Qdrant icon

Qdrant

Official n8n node to interface with Qdrant - https://qdrant.tech

Actions27

Collection → Create Collection

AI-generated

Overview

This node operation creates a new collection in Qdrant, a vector search engine. It allows users to define various parameters for the collection such as its name, vector configuration, sharding, replication, consistency, and other advanced settings. This operation is useful for setting up a new collection tailored to specific data storage and search requirements, such as creating a collection for storing and searching high-dimensional vectors in machine learning or AI applications.

Use Case Examples

  1. Creating a collection named 'ImageFeatures' with specific vector parameters for storing image embeddings.
  2. Setting up a collection with custom sharding and replication factors to optimize performance and fault tolerance.
  3. Configuring a collection with advanced options like HNSW index parameters and quantization for efficient vector search.

Properties

Name Meaning
Collection Name Name of the collection to be created.
Vectors Vector parameters of the collection defining the vector configuration.
Shard Number Number of shards in the collection to distribute data.
Sharding Method Method of sharding to use, either 'auto' or 'custom'.
Replication Factor Number of shard replicas for redundancy and fault tolerance.
Write Consistency Factor Number of replicas that must apply the operation for it to be considered successful.
On Disk Payload Whether to store the point's payload on disk, which will be read from disk every time it is requested.
HNSW Config Custom parameters for the HNSW index used in the collection.
WAL Config Custom parameters for the Write-Ahead Log (WAL) configuration.
Optimizers Config Custom parameters for optimizers used in the collection.
Init From Specify another collection to copy data from during initialization.
Quantization Config Parameters for quantization; if none provided, quantization is disabled.
Sparse Vectors Sparse vector parameters of the collection.
Strict Mode Config Configuration for strict mode in the collection.
Request Options Additional request options such as batching, SSL handling, proxy, and timeout settings.

Output

JSON

  • collectionName - The name of the created collection.
  • vectors - The vector parameters of the created collection.
  • shardNumber - The number of shards configured for the collection.
  • shardingMethod - The sharding method used for the collection.
  • replicationFactor - The replication factor set for the collection.
  • writeConsistencyFactor - The write consistency factor for the collection.
  • onDiskPayload - Indicates if the payload is stored on disk.
  • hnswConfig - Custom HNSW index parameters.
  • walConfig - Custom Write-Ahead Log configuration parameters.
  • optimizersConfig - Custom optimizer parameters.
  • initFrom - Source collection for data initialization.
  • quantizationConfig - Quantization parameters if enabled.
  • sparseVectors - Sparse vector parameters.
  • strictModeConfig - Strict mode configuration.

Dependencies

  • Qdrant REST API credentials

Troubleshooting

  • Ensure all required fields like 'Collection Name' and 'Vectors' are provided to avoid validation errors.
  • Check network connectivity and API credentials if the request to Qdrant fails.
  • If using custom sharding or advanced configurations, verify the parameters conform to Qdrant's API specifications to prevent errors.

Links

  • Qdrant Documentation - Official documentation for Qdrant, useful for understanding collection parameters and API usage.

Discussion