Update app.py

app.py

@@ -1,103 +1,221 @@
 import os
-import gradio as gr
-import requests
 import inspect
+import requests
 import pandas as pd
+import gradio as gr
+
+from smolagents import CodeAgent, LiteLLMModel, DuckDuckGoSearchTool, VisitWebpageTool, tool
 
-# (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 ------
+
+# ---------------------------------------------------------------------------
+# Custom tools for file-based question types (audio, images, python files)
+# ---------------------------------------------------------------------------
+
+@tool
+def transcribe_audio(file_path: str) -> str:
+    """
+    Transcribes an audio file (mp3/wav) to text using OpenAI Whisper.
+
+    Args:
+        file_path: Local path to the audio file to transcribe.
+
+    Returns:
+        The transcribed text.
+    """
+    from openai import OpenAI
+    client = OpenAI(api_key=os.environ.get("OPENAI_API_KEY"))
+    with open(file_path, "rb") as f:
+        transcript = client.audio.transcriptions.create(
+            model="whisper-1",
+            file=f
+        )
+    return transcript.text
+
+
+@tool
+def analyze_image(file_path: str, question: str) -> str:
+    """
+    Analyzes an image (e.g. a chess position) using a vision-capable LLM
+    and answers a question about it.
+
+    Args:
+        file_path: Local path to the image file.
+        question: The question to answer about the image.
+
+    Returns:
+        The model's answer about the image.
+    """
+    import base64
+    from openai import OpenAI
+    client = OpenAI(api_key=os.environ.get("OPENAI_API_KEY"))
+
+    with open(file_path, "rb") as f:
+        b64_image = base64.b64encode(f.read()).decode("utf-8")
+
+    response = client.chat.completions.create(
+        model="gpt-4o",
+        messages=[{
+            "role": "user",
+            "content": [
+                {"type": "text", "text": question},
+                {"type": "image_url", "image_url": {"url": f"data:image/png;base64,{b64_image}"}}
+            ]
+        }]
+    )
+    return response.choices[0].message.content
+
+
+@tool
+def run_python_file(file_path: str) -> str:
+    """
+    Reads and returns the contents of a Python (.py) file so the agent
+    can analyze or trace through the code to determine its output.
+
+    Args:
+        file_path: Local path to the python file.
+
+    Returns:
+        The raw source code as text.
+    """
+    with open(file_path, "r") as f:
+        return f.read()
+
+
+@tool
+def read_excel_file(file_path: str) -> str:
+    """
+    Reads an Excel (.xlsx) file and returns its contents as a string table.
+
+    Args:
+        file_path: Local path to the Excel file.
+
+    Returns:
+        A string representation of the spreadsheet data.
+    """
+    df = pd.read_excel(file_path)
+    return df.to_string()
+
+
+# ---------------------------------------------------------------------------
+# The Agent
+# ---------------------------------------------------------------------------
+
 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
 
-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
+        # LiteLLM lets you swap providers by just changing model_id, e.g.:
+        # "gpt-4o-mini", "claude-3-5-sonnet-20241022", "huggingface/Qwen/Qwen2.5-72B-Instruct"
+        self.model = LiteLLMModel(
+            model_id="gpt-4o-mini",
+            api_key=os.environ.get("OPENAI_API_KEY"),
+        )
+
+        self.agent = CodeAgent(
+            model=self.model,
+            tools=[
+                DuckDuckGoSearchTool(),
+                VisitWebpageTool(),
+                transcribe_audio,
+                analyze_image,
+                run_python_file,
+                read_excel_file,
+            ],
+            max_steps=8,
+        )
+
+    def __call__(self, question: str, file_path: str = None) -> str:
+        print(f"Agent received question (first 80 chars): {question[:80]}...")
+
+        prompt = question
+        if file_path:
+            prompt += f"\n\nA file has been downloaded for this question at local path: {file_path}. Use the appropriate tool to read it before answering."
+
+        prompt += "\n\nIMPORTANT: Respond with ONLY the final answer. No explanation, no 'FINAL ANSWER:' prefix, just the answer itself, formatted exactly as requested in the question."
+
+        try:
+            answer = self.agent.run(prompt)
+        except Exception as e:
+            print(f"Agent error: {e}")
+            answer = "ERROR"
+
+        answer = str(answer).strip()
+        print(f"Agent returning answer: {answer}")
+        return answer
+
+
+# ---------------------------------------------------------------------------
+# Evaluation + submission logic
+# ---------------------------------------------------------------------------
+
+def run_and_submit_all(profile: gr.OAuthProfile | None):
+    space_id = os.getenv("SPACE_ID")
 
     if profile:
-        username= f"{profile.username}"
+        username = profile.username
         print(f"User logged in: {username}")
     else:
-        print("User not logged in.")
-        return "Please Login to Hugging Face with the button.", None
+        return "Please log in to Hugging Face first.", None
 
     api_url = DEFAULT_API_URL
     questions_url = f"{api_url}/questions"
+    files_url = f"{api_url}/files"
     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 = BasicAgent()
     agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
-    print(agent_code)
 
-    # 2. Fetch Questions
-    print(f"Fetching questions from: {questions_url}")
+    # 1. Fetch questions
     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
+        return f"Error fetching questions: {e}", None
 
-    # 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")
+        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
+
+        file_path = None
+        if file_name:
+            try:
+                file_resp = requests.get(f"{files_url}/{task_id}", timeout=30)
+                file_resp.raise_for_status()
+                file_path = f"/tmp/{file_name}"
+                with open(file_path, "wb") as f:
+                    f.write(file_resp.content)
+            except Exception as e:
+                print(f"Could not download file for {task_id}: {e}")
+
         try:
-            submitted_answer = agent(question_text)
-            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})
+            submitted_answer = agent(question_text, file_path)
         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}"})
+            submitted_answer = f"AGENT ERROR: {e}"
+
+        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})
 
     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)
+        return "No answers were generated.", 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)
+    # 2. Submit
+    submission_data = {
+        "username": username.strip(),
+        "agent_code": agent_code,
+        "answers": answers_payload
+    }
 
-    # 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()
@@ -107,90 +225,35 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
             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.')}"
+            f"Message: {result_data.get('message', '')}"
         )
-        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
+        return final_status, pd.DataFrame(results_log)
     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
+        return f"Submission failed: {e}", pd.DataFrame(results_log)
+
 
+# ---------------------------------------------------------------------------
+# Gradio UI
+# ---------------------------------------------------------------------------
 
-# --- 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.
+        1. This Space defines your agent's logic, tools, and required packages.
+        2. Log in to your Hugging Face account using the button below.
+        3. Click 'Run Evaluation & Submit All Answers' to fetch questions, run your agent, submit answers, and see the score.
         """
     )
 
     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]
-    )
+    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...")
+if __name__ == "__main__":
     demo.launch(debug=True, share=False)