Skip to main content
Pinecone Docs
current

Search documentation

Type to search this documentation.

Create an index

Create an index for vectors created with an external embedding model.

For guidance and examples, see Create an index.

Python
# pip install "pinecone[grpc]"
# Serverless index
from pinecone.grpc import PineconeGRPC as Pinecone
from pinecone import ServerlessSpec

pc = Pinecone(api_key="YOUR_API_KEY")

pc.create_index(
  name="docs-example1",
  dimension=1536,
  metric="cosine",
  spec=ServerlessSpec(
    cloud="aws",
    region="us-east-1",
  ),
  deletion_protection="disabled"
)

# Pod-based index
from pinecone.grpc import PineconeGRPC as Pinecone, PodSpec

pc = Pinecone(api_key="YOUR_API_KEY")

pc.create_index(
  name="docs-example2",
  dimension=1536,
  metric="cosine",
  spec=PodSpec(
    environment="us-west1-gcp",
    pod_type="p1.x1",
    pods=1,
  ),
  deletion_protection="disabled"
)
JavaScript
// npm install @pinecone-database/pinecone
// Serverles index
import { Pinecone } from '@pinecone-database/pinecone'

const pc = new Pinecone({
  apiKey: 'YOUR_API_KEY'
});

await pc.createIndex({
  name: 'serverless-index',
  dimension: 1536,
  metric: 'cosine',
  spec: {
    serverless: {
      cloud: 'aws',
      region: 'us-east-1'
    }
  },
  deletionProtection: 'disabled',
});

// Pod-based index
await pc.createIndex({
  name: 'docs-example2',
  dimension: 1536,
  metric: 'cosine',
  spec: {
    pod: {
      environment: 'us-west1-gcp',
      podType: 'p1.x1',
      pods: 1
    }
  },
  deletionProtection: 'disabled',
});
Java
import io.pinecone.clients.Pinecone;
import org.openapitools.db_control.client.model.IndexModel;
import org.openapitools.db_control.client.model.DeletionProtection;

// Serverless index
public class CreateServerlessIndexExample {
    public static void main(String[] args) {
        Pinecone pc = new Pinecone.Builder("YOUR_API_KEY").build();
        pc.createServerlessIndex("docs-example1", "cosine", 1536, "aws", "us-east-1", DeletionProtection.disabled);
    }
}

// Pod-based index
public class CreatePodIndexExample {
    public static void main(String[] args) {
        Pinecone pc = new Pinecone.Builder("YOUR_API_KEY").build();
        pc.createPodsIndex("docs-example2", 1536, "us-west1-gcp",
                "p1.x1", "cosine", DeletionProtection.disabled);
    }
}
Go
package main

import (
    "context"
    "fmt"
    "log"

    "github.com/pinecone-io/go-pinecone/v2/pinecone"
)

func main() {
    ctx := context.Background()

    pc, err := pinecone.NewClient(pinecone.NewClientParams{
        ApiKey: "YOUR_API_KEY",
    })
    if err != nil {
        log.Fatalf("Failed to create Client: %v", err)
    }

    deletionProtection := pinecone.DeletionProtectionDisabled

    // Serverless index
    idx1, err := pc.CreateServerlessIndex(ctx, &pinecone.CreateServerlessIndexRequest{
        Name:      "docs-example1",
        Dimension: 1536,
        Metric:    pinecone.Cosine,
        Cloud:     pinecone.Aws,
        Region:    "us-east-1",
        DeletionProtection: &deletionProtection,
    })
  	if err != nil {
        log.Fatalf("Failed to create serverless index: %v", idx1.Name)
    } else {
        fmt.Printf("Successfully created serverless index: %v", idx1.Name)
    }

    // Pod-based index
    idx2, err := pc.CreatePodIndex(ctx, &pinecone.CreatePodIndexRequest{
        Name:        "docs-example2",
        Dimension:   1536,
        Metric:      pinecone.Cosine,
        Environment: "us-east1-gcp",
        PodType:     "p1.x1",
        DeletionProtection: &deletionProtection,
    })
  	if err != nil {
        log.Fatalf("Failed to create pod-based index: %v", idx2.Name)
    } else {
        fmt.Printf("Successfully created pod-based index: %v", idx2.Name)
    }
}
C#
using Pinecone;

var pinecone = new PineconeClient("YOUR_API_KEY");

