Retrieve context snippets from an assistant to use as part of RAG or any agentic flow.

For guidance and examples, see [Retrieve context snippets](https://docs.pinecone.io/guides/assistant/retrieve-context-snippets).

Retrieve context from an assistant

The MessageModel describes the format of a message in a chat.

Role of the message such as 'user' or 'assistant'

The SnippetModel represents a part of a document that is relevant to the user query.

The TypedReferenceModel represents a reference for the information provided.

The UsageModel describes the usage of a chat completion.

The desired configuration to retrieve context from an assistant.

Parameters to retrieve context from an assistant.

ApiKeyAuth

The response format containing the context from an assistant.

Bad request. The request body included invalid request parameters.

The response shape used for all error responses.

Unauthorized. Possible causes: Invalid API key.

Pinecone Docs

Overview

Pinecone Documentation

Database quickstart

Pinecone Database quickstart

Assistant quickstart

Pinecone Assistant quickstart

Key features

Glossary

Understanding indexes

Create an index

Create a serverless index

Implement multitenancy

Implement multitenancy using namespaces

Manage indexes

Manage serverless indexes

Sparse indexes

Get started with sparse indexes

Upsert data

Query data

Fetch data

Update data

Delete data

List record IDs

Target an index

Understanding metadata

Manage RAG documents

Understanding Pinecone Inference

Embed data

Rerank documents

Upsert and search with integrated inference

Understanding Pinecone Assistant

Create an assistant

Manage files

Chat with an assistant

Manage assistants

Local development

Local development with Pinecone Local

Automated testing

CI/CD with Pinecone Local and GitHub Actions

Move to production

Performance tuning

Monitoring

Understanding organizations

Manage organization members

Understanding projects

Create a project

Manage API keys

Manage project members

Rename a project

Notebooks

Sample apps

Reference architectures

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

View all

Integrations

Become a Pinecone partner

Attribute usage to your integration

Connect your users to Pinecone

Contact Support

How to work with Support

Pinecone Support SLAs

Login code issues

Custom data processing agreements

Delete your organization

Delete your account

Billing disputes and refunds

Available cloud regions

Export indexes

Wait for index creation to be complete

Select index type and size

How and when to increase index size

Use namespaces instead of several indexes

Namespaces vs. metadata filtering

Restrictions on index names

Return all vectors in an index

Vertically downscaling

Pods are full

Parallel queries

Minimize latencies

Embedding values changed when upserted

How and when to add replicas

Keep customer data separate in Pinecone

Limitations of querying by ID

Create and manage vectors with metadata

Metadata re-configuration

Metadata string value returned as a datetime object

Remove 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

PineconeAttribute errors with LangChain

Error: Cannot import name 'Pinecone' from 'pinecone'

Python AttributeError: module pinecone has no attribute init

Best Practices

Differences between Lexical and Semantic Search regarding relevancy

Node.js Troubleshooting

CORS Issues

Debug model vs. Pinecone recall issues

Non-indexed field filter issues

Unable to pip install

2025 releases

2024 releases

2023 releases

2022 releases

Feature availability

Build a RAG chatbot

Semantic search

Image search

Multimodal search

Recommender

Threat detection

More examples

Understanding backups

Back up an index

Restore an index

Understanding pod-based indexes

Migrate a pod-based index to serverless

Choose a pod type

Choose a pod type and size

Create a pod-based index

Manage pod-based indexes

Scale pod-based indexes

Understanding imports

Import data

Understanding data freshness

Check data freshness

Understanding hybrid search

Encode sparse vectors

Upsert sparse-dense vectors

Query sparse-dense vectors

Understanding evaluation

Evaluate answers

Understanding context snippets

Retrieve context snippets

Understanding security

Configure SSO with Okta

Configure CMEK

Configure customer-managed encryption keys

Connect to AWS PrivateLink

Manage storage integrations

Integrate with Amazon S3

Change your billing plan

Set up billing through AWS Marketplace

Set up billing through Azure Marketplace

Set up billing through GCP Marketplace

Understanding cost

Monitor your usage

Manage cost

Introduction

API reference

Authentication

Versioning

API versioning

Database limits

Pinecone Database limits

Inference limits

Pinecone Inference limits

Assistant limits

Pinecone Assistant limits

Known limitations

Errors

List indexes

Create 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/guides/indexes/create-an-index#create-a-serverless-index).


Create a serverless integrated inference index for a specific embedding model.

Refer to the [model guide](https://docs.pinecone.io/guides/inference/understanding-inference#embedding-models) for available models and model details.

Create an index for an embedding model

Describe an index

Delete an index

Configure an existing index. For serverless indexes, you can configure index deletion protection, tags, and integrated inference embedding settings for the index. For pod-based indexes, you can configure the pod size, number of replicas, tags, and index deletion protection.

It is not possible to change the pod type of a pod-based index. However, you can create a collection from a pod-based index and then [create a new pod-based index with a different pod type](http://docs.pinecone.io/guides/indexes/pods/create-a-pod-based-index#create-a-pod-index-from-a-collection) from the collection. For guidance and examples, see [Configure an index](http://docs.pinecone.io/guides/indexes/pods/manage-pod-based-indexes).

Configure an index

Return statistics about the contents of an index, including the vector count per namespace, the number of dimensions, and the index fullness.

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

Get index stats

Upsert 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/guides/data/upsert-data#upsert-vectors).

Upsert vectors

Upsert text into a namespace.

Upserting text is supported only for [indexes with integrated embedding](https://docs.pinecone.io/reference/api/2025-01/control-plane/create_for_model).

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

Upsert text

Look up and return 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/guides/data/fetch-data).

Fetch vectors

Update 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/guides/data/update-data).

Update a vector

Delete vectors by id from a single namespace.

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

Delete vectors

List 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.

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 [List record IDs](https://docs.pinecone.io/guides/data/list-record-ids).

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

List vector IDs

Search a namespace with a query vector or record ID and return the IDs of the most similar records, along with their similarity scores.

Search with a vector

APIs

Database

Inference

Assistant

SDKs

Tools

Architecture

Retrieve context from an assistant

Authorizations

Path Parameters

Body

Response