["deepseek/deepseek-chat","deepseek/deepseek-r1:free","google/gemini-2.0-flash-thinking-exp:free","google/gemini-2.0-flash-exp:free","google/gemini-exp-1206:free"]
        fetch: true
      titleConvo: true
      titleModel: "google/gemini-2.0-flash-exp:free"
      # Recommended: Drop the stop parameter from the request as Openrouter models use a variety of stop tokens.
      dropParams: ["stop"]
      modelDisplayLabel: "OpenRouter"
    # Groq Example
    - name: 'groq'
      apiKey: '${GROQ_API_KEY}'
      baseURL: 'https://api.groq.com/openai/v1/'
      models:
        default:
          [
            'deepseek-r1-distill-qwen-32b',
            'deepseek-r1-distill-llama-70b',
            'llama-3.3-70b-versatile',
            'mixtral-8x7b-32768',
            'qwen-qwq-32b',
          ]
        fetch: false
      titleConvo: true
      titleModel: 'mixtral-8x7b-32768'
      modelDisplayLabel: 'groq'
    - name: 'Tiny' # Unique name for the endpoint
      # For `apiKey` and `baseURL`, you can use environment variables that you define.
      # recommended environment variables:
      apiKey: '77ea72d89b98d279c1848389cd027a51c408'
      baseURL: 'https://962f-182-69-182-236.ngrok-free.app'

      # Models configuration
      models:
        # List of default models to use. At least one value is required.
        default: ['gemini-2.0-flash-thinking-exp-01-21' ,'deepseek.r1','deepseek-reasoner','deepseek-chat','gemini-2.0-pro-exp-02-05','deepseek-r1-distill-llama-70b', 'qwen-qwq-32b','QwQ-32B','llama-3.3-70b-versatile','DeepSeek-V3','DeepSeekV3-togetherAI','DeepSeek-R1','DeepSeekR1-togetherAI','gpt-4o','DeepSeek-R1-dev','DeepSeek-V3-dev']
        # Fetch option: Set to true to fetch models from API.
        # fetch: true # Defaults to false.

      # Optional configurations

      # Title Conversation setting
      titleConvo: true # Set to true to enable title conversation

      modelDisplayLabel: 'AI' # Default is "AI" when not set.
    - name: 'Tiny-DEV' # Unique name for the endpoint
      # For `apiKey` and `baseURL`, you can use environment variables that you define.
      # recommended environment variables:
      apiKey: '77ea72d89b98d279c1848389cd027a51c408'
      baseURL: 'https://akiko19191-backend.hf.space/'

      # Models configuration
      models:
        # List of default models to use. At least one value is required.
        default: ['gemini-2.0-flash-thinking-exp-01-21' ,'deepseek.r1','deepseek-reasoner','deepseek-chat','gemini-2.0-pro-exp-02-05','deepseek-r1-distill-llama-70b', 'qwen-qwq-32b','QwQ-32B','llama-3.3-70b-versatile','DeepSeek-V3','DeepSeekV3-togetherAI','DeepSeek-R1','DeepSeekR1-togetherAI','gpt-4o','DeepSeek-R1-dev','DeepSeek-V3-dev']
        # Fetch option: Set to true to fetch models from API.
        # fetch: false # Defaults to false.

      # Optional configurations

      # Title Conversation setting
      titleConvo: true # Set to true to enable title conversation

      modelDisplayLabel: 'Tiny' # Default is "AI" when not set.
  #   # Mistral AI Example
  #   - name: 'Mistral' # Unique name for the endpoint
  #     # For `apiKey` and `baseURL`, you can use environment variables that you define.
  #     # recommended environment variables:
  #     apiKey: '${MISTRAL_API_KEY}'
  #     baseURL: 'https://api.mistral.ai/v1'

  #     # Models configuration
  #     models:
  #       # List of default models to use. At least one value is required.
  #       default: ['mistral-tiny', 'mistral-small', 'mistral-medium']
  #       # Fetch option: Set to true to fetch models from API.
  #       fetch: true # Defaults to false.

  #     # Optional configurations

  #     # Title Conversation setting
  #     titleConvo: true # Set to true to enable title conversation

  #     # Title Method: Choose between "completion" or "functions".
  #     # titleMethod: "completion"  # Defaults to "completion" if omitted.

