Lola Vision icon

Lola Vision

Basic Lola Sample Node
Join our community

Overview

The "Lola Vision" node is designed to process images using various computer vision and OCR (Optical Character Recognition) algorithms. It supports tasks such as image labeling, biometric face extraction and matching, and extracting information from identity documents (like US driver licenses and passports). This node is useful in scenarios where you need to automate the analysis of images for identification, verification, or classification purposes.

Practical examples:

  • Automatically label objects in uploaded images.
  • Extract faces from photos for biometric authentication.
  • Match two face images to verify identity.
  • Extract structured data from scanned ID documents (e.g., driver's license).
  • Classify US ID documents as either a driver license or passport.

Properties

Name Meaning
User Identifier An identifier to track the user associated with the chat session. Required.
Chat Identifier An identifier to track the chat session. Required.
Message Identifier A message identifier to track the message.
tracerId A message identifier to track the message.
Algorithm The processing algorithm to use. Options:
- Biometrics - Extract Face
- Biometrics - Face Match
- Labeling
- OCR - Classify US ID Documents
- OCR - Generic ID
- OCR - US Driver License
- OCR - US Passport
ID Country Country of the ID. Only shown when Algorithm is "OCR - Generic ID".
ID Type Type of the ID. Only shown when Algorithm is "OCR - Generic ID".
Image 1 (Base64) The first image in base64 format. Used as input for most algorithms.
Image 2 (Base64) The second image in base64 format. Only shown when Algorithm is "Biometrics - Face Match".
Image 1 (Store Key) Store key reference for the first image.
Image 1 (URL) URL for the first image. Only shown for certain algorithms ("OCR - Generic ID", "Biometrics - Extract Face", "Biometrics - Face Match").
Image 2 (Store Key) Store key reference for the second image. Only shown when Algorithm is "Biometrics - Face Match".
Image 2 (URL) URL for the second image. Only shown for certain algorithms ("OCR - Generic ID", "Biometrics - Extract Face", "Biometrics - Face Match").

Output

The node outputs a JSON object under the field lola_vision. The structure of this object depends on the selected algorithm:

{
  "lola_vision": {
    // Result varies by algorithm:
    // - For "Labeling": List of labels with their scores.
    // - For "Biometrics - Extract Face": Base64 string of the extracted face.
    // - For "Biometrics - Face Match": Matching score or result.
    // - For OCR algorithms: Extracted fields and values from the document.
    // - For unimplemented/unsupported operations: May be empty or throw an error.
  }
}

If the operation is not implemented (e.g., "OCR - US Passport"), an error will be thrown.

Dependencies

  • External Services: The node may require access to external APIs or services for image processing and OCR.
  • API Key: Optionally uses credentials named lolaKeyApi if configured.
  • n8n Configuration: No special configuration required unless using credentials.

Troubleshooting

  • Common Issues:

    • Missing or invalid image data (base64 or URL) can cause errors or empty results.
    • Selecting an unsupported or unimplemented algorithm (e.g., "OCR - US Passport") will result in an error.
    • Required fields (User Identifier, Chat Identifier) must be provided.

  • Error Messages:

    • "Not implemented yet": Returned if you select an algorithm that is not supported (e.g., "OCR - US Passport"). To resolve, choose a different algorithm.
    • Errors related to missing parameters or invalid image formats may occur if required inputs are not provided or incorrectly formatted.

Links and References

Discussion