Update app.py

app.py

@@ -84,6 +84,9 @@ tools = [
     PythonInterpreterTool(),
     UserInputTool(),
 ]
+
+
+
 # ---------------------- MAIN LOGIC ---------------------- #
 
 class BasicAgent:
@@ -94,20 +97,9 @@ class BasicAgent:
         
         )
         print("BasicAgent initialized.")
-        # print("Available tools:", [tool.name for tool in self.agent.tools])
-    # def __call__(self, question):
-    #     if isinstance(question, dict):
-    #         text = question.get("question", "")
-    #         image = question.get("image", None)
-    #         if image:
-    #             question["image"] = {"type": "pil", "data": image}
-    #     else:
-    #         text = question
-    
-    #     print(f"Agent received question (first 50 chars): {text[:50]}...")
-    #     answer = self.agent.run(text)
-    #     return answer.strip()
+
     def __call__(self, question):
+        print("BasicAgent called")
         if isinstance(question, dict):
             text = question.get("question", "")
             image = question.get("image", None)
@@ -118,17 +110,33 @@ class BasicAgent:
         print(f"Agent received question (first 50 chars): {text[:50]}...")
     
         prompt = system_prompt + "\n\nUser: " + text.strip()
+        print("BasicAgent updated the prompt")
         inputs = {}
     
         if image:
             try:
                 image_caption = image_captioner(image=image, question=text)
                 prompt += f"\n\nThe image contains: {image_caption}"
+                print("BasicAgent added the image caption to the prompt")
                 inputs["image"] = image
             except Exception as e:
                 print(f"Image captioning failed: {e}")
-    
-        return self.agent.run(prompt, inputs=inputs).strip()
+
+        inputs["question"] = prompt
+        print("running the agent with the BasicAgent prompt")
+        print(f"Prompt length (chars): {len(prompt)}")
+        try:
+            # result = self.agent(prompt).strip()
+            result = self.agent(inputs).strip()
+            print(f"Agent returned result: {result[:100]}")  
+            print("Agent run completed")
+            return result
+        except Exception as e:
+            print(f"Error running the agent: {e}")
+            return "AGENT RUN ERROR"
+
+
+        
 
 
 
@@ -139,35 +147,37 @@ Your job is to:
 - Search the web or Wikipedia if needed
 - Perform Python calculations or date arithmetic
 - Automatically search for and describe images if the question mentions or refers to one
-
 Instructions:
 1. Think step-by-step and use tools wisely.
 2. If the question references an image (e.g. "What’s in this image of..."), search for a relevant image online and generate a caption to assist your reasoning.
 3. Use the image caption internally to help answer the question, but do not include it in your response.
 4. Always return a single, short, direct answer — no explanation, formatting, or extra information.
-
 Examples:
 - Q: What is the capital of France?
 - A: Paris
-
 - Q: What date is 30 days after January 1, 2023?
 - A: January 31, 2023
-
 - Q: What is 17 times 4?
 - A: 68
-
 - Q: What is the tallest building shown in the image of Dubai’s skyline?
 - A: Burj Khalifa
-
 - Q: What fruit is in the image of a bowl on the kitchen table?
 - A: Bananas
-
 - Q: What is shown in the picture of the moon landing?
 - A: Astronaut on the Moon
-
 Your output must be: a single clean answer string only.
 """
 
+# Agent initialization - moved here from the submit_and_run_all()
+try:
+    agent = BasicAgent(model=model, tools=tools) 
+except Exception as e:
+    agent = None
+    print(f"Error instantiating agent: {e}")
+    # return f"Error initializing agent: {e}", None
+        
+# -----------------------------------------------------
+    
 
 def find_image_online(query):
     """Use DuckDuckGo to find an image related to the query."""
@@ -187,35 +197,83 @@ def download_image(url):
     except Exception:
         return None
 
