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

# Custom Chunking

> Implement your own chunking strategy by subclassing ChunkingStrategy.

Subclass `ChunkingStrategy` and implement `chunk()` to return a list of `Document` objects.

<Steps>
  <Step title="Create a Python file">
    ```python custom_chunking.py theme={null}
    from pathlib import Path
    from typing import List

    from agno.agent import Agent
    from agno.knowledge.chunking.strategy import ChunkingStrategy
    from agno.knowledge.document import Document
    from agno.knowledge.knowledge import Knowledge
    from agno.knowledge.reader.text_reader import TextReader
    from agno.vectordb.pgvector import PgVector


    class CustomChunking(ChunkingStrategy):
        def __init__(self, separator: str = "---"):
            self.separator = separator

        def chunk(self, document: Document) -> List[Document]:
            result = []
            for chunk_content in document.content.split(self.separator):
                chunk_content = self.clean_text(chunk_content).strip()
                if not chunk_content:
                    continue

                chunk_number = len(result) + 1
                meta_data = document.meta_data.copy()
                meta_data["chunk"] = chunk_number
                meta_data["chunk_size"] = len(chunk_content)
                result.append(
                    Document(
                        id=self._generate_chunk_id(
                            document,
                            chunk_number,
                            chunk_content,
                        ),
                        name=document.name,
                        meta_data=meta_data,
                        content=chunk_content,
                    )
                )
            return result


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

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

    content_path = Path("tmp/recipes.txt")
    content_path.parent.mkdir(parents=True, exist_ok=True)
    content_path.write_text(
        "Tom kha gai uses coconut milk.\n---\nMassaman curry uses warm spices.",
        encoding="utf-8",
    )

    knowledge.insert(
        path=str(content_path),
        reader=TextReader(
            name="Custom Chunking Reader",
            chunking_strategy=CustomChunking(separator="---"),
        ),
    )

    agent = Agent(
        knowledge=knowledge,
        search_knowledge=True,
    )

    agent.print_response("Which recipe uses coconut milk?", markdown=True)
    ```
  </Step>

  <Snippet file="create-venv-step.mdx" />

  <Step title="Install dependencies">
    ```bash theme={null}
    uv pip install -U agno openai pgvector psycopg sqlalchemy
    ```
  </Step>

  <Step title="Export your OpenAI API key">
    <Snippet file="set-openai-key.mdx" />
  </Step>

  <Snippet file="run-pgvector-step.mdx" />

  <Step title="Run the script">
    ```bash theme={null}
    python custom_chunking.py
    ```
  </Step>
</Steps>

## Custom Chunking Params

<Snippet file="chunking-custom.mdx" />

## Developer Resources

* [Chunking overview](/knowledge/concepts/chunking/overview)