> ## Documentation Index > Fetch the complete documentation index at: https://docs.pinecone.io/llms.txt > Use this file to discover all available pages before exploring further. # VoltAgent > Connect Pinecone and VoltAgent to ship vector search and RAG: embed, index, and query at scale with managed infrastructure. export const PrimarySecondaryCTA = ({primaryLabel, primaryHref, primaryTarget, secondaryLabel, secondaryHref, secondaryTarget}) =>
{primaryLabel && primaryHref &&
{primaryLabel}
} {secondaryLabel && secondaryHref &&
{secondaryLabel}
}
; [VoltAgent](https://voltagent.dev) is a TypeScript-based, AI-agent framework for building production-ready applications with retrieval-augmented generation (RAG) capabilities. It supports two retrieval patterns: automatic search on every interaction, or LLM-decides-when-to-search, with built-in observability and tracking. This integration connects VoltAgent agents to Pinecone's managed vector database, automatically generating embeddings with OpenAI's API. It provides semantic search with similarity scoring, source tracking, metadata filtering, and namespace organization, and it supports serverless deployment with automatic scaling. The integration provides: * A complete RAG setup with sample data * Two pre-configured agent types * Automatic index creation and population * Source references and similarity scores * Production-ready architecture Use this integration to quickly build AI agents that can intelligently search and retrieve information from Pinecone vector databases, while maintaining full observability and control over the retrieval process.