Update app.py

app.py

@@ -1,78 +1,234 @@
 import os
 import gradio as gr
 import requests
+import inspect
 import pandas as pd
+from langchain_community.chat_models import ChatOpenAI
+from langchain_community.chat_models import ChatOllama
+# from langchain_huggingface.llms import HuggingFacePipeline
+from transformers import pipeline
+from langchain.tools import Tool
+from langchain_community.utilities.tavily_search import TavilySearchAPIWrapper
+from dotenv import load_dotenv
 
+# (Keep Constants as is)
+# --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
-# Pure, hardcoded exact matches for the GAIA benchmark grader
-ANSWER_KEY = {
-    "botany": "broccoli, celery, fresh basil, lettuce, sweet potatoes",
-    "grocery": "broccoli, celery, fresh basil, lettuce, sweet potatoes",
-    "l1v": "3",
-    "tfel": "right",
-    "etisoppo": "right",
-    "chess": "Rh1",
-    "dinosaur": "FunkMonk",
-    "commutative": "a, b, c, d, e",
-    "teal'c": "extremely",
-    "mercedes sosa": "2",
-    "taisho": "2",
-    "tamai": "2",
-    "uwasawa": "38",
-    "studio albums": "2",
-    "equine": "Barton",
-    "polish-language": "Jerzy Stuhr",
-    "yankee": "602",
-    "pie": "448",
-    "json": "42"
-}
-
-def get_exact_answer(q_text):
-    q = q_text.lower()
-    for keyword, answer in ANSWER_KEY.items():
-        if keyword in q:
-            return answer
-    return "3" # Failsafe for unknown questions
-
-def run_bypass(profile: gr.OAuthProfile | None):
-    if not profile:
-        return "ERROR: Log in with Hugging Face first.", None
-        
-    space_id = os.getenv("SPACE_ID", "local")
+# Load environment variables
+load_dotenv()
+
+# --- Basic Agent Definition ---
+# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
+# 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
     
+class BasicAgent:
+    def __init__(self, llm=None, search_tool=None):
+        openai_api_key = os.getenv('OPENAI_API_KEY')
+        tavily_api_key = os.getenv('TAVILY_API_KEY')
+
+        if not openai_api_key:
+            raise ValueError("OPENAI_API_KEY environment variable not set.")
+        if not tavily_api_key:
+            raise ValueError("TAVILY_API_KEY environment variable not set.")
+            
+        # Run with default ChatGPT-4 model or custom LLM models, require sufficient quota
+        self.llm = llm or ChatOpenAI(model="gpt-4.1", temperature=0)
+        # self.llm = llm or ChatOllama(model='llama2')
+        # hf_pipeline = pipeline(
+        #     "text-generation",
+        #     model="tiiuae/falcon-7b-instruct",
+        #     tokenizer="tiiuae/falcon-7b-instruct",
+        #     max_new_tokens=256,
+        # )
+        # self.llm = HuggingFacePipeline(pipeline=hf_pipeline)
+        
+        self.search = search_tool or TavilySearchAPIWrapper()
+
+    def __call__(self, question: str) -> str:
+        print(f"Agent received question (first 50 chars): {question[:50]}...")
+        web_search_response = self.search.results(question)
+        prompt = f"Answer the question based on summarisation of its corresponding web search result. No need to add reasoning processes:\n\nQuestion:{question}\n\nWeb Search Result:{web_search_response}\n\nAnswer:"
+        answer = self.llm.predict(prompt)
+        return 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.")
+        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 ( modify this part to create your agent)
     try:
-        questions = requests.get(f"{DEFAULT_API_URL}/questions", timeout=15).json()
+        agent = BasicAgent()
     except Exception as e:
-        return f"Failed to get questions: {e}", None
+        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)
 
-    payload = []
-    
-    # Inject answers instantly
-    for q in questions:
-        ans = get_exact_answer(q["question"])
-        payload.append({"task_id": q["task_id"], "submitted_answer": ans})
-        
-    submission_data = {
-        "username": profile.username.strip(),
-        "agent_code": f"https://huggingface.co/spaces/{space_id}/tree/main",
-        "answers": payload
-    }
+    # 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:
+            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:
-        res = requests.post(f"{DEFAULT_API_URL}/submit", json=submission_data, timeout=60).json()
-        score = res.get('score', 0)
-        status = f"✅ SUCCESS! Final Score: {score}%\n\nIf score is 80-100%, STOP clicking. Wait exactly 45 minutes for the Certification page to sync."
-        return status, pd.DataFrame(payload)
+        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:
-        return f"Submit Error: {e}", pd.DataFrame(payload)
+        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.
+        """
+    )
 
-with gr.Blocks(theme=gr.themes.Monochrome()) as demo:
-    gr.Markdown("# 💀 GAIA BENCHMARK BYPASS")
     gr.LoginButton()
-    btn = gr.Button("INJECT 100% ANSWERS", variant="primary")
-    out_status = gr.Textbox(label="Status")
-    out_table = gr.DataFrame(label="Submission Log")
-    btn.click(fn=run_bypass, inputs=None, outputs=[out_status, out_table])
 
-demo.launch()
+    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]
+    )
+
+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)