VLM Run icon

VLM Run

Interact with VLM.run API

Actions15

Overview

The Agent AI node with the "Linkedin" operation is designed to generate webpage content based on a provided URL using an AI model. It interacts with an external AI service to process the URL and produce generated web data, which can be used for tasks such as content summarization, analysis, or enrichment of LinkedIn pages or similar web resources.

This node is beneficial in scenarios where automated extraction and generation of webpage information are needed, for example:

  • Automatically generating summaries or insights from LinkedIn profile URLs.
  • Enriching CRM or marketing databases with AI-generated content from social media or professional networking sites.
  • Assisting in market research by quickly generating structured data from web pages.

Properties

Name Meaning
URL The URL of the webpage to generate or analyze.
Model The AI model to use for processing; currently supports "VLM-1".
Mode The mode of generation: "Fast" (quicker results) or "Accurate" (more thorough processing).
Headers Optional HTTP headers to include in the request, specified as key-value pairs.
Query Parameters Optional query parameters to include in the request URL, specified as key-value pairs.
Type of Data The format of the data sent in the request body: either JSON or Form Data.

Output

The node outputs a JSON object containing the generated webpage data returned from the AI service. This typically includes structured information derived from the input URL, such as text content, metadata, or other AI-generated insights relevant to the webpage.

If binary data were involved (not indicated for this operation), it would represent files or media related to the output, but for the Linkedin operation, output is JSON only.

Dependencies

  • Requires an API key credential for authenticating with the external AI service.
  • Depends on network access to the AI service endpoint to send requests and receive responses.
  • The node uses internal helper functions to handle HTTP requests and retries when waiting for asynchronous processing completion.

Troubleshooting

  • Missing or invalid URL: Ensure the URL property is correctly set and points to a valid webpage.
  • Authentication errors: Verify that the API key credential is configured properly and has necessary permissions.
  • Timeouts or slow responses: Using the "Fast" mode may reduce wait times at the cost of accuracy; network issues can also affect response times.
  • Unexpected response structure: If the AI service changes its API, the node might fail to parse the output correctly; check for updates or service status.
  • Headers or query parameters misconfiguration: Incorrectly formatted headers or parameters may cause request failures; ensure keys and values are correct.

Common error messages will relate to missing input data, failed HTTP requests, or API authentication failures. Resolving these usually involves verifying inputs, credentials, and network connectivity.

Links and References

Discussion