Changed temporarily to llmagent as model in multiagent not available

app.py

@@ -16,27 +16,30 @@ import phoenix as px
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
+
 # --- Basic Agent Definition ---
 # ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
 class BasicAgent:
     def __init__(self):
         print("BasicAgent initialized.")
+
     def __call__(self, question: str) -> str:
         print(f"Agent received question (first 50 chars): {question[:50]}...")
         fixed_answer = "This is a default answer."
         print(f"Agent returning fixed answer: {fixed_answer}")
         return fixed_answer
 
-def run_and_submit_all( profile: gr.OAuthProfile | None, limit: int | None):
+
+def run_and_submit_all(profile: gr.OAuthProfile | None, limit: int | 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")  # Get the SPACE_ID for sending link to the code
 
     if profile:
-        username= f"{profile.username}"
+        username = f"{profile.username}"
         print(f"User logged in: {username}")
     else:
         print("User not logged in.")
@@ -49,7 +52,7 @@ def run_and_submit_all( profile: gr.OAuthProfile | None, limit: int | None):
 
     # 1. Instantiate Agent ( modify this part to create your agent)
     try:
-        agent = MultiAgent()
+        agent = LLMOnlyAgent()
     except Exception as e:
         print(f"Error instantiating agent: {e}")
         return f"Error initializing agent: {e}", None
@@ -64,7 +67,7 @@ def run_and_submit_all( profile: gr.OAuthProfile | None, limit: int | None):
         print("Fetching questions from local file")
         with open("data/questions.json", "r") as f:
             questions_data = json.load(f)
-            questions_data = [q for q in questions_data if q['task_id'] in task_ids]
+            questions_data = [q for q in questions_data if q["task_id"] in task_ids]
     # Otherwise fetch from Hugging Face API
     else:
         print(f"Fetching questions from: {questions_url}")
@@ -99,20 +102,38 @@ def run_and_submit_all( profile: gr.OAuthProfile | None, limit: int | None):
         task_id = item.get("task_id")
         file_name = item.get("file_name")
         if file_name != "":
-           file_path = f"{files_url}/{task_id}"
-           question_text = item.get("question") + "The mentionned file can be downloaded from the following link: " + file_path
+            file_path = f"{files_url}/{task_id}"
+            question_text = (
+                item.get("question")
+                + "The mentionned file can be downloaded from the following link: "
+                + file_path
+            )
         else:
-           question_text = item.get("question")
+            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.")
@@ -136,21 +157,29 @@ def run_and_submit_all( profile: gr.OAuthProfile | None, limit: int | None):
         # Log evaluations to Phoenix
         log_evaluations_to_phoenix(evaluations_df)
 
-        print(f"Ground truth comparison completed: {summary_stats['exact_matches']}/{summary_stats['total_questions']} exact matches")
+        print(
+            f"Ground truth comparison completed: {summary_stats['exact_matches']}/{summary_stats['total_questions']} exact matches"
+        )
 
     except Exception as e:
         print(f"Error during ground truth comparison: {e}")
         summary_stats = {"error": str(e)}
 
     # 4. Prepare Submission
-    submission_data = {"username": username.strip(), "agent_code": agent_code, "answers": answers_payload}
+    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}'..."
 
     # Add ground truth comparison to status
     if "error" not in summary_stats:
         status_update += f"\n\nGround Truth Comparison:\n"
         status_update += f"Exact matches: {summary_stats['exact_matches']}/{summary_stats['total_questions']} ({summary_stats['exact_match_rate']:.1%})\n"
-        status_update += f"Average similarity: {summary_stats['average_similarity']:.3f}\n"
+        status_update += (
+            f"Average similarity: {summary_stats['average_similarity']:.3f}\n"
+        )
         status_update += f"Contains correct answer: {summary_stats['contains_matches']}/{summary_stats['total_questions']} ({summary_stats['contains_match_rate']:.1%})\n"
         status_update += f"Evaluations logged to Phoenix ✅"
     else:
@@ -224,17 +253,16 @@ 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)
+    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]
-    )
+    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)
 
     # Telemetry
     register()
@@ -242,7 +270,7 @@ if __name__ == "__main__":
 
     # 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")  # Get SPACE_ID at startup
 
     if space_host_startup:
         print(f"✅ SPACE_HOST found: {space_host_startup}")
@@ -250,14 +278,18 @@ if __name__ == "__main__":
     else:
         print("ℹ️  SPACE_HOST environment variable not found (running locally?).")
 
-    if space_id_startup: # Print repo URLs if SPACE_ID is found
+    if space_id_startup:  # Print repo URLs if SPACE_ID is found
         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(
+            "ℹ️  SPACE_ID environment variable not found (running locally?). Repo URL cannot be determined."
+        )
 
-    print("-"*(60 + len(" App Starting ")) + "\n")
+    print("-" * (60 + len(" App Starting ")) + "\n")
 
     print("Launching Gradio Interface for Basic Agent Evaluation...")
     demo.launch(debug=True, share=False)