+# def ask_agent(question):
+#     try:
+#         prompt = system_prompt + "\n\nUser: " + question.strip()
+
+#         image = None
+#         image_caption = ""
+#         # Only try to get an image if the question mentions or implies one
+#         keywords = ["image", "picture","photo","painting", "what's in this picture", "describe this picture"]
+#         question_lower = question.lower()
+#         if any(word in question_lower for word in keywords):
+#             image_url = find_image_online(question)
+#             if image_url:
+#                 image = download_image(image_url)
+#                 if image:
+#                     # Use the ImageCaptioningTool to get a caption
+#                     image_captioner = [tool for tool in tools if tool.name == "image_captioner "][0] 
+#                     image_caption = image_captioner(image=image, question=question)
+#                     #Append the caption to the user's original question
+#                     prompt +=f"\n\nThe image contains: {image_caption}"
+
+#                 #Run the agent (image is passed only if present; prompt always includes the caption if available)
+#                 inputs = {"image":image} if image else{}
+#                 return agent.run(prompt, inputs=inputs).strip()
+
+#     except Exception as e:
+#         return f"Error: {e}"
+
+
 def ask_agent(question):
+    print("ask_agent called")
     try:
-        prompt = system_prompt + "\n\nUser: " + question.strip()
 
+        prompt = "\n\nUser: " + question.strip()
+        print("ask_agent updated the prompt")
         image = None
         image_caption = ""
-        # Only try to get an image if the question mentions or implies one
-        keywords = ["image", "picture","photo","painting", "what's in this picture", "describe this picture"]
+        question_input ={}
+        keywords = ["image", "picture", "photo", "painting", "what's in this picture", "describe this picture"]
         question_lower = question.lower()
+
         if any(word in question_lower for word in keywords):
             image_url = find_image_online(question)
             if image_url:
                 image = download_image(image_url)
                 if image:
-                    # Use the ImageCaptioningTool to get a caption
-                    image_captioner = [tool for tool in tools if tool.name == "image_captioner "][0] 
-                    image_caption = image_captioner(image=image, question=question)
-                    #Append the caption to the user's original question
-                    prompt +=f"\n\nThe image contains: {image_caption}"
+                    if image_captioner is None:
+                        return "Image captioning tool is missing"
 
-                #Run the agent (image is passed only if present; prompt always includes the caption if available)
-                inputs = {"image":image} if image else{}
-                return agent.run(prompt, inputs=inputs).strip()
+                    try:
+                        image_caption = image_captioner(image=image, question=question)
+                        prompt += f"\n\nThe image contains: {image_caption}"
 
-    except Exception as e:
-        return f"Error: {e}"
-        
 
-        
+
+                        print("ask_agent updated the prompt to include image caption")
+                    except Exception as e:
+                        print(f"Image captioning failed: {e}")
+
+        print("running agent with the ask_agent prompt")
+        result = agent(prompt)
+
+
+        try:
+            result = agent(prompt)
+
+            if not result or str(result).strip() == "":
+                return "I don't know"
+            return str(result).strip()
+
+        except Exception as e:
+            print(f"ask_agent error during agent call: {e}")
+            return "Error: Agent failed to generate a response."
+
+    except Exception as e:
+        print(f"ask_agent error: {e}")
+        return "Error: Unable to generate response."
+  
 
 def run_and_submit_all( profile: gr.OAuthProfile | None):
     """
@@ -237,11 +295,8 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
     submit_url = f"{api_url}/submit"
 
