Create a collection | Qdrant

# Minimal curl command to create a collection with a vector field
curl -X PUT http://localhost:6333/collections/collection_name \
     -H "api-key: <apiKey>" \
     -H "Content-Type: application/json" \
     -d '{
            "vectors": {
                "size": 300,
                "distance": "Cosine"
            } 
        }'
# Or with a sparse vector field
curl -X PUT http://localhost:6333/collections/collection_name \
     -H "api-key: <apiKey>" \
     -H "Content-Type: application/json" \
     -d '{
            "vectors": {
                "size": 1536,
                "distance": "Cosine"
            },
            "sparse_vectors": {
                "splade-model-name": {
                    "index": {
                        "on_disk": true
                    }
                }
            }
        }'

{
  "time": 1.1,
  "status": "string",
  "result": true
}

Creates a new collection with the given parameters.

Authentication

api-keystring

API Key authentication via header

Path parameters

collection_namestringRequired

Name of the new collection

Query parameters

timeoutintegerOptional

Wait for operation commit timeout in seconds. If timeout is reached - request will return with service error.

Request

Parameters of a new collection

vectorsobject or map from strings to objectsOptional

Vector params separator for single and multiple vector modes Single mode:

{ “size”: 128, “distance”: “Cosine” }

or multiple mode:

{ “default”: { “size”: 128, “distance”: “Cosine” } }

shard_numberuint or nullOptional

For auto sharding: Number of shards in collection. - Default is 1 for standalone, otherwise equal to the number of nodes - Minimum is 1 For custom sharding: Number of shards in collection per shard group. - Default is 1, meaning that each shard key will be mapped to a single shard - Minimum is 1

sharding_methodenum or anyOptional

Sharding method Default is Auto - points are distributed across all available shards Custom - points are distributed across shards according to shard key

replication_factoruint or nullOptional

Number of shards replicas. Default is 1 Minimum is 1

write_consistency_factoruint or nullOptional

Defines how many replicas should apply the operation for us to consider it successful. Increasing this number will make the collection more resilient to inconsistencies, but will also make it fail if not enough replicas are available. Does not have any performance impact.

on_disk_payloadboolean or nullOptional

If true - point’s payload will not be stored in memory. It will be read from the disk every time it is requested. This setting saves RAM by (slightly) increasing the response time. Note: those payload values that are involved in filtering and are indexed - remain in RAM.

hnsw_configobject or anyOptional

Custom params for HNSW index. If none - values from service configuration file are used.

wal_configobject or anyOptional

Custom params for WAL. If none - values from service configuration file are used.

optimizers_configobject or anyOptional

Custom params for Optimizers. If none - values from service configuration file are used.

init_fromobject or anyOptional

Specify other collection to copy data from.

quantization_configobject or anyOptional

Quantization parameters. If none - quantization is disabled.

sparse_vectorsmap from strings to objects or nullOptional

Sparse vector data config.

Response

successful operation

timedouble

Time spent to process this request

statusstring

resultboolean