# Agentic Chunking

Agentic chunking is an intelligent method of splitting documents into smaller chunks by using an LLM to determine natural breakpoints in the text. Rather than splitting text at fixed character counts, it analyzes the content to find semantically meaningful boundaries like paragraph breaks and topic transitions.

### [​](https://docs.phidata.com/chunking/agentic-chunking#usage)Usage <a href="#usage" id="usage"></a>

```python
from bitca.agent import Agent
from bitca.document.chunking.agentic import AgenticChunking
from bitca.knowledge.pdf import PDFUrlKnowledgeBase
from bitca.vectordb.pgvector import PgVector

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

knowledge_base = PDFUrlKnowledgeBase(
    urls=["https://bitca-public.s3.amazonaws.com/recipes/ThaiRecipes.pdf"],
    vector_db=PgVector(table_name="recipes_agentic_chunking", db_url=db_url),
    chunking_strategy=AgenticChunking(),
)
knowledge_base.load(recreate=False)  # Comment out after first run

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

agent.print_response("How to make Thai curry?", markdown=True)
```

### [​](https://docs.phidata.com/chunking/agentic-chunking#params)Params <a href="#params" id="params"></a>

| Parameter        | Type    | Default      | Description                     |
| ---------------- | ------- | ------------ | ------------------------------- |
| `model`          | `Model` | `OpenAIChat` | The model to use for chunking.  |
| `max_chunk_size` | `int`   | `5000`       | The maximum size of each chunk. |