// Serverless index
var createIndexRequest = await pinecone.CreateIndexAsync(new CreateIndexRequest
{
    Name = "docs-example1",
    Dimension = 1536,
    Metric = CreateIndexRequestMetric.Cosine,
    Spec = new ServerlessIndexSpec
    {
        Serverless = new ServerlessSpec
        {
            Cloud = ServerlessSpecCloud.Aws,
            Region = "us-east-1",
        }
    },
    DeletionProtection = DeletionProtection.Disabled
});

// Pod-based index
var createIndexRequest = await pinecone.CreateIndexAsync(new CreateIndexRequest
{
    Name = "pod index",
    Dimension = 1536,
    Metric = CreateIndexRequestMetric.Cosine,
    Spec = new PodIndexSpec
    {
        Pod = new PodSpec
        {
            Environment = "us-east1-gcp",
            PodType = "p1.x1",
            Pods = 1,
        }
    },
    DeletionProtection = DeletionProtection.Disabled
});
curl
PINECONE_API_KEY="YOUR_API_KEY"

# Serverless index
curl -s https://api.pinecone.io/indexes \
  -H "Accept: application/json" \
  -H "Content-Type: application/json" \
  -H "Api-Key: $PINECONE_API_KEY" \
  -H "X-Pinecone-Api-Version: 2024-07" \
  -d '{
         "name": "serverless-index",
         "dimension": 1536,
         "metric": "cosine",
         "spec": {
            "serverless": {
               "cloud": "aws",
               "region": "us-east-1"
            }
         },
         "deletion_protection": "disabled"
      }'

# Pod-based index
curl -s https://api.pinecone.io/indexes \
  -H "Accept: application/json" \
  -H "Content-Type: application/json" \
  -H "Api-Key: $PINECONE_API_KEY" \
  -H "X-Pinecone-Api-Version: 2024-07" \
  -d '{
         "name": "pod-index",
         "dimension": 1536,
         "metric": "cosine",
         "spec": {
            "pod": {
               "environment": "us-west1-gcp",
               "pod_type": "p1.x1",
               "pods": 1
            }
         },
         "deletion_protection": "disabled"
      }'
curl
# Serverless index
{
    "name": "docs-example1",
    "metric": "cosine",
    "dimension": 1536,
    "status": {
        "ready": true,
        "state": "Ready"
    },
    "host": "docs-example1-4zo0ijk.svc.dev-us-west2-aws.pinecone.io",
    "spec": {
        "serverless": {
            "region": "us-east-1",
            "cloud": "aws"
        }
    }
}

# Pod-based index
{
    "name": "docs-example2",
    "metric": "cosine",
    "dimension": 1536,
    "status": {
        "ready": true,
        "state": "Ready"
    },
    "host": "docs-example2-4zo0ijk.svc.us-west1-gcp.pinecone.io",
    "spec": {
        "pod": {
            "replicas": 1,
            "shards": 1,
            "pods": 1,
            "pod_type": "p1.x1",
            "environment": "us-west1-gcp"
        }
    }
}

POST /indexes

Api-Keystringrequired

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

The desired configuration for the index.

namestringrequired

The name of the index. 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. Example: example-index

Typestring
dimensionintegerrequired

The dimensions of the vectors to be inserted in the index.

Required range: 1 <= x <= 20000. Example: 1536

Typeinteger
metric?enum<string>

The distance metric to be used for similarity search. You can use 'euclidean', 'cosine', or 'dotproduct'.

Available options: cosine, euclidean, dotproduct

Typeenum<string>
Defaultcosine
deletion_protection?enum<string>

Available options: disabled, enabled

Typeenum<string>
Defaultdisabled

Whether deletion protection is enabled/disabled for the index.

specobjectrequired

The spec object defines how the index should be deployed. For serverless indexes, you define only the cloud and region where the index should be hosted. For pod-based indexes, you define the environment where the index should be hosted, the pod type and size to use, and other index characteristics.

Show child attributes
serverless?object

Configuration needed to deploy a serverless index.

Typeobject
Show child attributes
cloudenum<string>required

The public cloud where you would like your index hosted.

Available options: gcp, aws, azure. Example: aws

Typeenum<string>
regionstringrequired

The region where you would like your index to be created.

