Markdown Chunking

Markdown chunking is a method of splitting Markdown documents into smaller chunks based on structure like headers, paragraphs, and sections. Set split_on_headings to split on heading boundaries, or leave it off for size-based chunking with optional overlap.

Create a Python file

markdown_chunking.py

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.ainsert(
    url="https://raw.githubusercontent.com/agno-agi/agno/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)

Set up your virtual environment

uv venv --python 3.12
source .venv/bin/activate

uv venv --python 3.12
.venv\Scripts\activate

Install dependencies

uv pip install -U agno sqlalchemy psycopg pgvector unstructured markdown openai

Run PgVector

docker run -d \
  -e POSTGRES_DB=ai \
  -e POSTGRES_USER=ai \
  -e POSTGRES_PASSWORD=ai \
  -e PGDATA=/var/lib/postgresql \
  -v pgvolume:/var/lib/postgresql \
  -p 5532:5432 \
  --name pgvector \
  agnohq/pgvector:18

Run the script

python markdown_chunking.py

Markdown Chunking Params

Parameter	Type	Default	Description
`chunk_size`	`int`	`5000`	The maximum size of each chunk.
`overlap`	`int`	`0`	The number of characters to overlap between chunks.
`split_on_headings`	`Union[bool, int]`	`False`	Heading-based splitting. `False` uses size-based chunking. `True` splits on all headings (H1-H6). An `int` from 1 to 6 splits on headings at or above that level, e.g. `2` splits on H1 and H2.

Get Started

Basics

Advanced

Production

Providers

Other

Additional Resources

Markdown Chunking

Markdown Chunking Params

​Markdown Chunking Params

Markdown Chunking Params