Skip to main content
Markdown chunking splits Markdown documents while preserving heading structure and hierarchy. It respects Markdown syntax to create chunks that align with document sections, keeping headings with their associated content.

​
Code

import asyncio
from agno.agent import Agent
from agno.knowledge.chunking.markdown import MarkdownChunking
from agno.knowledge.knowledge import Knowledge
from agno.knowledge.reader.markdown_reader import MarkdownReader
from agno.vectordb.pgvector import PgVector

db_url = "postgresql+psycopg://ai:ai@localhost:5532/ai"

knowledge = Knowledge(
    vector_db=PgVector(table_name="recipes_markdown_chunking", db_url=db_url),
)

asyncio.run(knowledge.add_content_async(
    url="https://github.com/agno-agi/agno/blob/main/README.md",
    reader=MarkdownReader(
        name="Markdown Chunking Reader",
        chunking_strategy=MarkdownChunking(),
    ),
))
agent = Agent(
    knowledge=knowledge,
    search_knowledge=True,
)

agent.print_response("What is Agno?", markdown=True)

​
Usage

1

Create a virtual environment

Open the Terminal and create a python virtual environment.
python3 -m venv .venv
source .venv/bin/activate
2

Install libraries

pip install -U sqlalchemy psycopg pgvector agno
3

Run PgVector

docker run -d \
  -e POSTGRES_DB=ai \
  -e POSTGRES_USER=ai \
  -e POSTGRES_PASSWORD=ai \
  -e PGDATA=/var/lib/postgresql/data/pgdata \
  -v pgvolume:/var/lib/postgresql/data \
  -p 5532:5432 \
  --name pgvector \
  agno/pgvector:16
4

Run Agent

python cookbook/knowledge/chunking/markdown_chunking.py

​
Markdown Chunking Params

ParameterTypeDefaultDescription
chunk_sizeint5000The maximum size of each chunk.
overlapint0The number of characters to overlap between chunks.