updates

agent.py

@@ -5,14 +5,13 @@ import re
 from dotenv import load_dotenv
 from langchain_core.messages import (AIMessage, HumanMessage, SystemMessage,
                                      ToolMessage)
-from langchain_huggingface import (ChatHuggingFace, HuggingFaceEmbeddings,
-                                   HuggingFaceEndpoint)
+from langchain_huggingface import ChatHuggingFace, HuggingFaceEndpoint
 from langgraph.graph import START, MessagesState, StateGraph
 from langgraph.prebuilt import ToolNode, tools_condition
 
 from tools import (absolute, add, analyze_csv_file, analyze_excel_file,
                    arvix_search, audio_transcription, compound_interest,
-                   convert_temperature, divide, exponential,
+                   convert_temperature, divide, download_file, exponential,
                    extract_text_from_image, factorial, floor_divide,
                    get_current_time_in_timezone, greatest_common_divisor,
                    is_prime, least_common_multiple, logarithm, modulus,
@@ -35,6 +34,7 @@ tools = [
     wiki_search, analyze_excel_file, arvix_search,
     audio_transcription, python_code_parser, analyze_csv_file,
     extract_text_from_image, reverse_sentence, web_content_extract,
+    download_file,
 ]
 
 # Updated system prompt for cleaner output
@@ -42,7 +42,9 @@ system_prompt = """
 You are a helpful AI assistant. When asked a question, think through it step by step and provide only the final answer.
 
 CRITICAL INSTRUCTIONS:
+- If the question mentions attachments, files, images, documents, or URLs, use the download_file tool FIRST to download them
 - Use available tools when needed to gather information or perform calculations
+- For file analysis, use appropriate tools (analyze_csv_file, analyze_excel_file, extract_text_from_image, etc.)
 - After using tools and analyzing the information, provide ONLY the final answer
 - Do not include explanations, reasoning, or extra text in your final response
 - If the answer is a number, provide just the number (no units unless specifically requested)
@@ -190,5 +192,4 @@ if __name__ == "__main__":
                 else:
                     print("❌ Output is NOT in the correct format!")
             except Exception as e:
-                print("❌ Output is NOT in the correct format!", e)
-                
+                print("❌ Output is NOT in the correct format!", e)

tools.py

@@ -2,10 +2,13 @@ import base64
 import datetime
 import math
 import os
+import urllib.parse
+from pathlib import Path
 from typing import Dict, Union
 
 import pandas
 import pytz
+import requests
 from bs4 import BeautifulSoup
 from langchain_community.document_loaders import (
     ArxivLoader, AssemblyAIAudioTranscriptLoader, WikipediaLoader)
@@ -13,11 +16,83 @@ from langchain_community.document_loaders.generic import GenericLoader
 from langchain_community.document_loaders.parsers import LanguageParser
 from langchain_core.messages import HumanMessage
 # from langchain_community.tools import DuckDuckGoSearchRun
+# from langchain_community.tools import DuckDuckGoSearchRun
 from langchain_core.tools import tool
 from langchain_google_genai import ChatGoogleGenerativeAI
 from langchain_tavily import TavilySearch
 
 
+@tool
+def download_file(url: str, filename: str = None) -> str:
+    """
+    Download a file from a URL and save it locally for analysis.
+    
+    Args:
+        url: The URL of the file to download
+        filename: Optional custom filename. If not provided, will extract from URL
+        
+    Returns:
+        The local file path where the file was saved
+    """
+    try:
+        # Clean and validate URL
+        url = url.strip()
+        if not url.startswith(('http://', 'https://')):
+            return f"Error: Invalid URL format: {url}"
+        
+        # Create downloads directory if it doesn't exist
+        download_dir = Path("downloads")
+        download_dir.mkdir(exist_ok=True)
+        
+        # Determine filename
+        if not filename:
+            # Extract filename from URL
+            parsed_url = urllib.parse.urlparse(url)
+            filename = os.path.basename(parsed_url.path)
+            
+            # If no filename in URL, create one based on URL hash
+            if not filename or '.' not in filename:
+                url_hash = str(hash(url))[-8:]  # Last 8 characters of hash
+                filename = f"downloaded_file_{url_hash}"
+        
+        # Ensure filename has proper extension if we can detect content type
+        filepath = download_dir / filename
+        
+        # Download the file
+        headers = {
+            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36'
+        }
+        
+        print(f"Downloading file from: {url}")
+        response = requests.get(url, headers=headers, timeout=30, stream=True)
+        response.raise_for_status()
+        
+        # Try to get better filename from Content-Disposition header
+        if 'content-disposition' in response.headers:
+            import re
+            cd = response.headers['content-disposition']
+            filename_match = re.findall('filename=(.+)', cd)
+            if filename_match:
+                suggested_filename = filename_match[0].strip('"')
+                if suggested_filename:
+                    filepath = download_dir / suggested_filename
+        
+        # Write file to disk
+        with open(filepath, 'wb') as f:
+            for chunk in response.iter_content(chunk_size=8192):
+                f.write(chunk)
+        
+        file_size = os.path.getsize(filepath)
+        print(f"Successfully downloaded {filename} ({file_size} bytes)")
+        
+        return str(filepath)
+        
+    except requests.exceptions.RequestException as e:
+        return f"Error downloading file: {str(e)}"
+    except Exception as e:
+        return f"Error saving file: {str(e)}"
+
+
 @tool
 def multiply(a: Union[int, float], b: Union[int, float]) -> Union[int, float]:
     """Multiplies two numbers and returns the product.