Update app.py

app.py

@@ -1,106 +1,151 @@
 import os
-from openai import OpenAI  # new client entrypoint
+import openai                              # ← official OpenAI client
+from openai import OpenAI
 import gradio as gr
 import requests
 import pandas as pd
+from smolagents import DuckDuckGoSearchTool, tool
 
-# --- Configuration ---
-# In your Space settings, add OPENAI_API_KEY as a Secret; the client reads it automatically.
-API_URL = "https://agents-course-unit4-scoring.hf.space"
-MODEL_NAME = "gpt-4.1"
+# --- Constants ---
+DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
-# --- OpenAI Client ---
-client = OpenAI()  # reads OPENAI_API_KEY from env
+# --- Configure OpenAI SDK & Client ---
 
-# --- GPT-4.1 Caller ---
-def ask_chatgpt_4_1(question: str) -> str:
-    response = client.responses.create(
-        model=MODEL_NAME,
-        input=question
-    )
-    # The new library returns `output_text`
-    return response.output_text
+openai_api_key = os.getenv("OPENAI_API_KEY")
+if not openai_api_key:
+    raise RuntimeError("Set OPENAI_API_KEY in your Space secrets or env!")
+
+openai.api_key = openai_api_key
+client = OpenAI()  # new client object
+
+# --- Tool Definitions ---
+
+@tool
+def summarize_query(query: str) -> str:
+    """
+    Provides a structured summary to reframe a query if search results are unclear or poor.
+
+    Args:
+        query (str): The search query that needs summarization.
+    Returns:
+        str: A concise summary of key facts about the given query.
+    """
+    return f"Summarize and reframe: {query}"
+
+search_tool = DuckDuckGoSearchTool()
+
+# --- ReACT + Scratchpad + Auto‐Retry Instruction Prompt ---
+
+instruction_prompt = """
+You are a ReACT agent with scratchpad memory and a retry mechanism.
+
+For every question:
+1. Thought: Figure out what's needed.
+2. Action: (Optional) Call a tool with a precise query.
+3. Observation: Record tool output.
+
+If the first Observation is empty or irrelevant:
+4. Thought: Unclear result; reframe and retry.
+5. Action: summarize_query(original question).
+6. Action: DuckDuckGoSearchTool(reframed query).
+7. Observation: Record new result.
+
+Then:
+8. Thought: Reflect on all observations.
+9. FINAL ANSWER: Provide your answer.
+
+Formatting rules:
+You are a general AI assistant. I will ask you a question. Report your thoughts, and finish your answer with the following template: FINAL ANSWER: [YOUR FINAL ANSWER]. YOUR FINAL ANSWER should be a number OR as few words as possible OR a comma separated list of numbers and/or strings. If you are asked for a number, don't use comma to write your number neither use units such as $ or percent sign unless specified otherwise. If you are asked for a string, don't use articles, neither abbreviations (e.g. for cities), and write the digits in plain text unless specified otherwise. If you are asked for a comma separated list, apply the above rules depending of whether the element to be put in the list is a number or a string.
+"""
+
+# --- BasicAgent using the new OpenAI client ---
 
-# --- Agent Class ---
 class BasicAgent:
     def __init__(self):
-        print("BasicAgent using OpenAI GPT-4.1 (new client) ready.")
+        print("SmolAgent (GPT-4.1) with ReACT, Scratchpad & Retry initialized.")
 
     def __call__(self, question: str) -> str:
-        print(f"Q>> {question}")
+        # Build the full prompt
+        prompt = instruction_prompt.strip() + "\n\nQUESTION: " + question.strip()
+        print(f"Agent prompt (first 150 chars): {prompt[:150]}…")
+        # Call GPT-4.1 via the new client.responses.create API
         try:
-            return ask_chatgpt_4_1(question)
+            response = client.responses.create(
+                model="gpt-4.1",
+                input=prompt
+            )
+            return response.output_text
         except Exception as e:
             return f"AGENT ERROR: {e}"
 
