CSV Reader

CSVReader converts each CSV row into a document with RowChunking by default.

csv_reader.py

from pathlib import Path

from agno.knowledge.reader.csv_reader import CSVReader

reader = CSVReader()

csv_path = Path("tmp/test.csv")
csv_path.parent.mkdir(parents=True, exist_ok=True)
csv_path.write_text(
    "name,department\nJordan,Engineering\nTaylor,Product\n",
    encoding="utf-8",
)

documents = reader.read(csv_path)
for document in documents:
    print(document.content)

Run the Reader

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[csv]"

Run the script

python csv_reader.py

Reader Parameters

Parameter	Type	Default	Description
`chunking_strategy`	`Optional[ChunkingStrategy]`	`RowChunking()`	Strategy used to chunk documents

CSVReader also accepts the base Reader constructor parameters. Pass delimiter and quotechar to read() for other CSV dialects. CSVReader.async_read() accepts page_size to batch files with more than 10 rows before applying the chunking strategy.

Next Steps

Task	Guide
Configure row chunking	CSV Row Chunking
Label fields in each row	Field-Labeled CSV Reference
Compare available readers	Readers Overview

Get Started

Basics

Advanced

Production

Providers

Other

Additional Resources

Run the Reader

Reader Parameters

Next Steps

​Run the Reader

​Reader Parameters

​Next Steps

Run the Reader

Reader Parameters

Next Steps