Create app.py

app.py

@@ -0,0 +1,248 @@
+import os
+import gradio as gr
+import requests
+import pandas as pd
+
+# Import smol-agent and tool components
+from smolagents import CodeAgent, LiteLLMModel, tool
+from smolagents.tool import WebSearchTool
+from unstructured.partition.auto import partition
+
+
+# --- Constants ---
+DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
+
+# --- Agent Definition ---
+
+# 1. Define Your Tools
+@tool
+def file_reader(file_path: str) -> str:
+    """
+    Reads the content of a file at the given URL or local path and returns its text content.
+    Supports various file types like PDF, TXT, CSV, etc.
+    """
+    try:
+        if file_path.startswith("http://") or file_path.startswith("https://"):
+            response = requests.get(file_path, timeout=20)
+            response.raise_for_status()
+            with open("temp_file", "wb") as f:
+                f.write(response.content)
+            elements = partition("temp_file")
+            os.remove("temp_file") # Clean up
+        else:
+            elements = partition(file_path)
+        return "\n\n".join([str(el) for el in elements])
+    except Exception as e:
+        return f"Error reading or processing file '{file_path}': {e}"
+
+# 2. Define Your Agent Class
+class GaiaSmolAgent:
+    def __init__(self):
+        print("Initializing GaiaSmolAgent with OpenAI...")
+        # --- MODIFICATION 1: Use OPENAI_API_KEY ---
+        # Ensure you have set your OPENAI_API_KEY as a secret in your HF Space
+        api_key = os.getenv("OPENAI_API_KEY") 
+        if not api_key:
+            raise ValueError("API key 'OPENAI_API_KEY' not found in environment secrets.")
+
+        # --- MODIFICATION 2: Use an OpenAI Model ID ---
+        # The "Planner" model - for high-level reasoning
+        self.planner_model = LiteLLMModel(
+            model_id="gpt-4o", # Using OpenAI's gpt-4o model
+            api_key=api_key,
+            temperature=0.0,
+        )
+
+        # The "Executor" agent - for executing tasks with tools
+        self.executor_agent = CodeAgent(
+            model=self.planner_model, # Can use the same model
+            tools=[file_reader, WebSearchTool()],
+            # add_base_tools=True will add a Python interpreter
+            add_base_tools=True,
+        )
+        print("GaiaSmolAgent initialized successfully with OpenAI.")
+
+    def _generate_plan(self, question: str) -> list[str]:
+        """Generates a step-by-step plan to answer the question."""
+        print(f"Generating plan for question: {question[:100]}...")
+        prompt = f"""
+        You are an expert planner. Your job is to create a clear, step-by-step plan to answer the given question.
+        The final step must be to output the answer using the `final_answer` tool.
+        Each step should be a clear instruction for an agent to follow.
+
+        Question: "{question}"
+
+        Provide the plan as a Python list of strings. For example:
+        ["Search the web for the latest news on topic X.", "Analyze the search results to find the key person.", "final_answer('The key person is John Doe.')"]
+        """
+        response = self.planner_model.generate(prompt)
+        print(f"Generated plan: {response}")
+        try:
+            # Safely evaluate the string to a Python list
+            plan = eval(response)
+            if isinstance(plan, list):
+                return plan
+            else:
+                return [f"final_answer('Error: Plan generation failed. Could not parse plan: {response}')"]
+        except Exception as e:
+            print(f"Error parsing plan: {e}")
+            return [f"final_answer('Error: Plan generation failed. Could not parse plan: {response}')"]
+
+
+    def __call__(self, question: str) -> str:
+        """Runs the planner and executor to answer the question."""
+        print(f"Agent received question: {question[:100]}...")
+
+        # Step 1: Generate the plan
+        plan = self._generate_plan(question)
+
+        # Step 2: Execute the plan
+        final_answer = self.executor_agent.run(plan)
+
+        print(f"Agent returning final answer: {final_answer}")
+        return str(final_answer)
+
+
+def run_and_submit_all(profile: gr.OAuthProfile | None):
+    """
+    Fetches all questions, runs the GaiaSmolAgent on them, submits all answers,
+    and displays the results.
+    """
+    # --- Determine HF Space Runtime URL and Repo URL ---
+    space_id = os.getenv("SPACE_ID")
+
+    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
+    try:
+        # **MODIFIED PART: Instantiate your new agent**
+        agent = GaiaSmolAgent()
+    except Exception as e:
+        print(f"Error instantiating agent: {e}")
+        return f"Error initializing agent: {e}", None
+
+    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 Exception as e:
+        print(f"Error fetching questions: {e}")
+        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")
+        # GAIA questions can include file paths
+        question_text = item.get("question")
+        file_path = item.get("file") # Get the file URL if it exists
+        if file_path:
+             question_text += f"\n\nRelevant file is available at: {file_path}"
+
+        if not task_id or question_text is None:
+            print(f"Skipping item with missing task_id or question: {item}")
+            continue
+        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})
+        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 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
+
+# --- Gradio Interface ---
+# (This part remains unchanged)
+with gr.Blocks() as demo:
+    gr.Markdown("# GAIA Agent Evaluation Runner (smol-agent)")
+    gr.Markdown(
+        """
+        **Instructions:**
+
+        1.  Ensure you have added your **OpenAI API key** (as `OPENAI_API_KEY`) in the Space's secrets.
+        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.
+        """
+    )
+    
+    gr.LoginButton()
+
+    run_button = gr.Button("Run Evaluation & Submit All Answers")
+
+    status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False)
+    results_table = gr.DataFrame(label="Questions and Agent Answers", wrap=True)
+
+    # This is the new way to bind the OAuth profile to the function
+    run_button.click(
+        fn=run_and_submit_all,
+        inputs=None, # No direct input components
+        outputs=[status_output, results_table],
+        api_name="run_evaluation" # Add an API name for programmatic access
+    )
+
+# The __main__ block remains the same
+if __name__ == "__main__":
+    print("Launching Gradio Interface for GAIA Agent Evaluation...")
+    demo.launch(debug=True, share=False)