skeleton

README.md

@@ -12,4 +12,39 @@ hf_oauth: true
 hf_oauth_expiration_minutes: 480
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+
+# Modular Agent Evaluation Template
+
+This project provides a modular, production-ready template for evaluating agents using the Hugging Face Unit 4 Evaluation API.
+
+## Architecture
+
+- `app.py`: Gradio UI and orchestration
+- `agent.py`: Agent logic (extend `BaseAgent`)
+- `api.py`: API interaction and error handling
+- `requirements.txt`: Dependencies
+
+## Setup
+
+```bash
+pip install -r requirements.txt
+python app.py
+```
+
+## Usage
+
+1. Log in with your Hugging Face account in the UI.
+2. Click "Run Evaluation & Submit All Answers" to evaluate and submit.
+3. Extend `agent.py` to implement your own agent logic.
+
+## Extending the Agent
+
+- Edit `agent.py` and subclass `BaseAgent`.
+- Implement the `__call__` method to generate answers for questions.
+
+## Troubleshooting
+
+- Ensure all dependencies are installed.
+- Check API availability and network connection.
+- Review error messages in the UI for guidance.

agent.py

@@ -0,0 +1,9 @@
+class BaseAgent:
+    """Base class for all agents. Override __call__ to implement agent logic."""
+    def __call__(self, question: str) -> str:
+        raise NotImplementedError("Agent must implement __call__ method.")
+
+class ExampleAgent(BaseAgent):
+    """A simple agent that returns a fixed answer for demonstration purposes."""
+    def __call__(self, question: str) -> str:
+        return "42" 

api.py

@@ -0,0 +1,43 @@
+import requests
+
+class APIClient:
+    """Handles all API interactions with error handling."""
+    def __init__(self, base_url):
+        self.base_url = base_url.rstrip('/')
+
+    def get_questions(self):
+        """Fetch the full list of evaluation questions."""
+        try:
+            resp = requests.get(f"{self.base_url}/questions", timeout=10)
+            resp.raise_for_status()
+            return resp.json()
+        except Exception as e:
+            raise RuntimeError(f"Failed to fetch questions: {e}")
+
+    def get_random_question(self):
+        """Fetch a single random question."""
+        try:
+            resp = requests.get(f"{self.base_url}/random-question", timeout=10)
+            resp.raise_for_status()
+            return resp.json()
+        except Exception as e:
+            raise RuntimeError(f"Failed to fetch random question: {e}")
+
+    def get_file(self, task_id):
+        """Download a specific file associated with a given task ID."""
+        try:
+            resp = requests.get(f"{self.base_url}/files/{task_id}", timeout=20)
+            resp.raise_for_status()
+            return resp.content
+        except Exception as e:
+            raise RuntimeError(f"Failed to fetch file for task {task_id}: {e}")
+
+    def submit(self, username, agent_code, answers):
+        """Submit agent answers and return the result."""
+        data = {"username": username, "agent_code": agent_code, "answers": answers}
+        try:
+            resp = requests.post(f"{self.base_url}/submit", json=data, timeout=60)
+            resp.raise_for_status()
+            return resp.json()
+        except Exception as e:
+            raise RuntimeError(f"Failed to submit answers: {e}") 

app.py

@@ -1,107 +1,57 @@
 import os
 import gradio as gr
-import requests
-import inspect
 import pandas as pd
+from agent import ExampleAgent
+from api import APIClient
 
 # (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):
+def run_and_submit_all(profile: gr.OAuthProfile | None):
     """
-    Fetches all questions, runs the BasicAgent on them, submits all answers,
-    and displays the results.
+    Fetches all questions, runs the ExampleAgent on them, submits all answers,
+    and displays the results. Uses modular agent and API logic.
     """
-    # --- Determine HF Space Runtime URL and Repo URL ---
-    space_id = os.getenv("SPACE_ID") # Get the SPACE_ID for sending link to the code
-
+    space_id = os.getenv("SPACE_ID")
     if profile:
-        username= f"{profile.username}"
-        print(f"User logged in: {username}")
+        username = f"{profile.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)
+    api = APIClient(DEFAULT_API_URL)
+    agent = ExampleAgent()
     agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
-    print(agent_code)
 
-    # 2. Fetch Questions
-    print(f"Fetching questions from: {questions_url}")
+    # Fetch questions
     try:
-        response = requests.get(questions_url, timeout=15)
-        response.raise_for_status()
-        questions_data = response.json()
+        questions_data = api.get_questions()
         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
+            return "Fetched questions list is empty or invalid format.", 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
+    # Run 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}"})
+            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}")
+    # Submit answers
     try:
-        response = requests.post(submit_url, json=submission_data, timeout=60)
-        response.raise_for_status()
-        result_data = response.json()
+        result_data = api.submit(username.strip(), agent_code, answers_payload)
         final_status = (
             f"Submission Successful!\n"
             f"User: {result_data.get('username')}\n"
@@ -109,40 +59,15 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
             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
+        return f"Submission Failed: {e}", results_df
 
-
-# --- Build Gradio Interface using Blocks ---
+# --- Gradio UI ---
 with gr.Blocks() as demo:
-    gr.Markdown("# Basic Agent Evaluation Runner")
+    gr.Markdown("# Modular Agent Evaluation Runner")
     gr.Markdown(
         """
         **Instructions:**
@@ -150,22 +75,16 @@ with gr.Blocks() as demo:
         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.
+        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 modular setup for robust, maintainable solutions.
         """
     )
-
     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]
@@ -192,5 +111,5 @@ if __name__ == "__main__":
 
     print("-"*(60 + len(" App Starting ")) + "\n")
 
-    print("Launching Gradio Interface for Basic Agent Evaluation...")
+    print("Launching Gradio Interface for Modular Agent Evaluation...")
     demo.launch(debug=True, share=False)