CSV
Read and manipulate CSV files
Overview
CSV tool allows you to read, write, and query CSV files.
The user points to a CSV file; the agent reads, filters, or writes rows and returns the result.
Installation
pip install "praisonai[tools]"Quick Start
- Simple Usage
python from praisonai_tools import CSVTool # Initialize csv_tool = CSVTool() # Read CSV data = csv_tool.read("data.csv") print(data) - With Configuration
Use the same tool with an agent — see Usage with Agent below, or pass env vars and options from the sections above.
Usage with Agent
from praisonaiagents import Agent
from praisonai_tools import CSVTool
agent = Agent(
name="DataAnalyst",
instructions="You help analyze CSV data.",
tools=[CSVTool()]
)
response = agent.chat("Read sales.csv and summarize the data")
print(response)Available Methods
read(path)
Read a CSV file.
from praisonai_tools import CSVTool
csv_tool = CSVTool()
data = csv_tool.read("data.csv")write(path, data)
Write data to a CSV file.
csv_tool.write("output.csv", [{"name": "Alice", "age": 30}])How It Works
Best Practices
Read a schema first
Inspect column names before querying so the agent references real fields, not guesses.
Stream large files
For big CSVs, process in chunks so memory stays bounded.
Validate before writing
Confirm row shape before write so you don’t corrupt an existing file.