VLM Run icon

VLM Run

Interact with VLM Run API

Overview

The node integrates with the VLM Run API to analyze various types of media files and execute agents. Specifically, for the Analyze Document operation, it uploads a document file, optionally processes it asynchronously, and extracts structured data such as resumes, invoices, presentations, or other document types. This is useful in automating data extraction workflows where documents need to be parsed into usable structured formats without manual intervention.

Practical examples include:

  • Automatically extracting invoice details from uploaded PDFs.
  • Parsing resumes to extract candidate information for HR systems.
  • Analyzing presentations to generate summaries or metadata.

Properties

Name Meaning
File The document file data from a previous node, typically binary content or a reference to it.
Domain Name or ID The domain context used for analysis, selectable from a list or specified via an expression.
Process Asynchronously Whether to process the document analysis request asynchronously (true/false).
Callback URL Required if asynchronous processing is enabled; the URL that VLM Run will call when processing completes.

Output

The node outputs JSON data representing the result of the document analysis. The structure depends on the response from the VLM Run API but generally includes extracted structured data relevant to the document content.

If asynchronous processing is enabled, the output may initially contain status or job identifiers, with the final results delivered to the specified callback URL.

No binary output is produced by this operation.

Dependencies

  • Requires an API key credential for authenticating with the VLM Run API.
  • Depends on the VLM Run service being accessible and configured properly.
  • The node uses internal helper functions to upload files and send requests to the API.
  • If asynchronous processing is enabled, a publicly accessible callback URL must be provided to receive completion notifications.

Troubleshooting

  • File Upload Failures: Ensure the input file data is correctly passed from the previous node and is accessible.
  • Invalid Domain: Selecting or specifying a domain not recognized by the API will cause errors. Use the domain dropdown or valid expressions.
  • Missing Callback URL: When asynchronous processing is enabled, omitting the callback URL will cause the node to throw an error.
  • API Errors: Network issues or invalid credentials can cause failures. Verify API keys and network connectivity.
  • Unsupported Operation: Using an operation other than "document" with these properties will raise an error.

Common error messages:

  • "Failed to load domains: ..." indicates issues fetching available domains.
  • "At least one file mapping is required when multiple files is enabled" applies to agent execution but signals missing required inputs.
  • "The operation \"document\" is not supported!" would indicate a misconfiguration or code issue.

Links and References

Discussion