created the agent

app.py

@@ -1,34 +1,212 @@
 import os
 import gradio as gr
 import requests
-import inspect
 import pandas as pd
+from langchain.agents import create_agent
+from langchain_google_genai import ChatGoogleGenerativeAI
+from langchain_openai import ChatOpenAI
+from langchain.tools import tool
+from dotenv import load_dotenv
+from langchain_community.document_loaders import ArxivLoader, WikipediaLoader
+from ddgs import DDGS
+
+# Load environment variables
+load_dotenv()
 
-# (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 ------
-class BasicAgent:
+# --- Agent Setup ---
+openai_key = os.getenv("OPENAI_API_KEY")
+googleai_key = os.getenv("GOOGLE_API_KEY")
+
+# Initialize the model
+model = ChatGoogleGenerativeAI(
+    model="gemini-2.5-flash",
+    temperature=0,
+    max_tokens=5000,
+    timeout=None,
+    max_retries=2,
+)
+
+# --- Tools Definition ---
+@tool
+def multiply(a: int, b: int) -> int:
+    """Multiply two numbers.
+    Args:
+        a: first int
+        b: second int
+    """
+    return a * b
+
+@tool
+def add(a: int, b: int) -> int:
+    """Add two numbers.
+    
+    Args:
+        a: first int
+        b: second int
+    """
+    return a + b
+
+@tool
+def subtract(a: int, b: int) -> int:
+    """Subtract two numbers.
+    
+    Args:
+        a: first int
+        b: second int
+    """
+    return a - b
+
+@tool
+def divide(a: int, b: int) -> int:
+    """Divide two numbers.
+    
+    Args:
+        a: first int
+        b: second int
+    """
+    if b == 0:
+        raise ValueError("Cannot divide by zero.")
+    return a / b
+
+@tool
+def modulus(a: int, b: int) -> int:
+    """Get the modulus of two numbers.
+    
+    Args:
+        a: first int
+        b: second int
+    """
+    return a % b
+
+@tool
+def wiki_search(query: str) -> str:
+    """Search Wikipedia for a query and return maximum 2 results.
+    
+    Args:
+        query: The search query."""
+    search_docs = WikipediaLoader(query=query, load_max_docs=2).load()
+    formatted_search_docs = "\n\n---\n\n".join(
+        [
+            f'<Document source="{doc.metadata["source"]}" page="{doc.metadata.get("page", "")}"/>\n{doc.page_content}\n</Document>'
+            for doc in search_docs
+        ])
+    return {"wiki_results": formatted_search_docs}
+
+@tool
+def web_search(query: str) -> str:
+    """Search DDGS for a query and return maximum 3 results.
+    
+    Args:
+        query: The search query."""
+    search_docs = DDGS().text(query,max_results=3)
+    formatted_search_docs = "\n\n---\n\n".join(
+        [
+            f'Title:{doc["title"]}\nContent:{doc["body"]}\n--\n'
+            for doc in search_docs
+        ])
+    return formatted_search_docs
+
+@tool
+def arvix_search(query: str) -> str:
+    """Search Arxiv for a query and return maximum 3 result.
+    
+    Args:
+        query: The search query."""
+    search_docs = ArxivLoader(query=query, load_max_docs=3).load()
+    formatted_search_docs = "\n\n---\n\n".join(
+        [
+            f'<Document source="{doc.metadata["source"]}" page="{doc.metadata.get("page", "")}"/>\n{doc.page_content[:1000]}\n</Document>'
+            for doc in search_docs
+        ])
+    return {"arvix_results": formatted_search_docs}
+
+@tool
+def image_search(query: str) -> str:
+    """Searches DDGS for an image query and returns maximum 10 image results"""
+    search_images = DDGS().images(query=query)
+    formatted_result = "\n\n---\n\n".join(
+        [
+            f'Image Title:{image["title"]}\nImage URL: {image["url"]}'
+            for image in search_images
+        ])
+
+
+# Tools list
+tools = [
+    multiply, add, subtract, divide, modulus,
+    wiki_search, web_search, arvix_search, image_search
+]
+
+# System prompt
+sys_prompt = """You are a helpful agent, please provide clear and concise answers to asked questions.
+Keep your word limit for answers as minimum as you can. You are equipped with the following tools:
+1. [multiply], [add], [subtract], [divide], [modulus] - basic calculator operations.
+2. [wiki_search] - search Wikipedia and return up to 2 documents as text.
+3. [web_search] - perform a web search and return up to 3 documents as text.
+4. [arxiv_search] - search arXiv and return up to 3 documents as text.
+5. [image_search] - Searches the internet for an image query and returns maximum 10 image results
+
+Under any circumstances, if you fail to provide the accurate answer expected by the user, you may say the same to the user and provide a similar answer which is approximately the closest. Disregard spelling mistakes and provide answer with results retreived from the correct spelling. 
+
+For every tool you use, append a single line at the end of your response exactly in this format:
+[TOOLS USED: (tool_name)]
+When no tools are used, append:
+[TOOLS USED WERE NONE]"""
+
+# --- Agent Class ---
+class GAIAAgent:
     def __init__(self):
-        print("BasicAgent initialized.")
+        print("GAIAAgent initialized with LangChain agent.")
+        try:
+            self.agent = create_agent(model, tools=tools, system_prompt=sys_prompt)
+            print("Agent created successfully.")
+        except Exception as e:
+            print(f"Error creating agent: {e}")
+            raise
+    
     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
+        print(f"Agent received question (first 100 chars): {question[:100]}...")
+        try:
+            result = self.agent.invoke({
+                "messages": [{"role": "user", "content": question}]
+            })
+            
+            # Get the content from the last message
+            raw_content = result["messages"][-1].content
+            
+            # Parse the response format: list of dicts with 'text' key
+            if isinstance(raw_content, list) and len(raw_content) > 0:
+                if isinstance(raw_content[0], dict) and 'text' in raw_content[0]:
+                    answer = raw_content[0]['text']
+                else:
+                    # Fallback: convert list to string
+                    answer = str(raw_content)
+            elif isinstance(raw_content, str):
+                answer = raw_content
+            else:
+                answer = str(raw_content)
+            
+            print(f"Agent returning answer (first 100 chars): {answer[:100]}...")
+            return answer
+        except Exception as e:
+            print(f"Error in agent execution: {e}")
+            import traceback
+            traceback.print_exc()
+            return f"Error: {str(e)}"
 
