Create an index with integrated embedding
Create an index with integrated embedding.
With this type of index, you provide source text, and Pinecone uses a hosted embedding model to convert the text automatically during upsert and search.
For guidance and examples, see Create an index.
# pip install --upgrade pinecone
from pinecone import Pinecone
pc = Pinecone(api_key="YOUR_API_KEY")
index_name = "integrated-dense-py"
index_model = pc.create_index_for_model(
name=index_name,
cloud="aws",
region="us-east-1",
embed={
"model":"llama-text-embed-v2",
"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'
)
)// npm install @pinecone-database/pinecone
import { Pinecone } from '@pinecone-database/pinecone'
const pc = new Pinecone({ apiKey: 'YOUR_API_KEY' });
await pc.createIndexForModel({
name: 'integrated-dense-js',
cloud: 'aws',
region: 'us-east-1',
embed: {
model: 'llama-text-embed-v2',
fieldMap: { text: 'chunk_text' },
},
waitUntilReady: true,
});import io.pinecone.clients.Pinecone;
import org.openapitools.db_control.client.ApiException;
import org.openapitools.db_control.client.model.CreateIndexForModelRequest;
import org.openapitools.db_control.client.model.CreateIndexForModelRequestEmbed;
import org.openapitools.db_control.client.model.DeletionProtection;
import org.openapitools.db_control.client.model.IndexModel;
import java.util.HashMap;
import java.util.Map;
public class CreateIntegratedIndex {
public static void main(String[] args) throws ApiException {
Pinecone pc = new Pinecone.Builder("YOUR_API_KEY").build();
String indexName = "integrated-dense-java";
String region = "us-east-1";
HashMap<String, String> fieldMap = new HashMap<>();
fieldMap.put("text", "chunk_text");
CreateIndexForModelRequestEmbed embed = new CreateIndexForModelRequestEmbed()
.model("llama-text-embed-v2")
.fieldMap(fieldMap);
Map<String, String> tags = new HashMap<>();
tags.put("environment", "development");
IndexModel index = pc.createIndexForModel(
indexName,
CreateIndexForModelRequest.CloudEnum.AWS,
region,
embed,
DeletionProtection.DISABLED,
tags
);
System.out.println(index);
}
}package main
import (
"context"
"fmt"
"log"
"github.com/pinecone-io/go-pinecone/v4/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)
}
indexName := "integrated-dense-go"
DeletionProtection: &deletionProtection,
index, err := pc.CreateIndexForModel(ctx, &pinecone.CreateIndexForModelRequest{
Name: indexName,
Cloud: pinecone.Aws,
Region: "us-east-1",
Embed: pinecone.CreateIndexForModelEmbed{
Model: "llama-text-embed-v2",
FieldMap: map[string]interface{}{"text": "chunk_text"},
},
DeletionProtection: &deletionProtection,
Tags: &pinecone.IndexTags{ "environment": "development" },
})
if err != nil {
log.Fatalf("Failed to create serverless integrated index: %v", idx.Name)
} else {
fmt.Printf("Successfully created serverless integrated index: %v", idx.Name)
}
}using Pinecone;
var pinecone = new PineconeClient("YOUR_API_KEY");
var createIndexRequest = await pinecone.CreateIndexForModelAsync(
new CreateIndexForModelRequest
{
Name = "integrated-dense-dotnet",
Cloud = CreateIndexForModelRequestCloud.Aws,
Region = "us-east-1",
Embed = new CreateIndexForModelRequestEmbed
{
Model = "llama-text-embed-v2",
FieldMap = new Dictionary<string, object?>() { { "text", "chunk_text" } },
},
DeletionProtection = DeletionProtection.Disabled,
Tags = new Dictionary<string, string>
{
{ "environment", "development" }
}
}
);PINECONE_API_KEY="YOUR_API_KEY"
curl -X POST https://api.pinecone.io/indexes/create-for-model \
-H "Content-Type: application/json" \
-H "Api-Key: $PINECONE_API_KEY" \
-H "X-Pinecone-Api-Version: 2025-04" \
-d '{
"name": "integrated-dense-curl",
"cloud": "aws",
"region": "us-east-1",
"embed": {
"model": "llama-text-embed-v2",
"metric": "cosine",
"field_map": {
"text": "chunk_text"
},
"write_parameters": {
"input_type": "passage",
"truncate": "END"
},
"read_parameters": {
"input_type": "query",
"truncate": "END"
}
}
}'# Target the project where you want to create the index.