Example: us-east-1

Typestring
pod?object

Configuration needed to deploy a pod-based index.

Typeobject
Show child attributes
environmentstringrequired

The environment where the index is hosted.

Example: us-east1-gcp

Typestring
replicas?integer

The number of replicas. Replicas duplicate your index. They provide higher availability and throughput. Replicas can be scaled up or down as your needs change.

Required range: 1 <= x

Typeinteger
Default1
shards?integer

The number of shards. Shards split your data across multiple pods so you can fit more data into an index.

Required range: 1 <= x

Typeinteger
Default1
pod_typestringrequired

The type of pod to use. One of s1, p1, or p2 appended with . and one of x1, x2, x4, or x8.

Typestring
Defaultp1.x1
pods?integer

The number of pods to be used in the index. This should be equal to shards x replicas.'

Required range: 1 <= x. Example: 1

Typeinteger
Default1
metadata_config?object

Configuration for the behavior of Pinecone's internal metadata index. By default, all metadata is indexed; when metadata_config is present, only specified metadata fields are indexed. These configurations are only valid for use with pod-based indexes.

Typeobject
Show child attributes
indexed?string[]

By default, all metadata is indexed; to change this behavior, use this property to specify an array of metadata fields that should be indexed.

Typestring[]
source_collection?string

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

Example: movie-embeddings

Typestring

201 — The index has been successfully created.

The IndexModel describes the configuration and status of a Pinecone index.

namestringrequired

The name of the index. 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. Example: example-index

Typestring
dimensionintegerrequired

The dimensions of the vectors to be inserted in the index.

Required range: 1 <= x <= 20000. Example: 1536

Typeinteger
metricenum<string>required

The distance metric to be used for similarity search. You can use 'euclidean', 'cosine', or 'dotproduct'.

Available options: cosine, euclidean, dotproduct

Typeenum<string>
Defaultcosine
hoststringrequired

The URL address where the index is hosted.

Example: semantic-search-c01b5b5.svc.us-west1-gcp.pinecone.io

Typestring
deletion_protection?enum<string>

Available options: disabled, enabled

Typeenum<string>
Defaultdisabled

Whether deletion protection is enabled/disabled for the index.

specobjectrequired
Show child attributes
pod?object

Configuration needed to deploy a pod-based index.

Typeobject
Show child attributes
environmentstringrequired

The environment where the index is hosted.

Example: us-east1-gcp

Typestring
replicas?integer

The number of replicas. Replicas duplicate your index. They provide higher availability and throughput. Replicas can be scaled up or down as your needs change.

Required range: 1 <= x

Typeinteger
Default1
shards?integer

The number of shards. Shards split your data across multiple pods so you can fit more data into an index.

Required range: 1 <= x

Typeinteger
Default1
pod_typestringrequired

The type of pod to use. One of s1, p1, or p2 appended with . and one of x1, x2, x4, or x8.

Typestring
Defaultp1.x1
pods?integer

The number of pods to be used in the index. This should be equal to shards x replicas.'

Required range: 1 <= x. Example: 1

Typeinteger
Default1
metadata_config?object

Configuration for the behavior of Pinecone's internal metadata index. By default, all metadata is indexed; when metadata_config is present, only specified metadata fields are indexed. These configurations are only valid for use with pod-based indexes.

Typeobject
Show child attributes
indexed?string[]

By default, all metadata is indexed; to change this behavior, use this property to specify an array of metadata fields that should be indexed.

Typestring[]
source_collection?string

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

Example: movie-embeddings

Typestring
serverless?object

Configuration needed to deploy a serverless index.

Typeobject
Show child attributes
cloudenum<string>required

The public cloud where you would like your index hosted.

Available options: gcp, aws, azure. Example: aws

Typeenum<string>
regionstringrequired

The region where you would like your index to be created.

Example: us-east-1

Typestring
statusobjectrequired
Show child attributes
readybooleanrequired
stateenum<string>required

Available options: Initializing, InitializationFailed, ScalingUp, ScalingDown, ScalingUpPodSize, ScalingDownPodSize, Terminating, Ready

Typeenum<string>
Suggest an edit

Propose a replacement for this page. The site team reviews it before applying any changes.

Export
Documentation menu