Docs
⚙️ Configuration
librechat.yaml
Settings
OCR

OCR Config Object Structure

Overview

The ocr object allows you to configure Optical Character Recognition (OCR) settings for the application, enabling the extraction of text from images. This section provides a detailed breakdown of the ocr object structure.

There are 4 main fields under ocr:

  • mistralModel
  • apiKey
  • baseURL
  • strategy

Notes:

  • If using the Mistral OCR API, you don’t need to edit your librechat.yaml file.
    • You only need the following environment variables to get started: OCR_API_KEY and OCR_BASEURL.
  • OCR functionality allows the application to extract text from images, which can then be processed by AI models.
  • The default strategy is mistral_ocr, which uses Mistral’s OCR capabilities.
  • You can also configure a custom OCR service by setting the strategy to custom_ocr.
  • Azure-deployed Mistral OCR models can be used by setting the strategy to azure_mistral_ocr.
  • Google Vertex AI-deployed Mistral OCR models can be used by setting the strategy to vertexai_mistral_ocr.
    • Requires the GOOGLE_SERVICE_KEY_FILE environment variable to be set with service account credentials
    • The service key can be provided as: file path, URL, base64 encoded JSON, or raw JSON string
    • Project ID and location are automatically extracted from the service account credentials
  • If using the default Mistral OCR, you may optionally specify a specific Mistral model to use.
  • Environment variable parsing is supported for apiKey, baseURL, and mistralModel parameters.
  • A user_provided strategy option is planned for future releases but is not yet implemented.

Example

ocr
ocr:
  mistralModel: "mistral-ocr-latest"
  apiKey: "your-mistral-api-key"
  strategy: "mistral_ocr"

Example with custom OCR:

ocr with custom OCR
ocr:
  apiKey: "your-custom-ocr-api-key"
  baseURL: "https://your-custom-ocr-service.com/api"
  strategy: "custom_ocr"

Example with Azure Mistral OCR:

ocr with Azure Mistral OCR
ocr:
  mistralModel: "deployed-mistral-ocr-2503" # should match deployment name on Azure
  apiKey: "${AZURE_MISTRAL_OCR_API_KEY}" # arbitrary .env var reference
  baseURL: "https://your-deployed-endpoint.models.ai.azure.com/v1" # hardcoded, can also be .env var reference
  strategy: "azure_mistral_ocr"

Example with Google Vertex AI Mistral OCR:

ocr with Google Vertex AI Mistral OCR
ocr:
  mistralModel: "mistral-ocr-2505" # model name as deployed in Vertex AI
  strategy: "vertexai_mistral_ocr"

mistralModel

KeyTypeDescriptionExample
mistralModelStringThe Mistral model to use for OCR processing. For Azure deployments, this should match your deployment name. For Google Vertex AI, this should match the model name in your deployment.Optional. Specifies which Mistral model should be used when the strategy is set to mistral_ocr, azure_mistral_ocr, or vertexai_mistral_ocr.
ocr / mistralModel
ocr:
  mistralModel: "mistral-ocr-latest"

For Azure deployments:

ocr / mistralModel (Azure)
ocr:
  mistralModel: "deployed-mistral-ocr-2503" # Your Azure deployment name

For Google Vertex AI deployments:

ocr / mistralModel (Google Vertex AI)
ocr:
  mistralModel: "mistral-ocr-2505" # Your Vertex AI model name

apiKey

KeyTypeDescriptionExample
apiKeyStringThe API key for the OCR service. Not used for Google Vertex AI (uses service account authentication via GOOGLE_SERVICE_KEY_FILE).Optional. Defaults to the environment variable OCR_API_KEY if not specified.
ocr / apiKey
ocr:
  apiKey: "your-ocr-api-key"

baseURL

KeyTypeDescriptionExample
baseURLStringThe base URL for the OCR service API. For Google Vertex AI, this is automatically constructed from the service account credentials.Optional. Defaults to the environment variable OCR_BASEURL if not specified.
ocr / baseURL
ocr:
  baseURL: "https://your-ocr-service.com/api"

strategy

KeyTypeDescriptionExample
strategyStringThe OCR strategy to use.Determines which OCR service to use. Options are "mistral_ocr", "azure_mistral_ocr", "vertexai_mistral_ocr", or "custom_ocr". Defaults to "mistral_ocr".
ocr / strategy
ocr:
  strategy: "custom_ocr"

Available Strategies: