> ## Documentation Index
> Fetch the complete documentation index at: https://praison.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.
# 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.
```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
graph LR
subgraph "CSVTool Flow"
User[👤 User] --> Agent[🤖 Agent]
Agent --> Tool[🔧 CSVTool]
Tool --> Result[✅ Result]
Result --> Agent
end
classDef agent fill:#8B0000,stroke:#7C90A0,color:#fff
classDef tool fill:#189AB4,stroke:#7C90A0,color:#fff
classDef output fill:#10B981,stroke:#7C90A0,color:#fff
class User,Agent agent
class Tool tool
class Result output
```
## Installation
```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
pip install "praisonai[tools]"
```
## Quick Start
```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
from praisonai_tools import CSVTool
# Initialize
csv_tool = CSVTool()
# Read CSV
data = csv_tool.read("data.csv")
print(data)
```
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
```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
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.
```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
from praisonai_tools import CSVTool
csv_tool = CSVTool()
data = csv_tool.read("data.csv")
```
### write(path, data)
Write data to a CSV file.
```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
csv_tool.write("output.csv", [{"name": "Alice", "age": 30}])
```
## How It Works
```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
sequenceDiagram
participant User
participant Agent
participant Tool as Tool
participant Svc as CSV file
User->>Agent: Request
Agent->>Tool: Call tool
Tool->>Svc: Query
Svc-->>Tool: Data
Tool-->>Agent: Result
Agent-->>User: Response
```
***
## Best Practices
Inspect column names before querying so the agent references real fields, not guesses.
For big CSVs, process in chunks so memory stays bounded.
Confirm row shape before `write` so you don't corrupt an existing file.
***
## Related Tools
JSON files
Data analysis
General files