op

app.py

@@ -3,16 +3,18 @@ import gradio as gr
 import requests
 import pandas as pd
 
-from smolagents import CodeAgent, InferenceClientModel
+from smolagents import CodeAgent, HfApiModel, DuckDuckGoSearchTool, PythonInterpreterTool
 
 
-# --- Constants ---
+# -------------------------------------------------------------------
+# Constants
+# -------------------------------------------------------------------
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
 GAIA_SYSTEM_PROMPT = """
 You are solving GAIA level 1 questions.
 
-Return only your answer, which should be a number, or a short phrase with as few words as possible, 
+Return only your answer, which should be a number, or a short phrase with as few words as possible,
 or a comma separated list of numbers and/or strings.
 
 If the answer is a number, return only the number without any units unless specified otherwise.
@@ -22,63 +24,70 @@ Do NOT write 'FINAL ANSWER:' – return only the raw answer.
 """
 
 
+# -------------------------------------------------------------------
+# smolagents-based GAIA Agent
+# -------------------------------------------------------------------
+class SmolGaiaAgent:
     """
     Wraps a smolagents CodeAgent so that we can call it like a simple function:
-    answer = agent(question).
+        answer = agent(question)
     """
 
     def __init__(self):
         print("Initializing SmolGaiaAgent...")
 
-        # 1) Model via Hugging Face Inference Router
-        # Add HF_TOKEN as a secret in the Space settings if the model requires auth
-        self.model = InferenceClientModel(
-            model_id="Qwen/Qwen2.5-Coder-32B-Instruct",
-            api_key=os.getenv("HF_TOKEN"),   # can be None for fully public models
-        )
+        # 1) Model: use default HfApiModel (Qwen2.5-Coder via router.huggingface.co)
+        # If you have a token, set it as HF_TOKEN in the Space secrets – HfApiModel picks it up.
+        self.model = HfApiModel()
+
+        # 2) Tools: web search + python interpreter
+        self.tools = [
+            DuckDuckGoSearchTool(),
+            PythonInterpreterTool(),
+        ]
 
-        # 2) CodeAgent with default toolbox (DuckDuckGoSearchTool, PythonInterpreterTool, Transcriber)
-        # IMPORTANT: Pass system_prompt during initialization, not during run()
+        # 3) CodeAgent
+        # NOTE: name must be a valid Python identifier (no dashes, not a keyword)
         self.agent = CodeAgent(
-            tools=[],                # we'll rely on add_base_tools
-            add_base_tools=True,     # gives search + python + speech tools
+            tools=self.tools,
             model=self.model,
             max_steps=8,
             name="gaia_code_agent",
-            description="Agent that uses web search and python to solve GAIA level 1 questions.",
-            system_prompt=GAIA_SYSTEM_PROMPT,  # FIX: Add system_prompt here
+            description="Agent that uses web search and Python to solve GAIA level 1 questions.",
         )
 
     def __call__(self, question: str) -> str:
         """
         Runs the CodeAgent on one question and returns the final answer string.
+        We inline the GAIA system prompt into the user message instead of using a
+        `system_prompt` kwarg (not supported in MultiStepAgent.run()).
         """
-        print(f"[SmolGaiaAgent] Question: {question[:80]}...")
-        # FIX: Remove system_prompt parameter from run()
-        answer = self.agent.run(question)
+        print(f"[SmolGaiaAgent] Question (first 80 chars): {question[:80]}...")
+        prompt = f"{GAIA_SYSTEM_PROMPT.strip()}\n\nQuestion:\n{question}"
+        answer = self.agent.run(prompt)
         answer = str(answer).strip()
         print(f"[SmolGaiaAgent] Answer: {answer}")
         return answer
 
 
-def run_and_submit_all(request: gr.Request):
+# -------------------------------------------------------------------
+# Evaluation + Submission Logic (from the course template)
+# -------------------------------------------------------------------
+def run_and_submit_all(profile: gr.OAuthProfile | None):
     """
-    Fetches all questions, runs the BasicAgent on them, submits all answers,
+    Fetches all questions, runs the SmolGaiaAgent on them, submits all answers,
     and displays the results.
     """
-    # Get the user from the request object
-    # FIX: Changed from profile parameter to request parameter
-    profile = request.username if hasattr(request, 'username') and request.username else None
-    
-    space_id = os.getenv("SPACE_ID")
+    # --- 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 not profile:
+    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
 
-    username = profile
-    print(f"User logged in: {username}")
-
     api_url = DEFAULT_API_URL
     questions_url = f"{api_url}/questions"
     submit_url = f"{api_url}/submit"
@@ -89,9 +98,10 @@ def run_and_submit_all(request: gr.Request):
     except Exception as e:
         print(f"Error instantiating agent: {e}")
         return f"Error initializing agent: {e}", None
-    
+
+    # Link to this Space's code (shown on leaderboard)
     agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
-    print(agent_code)
+    print(f"Agent code link: {agent_code}")
 
     # 2. Fetch Questions
     print(f"Fetching questions from: {questions_url}")
@@ -100,21 +110,21 @@ def run_and_submit_all(request: gr.Request):
         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("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
+        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
+    # 3. Run your Agent on each question
     results_log = []
     answers_payload = []
     print(f"Running agent on {len(questions_data)} questions...")
@@ -126,22 +136,42 @@ def run_and_submit_all(request: gr.Request):
             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})
+            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}"})
+            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}'..."
+    # 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
+    # 5. Submit to scoring API
     print(f"Submitting {len(answers_payload)} answers to: {submit_url}")
     try:
         response = requests.post(submit_url, json=submission_data, timeout=60)
@@ -185,7 +215,9 @@ def run_and_submit_all(request: gr.Request):
         return status_message, results_df
 
 
-# --- Build Gradio Interface using Blocks ---
+# -------------------------------------------------------------------
+# Gradio UI
+# -------------------------------------------------------------------
 with gr.Blocks() as demo:
     gr.Markdown("# Basic Agent Evaluation Runner")
     gr.Markdown(
@@ -198,8 +230,8 @@ with gr.Blocks() as demo:
 
         ---
         **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 basic setup and is intentionally sub-optimal to encourage you to develop your own, more robust solution.
         """
     )
 
@@ -207,16 +239,22 @@ with gr.Blocks() as demo:
 
     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)
+    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]
+        outputs=[status_output, results_table],
     )
 
+
 if __name__ == "__main__":
-    print("\n" + "-"*30 + " App Starting " + "-"*30)
+    print("\n" + "-" * 30 + " App Starting " + "-" * 30)
     space_host_startup = os.getenv("SPACE_HOST")
     space_id_startup = os.getenv("SPACE_ID")
 
@@ -229,11 +267,14 @@ if __name__ == "__main__":
     if space_id_startup:
         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")
+        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(
+            "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)
+    demo.launch(debug=True, share=False)