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

# Knowledge Storage

> Vector store backends for knowledge and document retrieval

# Knowledge Storage

Knowledge uses vector stores to index and retrieve documents. Choose the right backend for your use case.

## Quick Setup

```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
from praisonaiagents import Agent

# Default: Chroma (zero-config, local)
agent = Agent(knowledge=["docs/"])

# With specific provider
agent = Agent(
    knowledge={
        "sources": ["docs/"],
        "vector_store": {
            "provider": "qdrant",
            "config": {"url": "http://localhost:6333"}
        }
    }
)
```

## Supported Vector Stores

<CardGroup cols={3}>
  <Card title="Qdrant" icon="cube" href="/docs/databases/qdrant">
    High-performance vector search
  </Card>

  <Card title="Chroma" icon="palette" href="/docs/databases/chroma">
    Zero-config local storage
  </Card>

  <Card title="Pinecone" icon="tree" href="/docs/databases/pinecone">
    Managed cloud service
  </Card>

  <Card title="Weaviate" icon="shapes" href="/docs/databases/weaviate">
    Open-source, scalable
  </Card>

  <Card title="LanceDB" icon="database" href="/docs/databases/lancedb">
    Serverless vector DB
  </Card>

  <Card title="Milvus" icon="server" href="/docs/databases/milvus">
    Enterprise-grade
  </Card>

  <Card title="PGVector" icon="elephant" href="/docs/databases/pgvector">
    PostgreSQL extension
  </Card>

  <Card title="Cassandra" icon="table" href="/docs/databases/cassandra">
    Distributed storage
  </Card>

  <Card title="ClickHouse" icon="bolt" href="/docs/databases/clickhouse">
    Analytics-optimized
  </Card>
</CardGroup>

## Choosing a Vector Store

| Use Case                 | Recommended     | Why                     |
| ------------------------ | --------------- | ----------------------- |
| Local development        | Chroma          | Zero config, embedded   |
| Production (hosted)      | Pinecone        | Managed, scalable       |
| Production (self-hosted) | Qdrant/Weaviate | Performant, open-source |
| PostgreSQL stack         | PGVector        | Same infrastructure     |
| Enterprise               | Milvus          | High availability       |

## Configuration Examples

<Tabs>
  <Tab title="Chroma">
    ```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
    agent = Agent(
        knowledge={
            "sources": ["docs/"],
            "vector_store": {
                "provider": "chroma",
                "config": {
                    "collection_name": "my_docs",
                    "path": ".praison/chroma"
                }
            }
        }
    )
    ```
  </Tab>

  <Tab title="Qdrant">
    ```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
    agent = Agent(
        knowledge={
            "sources": ["docs/"],
            "vector_store": {
                "provider": "qdrant",
                "config": {
                    "url": "http://localhost:6333",
                    "collection_name": "my_docs"
                }
            }
        }
    )
    ```
  </Tab>

  <Tab title="Pinecone">
    ```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
    agent = Agent(
        knowledge={
            "sources": ["docs/"],
            "vector_store": {
                "provider": "pinecone",
                "config": {
                    "api_key": "your-api-key",
                    "index_name": "my-index"
                }
            }
        }
    )
    ```
  </Tab>
</Tabs>

## Related

<CardGroup cols={2}>
  <Card title="Database Overview" icon="database" href="/docs/databases/overview">
    All database backends
  </Card>

  <Card title="Knowledge Quick Start" icon="rocket" href="/docs/knowledge/quickstart">
    Get started with knowledge
  </Card>
</CardGroup>