     # 1. Instantiate Agent ( modify this part to create your agent)
-    try:
-        agent = BasicAgent(model=model, tools=tools)
-    except Exception as e:
-        print(f"Error instantiating agent: {e}")
-        return f"Error initializing agent: {e}", None
+    # moved to the top of ask_agent() to keep the agent global
+    
     # In the case of an app running as a hugging Face space, this link points toward your codebase ( usefull for others so please keep it public)
     agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
     print(agent_code)
@@ -360,11 +415,9 @@ with gr.Blocks() as demo:
     gr.Markdown(
         """
         **Instructions:**
-
         1.  Please clone this space, then modify the code to define your agent's logic, the tools, the necessary packages, etc ...
         2.  Log in to your Hugging Face account using the button below. This uses your HF username for submission.
         3.  Click 'Run Evaluation & Submit All Answers' to fetch questions, run your agent, submit answers, and see the score.
-
         ---
         **Disclaimers:**
         Once clicking on the "submit button, it can take quite some time ( this is the time for the agent to go through all the questions).
@@ -408,286 +461,3 @@ if __name__ == "__main__":
 
     print("Launching Gradio Interface for Basic Agent Evaluation...")
     demo.launch(debug=True, share=False)
-
-# DEBUG TEST
-agent = BasicAgent(model, tools)
-print(agent("What is the capital of France?"))
-# import os
-# import pandas as pd
-# import requests
-# import smolagents
-# print("SmolAgents version:", smolagents.__version__)
-# from smolagents import Tool, CodeAgent, InferenceClientModel, load_tool
-# from smolagents import DuckDuckGoSearchTool, WikipediaSearchTool, PythonInterpreterTool, UserInputTool
-# import gradio as gr
-# from PIL import Image
-
-# # 🧠 Inference model
-# model = InferenceClientModel("qwen/Qwen2.5-0.5B-Instruct", max_tokens=512)
-# # (Keep Constants as is)
-# # --- Constants ---
-# DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
-
-# # --- Basic Agent Definition ---
-# # ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
-# # class BasicAgent:
-# #     def __init__(self):
-# #         print("BasicAgent initialized.")
-# #     def __call__(self, question: str) -> str:
-# #         print(f"Agent received question (first 50 chars): {question[:50]}...")
-# #         fixed_answer = "This is a default answer."
-# #         print(f"Agent returning fixed answer: {fixed_answer}")
-# #         return fixed_answer
-
-
-# # class ImageCaptioningTool(Tool):
-# #     name = "image_captioner"
-# #     description = "Generate a caption for an image."
-# #     inputs = {"image": "image"}
-# #     output_type = "text"
-    
-# #     def run(self, inputs: dict) -> str:
-# #         image = inputs.get("image")
-# #         if not image:
-# #             return "No image provided."
-# #         # You could run your model here instead
-# #         return "This is a placeholder caption for the uploaded image."
-        
-# class BasicAgent:
-#     def __init__(self):
-#         model = InferenceClientModel(
-#             "qwen/Qwen2.5-0.5B-Instruct",
-#             max_tokens=512,
-#             system_message="""
-# You are a highly capable AI assistant designed to solve real-world, multi-step reasoning tasks in the GAIA benchmark.
-# Your job is to:
-# - Search the web or Wikipedia if needed
-# - Perform Python calculations or date arithmetic
-
-# Instructions:
-# 1. Think step-by-step and use tools wisely.
-# 2. Always return a short, direct answer — no explanation or formatting.
-
-# Examples:
-# - Q: What is the capital of France?
-# - A: Paris
-
-# Your output must be: a single clean answer string only.
-
-# """
-#         )
-#         self.agent = CodeAgent(
-#             tools=[
-#                     DuckDuckGoSearchTool(max_results=5, rate_limit=2.0),
-#                     WikipediaSearchTool(user_agent="my-agent", language="en"),
-#                     PythonInterpreterTool(),
-#                     UserInputTool(),
-#                     # ImageCaptioningTool(),
-#             ],
-#             model=model
-        
-#         )
-#         print("BasicAgent initialized.")
-#         # print("Available tools:", [tool.name for tool in self.agent.tools])
-#     def __call__(self, question):
-#         if isinstance(question, dict):
