Update app.py

app.py

@@ -4,24 +4,20 @@ import requests
 import inspect
 import pandas as pd
 from huggingface_hub import InferenceClient
+import time
+from langchain_core.prompts import PromptTemplate
+from ddgs import DDGS
+import re
 
-# (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 ------
-import os
-from huggingface_hub import InferenceClient
-from langchain_core.prompts import PromptTemplate
-from ddgs import DDGS
-import re
-
 class BasicAgent:
     def __init__(self):
-        print("BasicAgent initialized with Qwen/Qwen3-Next-80B-A3B-Instruct")
+        print("BasicAgent initialized with Qwen/Qwen2.5-72B-Instruct")
         self.client = InferenceClient(
-            model="Qwen/Qwen3-Next-80B-A3B-Instruct",
+            model="Qwen/Qwen2.5-72B-Instruct",
             token=os.getenv("HF_TOKEN")
         )
 
@@ -60,108 +56,96 @@ Question: {question}
 
 Thought:
 """)
-
         full_prompt_start = prompt_template.format(question=question)
-
         max_steps = 6
         history = ""
-
         for step in range(max_steps):
             current_prompt = full_prompt_start + history
-
-            try:
-                generation = self.client.text_generation(
-                    current_prompt,
-                    max_new_tokens=320,
-                    temperature=0.12,
-                    stop_sequences=["Final Answer:", "Observation:"]
-                )
-            except Exception as e:
-                print(f"Generation failed: {e}")
+            new_text = None
+            for attempt in range(3):  # Retry logic
+                try:
+                    messages = [{"role": "user", "content": current_prompt}]
+                    response = self.client.chat_completion(
+                        messages=messages,
+                        max_tokens=320,
+                        temperature=0.12,
+                        stop=["Final Answer:", "Observation:"]
+                    )
+                    new_text = response.choices[0].message.content.strip()
+                    break
+                except Exception as e:
+                    print(f"Attempt {attempt+1} failed: {str(e)}")
+                    if attempt < 2:
+                        time.sleep(5 * (attempt + 1))  # Backoff
+                    else:
+                        return "Generation error after retries"
+            if new_text is None:
                 return "Generation error"
-
-            new_text = generation.strip()
             history += new_text + "\n"
-
             # Look for tool call
             action_match = re.search(
                 r"Action:\s*web_search\s*\[([^\]]+)\]",
                 history,
                 re.IGNORECASE | re.DOTALL
             )
-
             if action_match:
                 query = action_match.group(1).strip()
                 print(f"Tool call → {query}")
                 observation = self.search_web(query)
                 obs_short = observation[:1400] + "..." if len(observation) > 1400 else observation
                 history += f"\nObservation: {obs_short}\nThought: "
-
             # Look for final answer
             if "Final Answer:" in history:
                 parts = history.split("Final Answer:")
                 answer_part = parts[-1].strip()
-                # Take first clean line, remove trailing punctuation if not needed
                 answer = answer_part.split("\n")[0].strip()
                 answer = answer.replace(".", "").replace(",", "").strip()
                 print(f"→ Final answer: {answer}")
                 return answer
-
         print("Max steps reached - no final answer")
         return "Unable to 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.
     """
-    # --- 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.")
         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)
     agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
     print(agent_code)
-
-    # 2. Fetch Questions
     print(f"Fetching questions from: {questions_url}")
     try:
         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("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
     results_log = []
     answers_payload = []
     print(f"Running agent on {len(questions_data)} questions...")
@@ -176,19 +160,14 @@ 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 
     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}")
     try:
         response = requests.post(submit_url, json=submission_data, timeout=60)
@@ -231,33 +210,25 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
         results_df = pd.DataFrame(results_log)
         return status_message, results_df
 
-
 # --- Build Gradio Interface using Blocks ---
 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.
         """
     )
-
     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]
@@ -265,24 +236,19 @@ with gr.Blocks() as demo:
 
 if __name__ == "__main__":
     print("\n" + "-"*30 + " App Starting " + "-"*30)
-    # Check for SPACE_HOST and SPACE_ID at startup for information
     space_host_startup = os.getenv("SPACE_HOST")
-    space_id_startup = os.getenv("SPACE_ID") # Get SPACE_ID at startup
-
+    space_id_startup = os.getenv("SPACE_ID")
     if space_host_startup:
         print(f"✅ SPACE_HOST found: {space_host_startup}")
-        print(f"   Runtime URL should be: https://{space_host_startup}.hf.space")
+        print(f" Runtime URL should be: https://{space_host_startup}.hf.space")
     else:
-        print("ℹ️  SPACE_HOST environment variable not found (running locally?).")
-
-    if space_id_startup: # Print repo URLs if SPACE_ID is found
+        print("ℹ️ SPACE_HOST environment variable not found (running locally?).")
+    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 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")
-
     print("Launching Gradio Interface for Basic Agent Evaluation...")
     demo.launch(debug=True, share=False)