/* Global styles */

#topbar-cta-button span {
  border-radius: 4px;
  padding: 4px 2px;
  font-weight: bold;
}

.documentation-link {
  color: #1c17ff;
  text-decoration: none;
}

.documentation-link:hover {
  color: #000000; /* Black color when hovering */
}

.custom-button {
  display: inline-block;
  padding: 2px 8px;
  background-color: #f1f1f1;
  color: #333; /* Text color */
  border: 1px solid #aaa; /* Border color */
  border-radius: 25px; /* Rounded borders */
  text-align: center;
  user-select: none;
  transition: background-color 0.3s ease; /* Smooth transition for background color */
}

/* Change the button color on hover (make it unclickable) */
.custom-button:hover {
  background-color: #1c17ff;
  color: #f1f1f1;
}

/* Adjust the width for the second column */
td:nth-child(2) {
  width: 200px; /* Adjust the width as per your requirement */
}

/* 
Add an announcement bar 
TODO: Figure out how to make this versions-specific. 
*/
/* #navbar:before {
  background-color: #ff4c04;
  content: "This API is currently in beta. If you'd like to request access, contact our Support Team";
  color: rgb(255, 255, 255);
  display: block;
  text-align: center;
  padding: 6px;
  font-size: 90%;
} */


The `Query` operation searches a <a href='https://docs.pinecone.io/docs/namespaces'>namespace</a>, using a query vector.
It retrieves the ids of the most similar items in a namespace, along with their similarity scores.

Query

A single query vector within a `QueryRequest`.

An override for the metadata filter to apply. This replaces the request-level filter.

The <a href='https://docs.pinecone.io/docs/namespaces'>namespace</a> to search.

An override for the number of results to return for this query vector.

The query vector values. This should be the same length as the dimension of the index being queried.

This is a measure of similarity between this vector and the query vector.  The higher the score, the more they are similar.

This is the vector data, if it is requested.

Vector sparse data. Represented as a list of indices and a list of corresponded values, which must be the same length.

The corresponding values of the sparse data, which must be the same length as the indices.

ApiKeyAuth

The response for the `Query` operation. These are the matches found for a particular query vector. The matches are ordered from most similar to least similar.

URL for the target Pinecone index. See app.pinecone.io > Indexes > Index Name.

Pinecone

Forum

Support

Status

Guides

Reference

Examples

Integrations

Libraries

Tools

Troubleshooting

Releases

Sign Up Free

Log In

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

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

Single sign-on with Okta

Manage organization members

Understanding projects

Create a project

Manage project 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

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

Airbyte

Confluent

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

Databricks

Snowflake

Pinecone as a Knowledge Base for Amazon Bedrock

Amazon Bedrock

Amazon SageMaker

Haystack

LangChain

LlamaIndex

Amazon Web Services (AWS)

Azure

Google Cloud Platform (GCP)

Pulumi

Vercel

Anyscale

Cohere

Hugging Face Inference Endpoints

OpenAI

Datadog

New Relic

Using TruLens and Pinecone to evaluate grounded LLM applications

TruLens

Become a Pinecone partner

Attribute API activity

Contact Support

How to work with Support

Pinecone Support SLAs

Login code issues

Custom data processing agreements

Delete your Pinecone account

Billing disputes and refunds

Exporting indexes

Waiting for index creation to be complete

Selecting index type and size

How and when to increase the size of an index

Using namespaces instead of several indexes

Using namespaces vs. metadata filtering

Restrictions on index names

Returning all vectors in an index

Vertically downscaling

Deleting a namespace

Pods are full

Parallel queries

Minimize latencies

Embedding values changed when upserted

How and when to add replicas

Keeping customer data separate in Pinecone

Creating and managing vectors with metadata

Handling large numbers of deletes by metadata

Metadata re-configuration

Metadata string value returned as a datetime object

Removing a metadata field from a record

Index creation error - missing spec parameter

Serverless index creation error - max serverless indexes

Serverless index connection errors

Error: Handshake read failed when connecting

Error messages about controller.[...].pinecone.io on serverless indexes

Error: Pinecone has no attribute 'from_texts'

Python AttributeError: module pinecone has no attribute init

General FAQs

Best Practices

Differences between Lexical and Semantic Search regarding relevancy

Node.JS Troubleshooting

CORS Issues

Debugging model vs. Pinecone recall issues

Understanding and resolving non-indexed field filter issues

Unable to pip install

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).

REST API

Query

Authorizations

Body

Response