Cloudflare Vectorize icon

Cloudflare Vectorize

Execute operations against Cloudflare Vectorize vector databases. Supports vector operations (insert, upsert, query), index management, metadata filtering, and can be used as a tool by AI Agents for semantic search and RAG applications.

Actions16

Vector → Delete by IDs

AI-generated

Overview

The "Cloudflare Vectorize" node enables interaction with Cloudflare's Vectorize vector database service. It supports managing vector indexes and performing vector operations such as inserting, updating, querying, retrieving, and deleting vectors by their IDs. This node is particularly useful for applications involving semantic search, recommendation systems, or any AI-driven solution that requires efficient vector similarity searches.

For the Vector - Delete by IDs operation specifically, the node deletes one or more vectors from a specified vector index using their unique vector IDs. This is beneficial when you need to remove outdated or irrelevant vectors from your index to maintain data accuracy and relevance.

Practical example:
If you have an index storing product embeddings for a recommendation engine, and some products are discontinued, you can use this operation to delete the corresponding vectors by their IDs, ensuring they no longer appear in search results.

Properties

Name Meaning
Index Name The name of the Vectorize index from which vectors will be deleted. Must be lowercase and contain only letters, numbers, and hyphens.
Vector IDs An array of vector IDs (strings) specifying which vectors to delete from the index. Example: ["vector-1", "vector-2"]

Output

The output JSON object for the "Delete by IDs" operation includes:

  • mutationId: A unique identifier for the delete mutation request, useful for tracking or logging.
  • deletedCount: The number of vectors successfully deleted, which corresponds to the count of provided vector IDs.

Example output:

{
  "mutationId": "some-unique-id",
  "deletedCount": 2
}

This confirms the deletion operation was processed and how many vectors were removed.

Dependencies

  • Requires an API key credential for authenticating with the Cloudflare Vectorize service.
  • The node depends on the external Cloudflare Vectorize API to perform vector database operations.
  • Proper configuration of the API credentials within n8n is necessary for successful execution.

Troubleshooting

  • Common issues:

    • Providing an invalid or non-existent index name will cause errors.
    • Supplying vector IDs that do not exist in the index may result in fewer deletions than expected.
    • Malformed JSON input for vector IDs can cause parsing errors.

  • Error messages:

    • "Unknown vector operation": Indicates an unsupported operation was requested; ensure "deleteByIds" is selected.
    • "Unknown resource": Occurs if the resource parameter is incorrect; must be "vector" for this operation.
    • API authentication errors: Check that the API key credential is correctly configured and has sufficient permissions.

  • Resolution tips:

    • Verify the index name matches exactly the existing index.
    • Confirm vector IDs are correct and exist in the index.
    • Ensure JSON arrays are properly formatted.
    • Check API credentials and network connectivity.

Links and References

Discussion