DatabricksInstall

Overview

The "Create Index" operation of the Vector Search resource in this node allows users to create a new vector search index on a Databricks serving endpoint. This index is designed to store and query vector data efficiently, which is useful for applications involving similarity search, recommendation systems, or machine learning model outputs that rely on vector embeddings.

Typical use cases include:

• Creating an index to enable fast nearest neighbor searches over high-dimensional vector data.
• Setting up a vector search service endpoint to support semantic search or content-based retrieval.
• Preparing a vector database schema by specifying key columns such as the primary key and the vector column.

For example, a user might create an index named "product_embeddings" on a serving endpoint to enable searching similar products based on their vector representations.

Properties

Output

The output JSON structure after creating the index typically contains the response from the Databricks API confirming the creation status of the index. It may include details such as the index name, endpoint, and any metadata returned by the API.

No binary data output is expected from this operation.

Dependencies

• Requires an API authentication token credential to access the Databricks API.
• Needs the Databricks host URL configured in the credentials.
• The node uses HTTP requests to communicate with the Databricks REST API endpoints.

Troubleshooting

• Common Issues:

  • Incorrect or missing API authentication token can cause authorization failures.
  • Providing an invalid or non-existent endpoint name will result in errors from the API.
  • Using a primary key or vector column name that does not conform to the expected schema may cause the index creation to fail.

• Error Messages:

  • API Error: <status> <statusText>: Indicates the API responded with an error status code. Check the request parameters and credentials.
  • Network Error: No response received from server: Suggests connectivity issues or incorrect host configuration.
  • Validation errors if required properties like Index Name, Endpoint Name, Primary Key, or Vector Column are missing or invalid.

To resolve these, verify all input parameters, ensure the API token is valid, and confirm network connectivity to the Databricks host.

Links and References

• Databricks Vector Search Documentation (example link)
• Databricks REST API Reference
• n8n HTTP Request Node Documentation (for understanding underlying HTTP calls)