-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,
+    Fetches all questions, runs the GAIAAgent 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.")
@@ -38,15 +216,16 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
     questions_url = f"{api_url}/questions"
     submit_url = f"{api_url}/submit"
 
-    # 1. Instantiate Agent ( modify this part to create your agent)
+    # 1. Instantiate Agent
     try:
-        agent = BasicAgent()
+        agent = GAIAAgent()
     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)
+    
+    # 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" if space_id else "Local"
+    print(f"Agent code location: {agent_code}")
 
     # 2. Fetch Questions
     print(f"Fetching questions from: {questions_url}")
@@ -55,16 +234,16 @@ 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
@@ -73,26 +252,40 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
     results_log = []
     answers_payload = []
     print(f"Running agent on {len(questions_data)} questions...")
-    for item in questions_data:
+    for idx, item in enumerate(questions_data, 1):
         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
+        
+        print(f"Processing question {idx}/{len(questions_data)} - Task ID: {task_id}")
         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})
+            results_log.append({
+                "Task ID": task_id,
+                "Question": question_text[:100] + "..." if len(question_text) > 100 else question_text,
+                "Submitted Answer": submitted_answer[:200] + "..." if len(submitted_answer) > 200 else 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[:100] + "..." if len(question_text) > 100 else 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}
+    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)
 
@@ -142,28 +335,29 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
 
 # --- Build Gradio Interface using Blocks ---
 with gr.Blocks() as demo:
-    gr.Markdown("# Basic Agent Evaluation Runner")
+    gr.Markdown("# GAIA Benchmark Agent Evaluation")
     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.
+        1. This app integrates a LangChain agent with multiple tools (calculator, Wikipedia, web search, Arxiv).
+        2. Log in to your Hugging Face account using the button below.
+        3. Click 'Run Evaluation & Submit All Answers' to fetch GAIA questions, run your agent, and submit answers.
+        
+        **Agent Tools:**
+        - Mathematical operations (add, subtract, multiply, divide, modulus)
+        - Wikipedia search
+        - Web search (Tavily)
+        - Arxiv academic paper search
+        
+        **Note:** Processing all questions may take several minutes depending on the number of questions and API response times.
         """
     )
 
     gr.LoginButton()
 
-    run_button = gr.Button("Run Evaluation & Submit All Answers")
+    run_button = gr.Button("Run Evaluation & Submit All Answers", variant="primary")
 
     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(
@@ -173,9 +367,12 @@ 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
+    
+    # Check for required environment variables
     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")
+    google_api_key = os.getenv("GOOGLE_API_KEY")
+    tavily_api_key = os.getenv("TAVILY_API_KEY")
 
     if space_host_startup:
         print(f"✅ SPACE_HOST found: {space_host_startup}")
@@ -183,14 +380,24 @@ 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(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("ℹ️  SPACE_ID environment variable not found (running locally?).")
+
+    if google_api_key:
+        print("✅ GOOGLE_API_KEY found")
+    else:
+        print("⚠️  GOOGLE_API_KEY not found - agent will not work without it!")
+
+    if tavily_api_key:
+        print("✅ TAVILY_API_KEY found")
+    else:
+        print("⚠️  TAVILY_API_KEY not found - web search will not work!")
 
     print("-"*(60 + len(" App Starting ")) + "\n")
 
-    print("Launching Gradio Interface for Basic Agent Evaluation...")
+    print("Launching Gradio Interface for GAIA Agent Evaluation...")
     demo.launch(debug=True, share=False)