Upload 5 files

app.py

@@ -1,196 +1,57 @@
-import os
 import gradio as gr
 import requests
-import inspect
-import pandas as pd
-
-# (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.")
-    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.")
-        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:
-        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
-        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:
-        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)
-    # 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]
-    )
+import os
+from agent import run_agent_on_question
+from utils import get_hf_username, get_code_link
 
-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
+API_BASE = "https://agents-course-unit4-scoring.hf.space"
 
-    if space_host_startup:
-        print(f"✅ SPACE_HOST found: {space_host_startup}")
-        print(f"   Runtime URL should be: https://{space_host_startup}.hf.space")
+def fetch_questions():
+    response = requests.get(f"{API_BASE}/questions")
+    if response.status_code == 200:
+        return response.json()
     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")
+        return []
+
+def submit_answers(answers, username, code_link):
+    payload = {
+        "username": username,
+        "agent_code": code_link,
+        "answers": answers
+    }
+    response = requests.post(f"{API_BASE}/submit", json=payload)
+    if response.status_code == 200:
+        return response.json()
     else:
-        print("ℹ️  SPACE_ID environment variable not found (running locally?). Repo URL cannot be determined.")
+        return {"message": "Submission failed.", "score": 0}
+
+def run_and_submit():
+    print("Fetching questions...")
+    questions = fetch_questions()
+    print(f"Fetched {len(questions)} questions")
+
+    answers = []
+    for q in questions:
+        print(f"Running agent on task {q['task_id']}")
+        answer = run_agent_on_question(q)
+        answers.append({
+            "task_id": q["task_id"],
+            "submitted_answer": answer
+        })
+
+    username = get_hf_username()
+    code_link = get_code_link()
+    print(f"Submitting answers as {username} with code link {code_link}")
+
+    result = submit_answers(answers, username, code_link)
+    print(result)
+    return f"Score: {result.get('score', 0)}\nMessage: {result.get('message', 'No message')}"
 
-    print("-"*(60 + len(" App Starting ")) + "\n")
+with gr.Blocks() as demo:
+    gr.Markdown("## GAIA Agent Evaluation Space")
+    with gr.Row():
+        submit_btn = gr.Button("Run Evaluation & Submit All Answers")
+    output = gr.Textbox(label="Submission Result")
+    submit_btn.click(fn=run_and_submit, outputs=output)
 
-    print("Launching Gradio Interface for Basic Agent Evaluation...")
-    demo.launch(debug=True, share=False)
+demo.launch()

retriever.py

@@ -0,0 +1,27 @@
+import json
+from typing import List
+
+# Load context from a JSON file (make sure context.json is in the same directory)
+try:
+    with open("context.json", "r") as f:
+        document_store = json.load(f)
+except FileNotFoundError:
+    document_store = {}
+
+def retrieve_context(task_id: str, question: str) -> List[str]:
+    """
+    Retrieves relevant context using a local JSON context store.
+
+    Args:
+        task_id (str): The task ID from the GAIA question.
+        question (str): The actual question string (for fallback retrieval).
+
+    Returns:
+        List[str]: List of context strings.
+    """
+    if task_id in document_store:
+        return [document_store[task_id]]
+    elif "Titanic" in question:
+        return ["Titanic was featured in The Last Voyage."]
+    else:
+        return ["Context not found. Please refer to web or document tools."]

submission.py

@@ -0,0 +1,74 @@
+# submission.py
+
+import requests
+import gradio as gr
+from agent import run_agent_on_question
+from utils import format_answer
+
+API_BASE_URL = "https://agents-course-unit4-scoring.hf.space"
+
+def fetch_questions():
+    """
+    Retrieve all evaluation questions from the API.
+    """
+    response = requests.get(f"{API_BASE_URL}/questions")
+    return response.json() if response.status_code == 200 else []
+
+def submit_answers_to_leaderboard(username, agent_code_url):
+    """
+    Runs the agent on all evaluation questions and submits answers.
+    """
+    questions = fetch_questions()
+    print(f"Fetched {len(questions)} questions.")
+
+    answers = []
+
+    for q in questions:
+        print(f"\n🔍 Running agent on task: {q['task_id']}")
+        response = run_agent_on_question(q)  # ✅ Pass full task dictionary
+        formatted_answer = format_answer(response)
+
+        print(f"Answer: {formatted_answer}")
+        answers.append({
+            "task_id": q["task_id"],
+            "submitted_answer": formatted_answer
+        })
+
+    # Prepare final submission payload
+    submission = {
+        "username": username,
+        "agent_code": agent_code_url,
+        "answers": answers
+    }
+
+    res = requests.post(f"{API_BASE_URL}/submit", json=submission)
+    if res.status_code == 200:
+        print("\n✅ Submission Complete!")
+        print("Result:", res.json())
+        return res.json()
+    else:
+        print("\n❌ Submission Failed!")
+        print("Status Code:", res.status_code)
+        print("Response:", res.text)
+        return None
+
+# Optional Gradio UI for easier submission
+with gr.Blocks() as demo:
+    gr.Markdown("## 🤖 GAIA Agent Submission")
+
+    with gr.Row():
+        username = gr.Textbox(label="Your Hugging Face Username")
+        agent_code_url = gr.Textbox(label="Public URL to Your Hugging Face Space Code")
+
+    submit_btn = gr.Button("Run Evaluation & Submit All Answers")
+
+    output = gr.Textbox(label="Submission Result")
+
+    submit_btn.click(
+        fn=submit_answers_to_leaderboard,
+        inputs=[username, agent_code_url],
+        outputs=[output]
+    )
+
+if __name__ == "__main__":
+    demo.launch()

