LearnIntroducing Pinecone ServerlessLearn more

Pinecone Integrations

Supercharge your AI stack with Pinecone's growing number of third-party integrations.

Filters

Airbyte

Airbyte

Fetch, embed, and upsert your data using the Pinecone Airbyte Connector.

Data sources
Amazon Bedrock

Amazon Bedrock

Foundational models to build and scale GenAI applications with Pinecone.

Frameworks
Amazon Sagemaker

Amazon Sagemaker

Support RAG workflows with Amazon Sagemaker and Pinecone.

Frameworks
Amazon Web Services (AWS)

Amazon Web Services (AWS)

Access Pinecone through our AWS marketplace listing.

Infrastructure
Anyscale

Anyscale

Create and index vector embeddings with Canopy and Anyscale Endpoints.

Models
Azure

Azure

Access Pinecone through our Microsoft Azure marketplace listing.

Infrastructure
Cohere

Cohere

Create vector embeddings with Cohere’s Embed API.

Models
Confluent

Confluent

Build real-time AI applications with the Pinecone Sink Connector.

Data sources
Databricks

Databricks

Create and index vector embeddings at scale.

Data sources
Datadog

Datadog

Monitor usage and performance for Pinecone.

Observability
Google Cloud Platform

Google Cloud Platform

Access Pinecone through our GCP marketplace listing.

Infrastructure
Haystack

Haystack

Build customized, production-ready LLM applications.

Frameworks
Hugging Face Inference Points

Hugging Face Inference Points

Generate vector embeddings with Hugging Face.

Models
LangChain

LangChain

Create chatbot agents and provide long-term memory for your LLMs.

Frameworks
Llama Index

Llama Index

Perform traditional semantic search and build a RAG pipeline.

Frameworks
New Relic

New Relic

Monitor usage and performance for Pinecone (in preview).

Observability
OpenAI

OpenAI

Support for any OpenAI LLM and embedding model.

Models
Pulumi

Pulumi

Launch production-grade architectures with Pulumi’s Pinecone Provider.

Infrastructure
Snowflake

Snowflake

Deploy and run Pinecone with Snowpark Container Services (in preview).

Data sources
TruLens

TruLens

Evaluate and track LLM-based Pinecone applications.

Observability
Vercel

Vercel

Easily deploy your AI applications with Vercel.

Infrastructure