Update app.py

app.py

@@ -1,196 +1,273 @@
 import os
+import time
+import re
 import gradio as gr
 import requests
-import inspect
 import pandas as pd
+from groq import Groq
 
-# (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.")
+        api_key = os.getenv("GROQ_API_KEY")
+        if not api_key:
+            raise ValueError("GROQ_API_KEY not set!")
+        self.client = Groq(api_key=api_key)
+        print("Groq agent initialized.")
+
+    def is_reversed_text(self, text: str) -> bool:
+        """Detect if text looks reversed (common riddle pattern)."""
+        # Reversed text often ends with what would be capital letters/punctuation reversed
+        sample = text.strip()
+        return sample.endswith((".", "?")) is False and sample[:1].islower() and len(sample) > 20
+
+    def search_wikipedia(self, query: str) -> str:
+        """Search Wikipedia directly via API - much more reliable than DuckDuckGo."""
+        try:
+            # Step 1: search for the most relevant page title
+            search_resp = requests.get(
+                "https://en.wikipedia.org/w/api.php",
+                params={
+                    "action": "query",
+                    "list": "search",
+                    "srsearch": query,
+                    "format": "json",
+                    "srlimit": 1
+                },
+                headers={"User-Agent": "AgentBot/1.0"},
+                timeout=10
+            )
+            search_data = search_resp.json()
+            results = search_data.get("query", {}).get("search", [])
+            if not results:
+                return ""
+
+            title = results[0]["title"]
+
+            # Step 2: get the summary/extract of that page
+            extract_resp = requests.get(
+                "https://en.wikipedia.org/w/api.php",
+                params={
+                    "action": "query",
+                    "prop": "extracts",
+                    "exintro": True,
+                    "explaintext": True,
+                    "titles": title,
+                    "format": "json"
+                },
+                headers={"User-Agent": "AgentBot/1.0"},
+                timeout=10
+            )
+            extract_data = extract_resp.json()
+            pages = extract_data.get("query", {}).get("pages", {})
+            for page_id, page in pages.items():
+                extract = page.get("extract", "")
+                if extract:
+                    return extract[:2000]  # limit length
+            return ""
+        except Exception as e:
+            print(f"Wikipedia search error: {e}")
+            return ""
+
+    def search_duckduckgo(self, query: str) -> str:
+        """Fallback search via DuckDuckGo."""
+        try:
+            params = {"q": query, "format": "json", "no_html": "1"}
+            resp = requests.get(
+                "https://api.duckduckgo.com/",
+                params=params,
+                headers={"User-Agent": "Mozilla/5.0"},
+                timeout=8
+            )
+            data = resp.json()
+            results = []
+            if data.get("Abstract"):
+                results.append(data["Abstract"])
+            if data.get("Answer"):
+                results.append(data["Answer"])
+            for t in data.get("RelatedTopics", [])[:3]:
+                if isinstance(t, dict) and t.get("Text"):
+                    results.append(t["Text"])
+            return "\n".join(results) if results else ""
+        except Exception:
+            return ""
+
+    def search_web(self, query: str) -> str:
+        """Try Wikipedia first, fallback to DuckDuckGo."""
+        wiki_result = self.search_wikipedia(query)
+        if wiki_result:
+            return wiki_result
+        return self.search_duckduckgo(query)
+
     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
-
-    if profile:
-        username= f"{profile.username}"
-        print(f"User logged in: {username}")
-    else:
-        print("User not logged in.")
+        try:
+            original_question = question
+
+            # Handle reversed-text riddle questions
+            stripped = question.strip()
+            if stripped and stripped[-1] not in ".?!" and stripped[0].islower():
+                reversed_q = stripped[::-1]
+                if reversed_q[0].isupper() or "?" in reversed_q[-5:]:
+                    print("Detected reversed text question, decoding...")
+                    decoded = reversed_q
+                    # Ask the model to answer the decoded question directly
+                    prompt = f"""This question was written backwards. Decode it and answer it.
+Decoded question: {decoded}
+
+Answer with ONLY the final answer, no explanation."""
+                    response = self.client.chat.completions.create(
+                        model="llama-3.1-8b-instant",
+                        messages=[{"role": "user", "content": prompt}],
+                        max_tokens=50,
+                        temperature=0
+                    )
+                    answer = response.choices[0].message.content.strip()
+                    print(f"Reversed Q decoded -> A: {answer}")
+                    return answer
+
+            # Skip web search for math/logic-only questions (faster, more accurate)
+            math_keywords = ["table", "set s =", "commutative", "calculate", "solve"]
+            needs_search = not any(kw in question.lower() for kw in math_keywords)
+
+            search_results = ""
+            if needs_search:
+                search_results = self.search_web(question)
+
+            context = f"\n\nReference Information:\n{search_results}" if search_results else ""
+
+            prompt = f"""You are a precise question-answering assistant taking an exam.
+Answer with ONLY the final answer - no explanation, no extra words, no restating the question.
+For numbers: give just the number (e.g. "3" not "three studio albums").
+For names: give just the name.
+For yes/no: give just "Yes" or "No".
+For lists: give comma-separated values in the exact format requested.
+
+Question: {question}{context}
+
+Final Answer:"""
+
+            response = self.client.chat.completions.create(
+                model="llama-3.1-8b-instant",
+                messages=[
+                    {
+                        "role": "system",
+                        "content": "You are a precise, concise question-answering assistant. Never explain your reasoning, only give the final answer."
+                    },
+                    {"role": "user", "content": prompt}
+                ],
+                max_tokens=150,
+                temperature=0
+            )
+            answer = response.choices[0].message.content.strip()
+
+            # Clean up common prefixes
+            for prefix in ["Final Answer:", "Answer:", "The answer is:", "The answer is"]:
+                if answer.lower().startswith(prefix.lower()):
+                    answer = answer[len(prefix):].strip()
+
+            print(f"Q: {original_question[:60]} | A: {answer[:60]}")
+            return answer
+
+        except Exception as e:
+            print(f"Error: {e}")
+            return f"Error: {e}"
+
+
+def run_and_submit_all(profile: gr.OAuthProfile | None):
+    space_id = os.getenv("SPACE_ID")
+
+    if not profile:
         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"
+    username = profile.username
 