tools.py

@@ -0,0 +1,35 @@
+
+from smolagents import tool
+
+def clean_answer_with_prompt(agent_output: str) -> str:
+    """
+    Extracts and cleans the final answer from the agent output.
+    For GAIA, ensure no 'FINAL ANSWER:' prefix is returned — just the answer.
+    """
+    if "FINAL ANSWER:" in agent_output:
+        return agent_output.split("FINAL ANSWER:")[-1].strip()
+    return agent_output.strip()
+
+def build_prompt(question: str, context: str) -> str:
+    """
+    Combine the system instruction, context, and question to build the LLM prompt.
+    """
+    system_instruction = (
+        "You are an intelligent assistant helping answer complex real-world questions. "
+        "Use the provided context to reason and provide a concise factual answer. "
+        "Only answer what is asked. Do not include 'FINAL ANSWER:' or extra explanation.\n\n"
+    )
+    return f"{system_instruction}Context:\n{context}\n\nQuestion: {question}\nAnswer:"
+
+@tool
+def greeting_tool(name: str) -> str:
+    """
+    Generates a custom greeting for the guest.
+
+    Args:
+        name: Name of the guest
+
+    Returns:
+        A friendly greeting message.
+    """
+    return f"Welcome to the gala, {name}! We're honored to have you with us."

utils.py

@@ -0,0 +1,72 @@
+import requests
+import os
+import json
+
+# API base URL
+BASE_URL = "https://agents-course-unit4-scoring.hf.space"
+
+
+
+
+import os
+
+def get_hf_username():
+    """
+    Gets Hugging Face username for submission.
+    """
+    return os.environ.get("HF_USERNAME", "shrutikaP8497")  # replace with your HF username
+
+def get_code_link():
+    """
+    Returns the public URL to the Hugging Face Space code.
+    """
+    return "https://huggingface.co/spaces/shrutikaP8497/gaia_agent_code"
+
+
+def download_task_file(task_id, save_dir="downloads"):
+    """
+    Downloads a file associated with a task from the GAIA evaluation API.
+    """
+    os.makedirs(save_dir, exist_ok=True)
+    url = f"{BASE_URL}/files/{task_id}"
+    response = requests.get(url)
+
+    if response.status_code == 200:
+        filename = os.path.join(save_dir, task_id)
+        with open(filename, "wb") as f:
+            f.write(response.content)
+        return filename
+    else:
+        print(f"Failed to download file for task {task_id}")
+        return None
+
+
+def format_answer(agent_output):
+    """
+    Format the agent's response to meet submission requirements:
+    - Do NOT include 'FINAL ANSWER'
+    - Must be a concise string or comma-separated list
+    """
+    if isinstance(agent_output, str):
+        return agent_output.strip()
+    elif isinstance(agent_output, list):
+        return ", ".join(map(str, agent_output))
+    elif isinstance(agent_output, (int, float)):
+        return str(agent_output)
+    else:
+        return str(agent_output)
+
+
+def log_submission(task_id, answer, reasoning_trace=None, save_path="submission_log.jsonl"):
+    """
+    Log the task_id and answer for debugging/submission traceability.
+    """
+    entry = {
+        "task_id": task_id,
+        "submitted_answer": answer,
+    }
+    if reasoning_trace:
+        entry["reasoning_trace"] = reasoning_trace
+
+    with open(save_path, "a") as f:
+        f.write(json.dumps(entry) + "\n")