.mint-relative {
    position: relative
}
.\!mint-m-0 {
    margin: 0px !important
}
.mint-flex {
    display: flex
}
.mint-inline-flex {
    display: inline-flex
}
.mint-flex-col {
    flex-direction: column
}
.mint-items-start {
    align-items: flex-start
}
.mint-items-baseline {
    align-items: baseline
}
.mint-justify-between {
    justify-content: space-between
}
.mint-gap-2 {
    gap: 0.5rem
}
.mint-gap-5 {
    gap: 1.25rem
}
.mint-overflow-x-auto {
    overflow-x: auto
}
@media (min-width: 768px) {
    .md\:mint-flex-row {
        flex-direction: row
    }
    .md\:mint-items-center {
        align-items: center
    }
}

/**
 * This script is used when the Pinecone docs are embedded in the Pinecone Console.
 * 
 * IMPORTANT: You must coordinate changes to this file with changes in Console's DocsDrawer component.
*/
const DOCS_MESSAGE_TYPES = {
  LOAD: "pinecone-docs-load",
  UNLOAD: 'pinecone-docs-unload',
  INIT: "pinecone-docs-init",
  READY: "pinecone-docs-ready",
  GET_URL: "pinecone-docs-get-url",
  SEND_URL: "pinecone-docs-send-url",
  SEARCH: 'pinecone-docs-search',
};

window.addEventListener("message", (event) => {
  switch (event.data.type) {
    case DOCS_MESSAGE_TYPES.INIT:
      init();
      break;

    case DOCS_MESSAGE_TYPES.GET_URL:
      sendMessage(DOCS_MESSAGE_TYPES.SEND_URL, {
        url: window.location.href,
      });
      break;

    case DOCS_MESSAGE_TYPES.SEARCH:
      const searchInput = document.querySelector("#search-bar-entry");

      if (searchInput) {
        searchInput.dispatchEvent(new Event("click", { bubbles: true }));
      }
      break;

    default:
      break;
  }
});

window.self.addEventListener("load", () => {
  if (window.self !== window.top) {
    sendMessage(DOCS_MESSAGE_TYPES.LOAD);
  }
});

window.self.addEventListener("beforeunload", () => {
  if (window.self !== window.top) {
    sendMessage(DOCS_MESSAGE_TYPES.UNLOAD);
  }
});


function init() { 
  document.body.classList.add("pinecone-console-embed");
  sendMessage(DOCS_MESSAGE_TYPES.READY);
};

function sendMessage(type, data) {
  parent.postMessage(
    {
      type,
      ...data,
    },
    "*"
  );
}



Pinecone integrations enable you to build and deploy AI applications faster and more efficiently. Integrate Pinecone with your favorite frameworks, data sources, and infrastructure providers.

Model Gallery

Pinecone Docs

Assistant examples

Introduction

Pinecone Documentation

An introduction to the Pinecone vector database.

Overview

Pinecone overview

Quickstart

This guide explains how to authenticate API calls to your Pinecone project.

Authentication

Examples

Understanding organizations

Setting up billing through AWS Marketplace

Setting up billing through Azure Marketplace

Setting up billing through GCP Marketplace

Changing your billing plan

Understanding subscription status

Understanding cost

Monitoring your usage

Managing cost

Configure single sign-on

Single sign-on with Okta

Understanding projects

Create a project

Add members

Rename a project

Set a project pod limit

Understanding indexes

Create an index

View index information

Back up an index

Delete an index

Using namespaces

Choosing a pod type and size

Configure pod-based indexes

Scale pod-based indexes

Understanding collections

Convert a starter index to serverless

Upsert data

Query data

Fetch data

Update data

Delete data

List record IDs

Get an index endpoint

Filtering with metadata

Manage RAG documents

Understanding hybrid search

Encode sparse vectors

Upsert sparse-dense vectors

Query sparse-dense vectors

Using public Pinecone datasets

Creating and loading private datasets

Migrate to the new API

Moving to production

Performance tuning

Monitoring

Troubleshooting

Understanding multitenancy

Common errors

The `upsert` operation writes vectors into a namespace. If a new value is upserted for an existing vector ID, it will overwrite the previous value.

For guidance and examples, see [Upsert data](https://docs.pinecone.io/docs/upsert-data).

Upsert vectors

The `query` operation searches a namespace, using a query vector. It retrieves the ids of the most similar items in a namespace, along with their similarity scores.

For guidance and examples, see [Query data](https://docs.pinecone.io/docs/query-data).

Query vectors

The `fetch` operation looks up and returns vectors, by ID, from a single namespace. The returned vectors include the vector data and/or metadata.

For guidance and examples, see [Fetch data](https://docs.pinecone.io/docs/fetch-data).

