> ## Documentation Index
> Fetch the complete documentation index at: https://agno-v2.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Vector Databases

> Store embeddings and search for similar content.

Vector databases store content as embeddings and enable similarity search. When an agent searches the knowledge base, the query is converted to an embedding and matched against stored vectors to find relevant content.

## How It Works

**1. Chunk**

Documents are split into smaller pieces for more precise retrieval.

**2. Embed**

Each chunk is converted to a vector embedding and stored in the database.

**3. Search**

Queries are embedded and matched against stored vectors to find similar content.

## Hybrid Search

Many vector databases support a hybrid search mode that combines vector similarity with a provider-specific keyword or lexical ranking.

Hybrid search works by:

1. Finding semantically similar content via vector search
2. Finding lexical matches with the database's keyword-search implementation
3. Combining results using ranked fusion

## Supported Databases

> **[Azure Cosmos DB](https://agno-v2.mintlify.site/knowledge/vector-stores/azure_cosmos_mongodb/overview.md)**
>
> MongoDB vCore vector search

> **[Cassandra](https://agno-v2.mintlify.site/knowledge/vector-stores/cassandra/overview.md)**
>
> Distributed database with vector search

> **[Chroma](https://agno-v2.mintlify.site/knowledge/vector-stores/chroma/overview.md)**
>
> Open-source embedding database

> **[ClickHouse](https://agno-v2.mintlify.site/knowledge/vector-stores/clickhouse/overview.md)**
>
> Analytical database with vector search

> **[Couchbase](https://agno-v2.mintlify.site/knowledge/vector-stores/couchbase/overview.md)**
>
> NoSQL with vector search

> **[LanceDB](https://agno-v2.mintlify.site/knowledge/vector-stores/lancedb/overview.md)**
>
> Local, serverless, hybrid search

> **[LangChain](https://agno-v2.mintlify.site/knowledge/vector-stores/langchain/overview.md)**
>
> Use any LangChain vector store

> **[LightRAG](https://agno-v2.mintlify.site/knowledge/vector-stores/lightrag/overview.md)**
>
> Graph-based RAG

> **[LlamaIndex](https://agno-v2.mintlify.site/knowledge/vector-stores/llamaindex/overview.md)**
>
> Search existing LlamaIndex indexes

> **[Milvus](https://agno-v2.mintlify.site/knowledge/vector-stores/milvus/overview.md)**
>
> Scalable vector database

> **[MongoDB](https://agno-v2.mintlify.site/knowledge/vector-stores/mongodb/overview.md)**
>
> Atlas vector search

> **[PgVector](https://agno-v2.mintlify.site/knowledge/vector-stores/pgvector/overview.md)**
>
> PostgreSQL extension, hybrid search

> **[Pinecone](https://agno-v2.mintlify.site/knowledge/vector-stores/pinecone/overview.md)**
>
> Managed vector database

> **[Qdrant](https://agno-v2.mintlify.site/knowledge/vector-stores/qdrant/overview.md)**
>
> High-performance vector search

> **[Redis](https://agno-v2.mintlify.site/knowledge/vector-stores/redis/overview.md)**
>
> In-memory with vector search

> **[Valkey](https://agno-v2.mintlify.site/knowledge/vector-stores/valkey/overview.md)**
>
> In-memory with vector search

> **[SingleStore](https://agno-v2.mintlify.site/knowledge/vector-stores/singlestore/overview.md)**
>
> Real-time analytics with vectors

> **[SurrealDB](https://agno-v2.mintlify.site/knowledge/vector-stores/surrealdb/overview.md)**
>
> Multi-model database

> **[Upstash](https://agno-v2.mintlify.site/knowledge/vector-stores/upstash/overview.md)**
>
> Serverless vector search

> **[Weaviate](https://agno-v2.mintlify.site/knowledge/vector-stores/weaviate/overview.md)**
>
> Vector search with modules

## Choosing a Database

> **[Local Development](https://agno-v2.mintlify.site/knowledge/vector-stores/lancedb/overview.md)**
>
> **LanceDB** or **ChromaDB** for zero-setup local development

> **[Production](https://agno-v2.mintlify.site/knowledge/vector-stores/pgvector/overview.md)**
>
> **PgVector** if you already use PostgreSQL

> **[Managed Service](https://agno-v2.mintlify.site/knowledge/vector-stores/pinecone/overview.md)**
>
> **Pinecone** or **Weaviate Cloud** for vendor-operated infrastructure

> **[Distributed Deployment](https://agno-v2.mintlify.site/knowledge/vector-stores/qdrant/overview.md)**
>
> **Qdrant** or **Milvus** for a separately operated vector service

## Async Support

Vector databases with async support let an async application await ingestion and search I/O. Use `ainsert` and `asearch` inside an existing event loop.

```python theme={null}
# Async insert
await knowledge.ainsert(url="https://example.com/docs.pdf")

# Async search
results = await knowledge.asearch(query="How do I configure X?")
```


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.