-#             text = question.get("question", "")
-#             # ignoring image context for now since agent.run doesn't support it
-#         else:
-#             text = question
-    
-#         print(f"Agent received question (first 50 chars): {text[:50]}...")
-#         answer = self.agent.run(text)
-#         return answer.strip()
-
-        
-           
-# def run_and_submit_all( profile: gr.OAuthProfile | None):
-#     """
-#     Fetches all questions, runs the BasicAgent on them, submits all answers,
-#     and displays the results.
-#     """
-#     # --- Determine HF Space Runtime URL and Repo URL ---
-#     space_id = os.getenv("SPACE_ID") # Get the SPACE_ID for sending link to the code
-
-#     if profile:
-#         username= f"{profile.username}"
-#         print(f"User logged in: {username}")
-#     else:
-#         print("User not logged in.")
-#         return "Please Login to Hugging Face with the button.", None
-
-#     api_url = DEFAULT_API_URL
-#     questions_url = f"{api_url}/questions"
-#     submit_url = f"{api_url}/submit"
-
-#     # 1. Instantiate Agent ( modify this part to create your agent)
-#     try:
-#         agent = BasicAgent()
-#     except Exception as e:
-#         print(f"Error instantiating agent: {e}")
-#         return f"Error initializing agent: {e}", None
-#     # In the case of an app running as a hugging Face space, this link points toward your codebase ( usefull for others so please keep it public)
-#     agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
-#     print(agent_code)
-
-#     # 2. Fetch 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 "Fetched questions list is empty or invalid format.", None
-#         print(f"Fetched {len(questions_data)} questions.")
-#     except requests.exceptions.RequestException as e:
-#         print(f"Error fetching questions: {e}")
-#         return f"Error fetching questions: {e}", None
-#     except requests.exceptions.JSONDecodeError as e:
-#          print(f"Error decoding JSON response from questions endpoint: {e}")
-#          print(f"Response text: {response.text[:500]}")
-#          return f"Error decoding server response for questions: {e}", None
-#     except Exception as e:
-#         print(f"An unexpected error occurred fetching questions: {e}")
-#         return f"An unexpected error occurred fetching questions: {e}", None
-
-
-# #     question_text = item.get("question")
-# # question_input = {"question": question_text}
-# # if "image" in item:
-# #     question_input["image"] = item["image"]
-# # submitted_answer = agent(question_input)
-#     # 3. Run your Agent
-#     results_log = []
-#     answers_payload = []
-#     print(f"Running agent on {len(questions_data)} questions...")
-#     for item in questions_data:
-#         task_id = item.get("task_id")
-#         question_text = item.get("question")
-#         image = item.get("image", None)
-    
-#         if not task_id or question_text is None:
-#             print(f"Skipping item with missing task_id or question: {item}")
-#             continue
-    
-#         try:
-#             question_input = {"question": question_text}
-#             if image:
-#                 question_input["image"] = {"type": "image", "data": image}
-#             submitted_answer = agent(question_input)
-    
-#             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})
-    
-#         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}"})
-
-#     if not answers_payload:
-#         print("Agent did not produce any answers to submit.")
-#         return "Agent did not produce any answers to submit.", pd.DataFrame(results_log)
-
-#     # 4. Prepare Submission 
-#     submission_data = {"username": username.strip(), "agent_code": agent_code, "answers": answers_payload}
-#     status_update = f"Agent finished. Submitting {len(answers_payload)} answers for user '{username}'..."
-#     print(status_update)
-
-#     # 5. Submit
-#     print(f"Submitting {len(answers_payload)} answers to: {submit_url}")
-#     try:
-#         response = requests.post(submit_url, json=submission_data, timeout=60)
-#         response.raise_for_status()
-#         result_data = response.json()
-#         final_status = (
-#             f"Submission Successful!\n"
-#             f"User: {result_data.get('username')}\n"
-#             f"Overall Score: {result_data.get('score', 'N/A')}% "
