What is Pinecone?
Pinecone is a vector database that helps power AI for the world's best companies. It enables developers to build knowledgeable AI applications faster and more efficiently.
Features of Pinecone
Start and Scale Seamlessly
Create an account and your first index in 30 seconds, then upload a few vector embeddings from any model or a few billion. Perform low-latency vector search to retrieve relevant data for search, RAG, recommendation, detection, and other applications.
Search and Scale Seamlessly
Perform low-latency vector search to retrieve relevant data for search, RAG, recommendation, detection, and other applications.
Filter by Metadata
Combine vector search with familiar metadata filters to get just the results you want.
Find Context
Fast and accurate vector search over all your data.
Update in Real-Time
As your data changes, the Pinecone index is updated in real-time to provide the freshest results.
Make (the Right) Keywords Matter
Combine vector search with keyword boosting for the best of both worlds (hybrid search).
How to Use Pinecone
Quickstart Guide
Create a serverless index, target the index, mock vector and metadata objects, and upsert your vector(s).
Python Example
from pinecone import Pinecone, ServerlessSpec
pc = Pinecone(api_key="YOUR_API_KEY")
pc.create_index(name="products", dimension=1536, spec=ServerlessSpec(cloud='aws', region='us-east-1'))
index = pc.Index("products")
vector = [0.010, 2.34,...] # len(vector) = 1536
metadata = {"id": 3056, "description": "Networked neural adapter"}
index.upsert(vectors=[{"id": "some_id", "values": vector, "metadata": metadata}])
Pricing
Create your first index for free, then upgrade and pay as you go when you're ready to scale, or talk to sales.
Helpful Tips
Performance
Pinecone provides 96% recall and 51ms query latency (p95) with the MSMarco V2 dataset of 138M embeddings (1536 dimensions).
Integrations
Use Pinecone with your favorite cloud provider, data sources, models, frameworks, and more.
Security
Pinecone is SOC 2 and HIPAA certified, providing secure and reliable solutions for your AI applications.
Frequently Asked Questions
What is a Vector Database?
A vector database is a type of database that stores and indexes vector embeddings, enabling fast and accurate similarity searches.
What is Retrieval Augmented Generation (RAG)?
RAG is a technique that uses vector databases to generate text based on user input.
What is Multimodal Search?
Multimodal search is a type of search that combines different modalities, such as text and images, to retrieve relevant results.