-# --- Evaluation & Submission ---
+# --- Gradio / HF‐Spaces submission logic ---
+
 def run_and_submit_all(profile: gr.OAuthProfile | None):
     if not profile:
-        return "Please log in to Hugging Face.", None
+        return "Please log in to Hugging Face using the login button above.", None
+
     username = profile.username
     space_id = os.getenv("SPACE_ID", "")
     agent = BasicAgent()
-    code_link = f"https://huggingface.co/spaces/{space_id}/tree/main"
+    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
 
     # 1. Fetch questions
     try:
-        resp = requests.get(f"{API_URL}/questions", timeout=15)
+        resp = requests.get(f"{DEFAULT_API_URL}/questions", timeout=15)
         resp.raise_for_status()
-        questions = resp.json()
-        if not questions:
-            return "No questions fetched.", None
+        questions = resp.json() or []
     except Exception as e:
         return f"Error fetching questions: {e}", None
 
-    # 2. Answer each
-    logs = []
-    payload = []
+    # 2. Run agent on each question
+    logs, payload = [], []
     for item in questions:
         tid = item.get("task_id")
-        q = item.get("question")
+        q   = item.get("question")
         if not tid or q is None:
             continue
         ans = agent(q)
-        logs.append({"Task ID": tid, "Question": q, "Answer": ans})
+        logs.append({"Task ID": tid, "Question": q, "Submitted Answer": ans})
         payload.append({"task_id": tid, "submitted_answer": ans})
 
     if not payload:
-        return "No answers generated.", pd.DataFrame(logs)
-
-    # 3. Submit
-    submission = {
-        "username": username,
-        "agent_code": code_link,
-        "answers": payload
-    }
+        return "Agent did not produce any answers.", pd.DataFrame(logs)
+
+    # 3. Submit answers
+    submission = {"username": username, "agent_code": agent_code, "answers": payload}
     try:
-        post = requests.post(f"{API_URL}/submit", json=submission, timeout=60)
+        post = requests.post(f"{DEFAULT_API_URL}/submit", json=submission, timeout=60)
         post.raise_for_status()
         res = post.json()
         status = (
-            f"Success! {res.get('username')} scored "
-            f"{res.get('score', 'N/A')}% "
-            f"({res.get('correct_count')}/{res.get('total_attempted')})"
+            f"Submission Successful!\n"
+            f"User: {res.get('username')}\n"
+            f"Overall Score: {res.get('score', 'N/A')}% "
+            f"({res.get('correct_count', '?')}/{res.get('total_attempted', '?')})\n"
+            f"Message: {res.get('message', '')}"
         )
         return status, pd.DataFrame(logs)
     except Exception as e:
         return f"Submission Failed: {e}", pd.DataFrame(logs)
 
 # --- Gradio Interface ---
+
 with gr.Blocks() as demo:
-    gr.Markdown("# SmolAgent GAIA Evaluation Runner 🚀")
+    gr.Markdown("# SmolAgent GAIA Runner (GPT-4.1) 🚀")
     gr.Markdown(
         """
-        1. Clone space and modify if needed  
-        2. Log in to Hugging Face  
-        3. Click **Run Evaluation & Submit All Answers**  
-        (May take several minutes)
+        **Instructions:**
+        1. Clone this space.
+        2. In Settings → Secrets add `OPENAI_API_KEY`.
+        3. Log in to Hugging Face.
+        4. Click **Run Evaluation & Submit All Answers**.
+        **Note:** Evaluation may take several minutes.
         """
     )
     gr.LoginButton()
-    run_btn = gr.Button("Run Evaluation & Submit All Answers")
+    run_btn    = gr.Button("Run Evaluation & Submit All Answers")
     status_out = gr.Textbox(label="Status", lines=5, interactive=False)
-    table_out = gr.DataFrame(label="Q&A Log", wrap=True)
+    table_out  = gr.DataFrame(label="Questions & Answers", wrap=True)
 
     run_btn.click(fn=run_and_submit_all, outputs=[status_out, table_out])