-#             f"({result_data.get('correct_count', '?')}/{result_data.get('total_attempted', '?')} correct)\n"
-#             f"Message: {result_data.get('message', 'No message received.')}"
-#         )
-#         print("Submission successful.")
-#         results_df = pd.DataFrame(results_log)
-#         return final_status, results_df
-#     except requests.exceptions.HTTPError as e:
-#         error_detail = f"Server responded with status {e.response.status_code}."
-#         try:
-#             error_json = e.response.json()
-#             error_detail += f" Detail: {error_json.get('detail', e.response.text)}"
-#         except requests.exceptions.JSONDecodeError:
-#             error_detail += f" Response: {e.response.text[:500]}"
-#         status_message = f"Submission Failed: {error_detail}"
-#         print(status_message)
-#         results_df = pd.DataFrame(results_log)
-#         return status_message, results_df
-#     except requests.exceptions.Timeout:
-#         status_message = "Submission Failed: The request timed out."
-#         print(status_message)
-#         results_df = pd.DataFrame(results_log)
-#         return status_message, results_df
-#     except requests.exceptions.RequestException as e:
-#         status_message = f"Submission Failed: Network error - {e}"
-#         print(status_message)
-#         results_df = pd.DataFrame(results_log)
-#         return status_message, results_df
-#     except Exception as e:
-#         status_message = f"An unexpected error occurred during submission: {e}"
-#         print(status_message)
-#         results_df = pd.DataFrame(results_log)
-#         return status_message, results_df
-
-
-# # --- Build Gradio Interface using Blocks ---
-# with gr.Blocks() as demo:
-#     gr.Markdown("# Basic Agent Evaluation Runner")
-#     gr.Markdown(
-#         """
-#         **Instructions:**
-
-#         1.  Please clone this space, then modify the code to define your agent's logic, the tools, the necessary packages, etc ...
-#         2.  Log in to your Hugging Face account using the button below. This uses your HF username for submission.
-#         3.  Click 'Run Evaluation & Submit All Answers' to fetch questions, run your agent, submit answers, and see the score.
-
-#         ---
-#         **Disclaimers:**
-#         Once clicking on the "submit button, it can take quite some time ( this is the time for the agent to go through all the questions).
-#         This space provides a basic setup and is intentionally sub-optimal to encourage you to develop your own, more robust solution. For instance for the delay process of the submit button, a solution could be to cache the answers and submit in a seperate action or even to answer the questions in async.
-#         """
-#     )
-
-#     gr.LoginButton()
-
-#     run_button = gr.Button("Run Evaluation & Submit All Answers")
-
-#     status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False)
-#     # Removed max_rows=10 from DataFrame constructor
-#     results_table = gr.DataFrame(label="Questions and Agent Answers", wrap=True)
-
-#     run_button.click(
-#         fn=run_and_submit_all,
-#         outputs=[status_output, results_table]
-#     )
-
-# if __name__ == "__main__":
-#     print("\n" + "-"*30 + " App Starting " + "-"*30)
-#     # Check for SPACE_HOST and SPACE_ID at startup for information
-#     space_host_startup = os.getenv("SPACE_HOST")
-#     space_id_startup = os.getenv("SPACE_ID") # Get SPACE_ID at startup
-
-#     if space_host_startup:
-#         print(f"✅ SPACE_HOST found: {space_host_startup}")
-#         print(f"   Runtime URL should be: https://{space_host_startup}.hf.space")
-#     else:
-#         print("ℹ️  SPACE_HOST environment variable not found (running locally?).")
-
-#     if space_id_startup: # Print repo URLs if SPACE_ID is found
-#         print(f"✅ SPACE_ID found: {space_id_startup}")
-#         print(f"   Repo URL: https://huggingface.co/spaces/{space_id_startup}")
-#         print(f"   Repo Tree URL: https://huggingface.co/spaces/{space_id_startup}/tree/main")
-#     else:
-#         print("ℹ️  SPACE_ID environment variable not found (running locally?). Repo URL cannot be determined.")
-
-#     print("-"*(60 + len(" App Starting ")) + "\n")
-
-#     print("Launching Gradio Interface for Basic Agent Evaluation...")
-#     demo.launch(debug=True, share=False)