Update app.py

app.py

@@ -2,67 +2,282 @@ import os
 import gradio as gr
 import requests
 import pandas as pd
+import time
 
-# --- Updated Imports for Modern LangChain (v1.0+) ---
-from langchain_google_genai import ChatGoogleGenerativeAI
-from langchain_community.tools import DuckDuckGoSearchRun
-from langgraph.prebuilt import create_react_agent
-from langchain_core.messages import SystemMessage
+# --- Built-in Tool: Wikipedia Search using standard 'requests' ---
+def search_wikipedia(query: str) -> str:
+    """A simple search tool using the Wikipedia API without extra libraries."""
+    print(f"  -> Tool Executing Search for: {query}")
+    url = "https://en.wikipedia.org/w/api.php"
+    params = {
+        "action": "query",
+        "format": "json",
+        "list": "search",
+        "srsearch": query,
+        "utf8": 1,
+        "srlimit": 3  # Return top 3 snippets
+    }
+    try:
+        response = requests.get(url, params=params, timeout=5)
+        data = response.json()
+        snippets = [item['snippet'].replace('<span class="searchmatch">', '').replace('</span>', '') for item in data['query']['search']]
+        if not snippets:
+            return "Observation: No results found."
+        return "Observation: " + " | ".join(snippets)
+    except Exception as e:
+        return f"Observation: Search error - {e}"
 
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
-# --- Modern LangGraph Gemini Agent ---
-class GeminiAgent:
+# --- Vanilla Gemini ReAct Agent Definition ---
+class GeminiReActAgent:
     def __init__(self):
-        api_key = os.getenv("GEMINI_API_KEY")
-        if not api_key:
+        self.api_key = os.getenv("GEMINI_API_KEY")
+        if not self.api_key:
             raise ValueError("GEMINI_API_KEY not set")
+        
+        # Direct REST API endpoint for Gemini 2.5 Flash
+        self.url = f"https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash:generateContent?key={self.api_key}"
+        print("Vanilla ReAct Gemini Agent initialized.")
 
-        # Initialize Gemini 2.5 Flash
-        self.llm = ChatGoogleGenerativeAI(
-            model="gemini-2.5-flash",
-            temperature=0,
-            google_api_key=api_key
-        )
-
-        # Equip the agent with Web Search
-        self.search_tool = DuckDuckGoSearchRun()
-        self.tools = [self.search_tool]
-
-        # Define the System Prompt
-        system_prompt = """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."""
-
-        # Create the LangGraph Agent (replaces AgentExecutor)
-        self.agent_executor = create_react_agent(
-            self.llm, 
-            self.tools,
-            state_modifier=SystemMessage(content=system_prompt)
-        )
-
-        print("LangGraph Agent initialized with Gemini 2.5 Flash")
+    def call_gemini(self, history) -> str:
+        """Helper to make direct HTTP requests to the Gemini API."""
+        payload = {
+            "contents": history,
+            "generationConfig": {
+                "temperature": 0.0,
+                # Tell Gemini to stop generating when it's time for an observation
+                "stopSequences": ["Observation:"] 
+            }
+        }
+        try:
+            response = requests.post(self.url, json=payload, timeout=20)
+            response.raise_for_status()
+            data = response.json()
+            return data["candidates"][0]["content"]["parts"][0]["text"].strip()
+        except Exception as e:
+            print(f"Gemini API Error: {e}")
+            if hasattr(e, 'response') and e.response is not None:
+                print(e.response.text)
+            return "Error"
 
     def __call__(self, question: str) -> str:
         print(f"Agent processing question: {question[:50]}...")
         
-        try:
-            # LangGraph expects input formatted as a list of messages
-            response = self.agent_executor.invoke({
-                "messages": [("user", question)]
-            })
+        system_instruction = """You are an expert assistant for the GAIA benchmark. 
+You must provide a short, factual, direct answer. No explanations.
+You have access to a Wikipedia search tool to find current facts.
+
+To use the tool, you MUST output exactly this format:
+Thought: <your reasoning>
+Action: Search
+Action Input: <search query>
+
+If you know the answer or have found it from the search, output exactly:
+Thought: <final reasoning>
+Final Answer: <the short, direct answer>"""
+
+        # Initialize conversation state
+        history = [
+            {"role": "user", "parts": [{"text": system_instruction + "\n\nQuestion: " + question}]}
+        ]
+
+        # The ReAct Loop (Max 5 iterations to prevent infinite loops)
+        for iteration in range(5):
+            time.sleep(1) # Pace requests to respect API limits
             
-            # The final answer is the content of the last message in the sequence
-            answer = response["messages"][-1].content.strip()
+            reply = self.call_gemini(history)
             
-            if not answer:
-                answer = "0"
-                
-            return answer
+            if reply == "Error":
+                return "0"
 
+            # Add model's reply to history
+            history.append({"role": "model", "parts": [{"text": reply}]})
+
+            # 1. Check if the model arrived at the final answer
+            if "Final Answer:" in reply:
+                answer = reply.split("Final Answer:")[-1].strip()
+                return answer if answer else "0"
+            
+            # 2. Check if the model wants to use the Search tool
+            elif "Action: Search" in reply and "Action Input:" in reply:
+                query_lines = [line for line in reply.split('\n') if "Action Input:" in line]
+                if query_lines:
+                    query = query_lines[0].split("Action Input:")[-1].strip()
+                    observation = search_wikipedia(query)
+                    
+                    # Feed the search results back into the model's context
+                    history.append({"role": "user", "parts": [{"text": observation}]})
+                    continue
+            
+            # 3. Fallback if the model breaks formatting
+            else:
+                history.append({
+                    "role": "user", 
+                    "parts": [{"text": "Format error. Please use 'Action: Search' or 'Final Answer:'"}]
+                })
+        
+        # Fallback if loops exhaust
+        return "0"
+
+def run_and_submit_all(profile: gr.OAuthProfile | None):
+    # --- Determine HF Space Runtime URL and Repo URL ---
+    space_id = os.getenv("SPACE_ID") 
+
+    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 Agent
+    try:
+        agent = GeminiReActAgent()
+    except Exception as e:
+        print(f"Error instantiating agent: {e}")
+        return f"Error initializing agent: {e}", None
+
+    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("Agent execution error:", e)
-            return f"Error occurred: {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)
+    space_host_startup = os.getenv("SPACE_HOST")
+    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")
+    else:
+        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")
+    else:
+        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 Gemini Agent Evaluation...")
+    demo.launch(debug=True, share=False)