langgraph_impl/file_parser.py

import pandas as pd
import os

def parse_file_and_summarize(file_path: str, query: str = "") -> str:
    """
    Reads a CSV or Excel file and optionally answers a simple question about it.
    Args:
        file_path (str): Path to the file (.csv or .xlsx).
        query (str): Optional freeform instruction (e.g. "total food sales").
    Returns:
        str: Summary or result from the file.
    """
    try:
        _, ext = os.path.splitext(file_path.lower())
        if ext == ".csv":
            df = pd.read_csv(file_path)
        elif ext in [".xls", ".xlsx"]:
            df = pd.read_excel(file_path)
        else:
            return "Unsupported file format. Please upload CSV or Excel."

        if df.empty:
            return "The file is empty or unreadable."

        if not query:
            return f"Loaded file with {df.shape[0]} rows and {df.shape[1]} columns.\nColumns: {', '.join(df.columns)}"

        # Very basic natural language query handling (expand with LLM if needed)
        if "total" in query.lower() and "food" in query.lower():
            food_rows = df[df['category'].str.lower() == "food"]
            if "sales" in df.columns:
                total = food_rows["sales"].sum()
                return f"Total food sales: ${total:.2f}"
            else:
                return "Could not find 'sales' column in the file."
        else:
            return "Query not supported. Please specify a clearer question."

    except Exception as e:
        return f"File parsing error: {str(e)}"