Create an index with integrated embedding

POST

indexes

create-for-model

# pip install --upgrade pinecone
from pinecone import Pinecone

pc = Pinecone(api_key="YOUR_API_KEY")

index_name = "example-index"

index_model = pc.create_index_for_model(
    name=index_name,
    cloud="aws",
    region="us-east-1",
    embed={
        "model":"multilingual-e5-large",
        "field_map":{"text": "chunk_text"}
    }
)

# Import specific classes to get type hints and autocompletions
from pinecone import CloudProvider, AwsRegion, IndexEmbed, EmbedModel

index_model = pc.create_index_for_model(
    name=index_name,
    cloud=CloudProvider.AWS,
    region=AwsRegion.US_EAST_1,
    embed=IndexEmbed(
        model=EmbedModel.Multilingual_E5_Large,
        field_map={"text": "chunk_text"},
        metric='cosine'
    )
)

{'deletion_protection': 'disabled',
 'dimension': 1024,
 'embed': {'dimension': 1024,
           'field_map': {'text': 'chunk_text'},
           'metric': 'cosine',
           'model': 'multilingual-e5-large',
           'read_parameters': {'input_type': 'query', 'truncate': 'END'},
           'write_parameters': {'input_type': 'passage', 'truncate': 'END'}},
 'host': 'example-index-govk0nt.svc.aped-4627-b74a.pinecone.io',
 'id': '9dabb7cb-ec0a-4e2e-b79e-c7c997e592ce',
 'metric': 'cosine',
 'name': 'example-index',
 'spec': {'serverless': {'cloud': 'aws', 'region': 'us-east-1'}},
 'status': {'ready': True, 'state': 'Ready'},
 'tags': None}

# pip install --upgrade pinecone
from pinecone import Pinecone

pc = Pinecone(api_key="YOUR_API_KEY")

index_name = "example-index"

index_model = pc.create_index_for_model(
    name=index_name,
    cloud="aws",
    region="us-east-1",
    embed={
        "model":"multilingual-e5-large",
        "field_map":{"text": "chunk_text"}
    }
)

# Import specific classes to get type hints and autocompletions
from pinecone import CloudProvider, AwsRegion, IndexEmbed, EmbedModel

index_model = pc.create_index_for_model(
    name=index_name,
    cloud=CloudProvider.AWS,
    region=AwsRegion.US_EAST_1,
    embed=IndexEmbed(
        model=EmbedModel.Multilingual_E5_Large,
        field_map={"text": "chunk_text"},
        metric='cosine'
    )
)

{'deletion_protection': 'disabled',
 'dimension': 1024,
 'embed': {'dimension': 1024,
           'field_map': {'text': 'chunk_text'},
           'metric': 'cosine',
           'model': 'multilingual-e5-large',
           'read_parameters': {'input_type': 'query', 'truncate': 'END'},
           'write_parameters': {'input_type': 'passage', 'truncate': 'END'}},
 'host': 'example-index-govk0nt.svc.aped-4627-b74a.pinecone.io',
 'id': '9dabb7cb-ec0a-4e2e-b79e-c7c997e592ce',
 'metric': 'cosine',
 'name': 'example-index',
 'spec': {'serverless': {'cloud': 'aws', 'region': 'us-east-1'}},
 'status': {'ready': True, 'state': 'Ready'},
 'tags': None}

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 index and associated embedding model.

name

string

required

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"

cloud

enum<string>

required

The public cloud where you would like your index hosted.

Available options:

gcp,

aws,

azure

Example:

"aws"

region

string

required

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

Example:

"us-east-1"

embed

object

required

Specify the integrated inference embedding configuration for the index.

Once set the model cannot be changed, but you can later update the embedding configuration for an integrated inference index including field map, read parameters, or write parameters.

Refer to the model guide for available models and model details.

embed.model

string

required

The name of the embedding model to use for the index.

Example:

"multilingual-e5-large"

embed.field_map

object

required

Identifies the name of the text field from your document model that will be embedded.

Example:

{ "text": "your-text-field" }

embed.metric

enum<string>

The distance metric to be used for similarity search. You can use 'euclidean', 'cosine', or 'dotproduct'. If not specified, the metric will be defaulted according to the model. Cannot be updated once set.

Available options:

cosine,

euclidean,

dotproduct

embed.read_parameters

object

The read parameters for the embedding model.

embed.write_parameters

object

The write parameters for the embedding model.

Example:

{
  "field_map": { "text": "your-text-field" },
  "metric": "cosine",
  "model": "multilingual-e5-large",
  "read_parameters": { "input_type": "query", "truncate": "NONE" },
  "write_parameters": { "input_type": "passage" }
}

deletion_protection

enum<string>

default:disabled

Whether deletion protection is enabled/disabled for the index.

Available options:

disabled,

enabled

Response

201

application/json

The index has successfully been created for the embedding model.

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

name

string

required

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"

metric

enum<string>

required

The distance metric to be used for similarity search. You can use 'euclidean', 'cosine', or 'dotproduct'. If the 'vector_type' is 'sparse', the metric must be 'dotproduct'. If the vector_type is dense, the metric defaults to 'cosine'.

