Actions26
- Collection Actions
- Payload Actions
- Point Actions
- Search Actions
- Vector Actions
Overview
The node provides an interface to manage collections in Qdrant, a vector search engine. Specifically, the "Create Collection" operation allows users to create a new collection with customizable parameters such as vector configurations, sharding, replication, and indexing options.
This operation is beneficial when setting up a new vector database collection tailored to specific data and performance requirements. For example, you might create a collection to store image embeddings for similarity search or text embeddings for semantic search applications.
Properties
| Name | Meaning |
|---|---|
| Collection Name | The name of the collection to be created. |
| Vectors | JSON object defining the vector parameters of the collection (e.g., vector size, distance metric). |
| Shard Number | Number of shards to split the collection into (optional). |
| Sharding Method | Method of sharding: "auto" (default) or "custom". |
| Replication Factor | Number of replicas per shard; minimum 1, default is 1 if not specified. |
| Write Consistency Factor | Number of replicas that must confirm a write operation for it to be considered successful. |
| On Disk Payload | Boolean flag indicating whether to store point payloads on disk (true) or in memory (false). |
| HNSW Config | JSON object with custom parameters for the HNSW index configuration (optional). |
| WAL Config | JSON object with custom parameters for the Write-Ahead Log (optional). |
| Optimizers Config | JSON object with custom parameters for optimizer settings (optional). |
| Init From | JSON object specifying another collection to copy data from during initialization (optional). |
| Quantization Config | JSON object defining quantization parameters; disables quantization if null (optional). |
| Sparse Vectors | JSON object defining sparse vector parameters (optional). |
| Strict Mode Config | JSON object configuring strict mode behavior for the collection (optional). |
Output
The node outputs JSON data representing the response from the Qdrant API after creating the collection. This typically includes confirmation details about the newly created collection, such as its name, status, and applied configurations.
If the node supports binary data output, it would relate to any binary payloads stored or retrieved, but this operation primarily deals with JSON metadata and configuration, so no binary output is expected here.
Dependencies
- Requires an active connection to a Qdrant instance via its REST API.
- Needs an API key or authentication token configured in n8n credentials to authorize requests.
- The base URL of the Qdrant service must be set in the node's credential configuration.
Troubleshooting
Common Issues:
- Invalid or missing collection name will cause the request to fail.
- Incorrect vector parameter definitions may lead to validation errors.
- Insufficient permissions or invalid API credentials will result in authorization errors.
- Providing incompatible or malformed JSON in optional config fields can cause request rejection.
Error Messages:
- "Collection name is required" — Ensure the collectionName property is provided.
- "Invalid vector configuration" — Verify the vectors JSON structure matches Qdrant's expected schema.
- "Unauthorized" or "Authentication failed" — Check API key validity and credential setup.
- "Bad Request" — Review all JSON inputs for syntax errors or unsupported parameters.
Resolving these usually involves validating input properties, checking credentials, and ensuring the Qdrant server is reachable.