  #     # Title Model: Specify the model to use for titles.
  #     titleModel: 'mistral-tiny' # Defaults to "gpt-3.5-turbo" if omitted.

  #     # Summarize setting: Set to true to enable summarization.
  #     # summarize: false

  #     # Summary Model: Specify the model to use if summarization is enabled.
  #     # summaryModel: "mistral-tiny"  # Defaults to "gpt-3.5-turbo" if omitted.

  #     # Force Prompt setting: If true, sends a `prompt` parameter instead of `messages`.
  #     # forcePrompt: false

  #     # The label displayed for the AI model in messages.
  #     modelDisplayLabel: 'Mistral' # Default is "AI" when not set.

  #     # Add additional parameters to the request. Default params will be overwritten.
  #     # addParams:
  #     # safe_prompt: true # This field is specific to Mistral AI: https://docs.mistral.ai/api/

  #     # Drop Default params parameters from the request. See default params in guide linked below.
  #     # NOTE: For Mistral, it is necessary to drop the following parameters or you will encounter a 422 Error:
  #     dropParams: ['stop', 'user', 'frequency_penalty', 'presence_penalty']

  #   # OpenRouter Example
  #   - name: 'OpenRouter'
  #     # For `apiKey` and `baseURL`, you can use environment variables that you define.
  #     # recommended environment variables:
  #     # Known issue: you should not use `OPENROUTER_API_KEY` as it will then override the `openAI` endpoint to use OpenRouter as well.
  #     apiKey: '${OPENROUTER_KEY}'
  #     baseURL: 'https://openrouter.ai/api/v1'
  #     models:
  #       default: ['meta-llama/llama-3-70b-instruct']
  #       fetch: true
  #     titleConvo: true
  #     titleModel: 'meta-llama/llama-3-70b-instruct'
  #     # Recommended: Drop the stop parameter from the request as Openrouter models use a variety of stop tokens.
  #     dropParams: ['stop']
  #     modelDisplayLabel: 'OpenRouter'
    # together.ai
    # https://api.together.ai/settings/api-keys
    # Model list: https://docs.together.ai/docs/inference-models
  #   # Portkey AI Example
  #   - name: "Portkey"
  #     apiKey: "dummy"  
  #     baseURL: 'https://api.portkey.ai/v1'
  #     headers:
  #         x-portkey-api-key: '${PORTKEY_API_KEY}'
  #         x-portkey-virtual-key: '${PORTKEY_OPENAI_VIRTUAL_KEY}'
  #     models:
  #         default: ['gpt-4o-mini', 'gpt-4o', 'chatgpt-4o-latest']
  #         fetch: true
  #     titleConvo: true
  #     titleModel: 'current_model'
  #     summarize: false
  #     summaryModel: 'current_model'
  #     forcePrompt: false
  #     modelDisplayLabel: 'Portkey'
  #     iconURL: https://images.crunchbase.com/image/upload/c_pad,f_auto,q_auto:eco,dpr_1/rjqy7ghvjoiu4cd1xjbf
fileConfig:
  endpoints:
    agents:
      fileLimit: 5
      fileSizeLimit: 100  # Maximum size for an individual file in MB
      totalSizeLimit: 500  # Maximum total size for all files in a single request in MB
      supportedMimeTypes:
        - "image/.*"
        - "application/pdf"
        - "video/.*"
        - "application/vnd.ms-excel"
        - "audio/mp3"
        - "audio/mpeg"
        - "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"
        - "application/vnd.openxmlformats-officedocument.wordprocessingml.document"
        - "application/msword"
    # openAI:
#       disabled: true  # Disables file uploading to the OpenAI endpoint
#     default:
#       totalSizeLimit: 20
#     YourCustomEndpointName:
#       fileLimit: 2
#       fileSizeLimit: 5
#   serverFileSizeLimit: 100  # Global server file size limit in MB
#   avatarSizeLimit: 2  # Limit for user avatar image size in MB
# See the Custom Configuration Guide for more information on Assistants Config:
# https://www.librechat.ai/docs/configuration/librechat_yaml/object_structure/assistants_endpoint