gthjk

app.py

@@ -1,86 +1,103 @@
 import os
-import gradio as gr
 import requests
 import pandas as pd
+import gradio as gr
 
-from smolagents import CodeAgent, InferenceClientModel
+from smolagents import CodeAgent
+from smolagents.models import HfApiModel
+from smolagents.tools import 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, 
-or a comma separated list of numbers and/or strings.
+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.
+If the answer is a number, return only the number without any units unless
+specified otherwise.
 If the answer is a string, don't include articles, and don't use abbreviations.
 If the answer is a comma separated list, apply the above rules to each element.
 Do NOT write 'FINAL ANSWER:' – return only the raw answer.
-"""
+""".strip()
 
 
-# --- Basic Agent Definition ---
+# -------------------------------------------------------------------
+# Smolagents-based GAIA Agent
+# -------------------------------------------------------------------
 class SmolGaiaAgent:
     """
-    Wraps a smolagents CodeAgent so that we can call it like a simple function:
-    answer = agent(question).
+    Simple wrapper around a smolagents CodeAgent so we can call it like:
+
+        answer = agent(question)
     """
 
-    def __init__(self):
+    def __init__(self) -> None:
         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(
+        # 1) Model via Hugging Face Inference (router.huggingface.co under the hood)
+        # If HF_TOKEN is set as a Space secret, it will be used; otherwise the
+        # HfApiModel will try to use the default HF auth.
+        self.model = HfApiModel(
             model_id="Qwen/Qwen2.5-Coder-32B-Instruct",
-            api_key=os.getenv("HF_TOKEN"),   # can be None for fully public models
+            token=os.getenv("HF_TOKEN"),  # safe even if None
         )
 
-        # 2) CodeAgent with default toolbox (DuckDuckGoSearchTool, PythonInterpreterTool, Transcriber)
-        # IMPORTANT: Pass system_prompt during initialization, not during run()
+        # 2) Tools: web search + python execution
+        tools = [
+            DuckDuckGoSearchTool(),
+            PythonInterpreterTool(),
+        ]
+
+        # 3) CodeAgent – IMPORTANT:
+        #    * `name` must be a valid Python identifier (no dashes).
+        #    * `system_prompt` is passed here, NOT to `.run(...)`
         self.agent = CodeAgent(
-            tools=[],                # we'll rely on add_base_tools
-            add_base_tools=True,     # gives search + python + speech tools
+            tools=tools,
             model=self.model,
+            system_prompt=GAIA_SYSTEM_PROMPT,
             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.",
+            add_base_tools=False,
         )
 
     def __call__(self, question: str) -> str:
         """
-        Runs the CodeAgent on one question and returns the final answer string.
+        Run the CodeAgent on a single question and return the final answer.
         """
         print(f"[SmolGaiaAgent] Question: {question[:80]}...")
-        # FIX: Remove system_prompt parameter from run()
+        # MultiStepAgent.run() in the course infra DOES NOT accept `system_prompt`,
+        # so we only pass the question here.
         answer = self.agent.run(question)
-        answer = str(answer).strip()
-        print(f"[SmolGaiaAgent] Answer: {answer}")
-        return answer
+        answer_str = str(answer).strip()
+        print(f"[SmolGaiaAgent] Answer: {answer_str}")
+        return answer_str
 
 
-def run_and_submit_all(request: gr.Request):
+# -------------------------------------------------------------------
+# Evaluation / Submission logic (kept close to template)
+# -------------------------------------------------------------------
+def run_and_submit_all(profile: gr.OAuthProfile | None):
     """
-    Fetches all questions, runs the BasicAgent on them, submits all answers,
-    and displays the results.
+    Fetch all questions, run the SmolGaiaAgent on them, submit all answers,
+    and display 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")  # Used to build link to this Space's 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"
@@ -91,9 +108,10 @@ 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 your codebase (shown on leaderboard)
     agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
-    print(agent_code)
+    print(f"Agent code URL: {agent_code}")
 
     # 2. Fetch Questions
     print(f"Fetching questions from: {questions_url}")
@@ -102,16 +120,17 @@ 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
+    except ValueError as e:
+        # JSON decode error
+        print(f"Error decoding JSON response from questions endpoint: {e}")
+        print(f"Response text (first 500 chars): {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
@@ -120,27 +139,51 @@ def run_and_submit_all(request: gr.Request):
     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})
+            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 "
+        f"for user '{username}'..."
+    )
     print(status_update)
 
     # 5. Submit
@@ -149,37 +192,43 @@ def run_and_submit_all(request: gr.Request):
         response = requests.post(submit_url, json=submission_data, timeout=60)
         response.raise_for_status()
         result_data = response.json()
+
         final_status = (
-            f"Submission Successful!\n"
+            "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"({result_data.get('correct_count', '?')}/"
+            f"{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:
+        except ValueError:
             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)
@@ -187,21 +236,27 @@ 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(
         """
         **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.
+        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 you click the submit button, it can take quite some time (the agent
+        has to go through all the questions). This space is intentionally
+        minimal to encourage you to improve it.
         """
     )
 
@@ -209,16 +264,19 @@ 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)
-
-    run_button.click(
-        fn=run_and_submit_all,
-        outputs=[status_output, results_table]
+    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)
+    print("\n" + "-" * 30 + " App Starting " + "-" * 30)
     space_host_startup = os.getenv("SPACE_HOST")
     space_id_startup = os.getenv("SPACE_ID")
 
@@ -231,11 +289,12 @@ 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?).")
 
+    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)