Pinecone

About

Managed vector database for semantic, full-text and hybrid search, with hosted embedding and reranking models. Built for RAG and search backends. The free Starter plan runs only in AWS us-east-1.

What you can do with it

• Store embeddings and query the nearest matches for RAG and similarity search
• Upsert raw text and let a hosted embedding model vectorize it
• Rerank search results with a hosted reranking model

Get started

1. Create a Pinecone account and an API key
2. Set PINECONE_API_KEY in your environment
3. Create an index, then upsert and search records

Example

curl "https://api.pinecone.io/indexes/create-for-model" \
  -H "Api-Key: $PINECONE_API_KEY" \
  -H "Content-Type: application/json" \
  -H "X-Pinecone-Api-Version: 2026-07" \
  -d '{
    "name": "docs-example",
    "cloud": "aws",
    "region": "us-east-1",
    "embed": {"model": "multilingual-e5-large", "field_map": {"text": "chunk_text"}}
  }'

Details

Hosting

Hosted service

Available in

Worldwide

Official SDKs

Python, JavaScript/TypeScript, Java, Go

MCP server

Local