> ## Documentation Index
> Fetch the complete documentation index at: https://docs-v1.agno.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Markdown Knowledge Base

> Learn how to use Markdown files in your knowledge base.

The **MarkdownKnowledgeBase** reads **local markdown** files, converts them into vector embeddings and loads them to a vector database.

## Usage

<Note>
  We are using a local PgVector database for this example. [Make sure it's running](https://docs-v1.agno.com/vectordb/pgvector)
</Note>

```python knowledge_base.py theme={null}
from agno.knowledge.markdown import MarkdownKnowledgeBase
from agno.vectordb.pgvector import PgVector

knowledge_base = MarkdownKnowledgeBase(
    path="data/markdown_files",
    vector_db=PgVector(
        table_name="markdown_documents",
        db_url="postgresql+psycopg://ai:ai@localhost:5532/ai",
    ),
)
```

Then use the `knowledge_base` with an Agent:

```python agent.py theme={null}
from agno.agent import Agent
from knowledge_base import knowledge_base

agent = Agent(
    knowledge_base=knowledge_base,
    search_knowledge=True,
)
agent.knowledge.load(recreate=False)

agent.print_response("Ask me about something from the knowledge base")
```

#### MarkdownKnowledgeBase also supports async loading.

```shell theme={null}
pip install qdrant-client
```

We are using a local Qdrant database for this example. [Make sure it's running](https://docs-v1.agno.com/vectordb/qdrant)

```python async_knowledge_base.py theme={null}
import asyncio
from pathlib import Path

from agno.agent import Agent
from agno.knowledge.markdown import MarkdownKnowledgeBase
from agno.vectordb.qdrant import Qdrant

COLLECTION_NAME = "essay-txt"

vector_db = Qdrant(collection=COLLECTION_NAME, url="http://localhost:6333")

# Initialize the MarkdownKnowledgeBase
knowledge_base = MarkdownKnowledgeBase(
    path=Path("tmp/mds"),
    vector_db=vector_db,
    num_documents=5,
)

# Initialize the Assistant with the knowledge_base
agent = Agent(
    knowledge=knowledge_base,
    search_knowledge=True,
)

if __name__ == "__main__":
    # Comment out after first run
    asyncio.run(knowledge_base.aload(recreate=False))

    asyncio.run(
        agent.aprint_response(
            "What knowledge is available in my knowledge base?", markdown=True
        )
    )
```

## Params

| Parameter | Type               | Default            | Description                                                                             |
| --------- | ------------------ | ------------------ | --------------------------------------------------------------------------------------- |
| `path`    | `Union[str, Path]` | -                  | Path to md files. Can point to a single md file or a directory of md files.             |
| `formats` | `List[str]`        | `[".md"]`          | Formats accepted by this knowledge base.                                                |
| `reader`  | `MarkdownReader`   | `MarkdownReader()` | A `MarkdownReader` that converts the md files into `Documents` for the vector database. |

`MarkdownKnowledgeBase` is a subclass of the [AgentKnowledge](/reference/knowledge/base) class and has access to the same params.

## Developer Resources

* View [Sync loading Cookbook](https://github.com/agno-agi/agno/blob/main/cookbook/agent_concepts/knowledge/markdown_kb.py)
* View [Async loading Cookbook](https://github.com/agno-agi/agno/blob/main/cookbook/agent_concepts/knowledge/markdown_kb_async.py)