trying with file handling

app.py

@@ -28,6 +28,7 @@ from tools import (
     analyze_csv_file_tool,
     analyze_excel_file_tool,
     handle_file_tool,
+    download_gaia_file_tool,
     download_file,
 )
 import re
@@ -57,6 +58,7 @@ tools = [
     analyze_csv_file_tool,
     analyze_excel_file_tool,
     handle_file_tool,
+    download_gaia_file_tool,
 ]
 chat_with_tools = llm.bind_tools(tools)
 
@@ -77,13 +79,18 @@ def process_question_with_files(question_data: dict) -> str:
     """
     question_text = question_data.get('question', '')
     file_name = question_data.get('file_name', '')
+    task_id = question_data.get('task_id', '')
 
     if not file_name:
         return question_text
 
-    # Simple approach: just tell the agent about the file
-    # Let the agent use its tools to download and process the file
-    file_url = f"{DEFAULT_API_URL}/files/{file_name}"
+    # Use the correct API endpoint based on the documentation
+    # Files are accessed via /files/{task_id} not /files/{file_name}
+    if task_id:
+        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}"
 
     return f"{question_text}\n\n[There is an attached file: {file_name}. You can download it from: {file_url}]"
 
@@ -142,8 +149,8 @@ def assistant(state: MyAgent):
 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_from_url_tool to download the file from the provided URL
-   (Alternative: use handle_file_tool with file_type="url" for more flexible file handling)
+1. For GAIA files: Use download_gaia_file_tool with the task_id to download the file
+   (Alternative: use download_file_from_url_tool for other URLs, or handle_file_tool for flexible handling)
 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
@@ -246,19 +253,29 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
     for item in questions_data:
         task_id = item.get("task_id")
         question_text = item.get("question")
+        file_name = item.get("file_name", "")
+
         if not task_id or question_text is None:
             print(f"Skipping item with missing task_id or question: {item}")
             continue
+
+        # Create complete question data for the agent
+        question_data = {
+            "task_id": task_id,
+            "question": question_text,
+            "file_name": file_name
+        }
+
         try:
-            submitted_answer = agent(question_text)
+            submitted_answer = agent(question_data)
             answers_payload.append(
                 {"task_id": task_id, "submitted_answer": submitted_answer})
             results_log.append(
-                {"Task ID": task_id, "Question": question_text, "Submitted Answer": submitted_answer})
+                {"Task ID": task_id, "Question": question_text, "File": file_name, "Submitted Answer": submitted_answer})
         except Exception as e:
             print(f"Error running agent on task {task_id}: {e}")
             results_log.append(
-                {"Task ID": task_id, "Question": question_text, "Submitted Answer": f"AGENT ERROR: {e}"})
+                {"Task ID": task_id, "Question": question_text, "File": file_name, "Submitted Answer": f"AGENT ERROR: {e}"})
 
     if not answers_payload:
         print("Agent did not produce any answers to submit.")

test_agent.py

@@ -1,38 +0,0 @@
-import os
-import requests
-
-
-def fetch_questions():
-    api_url = os.getenv("DEFAULT_API_URL",
-                        "https://agents-course-unit4-scoring.hf.space")
-    questions_url = f"{api_url}/questions"
-    print(f"Fetching questions from: {questions_url}")
-    try:
-        response = requests.get(questions_url, timeout=15)
-        response.raise_for_status()
-        questions_data = response.json()
-        if not questions_data:
-            print("Fetched questions list is empty.")
-            return []
-        print(f"Fetched {len(questions_data)} questions.")
-        return questions_data
-    except Exception as e:
-        print(f"Error fetching questions: {e}")
-        return []
-
-
-def main():
-    questions = fetch_questions()
-    if not questions:
-        print("No questions to display.")
-        return
-    print("\nFirst 20 questions from the API:")
-    for idx, q in enumerate(questions[:20], 1):
-        print(f"\n[{idx}] Task ID: {q.get('task_id')}")
-        print(f"Question: {q.get('question')}")
-        if q.get('file_name'):
-            print(f"Attached file: {q['file_name']}")
-
-
-if __name__ == "__main__":
-    main()

tools.py

@@ -659,6 +659,48 @@ analyze_excel_file_tool = Tool(
     description="Analyze an Excel file using pandas and answer a question about it."
 )
 
+# =========================
+# GAIA-Specific File Download Tool
+# =========================
+
+
+def download_gaia_file(task_id: str, filename: str = None) -> str:
+    """
+    Download a file from the GAIA API using the task_id.
+
+    Args:
+        task_id: The task ID from the GAIA API
+        filename: Optional filename to save as (defaults to task_id)
+    """
+    try:
+        if not filename:
+            filename = f"gaia_file_{task_id}"
+
+        # Use the correct GAIA API endpoint
+        api_url = "https://agents-course-unit4-scoring.hf.space"
+        file_url = f"{api_url}/files/{task_id}"
+
+        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."
+    except Exception as e:
+        return f"Error downloading GAIA file: {str(e)}"
+
+
+download_gaia_file_tool = Tool(
+    name="download_gaia_file_tool",
+    func=download_gaia_file,
+    description="Download a file from the GAIA API using task_id. Use this specifically for GAIA benchmark files."
+)
+
 # =========================
 # Comprehensive File Handling Tool
 # =========================