pc target -o "example-org" -p "example-project"
# Create the index.
pc index create \
--name "integrated-dense-cli" \
--dimension 1024 \
--metric "cosine" \
--cloud "aws" \
--region "us-east-1" \
--model "llama-text-embed-v2" \
--field_map "text=chunk_text"{'deletion_protection': 'disabled',
'dimension': 1024,
'embed': {'dimension': 1024,
'field_map': {'text': 'chunk_text'},
'metric': 'cosine',
'model': 'llama-text-embed-v2',
'read_parameters': {'input_type': 'query', 'truncate': 'END'},
'write_parameters': {'input_type': 'passage', 'truncate': 'END'}},
'host': 'integrated-dense-py-govk0nt.svc.aped-4627-b74a.pinecone.io',
'id': '9dabb7cb-ec0a-4e2e-b79e-c7c997e592ce',
'metric': 'cosine',
'name': 'integrated-dense-py',
'spec': {'serverless': {'cloud': 'aws', 'region': 'us-east-1'}},
'status': {'ready': True, 'state': 'Ready'},
'tags': None}{
"name": "integrated-dense-js",
"dimension": 1024,
"metric": "cosine",
"host": "integrated-dense-js-govk0nt.svc.aped-4627-b74a.pinecone.io",
"deletionProtection": "disabled",
"tags": undefined,
"embed": {
"model": "llama-text-embed-v2",
metric: 'cosine',
dimension: 1024,
vectorType: 'dense',
fieldMap: { text: 'chunk_text' },
readParameters: { input_type: 'query', truncate: 'END' },
writeParameters: { input_type: 'passage', truncate: 'END' }
},
spec: { pod: undefined, serverless: { cloud: 'aws', region: 'us-east-1' } },
status: { ready: true, state: 'Ready' },
vectorType: 'dense'
}class IndexModel {
name: integrated-dense-java
dimension: 1024
metric: cosine
host: integrated-dense-java-govk0nt.svc.aped-4627-b74a.pinecone.io
deletionProtection: disabled
tags: {environment=development}
embed: class ModelIndexEmbed {
model: llama-text-embed-v2
metric: cosine
dimension: 1024
vectorType: dense
fieldMap: {text=chunk_text}
readParameters: {dimension=1024.0, input_type=query, truncate=END}
writeParameters: {dimension=1024.0, input_type=passage, truncate=END}
additionalProperties: null
}
spec: class IndexModelSpec {
byoc: null
pod: null
serverless: class ServerlessSpec {
cloud: aws
region: us-east-1
additionalProperties: null
}
additionalProperties: null
}
status: class IndexModelStatus {
ready: false
state: Initializing
additionalProperties: null
}
vectorType: dense
additionalProperties: null
}{
"name": "integrated-dense-go",
"host": "integrated-dense-go-govk0nt.svc.aped-4627-b74a.pinecone.io",
"metric": "cosine",
"vector_type": "dense",
"deletion_protection": "disabled",
"dimension": 1024,
"spec": {
"serverless": {
"cloud": "aws",
"region": "us-east-1"
}
},
"status": {
"ready": true,
"state": "Ready"
},
"embed": {
"model": "llama-text-embed-v2",
"dimension": 1024,
"metric": "cosine",
"vector_type": "dense",
"field_map": {
"text": "chunk_text"
},
"read_parameters": {
"input_type": "query",
"truncate": "END"
},
"write_parameters": {
"input_type": "passage",
"truncate": "END"
}
}
}{
"name": "integrated-dense-dotnet",
"dimension": 1024,
"metric": "cosine",
"host": "integrated-dense-dotnet-govk0nt.svc.aped-4627-b74a.pinecone.io",
"deletion_protection": "disabled",
"tags": {
"environment": "development"
},
"embed": {
"model": "llama-text-embed-v2",
"metric": "cosine",
"dimension": 1024,
"vector_type": "dense",
"field_map": {
"text": "chunk_text"
},
"read_parameters": {
"dimension": 1024,
"input_type": "query",
"truncate": "END"
},
"write_parameters": {
"dimension": 1024,
"input_type": "passage",
"truncate": "END"
}
},
"spec": {
"serverless": {
"cloud": "aws",
"region": "us-east-1"
}
},
"status": {
"ready": true,
"state": "Ready"
},
"vector_type": "dense"
}{
"id": "9dabb7cb-ec0a-4e2e-b79e-c7c997e592ce",
"name": "integrated-dense-curl",
"metric": "cosine",
"dimension": 1024,
"status": {
"ready": false,
"state": "Initializing"
},
"host": "integrated-dense-curl-govk0nt.svc.aped-4627-b74a.pinecone.io",
"spec": {
"serverless": {
"region": "us-east-1",
"cloud": "aws"
}
},
"deletion_protection": "disabled",
"tags": null,
"embed": {
"model": "llama-text-embed-v2",
"field_map": {
"text": "chunk_text"
},
"dimension": 1024,
"metric": "cosine",
"write_parameters": {
"input_type": "passage",
"truncate": "END"
},
"read_parameters": {
"input_type": "query",
"truncate": "END"
}
}
}[SUCCESS] Index integrated-dense-cli created successfully. Run pc index describe --name integrated-dense-cli to check status.
