Refactor SmolAgent to utilize smolagents.CodeAgent and DuckDuckGoSearchTool for enhanced question answering. Update instructions and model integration, and modify requirements to include necessary packages.

app.py

@@ -1,99 +1,69 @@
 import os
 import gradio as gr
 import requests
-import inspect
 import pandas as pd
-from huggingface_hub import InferenceClient
+from smolagents import CodeAgent, InferenceClientModel, DuckDuckGoSearchTool
+from dotenv import load_dotenv
+
+# Load environment variables
+load_dotenv()
 
-# (Keep Constants as is)
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 HF_TOKEN = os.getenv("HF_TOKEN")
-SYSTEM_PROMPT = """You are a general AI assistant. I will ask you a question. Report your thoughts, and finish your answer with the following template: FINAL ANSWER: [YOUR FINAL ANSWER]. YOUR FINAL ANSWER should be a number OR as few words as possible OR a comma separated list of numbers and/or strings. If you are asked for a number, don't use comma to write your number neither use units such as $ or percent sign unless specified otherwise. If you are asked for a string, don't use articles, neither abbreviations (e.g. for cities), and write the digits in plain text unless specified otherwise. If you are asked for a comma separated list, apply the above rules depending of whether the element to be put in the list is a number or a string."""
-
+INSTRUCTIONS = """Your task is to answer the user's question.
+Return a number OR as few words as possible OR a comma separated list of numbers and/or strings.
+- If you are asked for a number, don't use a comma to write your number, and don't use units like $ or % unless specified otherwise.
+- If you are asked for a string, don't use articles or abbreviations (e.g., for cities), and write digits in plain text unless specified otherwise.
+- If you are asked for a comma-separated list, apply the above rules to each element.
+"""
 
 # --- Smol Agent Definition ---
-# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
 class SmolAgent:
     def __init__(self, hf_token: str):
-        print("Initializing SmolAgent...")
+        print("Initializing SmolAgent with smolagents...")
         if not hf_token:
-            raise ValueError("Hugging Face token not found. Please set HF_TOKEN environment variable in HF Spaces settings.")
-        
-        self.client = InferenceClient(
-            model="HuggingFaceTB/SmolLM-1.7B-Instruct",
+            raise ValueError("Hugging Face token not found. Please set HF_TOKEN environment variable.")
+
+        # Initialize the model
+        model = InferenceClientModel(
+            model_id="meta-llama/Meta-Llama-3-8B-Instruct",
             token=hf_token,
         )
-        print("SmolAgent initialized with direct inference client.")
+
+        # Initialize the agent with tools and instructions
+        self.agent = CodeAgent(
+            tools=[DuckDuckGoSearchTool()],
+            model=model,
+            instructions=INSTRUCTIONS,
+        )
+        print("SmolAgent initialized with CodeAgent and DuckDuckGoSearchTool.")
 
     def __call__(self, question: str) -> str:
         print(f"\n🪐 Running on question:\n{question}\n")
         try:
-            # Use chat completion format which is more reliable
-            messages = [
-                {"role": "system", "content": SYSTEM_PROMPT},
-                {"role": "user", "content": question}
-            ]
-            
-            response = self.client.chat_completion(
-                messages=messages,
-                max_tokens=100,
-                temperature=0.1,
-                stop=["\n"],
-            )
-            
-            # Extract the assistant's response
-            assistant_message = response.choices[0].message.content
-            cleaned_response = assistant_message.strip()
-            
-            print(f"✅ Raw model response:\n{assistant_message}\n")
-            print(f"✅ Cleaned response to submit:\n{cleaned_response}\n")
-            
-            # Parse the response to extract the final answer if it follows the template
-            if "FINAL ANSWER:" in cleaned_response:
-                final_answer_part = cleaned_response.split("FINAL ANSWER:")[1]
-                final_answer = final_answer_part.strip()
-                if final_answer.startswith('[') and final_answer.endswith(']'):
-                    final_answer = final_answer[1:-1]
-                print(f"✅ Extracted final answer: {final_answer}")
-                return final_answer
-            else:
-                print(f"⚠️ No 'FINAL ANSWER:' found, returning cleaned response")
-                return cleaned_response
-                
+            # The CodeAgent's run method returns the final answer directly
+            answer = self.agent.run(question)
+            print(f"✅ Agent's final answer: {answer}")
+            return str(answer) # Ensure the output is a string
         except Exception as e:
             import traceback
             traceback.print_exc()
-            print(f"❌ AGENT ERROR: {e}")
-            # Fallback: try text_generation with different parameters
-            try:
-                print("🔄 Trying fallback text_generation method...")
-                prompt = f"{SYSTEM_PROMPT}\n\nQuestion: {question}\n\nAnswer:"
-                response = self.client.text_generation(
-                    prompt,
-                    max_new_tokens=50,
-                    temperature=0.1,
-                    do_sample=True,
-                    return_full_text=False,
-                )
-                cleaned_response = response.strip()
-                print(f"✅ Fallback response: {cleaned_response}")
-                return cleaned_response
-            except Exception as fallback_error:
-                print(f"❌ Fallback also failed: {fallback_error}")
-                return f"AGENT ERROR: {e}"
+            error_message = f"AGENT ERROR: {e}"
+            print(f"❌ {error_message}")
+            return error_message
 
 
-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,
+    Fetches all questions, runs the SmolAgent 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}"
+        username = f"{profile.username}"
         print(f"User logged in: {username}")
     else:
         print("User not logged in.")
@@ -103,15 +73,15 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
     questions_url = f"{api_url}/questions"
     submit_url = f"{api_url}/submit"
 
-    # 1. Instantiate Agent ( modify this part to create your agent)
+    # 1. Instantiate Agent
     try:
         agent = SmolAgent(hf_token=HF_TOKEN)
     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)
+    print(f"Agent code link: {agent_code}")
 
     # 2. Fetch Questions
     print(f"Fetching questions from: {questions_url}")
@@ -120,16 +90,16 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
         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
@@ -149,14 +119,14 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
             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 
+    # 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)
@@ -212,15 +182,15 @@ with gr.Blocks() as demo:
         """
         **Instructions:**
 
-        1.  This space uses SmolLM-1.7B-Instruct model with direct inference for question answering.
+        1.  This space uses a `smolagents.CodeAgent` with the `meta-llama/Meta-Llama-3-8B-Instruct` model.
         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.
 
         ---
         **Model Information:**
-        - Using: HuggingFaceTB/SmolLM-1.7B-Instruct
-        - Framework: Direct InferenceClient (optimized for single-line answers)
-        - No additional tools (pure reasoning)
+        - Agent: `smolagents.CodeAgent`
+        - Model: `meta-llama/Meta-Llama-3-8B-Instruct`
+        - Tools: `DuckDuckGoSearchTool`
 
         **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).
@@ -262,5 +232,5 @@ if __name__ == "__main__":
 
     print("-"*(60 + len(" App Starting ")) + "\n")
 
-    print("Launching Gradio Interface for Basic Agent Evaluation...")
+    print("Launching Gradio Interface for Smol Agent Evaluation...")
     demo.launch(debug=True, share=False)

requirements.txt

@@ -1,4 +1,7 @@
-huggingface_hub
+-e git+https://github.com/huggingface/transformers.git
 gradio
+python-dotenv
 requests
-pandas
+pandas
+smolagents[toolkit]
+huggingface_hub