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

# What are Vector Databases?

> Vector databases enable us to store information as embeddings and search for "results similar" to our input query using cosine similarity or full text search. These results are then provided to the Agent as context so it can respond in a context-aware manner using Retrieval Augmented Generation (RAG).

Here's how vector databases are used with Agents:

<Steps>
  <Step title="Chunk the information">
    Break down the knowledge into smaller chunks to ensure our search query
    returns only relevant results.
  </Step>

  <Step title="Load the knowledge base">
    Convert the chunks into embedding vectors and store them in a vector
    database.
  </Step>

  <Step title="Search the knowledge base">
    When the user sends a message, we convert the input message into an
    embedding and "search" for nearest neighbors in the vector database.
  </Step>
</Steps>

Many vector databases also support hybrid search, which combines the power of vector similarity search with traditional keyword-based search. This approach can significantly improve the relevance and accuracy of search results, especially for complex queries or when dealing with diverse types of data.

Hybrid search typically works by:

1. Performing a vector similarity search to find semantically similar content.
2. Conducting a keyword-based search to identify exact or close matches.
3. Combining the results using a weighted approach to provide the most relevant information.

This capability allows for more flexible and powerful querying, often yielding better results than either method alone.

<Card title="⚡ Asynchronous Operations">
  <p>Several vector databases support asynchronous operations, offering improved performance through non-blocking operations, concurrent processing, reduced latency, and seamless integration with FastAPI and async agents.</p>

  <Tip className="mt-4">
    When building with Agno, use the <code>aload</code> methods for async knowledge base loading in production environments.
  </Tip>
</Card>

## Supported Vector Databases

The following VectorDb are currently supported:

* [PgVector](../vectordb/pgvector)\*
* [Cassandra](../vectordb/cassandra)
* [ChromaDb](../vectordb/chroma)
* [Couchbase](../vectordb/couchbase)\*
* [Clickhouse](../vectordb/clickhouse)
* [LanceDb](../vectordb/lancedb)\*
* [LightRAG](../vectordb/lightrag)
* [Milvus](../vectordb/milvus)
* [MongoDb](../vectordb/mongodb)
* [Pinecone](../vectordb/pinecone)\*
* [Qdrant](../vectordb/qdrant)
* [Singlestore](../vectordb/singlestore)
* [Weaviate](../vectordb/weaviate)

\*hybrid search supported

Each of these databases has its own strengths and features, including varying levels of support for hybrid search and async operations. Be sure to check the specific documentation for each to understand how to best leverage their capabilities in your projects.

## Popular Choices by Use Case

<CardGroup cols={2}>
  <Card title="Development & Testing" icon="laptop-code" href="/concepts/vectordb/lancedb">
    **LanceDB** - Fast, local, no setup required
  </Card>

  <Card title="Production at Scale" icon="server" href="/concepts/vectordb/pgvector">
    **PgVector** - Reliable, scalable, full SQL support
  </Card>

  <Card title="Managed Service" icon="cloud" href="/concepts/vectordb/pinecone">
    **Pinecone** - Fully managed, no operations overhead
  </Card>

  <Card title="High Performance" icon="gauge" href="/concepts/vectordb/qdrant">
    **Qdrant** - Optimized for speed and advanced features
  </Card>
</CardGroup>

## Next Steps

<CardGroup cols={2}>
  <Card title="Getting Started" icon="rocket" href="/concepts/knowledge/getting-started">
    Build your first knowledge base with a vector database
  </Card>

  <Card title="Embeddings" icon="vector-square" href="/concepts/knowledge/embedder/overview">
    Learn about creating vector representations of your content
  </Card>

  <Card title="Search & Retrieval" icon="magnifying-glass" href="/concepts/knowledge/core-concepts/search-retrieval">
    Understand how vector search works with your data
  </Card>

  <Card title="Performance Tips" icon="gauge" href="/concepts/knowledge/advanced/performance-tips">
    Optimize your vector database for speed and scale
  </Card>
</CardGroup>