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.

​
Usage

from phi.agent import Agent
from phi.document.chunking.agentic import AgenticChunking
from phi.knowledge.pdf import PDFUrlKnowledgeBase
from phi.vectordb.pgvector import PgVector

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

knowledge_base = PDFUrlKnowledgeBase(
    urls=["https://phi-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)

​
Params

ParameterTypeDefaultDescription
modelModelOpenAIChatThe model to use for chunking.
max_chunk_sizeint5000The maximum size of each chunk.

Was this page helpful?

Fixed Size ChunkingSemantic Chunking