Skip to main content
POST
/
collections
# pip install "pinecone[grpc]"
from pinecone.grpc import PineconeGRPC as Pinecone

pc = Pinecone(api_key="API_KEY")
pc.create_collection("example-collection", "docs-example")

{
  "name": "example-collection",
  "status": "Initializing",
  "environment": "us-east1-gcp",
  "size": 10000000,
  "dimension": 1536,
  "vector_count": 120000
}

Documentation Index

Fetch the complete documentation index at: https://docs.pinecone.io/llms.txt

Use this file to discover all available pages before exploring further.

# pip install "pinecone[grpc]"
from pinecone.grpc import PineconeGRPC as Pinecone

pc = Pinecone(api_key="API_KEY")
pc.create_collection("example-collection", "docs-example")

Authorizations

​
Api-Key
string
header
required

An API Key is required to call Pinecone APIs. Get yours from the console.

Body

application/json

The desired configuration for the collection.

The configuration needed to create a Pinecone collection.

​
name
string
required

The name of the collection to be created. Resource name must be 1-45 characters long, start and end with an alphanumeric character, and consist only of lower case alphanumeric characters or '-'.

Required string length: 1 - 45
​
source
string
required

The name of the index to be used as the source for the collection.

Example:

"example-source-index"

Response

The collection has been successfully created.

The CollectionModel describes the configuration and status of a Pinecone collection.

​
name
string
required

The name of the collection.

Example:

"example-collection"

​
status
enum<string>
required

The status of the collection.

Available options:
Initializing,
Ready,
Terminating
Example:

"Initializing"

​
environment
string
required

The environment where the collection is hosted.

Example:

"us-east1-gcp"

​
size
integer<int64>

The size of the collection in bytes.

Example:

10000000

​
dimension
integer<int32>

The dimension of the vectors stored in each record held in the collection.

Required range: 1 <= x <= 20000
Example:

1536

​
vector_count
integer<int32>

The number of records stored in the collection.

Example:

120000