Fetch vectors

The `update` operation updates a vector in a namespace. If a value is included, it will overwrite the previous value. If a `set_metadata` is included, the values of the fields specified in it will be added or overwrite the previous value.

For guidance and examples, see [Update data](https://docs.pinecone.io/docs/update-data).

Update a vector

The `delete` operation deletes vectors, by id, from a single namespace.

For guidance and examples, see [Delete data](https://docs.pinecone.io/docs/delete-data).

Delete vectors

The `list` operation lists the IDs of vectors in a single namespace of a serverless index. An optional prefix can be passed to limit the results to IDs with a common prefix.

`list` returns up to 100 IDs at a time by default in sorted order (bitwise/"C" collation). If the `limit` parameter is set, `list` returns up to that number of IDs instead. Whenever there are additional IDs to return, the response also includes a `pagination_token` that you can use to get the next batch of IDs. When the response does not include a `pagination_token`, there are no more IDs to return.

For guidance and examples, see [Get record IDs](https://docs.pinecone.io/docs/get-record-ids).

**Note:** `list` is supported only for serverless indexes.

List vector IDs

The `describe_index_stats` operation returns statistics about the contents of an index, including the vector count per namespace and the number of dimensions, and the index fullness.

Serverless indexes scale automatically as needed, so index fullness is relevant only for pod-based indexes.

For pod-based indexes, the index fullness result may be inaccurate during pod resizing; to get the status of a pod resizing process, use [`describe_index`](https://www.pinecone.io/docs/api/operation/describe_index/).

Get index stats

This operation returns a list of all indexes in a project.

List indexes

This operation deploys a Pinecone index. This is where you specify the measure of similarity, the dimension of vectors to be stored in the index, which cloud provider you would like to deploy with, and more.

For guidance and examples, see [Create an index](https://docs.pinecone.io/docs/create-an-index#create-a-serverless-index).

Describe an index

This operation deletes an existing index.

This operation specifies the pod type and number of replicas for an index. It applies to pod-based indexes only. Serverless indexes scale automatically based on usage.

Configure an index

This operation returns a list of your Pinecone collections.

Serverless and starter indexes do not support collections.


List collections

This operation creates a Pinecone collection.

Serverless and starter indexes do not support collections.


Create a collection

This operation gets a description of a collection.

Serverless and starter indexes do not support collections.


Describe a collection

This operation deletes an existing collection.

Serverless and starter indexes do not support collections.


Delete a collection

Pinecone clients

Community clients

Serverless architecture

Pod-based architecture

Limits

Security

Notebooks

Sample apps

Utilities

Reference architectures

Pinecone as a Knowledge Base for Amazon Bedrock

Amazon Bedrock

Amazon SageMaker

Cohere

Using Databricks and Pinecone to create and index vector embeddings at scale

Databricks

Datadog

Elasticsearch

Haystack

Hugging Face Inference Endpoints

LangChain

LlamaIndex

OpenAI

Using TruLens and Pinecone to evaluate grounded LLM applications

TruLens

2024 releases

2023 releases

2022 releases

This guide explains how to set up a Pinecone vector database in minutes.

Choosing index type and size

Manage billing

This document describes how to configure pay-as-you-go billing for your Pinecone organization through Amazon Web Services (AWS) Marketplace. To commit to annual spending, [contact Pinecone](https://www.pinecone.io/contact).

This document describes how to configure pay-as-you-go billing for your Pinecone organization through Azure Marketplace. To commit to annual spending, [contact Pinecone](https://www.pinecone.io/contact).

This document describes how to configure pay-as-you-go billing for your Pinecone organization through Google Cloud Platform (GCP) Marketplace. To commit to annual spending, [contact Pinecone](https://www.pinecone.io/contact).

This document describes how to change the billing plan for your Pinecone organization through the Pinecone console..

Manage cost

This document describes how to monitor the usage and costs for your Pinecone organization through the Pinecone console.

Manage projects

Add users to projects and organizations

Change project pod limit

gcp-starter environment

Manage indexes

Back up indexes

Scale indexes

Insert data

Manage datasets

You can limit your vector search based on metadata. Pinecone lets you attach metadata key-value pairs to vectors in an index, and specify filter expressions when you query the index.

Task	Embedding
Modality	Text
Max Input Tokens	2048
Price	$0.16 / million tokens

Task	Embedding
Modality	Text
Max Input Tokens	507
Price	$0.08 / million tokens

Task	Rerank
Modality	Text
Max Input Tokens	4096
Price	$2.00 / 1k requests

Task	Embedding
Modality	Text
Max Input Tokens	512
Price	$0.08 / million tokens

Task	Rerank
Modality	Text
Max Input Tokens	1024
Price	$2.00 / 1k requests

Models

Model Gallery

llama-text-embed-v2

multilingual-e5-large

cohere-rerank-3.5

pinecone-sparse-english-v0

bge-reranker-v2-m3