Exa Websets icon

Exa Websets

Create, manage, and query structured datasets from web sources using Exa Websets API

Actions28

Overview

The node "Exa Websets" allows users to interact with the Exa Websets API, which provides structured datasets from web sources. Specifically, for the Item resource and the List operation, this node fetches a list of individual items contained within a specified webset.

This operation is useful when you want to retrieve and process multiple content items (such as articles, images, videos, PDFs, or text snippets) that belong to a particular webset. For example, you might use it to:

  • Aggregate all news articles collected in a webset about a specific topic.
  • Retrieve images or videos stored in a webset for further processing or analysis.
  • Filter items by language, content type, or relevance score to focus on the most pertinent data.

Practical scenarios include content curation, automated data extraction workflows, or feeding downstream processes like sentiment analysis or machine learning models.

Properties

Name Meaning
Webset ID The unique identifier of the webset containing the items to be listed. This is required to specify which collection of items to query.
Return All Boolean flag indicating whether to return all matching results or limit the output to a maximum number.
Limit When Return All is false, this sets the maximum number of items to return. Must be at least 1.
Filters A set of optional filters to narrow down the items returned:
- Content Type: Filter by item type such as HTML, Image, PDF, Text, or Video.
- Domain: Filter items originating from a specific domain.
- Has Content: Whether to only include items that have extracted content.
- Language: Filter by content language (e.g., English, French, German).
- Max Score: Maximum relevance score (0 to 1).
- Min Score: Minimum relevance score (0 to 1).
Additional Options Extra options to customize the output:
- Include Content: Whether to include the full content of each item.
- Include Metadata: Whether to include metadata for each item.
- Sort By: Field to sort results by (Date Created, Date Updated, Relevance Score, Title, URL).
- Sort Order: Sort direction (Ascending or Descending).

Output

The node outputs an array of items matching the query criteria. Each item in the json output typically includes:

  • Core item data such as title, URL, content type, language, and relevance score.
  • Optionally, the full content of the item if Include Content is enabled.
  • Metadata fields if Include Metadata is enabled, which may include creation and update timestamps, source domain, and other descriptive attributes.

The output does not explicitly mention binary data, so it is assumed that all data is returned as JSON objects representing the items.

Dependencies

  • Requires an active connection to the Exa Websets API via an API key credential configured in n8n.
  • The node uses the base URL https://api.exa.ai for API requests.
  • No additional external dependencies are indicated beyond the API access.

Troubleshooting

  • Common Issues:

    • Invalid or missing Webset ID will cause the API call to fail; ensure the Webset ID is correct and accessible.
    • If no items match the filter criteria, the output will be empty; try adjusting filters or removing restrictive conditions.
    • API rate limits or connectivity issues can cause errors; verify network access and API quota.

  • Error Messages:

    • "Unknown resource" error indicates an invalid resource parameter; ensure "items" is selected.
    • Errors related to authentication usually mean the API key credential is missing or invalid.
    • If the node throws errors about parameters, check that required fields like Webset ID are provided and valid.

Links and References

If you need details on other resources or operations, feel free to ask!

Discussion