Update app.py

app.py

@@ -1,71 +1,255 @@
+import os
 import gradio as gr
 import requests
-import os
-from huggingface_hub import InferenceClient
-from tools import WikipediaTool, MathTool
-
-# Use a lightweight model that runs on free Spaces (optional: try mistralai/Mistral-7B-Instruct-v0.1 if you pay for GPU)
-MODEL_ID = "tiiuae/falcon-7b-instruct"
-client = InferenceClient(MODEL_ID, token=os.getenv("HF_TOKEN"))
-
-tools = [WikipediaTool(), MathTool()]
-
-# Prompt template
-def build_prompt(question):
-    return f"""You are a helpful AI tutor. Answer the following question very concisely but accurately.
-
-Question: {question}
-Answer:"""
-
-# Get questions from the evaluation server
-def fetch_questions():
-    res = requests.get("https://agents-course-unit4-scoring.hf.space/questions")
-    return res.json()
-
-# Submit answers back to the evaluation server
-def submit_answers(answers):
-    res = requests.post("https://agents-course-unit4-scoring.hf.space/submit", json={"answers": answers})
-    return res.json()
-
-# Core agent logic
-def run_agent(questions):
-    answers = []
-    logs = []
-    for q in questions:
-        prompt = build_prompt(q)
+import inspect
+import pandas as pd
+import re
+
+# --- 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):
+        self.api_url = "https://api-inference.huggingface.co/models/mixtral-7b-instruct-v0.3"
+        self.api_token = os.getenv("HF_TOKEN")
+        if not self.api_token:
+            raise ValueError("HF_TOKEN environment variable not set.")
+        self.headers = {"Authorization": f"Bearer {self.api_token}"}
+        print("BasicAgent initialized with Mistral-7B-Instruct-v0.3.")
+
+    def __call__(self, question: str) -> tuple[str, str]:
+        print(f"Agent received question (first 50 chars): {question[:50]}...")
+        try:
+            # Prompt designed for concise answers and detailed reasoning
+            prompt = (
+                f"Question: {question}\n"
+                "Please provide a concise answer (e.g., a number like '5' or a short phrase) "
+                "followed by a detailed explanation of your reasoning. "
+                "Format your response as: Answer: <concise answer>\nReasoning: <detailed reasoning>"
+            )
+            payload = {
+                "inputs": prompt,
+                "parameters": {"max_new_tokens": 300, "return_full_text": False}
+            }
+            response = requests.post(self.api_url, headers=self.headers, json=payload, timeout=10)
+            response.raise_for_status()
+            full_response = response.json()[0]["generated_text"].strip()
+
+            # Extract concise answer and reasoning
+            answer_match = re.search(r"Answer: (.*?)(?:\nReasoning: (.*))?$", full_response, re.DOTALL)
+            if answer_match:
+                concise_answer = answer_match.group(1).strip()
+                reasoning = answer_match.group(2).strip() if answer_match.group(2) else "No reasoning provided by model."
+            else:
+                # Fallback: Try to extract a concise answer (e.g., a number or short phrase)
+                concise_answer = self._extract_concise_answer(full_response)
+                reasoning = full_response
+
+            print(f"Agent returning concise answer: {concise_answer}")
+            print(f"Reasoning (first 50 chars): {reasoning[:50]}...")
+            return concise_answer, reasoning
+        except requests.exceptions.RequestException as e:
+            print(f"Error querying Inference API: {e}")
+            return f"Error: {e}", f"Error: Failed to get answer from model - {e}"
+        except Exception as e:
+            print(f"Unexpected error in agent: {e}")
+            return f"Error: {e}", f"Error: {e}"
+
+    def _extract_concise_answer(self, response: str) -> str:
+        """Extracts a concise answer (e.g., number or short phrase) from the model's response."""
+        # Try to find a number (integer or float)
+        number_match = re.search(r"\b\d+(\.\d+)?\b", response)
+        if number_match:
+            return number_match.group(0)
+        # Try to find a short phrase (up to 3 words)
+        words = response.split()[:3]
+        if len(words) <= 3 and len(" ".join(words)) <= 20:
+            return " ".join(words)
+        # Fallback: Use first sentence or first 10 characters
+        sentence_end = response.find(". ")
+        if sentence_end != -1:
+            return response[:sentence_end].strip()[:20]
+        return response[:20].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
+    try:
+        agent = BasicAgent()
+        agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
+        print(agent_code)
+    except Exception as e:
+        print(f"Error instantiating agent: {e}")
+        return f"Error initializing agent: {e}", None
+
+    # 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
+
+    # 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")
+        if not task_id or question_text is None:
+            print(f"Skipping item with missing task_id or question: {item}")
+            continue
         try:
-            output = client.text_generation(prompt, max_new_tokens=100, temperature=0.5)
-            final_answer = output.strip().split("Answer:")[-1].strip()
+            submitted_answer, reasoning = 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,
+                "Reasoning": reasoning
+            })
         except Exception as e:
-            final_answer = "AGENT ERROR"
-            output = str(e)
-
-        answers.append(final_answer)
-        logs.append(f"**Q:** {q}\n**Prompt:** {prompt}\n**Model Output:** {output}\n**Submitted Answer:** {final_answer}\n\n---\n")
-
-    return answers, "\n".join(logs)
-
-# Gradio UI
-def main():
-    with gr.Blocks() as demo:
-        gr.Markdown("# 🤖 Final Assignment Agent (Unit 4)")
-        with gr.Row():
-            run_button = gr.Button("🔍 Run Agent on 20 Questions")
-            submit_button = gr.Button("🚀 Submit to Evaluation")
-        output_text = gr.Textbox(label="Log Output", lines=30)
-        score_text = gr.Textbox(label="Score Result")
-        state = gr.State()
-
-        def run_and_log():
-            questions = fetch_questions()
-            answers, log = run_agent(questions)
-            return answers, log
-
-        def submit_wrapper(answers):
-            result = submit_answers(answers)
-            return str(result)
-
-        run_button.click(run_and_log, outputs=[state, output_text])
-        submit_button.click(submit_wrapper, inputs=[state], outputs=score_text)
-
-    demo.launch()
+             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}",
+                 "Reasoning": f"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)
+    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)