Ragdoll AI icon

Ragdoll AI

Consume Ragdoll AI API
Join our community

Actions14

Overview

The node integrates with the Ragdoll AI API to manage and interact with data sources, knowledge bases, and documents. Specifically, for the Data Source resource and the Start Indexing operation, it triggers the indexing process of a specified data source. This operation is useful when you want to initiate or refresh the indexing of content from a data source so that it can be efficiently searched or queried later.

Typical use cases include:

  • Starting the indexing of a web page, Notion workspace, or Google Drive folder previously added as a data source.
  • Configuring how the text content is chunked during indexing to optimize search performance.
  • Automating the re-indexing process after updating the data source content.

For example, after adding a new website as a data source, you can use this node operation to start indexing its content with specific chunk size and overlap settings to prepare it for search queries.

Properties

Name Meaning
Data Source ID The unique identifier of the data source to start indexing.
Chunk Size Size of text chunks to create during indexing (number of characters).
Chunk Overlap Number of overlapping characters between consecutive text chunks.
Chunking Type Type of chunking used; fixed to "fixedSize" (hidden property, not user-configurable).

Output

The node outputs the JSON response returned by the Ragdoll AI API after starting the indexing process on the specified data source. This typically includes status information about the indexing job, such as whether it was successfully started or any relevant metadata.

No binary data output is involved in this operation.

Dependencies

  • Requires an active connection to the Ragdoll AI API endpoint.
  • Requires an API authentication token credential configured in n8n to authorize requests.
  • The base URL for the API is taken from the provided credentials.
  • The node sends a POST request to /v1/data-sources/{dataSourceId}/indexing with the chunking configuration in the request body.

Troubleshooting

  • Invalid Data Source ID: If the provided data source ID does not exist or is incorrect, the API will likely return a 404 error. Verify the ID before running the node.
  • Authentication Errors: Missing or invalid API credentials will cause authorization failures. Ensure the API key/token is correctly set up in n8n credentials.
  • Chunk Size/Overlap Misconfiguration: Setting chunk size or overlap to inappropriate values (e.g., zero or negative) may cause errors or unexpected behavior. Use sensible defaults like chunk size 1000 and overlap 200.
  • API Endpoint Unreachable: Network issues or incorrect base URL in credentials can prevent the node from connecting to the API. Check network connectivity and credential configuration.

Links and References

Discussion