updates on how we handle files

app.py

@@ -25,9 +25,9 @@ from tools import (
     extract_text_from_image_tool,
     analyze_csv_file_tool,
     analyze_excel_file_tool,
-    download_file_tool,
 )
 import re
+import tempfile
 
 # (Keep Constants as is)
 # --- Constants ---
@@ -48,7 +48,6 @@ tools = [
     code_execution_tool,
     math_calculation_tool,
     python_repl_tool,
-    download_file_tool,
     extract_text_from_image_tool,
     analyze_csv_file_tool,
     analyze_excel_file_tool,
@@ -63,12 +62,12 @@ class MyAgent(TypedDict):
 
 
 # =========================
-# Simplified File Handling
+# Efficient File Handling - Download with Question
 # =========================
 def process_question_with_files(question_data: dict) -> str:
     """
-    Simple file handling - just pass the file info to the agent
-    and let it use its tools to handle the file.
+    Download file content when processing the question and include it directly.
+    This eliminates the need for the agent to download files separately.
     """
     question_text = question_data.get('question', '')
     file_name = question_data.get('file_name', '')
@@ -77,15 +76,51 @@ def process_question_with_files(question_data: dict) -> str:
     if not file_name:
         return question_text
 
-    # Use the correct API endpoint based on the documentation
-    # Files are accessed via /files/{task_id} not /files/{file_name}
-    if task_id:
+    print(f"📎 Downloading file for question: {file_name}")
+
+    try:
+        # Download the file content directly
         file_url = f"{DEFAULT_API_URL}/files/{task_id}"
-    else:
-        # Fallback to old method if task_id is not available
-        file_url = f"{DEFAULT_API_URL}/files/{file_name}"
+        response = requests.get(file_url, timeout=15)
+        response.raise_for_status()
+
+        # Save file to temporary location for processing
+        temp_dir = tempfile.gettempdir()
+        local_file_path = os.path.join(temp_dir, file_name)
+
+        with open(local_file_path, "wb") as f:
+            f.write(response.content)
+
+        # Process the file based on its type
+        ext = file_name.lower().split('.')[-1]
+
+        if ext in ['mp3', 'wav', 'm4a', 'flac', 'ogg']:
+            result = audio_processing_tool.invoke(local_file_path)
+            file_info = f"[Audio Transcription: {result}]"
+        elif ext in ['png', 'jpg', 'jpeg', 'gif', 'bmp']:
+            result = image_recognition_tool.invoke(local_file_path)
+            file_info = f"[Image Analysis: {result}]"
+        elif ext in ['csv', 'xls', 'xlsx']:
+            result = read_file_tool.invoke(local_file_path)
+            file_info = f"[Spreadsheet Content: {result}]"
+        elif ext in ['txt', 'md', 'py', 'json']:
+            result = read_file_tool.invoke(local_file_path)
+            file_info = f"[File Content: {result}]"
+        else:
+            result = read_file_tool.invoke(local_file_path)
+            file_info = f"[File Content: {result}]"
+
+        # Clean up the temporary file
+        try:
+            os.remove(local_file_path)
+        except Exception:
+            pass
 
-    return f"{question_text}\n\n[There is an attached file: {file_name}. You can download it from: {file_url}]"
+        return f"{question_text}\n\n{file_info}"
+
+    except Exception as e:
+        print(f"Error downloading/processing file {file_name}: {e}")
+        return f"{question_text}\n\n[Note: Could not download or process attached file {file_name}: {str(e)}]"
 
 
 def extract_final_answer(text: str) -> str:
@@ -141,17 +176,14 @@ def assistant(state: MyAgent):
     system_message = SystemMessage(content="""
 You are a helpful assistant tasked with answering questions using a set of tools. 
 