Available options:

cosine,

euclidean,

dotproduct

host

string

required

The URL address where the index is hosted.

Example:

"semantic-search-c01b5b5.svc.us-west1-gcp.pinecone.io"

spec

object

required

spec.pod

object

Configuration needed to deploy a pod-based index.

spec.pod.environment

string

required

The environment where the index is hosted.

Example:

"us-east1-gcp"

spec.pod.pod_type

string

default:p1.x1

required

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

spec.pod.replicas

integer

default:1

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: x >= 1

spec.pod.shards

integer

default:1

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

Required range: x >= 1

spec.pod.pods

integer

default:1

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

Required range: x >= 1

Example:

1

spec.pod.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.

Example:

{
  "indexed": ["genre", "title", "imdb_rating"]
}

spec.pod.source_collection

string

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

Example:

"movie-embeddings"

Example:

{
  "environment": "us-east1-gcp",
  "metadata_config": {
    "indexed": ["genre", "title", "imdb_rating"]
  },
  "pod_type": "p1.x1",
  "pods": 1,
  "replicas": 1,
  "shards": 1,
  "source_collection": "movie-embeddings"
}

spec.serverless

object

Configuration needed to deploy a serverless index.

Example:

{
  "pod": {
    "environment": "us-east-1-aws",
    "metadata_config": {
      "indexed": ["genre", "title", "imdb_rating"]
    },
    "pod_type": "p1.x1",
    "pods": 1,
    "replicas": 1,
    "shards": 1
  }
}

status

object

required

Example:

{
  "ready": true,
  "state": "ScalingUpPodSize"
}

vector_type

string

default:dense

required

The index vector type. You can use 'dense' or 'sparse'. If 'dense', the vector dimension must be specified. If 'sparse', the vector dimension should not be specified.

dimension

integer

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

Required range: 1 <= x <= 20000

Example:

1536

deletion_protection

enum<string>

default:disabled

Whether deletion protection is enabled/disabled for the index.

Available options:

disabled,

enabled

tags

object

Example:

{ "tag0": "val0", "tag1": "val1" }

embed

object

The embedding model and document fields mapped to embedding inputs.

embed.model

string

required

The name of the embedding model used to create the index.

Example:

"multilingual-e5-large"

embed.metric

enum<string>

Available options:

cosine,

euclidean,

dotproduct

embed.dimension

integer

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

Required range: 1 <= x <= 20000

Example:

1536

embed.vector_type

string

default:dense

The index vector type. You can use 'dense' or 'sparse'. If 'dense', the vector dimension must be specified. If 'sparse', the vector dimension should not be specified.

embed.field_map

object

Identifies the name of the text field from your document model that is embedded.

Example:

{ "text": "your-text-field" }

embed.read_parameters

object

The read parameters for the embedding model.

embed.write_parameters

object

The write parameters for the embedding model.

Example:

{
  "field_map": { "text": "your-text-field" },
  "metric": "cosine",
  "model": "multilingual-e5-large",
  "read_parameters": { "input_type": "query", "truncate": "NONE" },
  "write_parameters": { "input_type": "passage" }
}

Was this page helpful?

Create an index Describe an index

# pip install --upgrade pinecone
from pinecone import Pinecone

pc = Pinecone(api_key="YOUR_API_KEY")

index_name = "example-index"

index_model = pc.create_index_for_model(
    name=index_name,
    cloud="aws",
    region="us-east-1",
    embed={
        "model":"multilingual-e5-large",
        "field_map":{"text": "chunk_text"}
    }
)

# Import specific classes to get type hints and autocompletions
from pinecone import CloudProvider, AwsRegion, IndexEmbed, EmbedModel

index_model = pc.create_index_for_model(
    name=index_name,
    cloud=CloudProvider.AWS,
    region=AwsRegion.US_EAST_1,
    embed=IndexEmbed(
        model=EmbedModel.Multilingual_E5_Large,
        field_map={"text": "chunk_text"},
        metric='cosine'
    )
)

{'deletion_protection': 'disabled',
 'dimension': 1024,
 'embed': {'dimension': 1024,
           'field_map': {'text': 'chunk_text'},
           'metric': 'cosine',
           'model': 'multilingual-e5-large',
           'read_parameters': {'input_type': 'query', 'truncate': 'END'},
           'write_parameters': {'input_type': 'passage', 'truncate': 'END'}},
 'host': 'example-index-govk0nt.svc.aped-4627-b74a.pinecone.io',
 'id': '9dabb7cb-ec0a-4e2e-b79e-c7c997e592ce',
 'metric': 'cosine',
 'name': 'example-index',
 'spec': {'serverless': {'cloud': 'aws', 'region': 'us-east-1'}},
 'status': {'ready': True, 'state': 'Ready'},
 'tags': None}

APIs

Database

Inference

SDKs

Architecture

Tools

Create an index with integrated embedding

Authorizations

Body

Response