Cognee icon

Cognee

Add text data to a Cognee dataset, or trigger cognify to build a knowledge graph from added data, or run a search query on data in Cognee memory

Actions3

Cognify → Cognify

AI-generated

Overview

This node interacts with the Cognee service to manage and utilize text datasets for knowledge graph building and search. Specifically, the Cognify operation triggers Cognee to process one or more existing datasets to build a knowledge graph-based memory representation. This is useful after adding raw text data to Cognee datasets, enabling advanced semantic querying and knowledge extraction.

Common scenarios include:

  • Automating the transformation of raw text data into structured knowledge graphs.
  • Preparing datasets for efficient semantic search and retrieval.
  • Running background processing jobs to update knowledge graphs without blocking workflows.

For example, after collecting multiple text documents in Cognee datasets, you can use this node's Cognify operation to build a knowledge graph that represents relationships and concepts within the data, which can then be queried by other nodes or applications.

Properties

Name Meaning
Datasets One or more Cognee dataset names to process with the Cognify operation.
Run in Background Boolean flag indicating whether to run the cognify process asynchronously (fire-and-forget).

Output

The node outputs JSON data representing the response from the Cognee API after triggering the cognify process. This typically includes status information about the job execution or confirmation that the knowledge graph build has started or completed.

No binary data output is produced by this operation.

Dependencies

  • Requires an API key credential for authenticating with the Cognee service.
  • The base URL for the Cognee API must be configured in the node credentials.
  • The node sends HTTP POST requests to the /api/cognify endpoint of the Cognee API.

Troubleshooting

  • Common issues:

    • Invalid or missing API key credential will cause authentication failures.
    • Specifying dataset names that do not exist in Cognee will result in errors.
    • Network connectivity problems may prevent successful API calls.

  • Error messages:

    • Authentication errors usually indicate invalid or expired API keys; verify and update credentials.
    • Dataset not found errors suggest incorrect dataset names; double-check spelling and existence.
    • Timeout or connection errors may require checking network settings or Cognee service availability.

Links and References

Discussion