Updated tools

tools_doc.py

@@ -1,4 +1,5 @@
 import os
+import pandas as pd
 import re
 import requests
 import tempfile
@@ -6,9 +7,11 @@ import uuid
 
 from langchain_core.tools import tool
 
+from google import genai
+from google.genai import types
+
 # from smolagents import tool
 from typing import Optional, Dict, Union
-from urllib.parse import urlparse
 
 
 @tool
@@ -142,68 +145,114 @@ def extract_text_from_image(image_path: str) -> str:
         return f"Error extracting text from image: {str(e)}"
 
 
+# CSV Analysis Tool
 @tool
 def analyze_csv_file(file_path: str, query: str) -> str:
-    """
-    Analyze a CSV file using pandas and answer a question about it.
-
+    """Analyzes a CSV file and answers questions about its contents using Gemini.
     Args:
-        file_path: Path to the CSV file
-        query: Question about the data
-
+        file_path (str): the path to the CSV file to analyze.
+        query (str): the question to answer about the CSV file.
     Returns:
-        Analysis result or error message
+        str: The result of the analysis.
     """
     try:
-        import pandas as pd
-
         # Read the CSV file
         df = pd.read_csv(file_path)
 
-        # Run various analyses based on the query
-        result = f"CSV file loaded with {len(df)} rows and {len(df.columns)} columns.\n"
-        result += f"Columns: {', '.join(df.columns)}\n\n"
+        # Initialize Gemini
+        client = genai.Client(api_key=os.getenv("GEMINI_KEY"))
+        model = "models/gemini-1.5-flash-8b"
+
+        # Convert DataFrame to a string representation
+        df_str = df.to_string()
+
+        # Create a prompt for Gemini
+        prompt = f"""Analyze this CSV data and provide insights:
+Dimensions: {len(df)} rows × {len(df.columns)} columns
+Data:
+{df_str}
+Please provide:
+1. A summary of the data structure and content
+2. Key patterns and insights
+3. Potential data quality issues
+4. Suggestions for analysis
+User Query: {query}
+Please format your response in a clear, structured way with sections and bullet points."""
+
+        # Get analysis from Gemini
+        response = client.models.generate_content(
+            model=model,
+            contents=types.Content(
+                parts=[
+                    types.Part(text=df_str),
+                    types.Part(text=prompt),
+                ]
+            ),
+        )
 
-        # Add summary statistics
-        result += "Summary statistics:\n"
-        result += str(df.describe())
+        result = f"CSV file loaded with {len(df)} rows and {len(df.columns)} columns.\n\n"
+        result += response.text
 
         return result
-    except ImportError:
-        return "Error: pandas is not installed. Please install it with 'pip install pandas'."
     except Exception as e:
         return f"Error analyzing CSV file: {str(e)}"
 
 
+# Excel Analysis Tool
 @tool
 def analyze_excel_file(file_path: str, query: str) -> str:
-    """
-    Analyze an Excel file using pandas and answer a question about it.
-
+    """Analyzes an Excel file and answers questions about its contents using Gemini.
     Args:
-        file_path: Path to the Excel file
-        query: Question about the data
-
+        file_path (str): the path to the Excel file to analyze.
+        query (str): the question to answer about the Excel file.
     Returns:
-        Analysis result or error message
+        str: The result of the analysis.
     """
     try:
-        import pandas as pd
-
-        # Read the Excel file
-        df = pd.read_excel(file_path)
-
-        # Run various analyses based on the query
-        result = f"Excel file loaded with {len(df)} rows and {len(df.columns)} columns.\n"
-        result += f"Columns: {', '.join(df.columns)}\n\n"
-
-        # Add summary statistics
-        result += "Summary statistics:\n"
-        result += str(df.describe())
+        # Read all sheets from the Excel file
+        excel_file = pd.ExcelFile(file_path)
+        sheet_names = excel_file.sheet_names
+
+        # Initialize Gemini
+        client = genai.Client(api_key=os.getenv("GEMINI_KEY"))
+        model = "models/gemini-1.5-flash-8b"
+
+        result = f"Excel file loaded with {len(sheet_names)} sheets: {', '.join(sheet_names)}\n\n"
+
+        # Analyze each sheet
+        for sheet_name in sheet_names:
+            df = pd.read_excel(file_path, sheet_name=sheet_name)
+
+            # Convert DataFrame to a string representation
+            df_str = df.to_string()
+
+            # Create a prompt for Gemini
+            prompt = f"""Analyze this Excel sheet data and provide insights:
+Sheet Name: {sheet_name}
+Dimensions: {len(df)} rows × {len(df.columns)} columns
+Data:
+{df_str}
+Please provide:
+1. A summary of the data structure and content
+2. Key patterns and insights
+3. Potential data quality issues
+4. Suggestions for analysis
+User Query: {query}
+Please format your response in a clear, structured way with sections and bullet points."""
+
+            # Get analysis from Gemini
+            response = client.models.generate_content(
+                model=model,
+                contents=types.Content(
+                    parts=[types.Part(text=df_str), types.Part(text=prompt)]
+                ),
+            )
+
+            result += f"=== Sheet: {sheet_name} ===\n"
+            result += response.text + "\n"
+            result += "=" * 50 + "\n\n"
 
         return result
-    except ImportError:
-        return "Error: pandas and openpyxl are not installed. Please install them with 'pip install pandas openpyxl'."
     except Exception as e:
         return f"Error analyzing Excel file: {str(e)}"