qdrant_collection_create
Sets up a new Qdrant collection for vector storage and search by defining vector size, distance metric, named vectors, sparse vectors, and optional quantization or strict mode settings.
Instructions
Create a collection: either a single unnamed vector (vector_size
+ distance), or one or more named vectors (vectors, each a full
VectorParams — size, distance, and optionally its own
multivector_config for ColBERT-style multi-vectors or
quantization_config) — exactly one of the two. sparse_vectors
defines sparse (keyword-style) vectors at creation time.
quantization_config (scalar/product/binary) and
strict_mode_config apply to the whole collection.
Fails with a clear error if a collection with this name already exists.
Example (simple): {"collection_name": "docs", "vector_size": 4, "distance": "Cosine"}
Example (hybrid): {"collection_name": "docs", "vectors": {
"dense": {"size": 4, "distance": "Cosine"}
}, "sparse_vectors": {"sparse": {}}}
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| vectors | No | ||
| distance | No | Cosine | |
| metadata | No | ||
| vector_size | No | ||
| sparse_vectors | No | ||
| collection_name | Yes | ||
| strict_mode_config | No | ||
| quantization_config | No |
Output Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| config | Yes | Current statistics and configuration of the collection | |
| status | Yes | Current statistics and configuration of the collection | |
| warnings | No | Warnings related to the collection | |
| points_count | No | Approximate number of points (vectors + payloads) in collection. Each point could be accessed by unique id. | |
| update_queue | No | Update queue info | |
| payload_schema | Yes | Types of stored payload | |
| segments_count | Yes | Number of segments in collection. Each segment has independent vector as payload indexes | |
| optimizer_status | Yes | Current statistics and configuration of the collection | |
| indexed_vectors_count | No | Approximate number of indexed vectors in the collection. Indexed vectors in large segments are faster to query, as it is stored in a specialized vector index. |