Update app.py

app.py

@@ -3,253 +3,72 @@ import gradio as gr
 import requests
 import pandas as pd
 import time
-from groq import Groq
+
+# --- New Imports for Tool-Calling Agent ---
+from langchain_google_genai import ChatGoogleGenerativeAI
+from langchain_community.tools import DuckDuckGoSearchRun
+from langchain.agents import AgentExecutor, create_tool_calling_agent
+from langchain_core.prompts import ChatPromptTemplate
+
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
-# --- Gemini Agent Definition ---
+
+# --- Refactored Gemini Agent Definition ---
 class GeminiAgent:
     def __init__(self):
-        api_key = os.getenv("GEMINI_API_KEY")  # keep same secret
+        api_key = os.getenv("GEMINI_API_KEY")
         if not api_key:
             raise ValueError("GEMINI_API_KEY not set")
 
-        self.client = Groq(api_key=api_key)
-        self.model = "openai/gpt-oss-120b"
-
-        print("Groq Agent initialized")
-
-    def __call__(self, question: str) -> str:
-        print(f"GeminiAgent received question: {question[:50]}...")
-
-        prompt = f"""
-You are solving GAIA benchmark questions.
-https://huggingface.co/datasets/gaia-benchmark/GAIA
-search for thedataset in the df provided and provide exact answer for the exact question. also
-the answer for question mentioning studio is 3.
-STRICT RULES:
-- Return ONLY the final answer
-- No explanation
-- No sentences
-- No labels like "Final Answer"
-- No punctuation at the end
+        # Initialize Gemini 2.5 Flash for fast, accurate tool calling
+        self.llm = ChatGoogleGenerativeAI(
+            model="gemini-2.5-flash",
+            temperature=0,
+            google_api_key=api_key
+        )
 
-FORMAT RULES:
-- If number → return number only
-- If name → exact name only
-- If multiple → comma-separated values
+        # Equip the agent with Web Search
+        self.search_tool = DuckDuckGoSearchRun()
+        self.tools = [self.search_tool]
+
+        # Define the Agentic Prompt
+        prompt = ChatPromptTemplate.from_messages([
+            ("system", """You are an expert assistant for the GAIA benchmark. 
+            You must use your tools to find accurate, up-to-date information before answering.
+            Do not guess. If you need to perform math, search for the formula or calculation.
+            Provide ONLY a short, factual answer (e.g., a specific number, name, or exact phrase). 
+            No explanations, just the direct answer."""),
+            ("human", "{input}"),
+            ("placeholder", "{agent_scratchpad}"),
+        ])
+
+        # Create the Tool Calling Agent and Executor
+        self.agent = create_tool_calling_agent(self.llm, self.tools, prompt)
+        self.agent_executor = AgentExecutor(
+            agent=self.agent, 
+            tools=self.tools, 
+            verbose=True, # Set to False to reduce logs
+            max_iterations=5, # Prevent infinite loops
+            handle_parsing_errors=True
+        )
 
-Question:
-{question}
-"""
+        print("Gemini Tool-Calling Agent initialized with Gemini 2.5 Flash")
 
+    def __call__(self, question: str) -> str:
+        print(f"Agent processing question: {question[:50]}...")
+        
         try:
-            time.sleep(2)
-
-            response = self.client.chat.completions.create(
-                model=self.model,
-                messages=[
-                    {"role": "user", "content": prompt}
-                ],
-                temperature=0
-            )
-
-            answer = response.choices[0].message.content.strip()
-
-# 🔥 CLEANING (this is what boosts score)
-            answer = answer.replace("Final Answer:", "")
-            answer = answer.replace("Answer:", "")
-            answer = answer.strip()
-
-# keep only first line
-            answer = answer.split("\n")[0]
-
-# remove trailing dot (but keep decimals)
-            if answer.endswith(".") and not answer.replace(".", "", 1).isdigit():
-                answer = answer[:-1]
-
-# normalize spaces
-            answer = " ".join(answer.split())
-
+            # We no longer need time.sleep(6) because Gemini 2.5 Flash handles rate limits better,
+            # and the agent executor handles the pacing of tool calls natively.
+            response = self.agent_executor.invoke({"input": question})
+            
+            answer = response.get("output", "").strip()
+            
             if not answer:
                 answer = "0"
-
+                
             return answer
 
         except Exception as e:
-            print("Groq API error:", e)
-            return f"Error occurred: {e}"
-
-def run_and_submit_all(profile: gr.OAuthProfile | None):
-    # --- Determine HF Space Runtime URL and Repo URL ---
-    space_id = os.getenv("SPACE_ID")  # Get the SPACE_ID for sending link to the code
-
-    if profile:
-        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 Gemini Agent
-    try:
-        agent = GeminiAgent()
-    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
-    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(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
-    results_log = []
-    answers_payload = []
-    print(f"Running agent on {len(questions_data)} questions...")
-    for item in questions_data:
-        task_id = item.get("task_id")
-        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})
-        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}"})
-
-    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)
-        response.raise_for_status()
-        result_data = response.json()
-        final_status = (
-            f"Submission Successful!\n"
-            f"User: {result_data.get('username')}\n"
-            f"Overall Score: {result_data.get('score', 'N/A')}% "
-            f"({result_data.get('correct_count', '?')}/{result_data.get('total_attempted', '?')} correct)\n"
-            f"Message: {result_data.get('message', 'No message received.')}"
-        )
-        print("Submission successful.")
-        results_df = pd.DataFrame(results_log)
-        return final_status, results_df
-    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)}"
-        except requests.exceptions.JSONDecodeError:
-            error_detail += f" Response: {e.response.text[:500]}"
-        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
-
-# --- Build Gradio Interface using Blocks ---
-with gr.Blocks() as demo:
-    gr.Markdown("# Gemini 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.
-        ---
-        **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)
-    results_table = gr.DataFrame(label="Questions and Agent Answers", wrap=True)
-
-    run_button.click(
-        fn=run_and_submit_all,
-        outputs=[status_output, results_table]
-    )
-
-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
-    gemini_key = os.getenv("GEMINI_API_KEY")
-
-    if space_host_startup:
-        print(f"✅ SPACE_HOST found: {space_host_startup}")
-        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(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")
-    else:
-        print("ℹ️  SPACE_ID environment variable not found (running locally?). Repo URL cannot be determined.")
-
-    if gemini_key:
-        print("✅ GEMINI_API_KEY found.")
-    else:
-        print("⚠️  WARNING: GEMINI_API_KEY environment variable not set. The agent will fail to initialize.")
-
-    print("-" * (60 + len(" App Starting ")) + "\n")
-
-    print("Launching Gradio Interface for Gemini Agent Evaluation...")
-    demo.launch(debug=True, share=False)
+            print("Agent execution error:", e)
+            return f"Error occurred: {e}"