Page Inspect

The vector database to build knowledgeable AI | Pinecone

Meet us at re:Invent 2025. Come by Booth #534 and get a demo \- Learn moreDismiss

Product

DocsCustomers

Resources

Pricing

ContactLog inSign up

Build Knowledgeable AI# The vector database
for scale in production

Start BuildingGet a Demo

{rag}

{search}

{recommendations}

{agents}

## Performance at scale for {}

The purpose-built vector database delivering relevant results at any scale.

Learn More

Customer workload: Popular productivity app providing instant Q&A across company knowledge

Total vectors

Namespaces

Global writes per day

## Trusted in production

The world's most innovative companies are already in production with Pinecone.

USE CASE: RECOMMENDATIONS

Read case study

Gong achieves efficient vector searches, empowering Smart Trackers to offer users precise and relevant examples for concept tracking in conversations.

USE CASE: SEARCH

Read case study

Before Pinecone, Vanguard’s customer support teams relied on keyword-based search solutions to search for documents where answers to a customer’s question may live. With Pinecone and hybrid retrieval, they **boosted customer support with faster calls and 12% more accurate responses.**

USE CASE: AGENTS

"Pinecone also **supports hybrid search**, combining sparse and dense embeddings, to deliver a more robust and accurate search experience. This flexibility allows us to optimize costs and performance, whether dealing with enterprises with extensive documentation or smaller companies with fewer pages."

USE CASE: RAG

"Pinecone aligns with our vision to democratize data accessibility for all engineers, and we're excited to uncover more potential with its new serverless architecture."

Developer Experience

## Scale simplified

Fully managed and serverless for effortless scaling.

### Rapid setup

Launch your vector databases in seconds.

### Serverless scaling

Resources adjust to meet your demand automatically.

### Rock-solid reliability

Trust in consistent uptime for your critical applications.

agent/retriever.py

Quickstart guide

from pinecone import Pinecone

pc = Pinecone("<API KEY>")

pc.Index("semantic-search")

index.query(
namespace="breaking-news"
vector=[0.13, 0.45, 1.34, ...],
filter={"category": {"$eq": "technology"}},
top_k=3
)


Search

## Relevance, delivered

Advanced retrieval capabilities for precise search across dynamic datasets.

### Embeddings

Choose from our leading hosted models or bring your own vectors.

### Optimized recall

Benchmark leading algorithms maximize recall with low latency.

### Filters

Retrieve only the vectors that match your metadata filters.

### Real-time indexing

Upserted and updated vectors are dynamically indexed in real-time to ensure fresh reads.

### Full-text search

Get an exact keyword match with sparse indexes when semantic search isn't enough.

### Rerankers

Add an extra layer of precision with rerankers to boost the most relevant matches.

### Namespaces

Create partitions of your data with namespaces to ensure tenant isolation.

Learn how to achieve best-in-class relevance with cascading retrieval

View sample code

## Works where you do

Use Pinecone with your favorite cloud provider, data sources, models, frameworks, and more.

Explore Integrations

## Enterprise-ready AI

Meet security and operational requirements to bring AI products to market faster.

View Security

### Secure

With encryption at rest and in transit, hierarchical encryption keys, private networking, and more, your data is secure. Contact us to deploy a privately managed Pinecone region within your cloud.

### Reliable

Powering mission-critical applications of all sizes, with uptime SLAs, support SLAs, and observability.

### Compliant

Control your data and know it's safe. Pinecone is SOC 2, GDPR, ISO 27001, and HIPAA certified.

## Start building knowledgeable AI today

Create your first index for free, then pay as you go when you're ready to scale.

Start Building

Get a Demo

### Subscribe to Pinecone

Subscribe

Product

Vector DatabaseAssistantDocumentationPricingSecurityIntegrations

Resources

Community ForumLearning CenterBlogCustomer Case StudiesStatusWhat is a Vector DB?What is RAG?

Company

AboutPartnersCareersNewsroomContact

Legal

Customer TermsWebsite TermsPrivacyCookiesCookie Preferences

© Pinecone Systems, Inc. | San Francisco, CA

Pinecone is a registered trademark of Pinecone Systems, Inc.