tools/parse_csv/tool.py

import io
from typing import Any, Dict

import pandas as pd
import requests
from smolagents import tool


@tool
def parse_csv(csv_url: str) -> Dict[str, Any]:
    """
    Parse a CSV file and return its content as structured data.

    Args:
        csv_url: URL of the CSV file to parse

    Returns:
        Dictionary containing parsed CSV data
    """
    try:
        # Download the CSV
        response = requests.get(csv_url)
        response.raise_for_status()

        # Parse the CSV
        df = pd.read_csv(io.StringIO(response.text))

        # Convert to dictionary format
        columns = df.columns.tolist()
        data = df.to_dict(orient="records")

        # Return basic statistics and preview
        return {
            "columns": columns,
            "row_count": len(data),
            "preview": data[:5] if len(data) > 5 else data,
            "column_dtypes": {col: str(df[col].dtype) for col in columns},
        }
    except Exception as e:
        return {"error": str(e)}