Update app.py

app.py

@@ -3,32 +3,107 @@ import gradio as gr
 import requests
 import inspect
 import pandas as pd
+from dotenv import load_dotenv
+from openai import OpenAI
+from tenacity import retry, stop_after_attempt, wait_exponential
+
+# Load environment variables
+load_dotenv()
 
 # (Keep Constants as is)
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
+OPENAI_MODEL = "openai/gpt-4.1-nano"  # or "gpt-3.5-turbo" based on your preference
+
 
 # --- Basic Agent Definition ---
 # ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
 class BasicAgent:
     def __init__(self):
-        print("BasicAgent initialized.")
+        """Initialize the agent with OpenAI client and setup."""
+        print("BasicAgent initializing...")
+        self.client = OpenAI(api_key="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",base_url="https://models.github.ai/inference")
+        if not os.getenv("OPENAI_API_KEY"):
+            raise ValueError("OPENAI_API_KEY environment variable is not set")
+        print("BasicAgent initialized successfully.")
+
+    @retry(
+        stop=stop_after_attempt(3), wait=wait_exponential(multiplier=1, min=4, max=10)
+    )
+    def _get_completion(self, prompt: str) -> str:
+        """Get completion from OpenAI with retry logic."""
+        try:
+            response = self.client.chat.completions.create(
+                model=OPENAI_MODEL,
+                messages=[
+                    {
+                        "role": "system",
+                        "content": """You are a helpful AI assistant designed to answer questions from the GAIA benchmark. 
+                     Follow these guidelines:
+                     1. Provide clear, concise, and accurate answers
+                     2. If a question requires specific steps or calculations, show them clearly
+                     3. Format your response in a clean, readable way
+                     4. Be precise and avoid ambiguity
+                     5. If you're not completely sure about an answer, state your confidence level
+                     Remember: Your answers will be evaluated through exact matching.""",
+                    },
+                    {"role": "user", "content": prompt},
+                ],
+                temperature=0.2,  # Lower temperature for more consistent outputs
+                max_tokens=1000,
+            )
+            return response.choices[0].message.content.strip()
+        except Exception as e:
+            print(f"Error in OpenAI API call: {e}")
+            raise
+
+    def _preprocess_question(self, question: str) -> str:
+        """Preprocess the question to enhance clarity and context."""
+        enhanced_prompt = f"""Please analyze and answer the following question from the GAIA benchmark.
+        Question: {question}
+
+        Provide a clear, specific answer that can be evaluated through exact matching.
+        If the question requires multiple steps, please show your reasoning but ensure the final answer is clearly stated.
+        """
+        return enhanced_prompt
+
     def __call__(self, question: str) -> str:
+        """Process the question and return an answer."""
         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):
+        try:
+            # Preprocess the question
+            enhanced_prompt = self._preprocess_question(question)
+
+            # Get completion from OpenAI
+            response = self._get_completion(enhanced_prompt)
+
+            # Extract the final answer
+            # If the response contains multiple lines or explanations,
+            # we'll try to extract just the final answer
+            answer_lines = response.strip().split("\n")
+            final_answer = answer_lines[-1].strip()
+
+            # Log the response for debugging
+            print(f"Agent generated answer: {final_answer[:100]}...")
+
+            return final_answer
+
+        except Exception as e:
+            print(f"Error processing question: {e}")
+            return f"Error: {str(e)}"
+
+
+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")  # 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.")
@@ -55,16 +130,16 @@ 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
@@ -81,18 +156,36 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
             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}
+    # 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)
 
@@ -162,20 +255,19 @@ 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)
+    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)
     # 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}")
@@ -183,14 +275,18 @@ 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)
+    demo.launch(debug=True, share=False)