-    # 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
+        resp = requests.get(f"{DEFAULT_API_URL}/questions", timeout=15)
+        resp.raise_for_status()
+        questions_data = resp.json()
         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:
+
+    for i, item in enumerate(questions_data):
         task_id = item.get("task_id")
         question_text = item.get("question")
         if not task_id or question_text is None:
-            print(f"Skipping item with missing task_id or question: {item}")
             continue
+
+        print(f"Q{i+1}/{len(questions_data)}: {question_text[:60]}")
+
         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})
+            answer = agent(question_text)
         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}"})
+            answer = f"ERROR: {e}"
+
+        answers_payload.append({"task_id": task_id, "submitted_answer": answer})
+        results_log.append({
+            "Task ID": task_id,
+            "Question": question_text,
+            "Submitted Answer": answer
+        })
+        time.sleep(1)
 
     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 produced.", 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)
+    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()
-        result_data = response.json()
-        final_status = (
+        resp = requests.post(
+            f"{DEFAULT_API_URL}/submit",
+            json=submission_data,
+            timeout=60
+        )
+        resp.raise_for_status()
+        result = resp.json()
+        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.')}"
+            f"User: {result.get('username')}\n"
+            f"Score: {result.get('score', 'N/A')}% "
+            f"({result.get('correct_count', '?')}/{result.get('total_attempted', '?')} correct)\n"
+            f"Message: {result.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 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)
 
 
-# --- 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.Markdown("""
+**Instructions:**
+1. Log in with Hugging Face below
+2. Click **Run Evaluation & Submit All Answers**
+3. Wait ~1-2 minutes for results
+    """)
     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]
+    status_output = gr.Textbox(
+        label="Run Status / Submission Result",
+        lines=5,
+        interactive=False
     )
+    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)