ATTRIBUTE VALUE
Name integrated-dense-cli
Dimension 1024
Metric cosine
Deletion Protection disabled
Vector Type dense
State Initializing
Ready false
Host integrated-dense-cli-1c6ab6aa.svc.aped-4627-b74a.pinecone.io
Private Host <none>
Spec serverless
Cloud aws
Region us-east-1
Source Collection <none>
Model llama-text-embed-v2
Field Map {"text":"chunk_text"}
Read Parameters {"dimension":1024,"input_type":"query","truncate":"END"}
Write Parameters {"dimension":1024,"input_type":"passage","truncate":"END"}POST /indexes/create-for-model
Authorizations
Section titled “Authorizations”Api-KeystringrequiredAn API Key is required to call Pinecone APIs. Get yours from the console.
The desired configuration for the index and associated embedding model.
namestringrequiredThe 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
cloudenum<string>requiredThe public cloud where you would like your index hosted.
Available options: gcp, aws, azure. Example: aws
regionstringrequiredThe region where you would like your index to be created.
Example: us-east-1
deletion_protection?enum<string>Available options: disabled, enabled
Whether deletion protection is enabled/disabled for the index.
tags?objectCustom user tags added to an index. Keys must be 80 characters or less. Values must be 120 characters or less. Keys must be alphanumeric, '', or '-'. Values must be alphanumeric, ';', '@', '', '-', '.', '+', or ' '. To unset a key, set the value to be an empty string.
embedobjectrequiredSpecify 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.
Show child attributes
modelstringrequiredThe name of the embedding model to use for the index.
Example: multilingual-e5-large
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
field_mapobjectrequiredIdentifies the name of the text field from your document model that will be embedded.
dimension?integerThe dimension of embedding vectors produced for the index.
read_parameters?objectThe read parameters for the embedding model.
write_parameters?objectThe write parameters for the embedding model.
Response
Section titled “Response”201 — The index has successfully been created for the embedding model.
The IndexModel describes the configuration and status of a Pinecone index.
namestringrequiredThe 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
dimension?integerThe dimensions of the vectors to be inserted in the index.
Required range: 1 <= x <= 20000. Example: 1536
metricenum<string>requiredThe 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
hoststringrequiredThe URL address where the index is hosted.
Example: semantic-search-c01b5b5.svc.us-west1-gcp.pinecone.io
private_host?stringThe private endpoint URL of an index.
Example: semantic-search-c01b5b5.svc.private.us-west1-gcp.pinecone.io
deletion_protection?enum<string>Available options: disabled, enabled
Whether deletion protection is enabled/disabled for the index.
tags?objectCustom user tags added to an index. Keys must be 80 characters or less. Values must be 120 characters or less. Keys must be alphanumeric, '', or '-'. Values must be alphanumeric, ';', '@', '', '-', '.', '+', or ' '. To unset a key, set the value to be an empty string.
embed?objectThe embedding model and document fields mapped to embedding inputs.
Show child attributes
modelstringrequiredThe name of the embedding model used to create the index.
Example: multilingual-e5-large
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
dimension?integerThe dimensions of the vectors to be inserted in the index.
Required range: 1 <= x <= 20000. Example: 1536
vector_type?stringThe 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.
field_map?objectIdentifies the name of the text field from your document model that is embedded.
read_parameters?objectThe read parameters for the embedding model.
write_parameters?objectThe write parameters for the embedding model.
specobjectrequiredShow child attributes
byoc?objectConfiguration needed to deploy an index in a BYOC environment.
Show child attributes
environmentstringrequiredThe environment where the index is hosted.
Example: aws-us-east-1-b921
pod?objectConfiguration needed to deploy a pod-based index.
Show child attributes
environmentstringrequiredThe environment where the index is hosted.
Example: us-east1-gcp
replicas?integerThe 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
shards?integerThe number of shards. Shards split your data across multiple pods so you can fit more data into an index.
Required range: 1 <= x
pod_typestringrequiredThe type of pod to use. One of s1, p1, or p2 appended with . and one of x1, x2, x4, or x8.
pods?integerThe number of pods to be used in the index. This should be equal to shards x replicas.'
Required range: 1 <= x. Example: 1
metadata_config?objectConfiguration 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.
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.
source_collection?stringThe name of the collection to be used as the source for the index.
Example: movie-embeddings
serverless?objectConfiguration needed to deploy a serverless index.
Show child attributes
cloudenum<string>requiredThe public cloud where you would like your index hosted.
Available options: gcp, aws, azure. Example: aws
regionstringrequiredThe region where you would like your index to be created.
Example: us-east-1
source_collection?stringThe name of the collection to be used as the source for the index.
statusobjectrequiredShow child attributes
readybooleanrequiredstateenum<string>requiredAvailable options: Initializing, InitializationFailed, ScalingUp, ScalingDown, ScalingUpPodSize, ScalingDownPodSize, Terminating, Ready, Disabled
vector_typestringrequiredThe 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.