-IMPORTANT: When a question mentions an attached file, follow this process:
-1. Use download_file_tool with the task_id or URL to download the file
-   - For GAIA files: pass the task_id directly
-   - For other URLs: pass the full URL
-   - For content: pass the content to save as a file
-2. Use the appropriate analysis tool based on file type:
-   - For images: use image_recognition_tool or extract_text_from_image_tool
-   - For audio: use audio_processing_tool
-   - For spreadsheets: use analyze_csv_file_tool or analyze_excel_file_tool
-   - For text files: use read_file_tool
-   - For code files: use python_execution_tool or code_execution_tool
+IMPORTANT: File content is already processed and included in the question. You can use these tools to analyze the content:
+- For images: use image_recognition_tool or extract_text_from_image_tool
+- For audio: use audio_processing_tool
+- For spreadsheets: use analyze_csv_file_tool or analyze_excel_file_tool
+- For text files: use read_file_tool
+- For code files: use python_execution_tool or code_execution_tool
+- For math calculations: use math_calculation_tool
+- For web searches: use serp_search_tool or wiki_search_tool
 
 Think step by step and report your answer with the following template: 
 FINAL ANSWER: [YOUR FINAL ANSWER]. 

tools.py

@@ -618,80 +618,9 @@ analyze_excel_file_tool = Tool(
 # Smart File Download Tool (Consolidated)
 # =========================
 
+# Note: This tool is no longer needed since files are pre-processed
+# when questions are fetched. The agent receives file content directly.
 
-def download_file_smart(file_source: str, filename: str = "") -> str:
-    """
-    Smart file download tool that handles:
-    - GAIA files (using task_id)
-    - Regular URLs
-    - Content saving
-
-    Args:
-        file_source: task_id, URL, or content to save
-        filename: Optional filename (auto-generated if not provided)
-    """
-    try:
-        # Auto-detect the type of file_source
-        if file_source.startswith(('http://', 'https://')):
-            # Regular URL download
-            if filename == "":
-                path = urlparse(file_source).path
-                filename = os.path.basename(path)
-                if not filename:
-                    filename = f"downloaded_{uuid.uuid4().hex[:8]}"
-
-            temp_dir = tempfile.gettempdir()
-            filepath = os.path.join(temp_dir, filename)
-
-            response = requests.get(file_source, stream=True, timeout=15)
-            response.raise_for_status()
-
-            with open(filepath, "wb") as f:
-                for chunk in response.iter_content(chunk_size=8192):
-                    f.write(chunk)
-
-            return f"File downloaded to {filepath}. You can read this file to process its contents."
-
-        elif len(file_source) == 36 and '-' in file_source:
-            # Likely a GAIA task_id (UUID format)
-            if filename == "":
-                filename = f"gaia_file_{file_source}"
-
-            api_url = "https://agents-course-unit4-scoring.hf.space"
-            file_url = f"{api_url}/files/{file_source}"
-
-            temp_dir = tempfile.gettempdir()
-            filepath = os.path.join(temp_dir, filename)
-
-            response = requests.get(file_url, stream=True, timeout=15)
-            response.raise_for_status()
-
-            with open(filepath, "wb") as f:
-                for chunk in response.iter_content(chunk_size=8192):
-                    f.write(chunk)
-
-            return f"GAIA file downloaded to {filepath}. You can read this file to process its contents."
-
-        else:
-            # Treat as content to save
-            if filename == "":
-                temp_file = tempfile.NamedTemporaryFile(
-                    delete=False, dir=tempfile.gettempdir())
-                filepath = temp_file.name
-            else:
-                filepath = os.path.join(tempfile.gettempdir(), filename)
-
-            with open(filepath, "w") as f:
-                f.write(file_source)
-
-            return f"Content saved to {filepath}. You can read this file to process its contents."
-
-    except Exception as e:
-        return f"Error handling file: {str(e)}"
-
-
-download_file_tool = Tool(
-    name="download_file_tool",
-    func=download_file_smart,
-    description="Smart file download tool: automatically detects if input is a GAIA task_id, URL, or content and handles accordingly. Use this for all file operations."
-)
+# =========================
+# Image and Data Analysis Tools
+# =========================