Qdrant (Advanced)Install

Overview

This node provides advanced integration with the Qdrant vector search engine, allowing users to perform a wide range of operations on Qdrant collections and points. It supports managing collections (create, update, delete, list), manipulating points within collections (upsert, update, delete, retrieve), searching points by vector similarity, and counting points with optional filters.

Common scenarios include:

• Managing vector collections for machine learning or AI applications.
• Performing similarity searches on embedding vectors to find nearest neighbors.
• Maintaining and updating large datasets of vectorized data points.
• Counting or retrieving metadata about collections and their contents.

For example, you can use this node to create a new collection configured for your specific vector dimensions, upsert points representing documents or images with their embeddings, and then perform similarity searches to find related items.

Properties

Note: For the "List Collections" operation specifically, only the Collection Name property is relevant as an input parameter in the provided context, but it is required for other operations.

Output

The node outputs a JSON object containing the response from the Qdrant API corresponding to the selected operation:

• For List Collections, the output JSON contains an array of collection metadata objects describing all collections available in the Qdrant instance.
• For other operations, the output JSON structure varies accordingly, e.g., collection info, point data, success status, or search results.
• The node does not output binary data.

Example output for List Collections might look like:

[
  {
    "name": "collection1",
    "vectors_count": 1000,
    "config": { /* collection configuration details */ }
  },
  {
    "name": "collection2",
    "vectors_count": 500,
    "config": { /* collection configuration details */ }
  }
]

Dependencies

• Requires access to a Qdrant instance via its REST API.
• Needs an API key credential for authentication with Qdrant.
• Uses the official Qdrant JavaScript client library (@qdrant/js-client-rest).
• Requires proper configuration of the Qdrant API URL and API key in n8n credentials.

Troubleshooting

• Missing Collection Name: The node throws an error if the collection name is not provided when required.
• Invalid JSON Inputs: Many parameters accept JSON strings or objects; malformed JSON will cause errors.
• API Authentication Errors: Ensure the API key and URL are correctly set in credentials.
• Operation Not Supported: Selecting an unsupported operation will result in an error.
• Empty Required Fields: Operations like search require non-empty vectors and limits; missing these will throw errors.
• Network Issues: Connectivity problems with the Qdrant server will cause API call failures.

To resolve errors:

• Verify all required fields are filled and valid.
• Check JSON syntax carefully for parameters accepting JSON.
• Confirm API credentials and endpoint URL are correct.
• Review Qdrant server availability and network connectivity.

Links and References

• Qdrant Official Documentation
• Qdrant JavaScript Client GitHub
• Vector Search Concepts