Update app.py

app.py

@@ -2,10 +2,9 @@ import os
 import re
 import gradio as gr
 import requests
-import inspect
 import pandas as pd
 
-from smolagents import CodeAgent, DuckDuckGoSearchTool, LiteLLMModel
+from smolagents import ToolCallingAgent, DuckDuckGoSearchTool, LiteLLMModel
 
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
@@ -17,33 +16,45 @@ class BasicAgent:
 
         groq_key = os.getenv("GROQ_API_KEY")
         if not groq_key:
-            raise ValueError("GROQ_API_KEY is missing. Add it in Space Settings → Variables and secrets.")
+            raise ValueError(
+                "GROQ_API_KEY is missing. Add it in Space Settings → Variables and secrets."
+            )
 
         model = LiteLLMModel(
-            model_id="groq/llama-3.1-8b-instant",
-            api_key=groq_key
+            model_id="groq/llama-3.3-70b-versatile",
+            api_key=groq_key,
         )
 
-        self.agent = CodeAgent(
-            tools=[DuckDuckGoSearchTool()],
+        self.agent = ToolCallingAgent(
+            tools=[DuckDuckGoSearchTool(max_results=8)],
             model=model,
-            max_steps=8,
+            max_steps=6,
+            name="search_agent",
+            description="Searches the web and returns short exact answers.",
         )
 
     def clean_answer(self, answer: str) -> str:
         answer = str(answer).strip()
 
+        # Remove common unwanted prefixes.
         answer = re.sub(r"(?i)^final answer\s*:\s*", "", answer).strip()
         answer = re.sub(r"(?i)^answer\s*:\s*", "", answer).strip()
         answer = re.sub(r"(?i)^the answer is\s*", "", answer).strip()
 
+        # Remove markdown/code wrapping.
+        answer = answer.replace("```", "").strip()
         answer = answer.strip("`")
         answer = answer.strip('"')
         answer = answer.strip("'")
 
+        # Remove common final-answer phrasing if it appears later.
+        answer = re.sub(r"(?i)final answer\s*:\s*", "", answer).strip()
+
+        # If the model gives multiple lines, prefer the shortest useful final-looking line.
         lines = [line.strip() for line in answer.splitlines() if line.strip()]
         if lines:
-            answer = lines[-1] if len(lines) > 1 and len(lines[-1]) < 80 else lines[0]
+            short_lines = [line for line in lines if len(line) <= 120]
+            answer = short_lines[-1] if short_lines else lines[-1]
 
         return answer.strip()
 
@@ -63,7 +74,9 @@ Rules:
 - If the answer is a name, return only the name.
 - If the answer is a number, return only the number and unit if required.
 - If the answer is a date, use the clearest standard date format.
-- Search the web when needed.
+- Use the search tool when the answer requires factual lookup.
+- If the question can be solved directly by reasoning, solve it directly without search.
+- For comma-separated answers, use exactly this style: item 1, item 2, item 3
 
 Question:
 {question}
@@ -85,8 +98,7 @@ 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
+    space_id = os.getenv("SPACE_ID")
 
     if profile:
         username = f"{profile.username}"
@@ -106,8 +118,6 @@ def run_and_submit_all(profile: gr.OAuthProfile | 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.
     agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
     print(agent_code)
 
@@ -117,22 +127,27 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
         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
+    # 3. Run Agent
     results_log = []
     answers_payload = []
     print(f"Running agent on {len(questions_data)} questions...")
@@ -147,12 +162,14 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
 
         try:
             submitted_answer = agent(question_text)
+
             answers_payload.append(
                 {
                     "task_id": task_id,
                     "submitted_answer": submitted_answer,
                 }
             )
+
             results_log.append(
                 {
                     "Task ID": task_id,
@@ -160,6 +177,7 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
                     "Submitted Answer": submitted_answer,
                 }
             )
+
         except Exception as e:
             print(f"Error running agent on task {task_id}: {e}")
             results_log.append(
@@ -181,7 +199,9 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
         "answers": answers_payload,
     }
 
-    status_update = f"Agent finished. Submitting {len(answers_payload)} answers for user '{username}'..."
+    status_update = (
+        f"Agent finished. Submitting {len(answers_payload)} answers for user '{username}'..."
+    )
     print(status_update)
 
     # 5. Submit
@@ -205,6 +225,7 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
 
     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)}"
@@ -213,24 +234,28 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
 
         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
 
@@ -291,7 +316,9 @@ if __name__ == "__main__":
         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(
+            "ℹ️  SPACE_ID environment variable not found (running locally?). Repo URL cannot be determined."
+        )
 
     print("-" * (60 + len(" App Starting ")) + "\n")