Update app.py

app.py

@@ -1,23 +1,120 @@
 import os
 import gradio as gr
 import requests
-import inspect
 import pandas as pd
+from langchain.agents import AgentExecutor, create_react_agent
+from langchain.tools import tool
+from langchain.prompts import PromptTemplate
+from langchain_openai import ChatOpenAI  # OpenAI-compatible for Groq API
+from ddgs import DDGS  # Updated DuckDuckGo Search
+from dotenv import load_dotenv
+import re
+import json
 
 # (Keep Constants as is)
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
+# --- Define Tools ---
+@tool
+def python_code_executor(code: str) -> str:
+    """Execute Python code and return the result as a string. Use for calculations or data processing."""
+    try:
+        local_vars = {}
+        exec(code, {}, local_vars)
+        return str(local_vars.get("result", "No result defined. Set 'result' variable."))
+    except Exception as e:
+        return f"Error: {str(e)}"
+
+@tool
+def download_file(url: str) -> str:
+    """Download a file from URL and return its content (text if possible)."""
+    try:
+        response = requests.get(url, timeout=10)
+        response.raise_for_status()
+        return response.text[:1000]  # Truncate for brevity
+    except Exception as e:
+        return f"Error downloading: {str(e)}"
+
+@tool
+def duckduckgo_search(query: str) -> str:
+    """Perform a DuckDuckGo search and return top results as a short summary."""
+    try:
+        with DDGS() as ddgs:
+            results = list(ddgs.text(query, max_results=3))
+        if not results:
+            return "No good results found."
+        return json.dumps([{"title": r["title"], "snippet": r["body"]} for r in results])
+    except Exception as e:
+        return f"Search error: {str(e)}"
+        
 # --- 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
+        llm = ChatGoogleGenerativeAI(model="gemini-2.0-flash", temperature=0)
+        tools = [duckduckgo_search, python_code_executor, download_file]
+        # Prompt for short, exact answers (GAIA-style) with required ReAct variables
+        prompt_template = PromptTemplate.from_template("""
+        You are an AI agent solving GAIA benchmark tasks. Use tools if needed (web search, code execution, file download).
+        
+        You have access to the following tools:
+        {tools}
+        
+        Use the following format:
+        
+        Question: the input question you must answer
+        Thought: you should always think about what to do
+        Action: the action to take, should be one of [{tool_names}]
+        Action Input: the input to the action
+        Observation: the result of the action
+        ... (this Thought/Action/Action Input/Observation can repeat N times)
+        Thought: I now know the final answer
+        Final Answer: the final answer to the original input question
+        
+        Begin!
+        
+        Question: {question}
+        File content (if any): {file_content}
+        
+        Reason step-by-step, but return ONLY the final answer as a short string (e.g., a number or phrase). No explanations, no extra text.
+        {agent_scratchpad}
+        """)
+        
+        agent = create_react_agent(llm, tools, prompt_template)
+        self.agent_executor = AgentExecutor(
+            agent=agent,
+            tools=tools,
+            verbose=True,  # Set to False for production to reduce logs
+            max_iterations=10  # Limit for efficiency
+        )
+        
+    def __call__(self, question: str, task_id: str = None, api_url: str = DEFAULT_API_URL) -> str:
+        print(f"Agent processing question: {question[:50]}...")
+        
+        # Fetch file if task involves one
+        file_content = ""
+        if task_id:
+            file_url = f"{api_url}/files/{task_id}"
+            try:
+                response = requests.get(file_url, timeout=10)
+                file_content = response.text[:1000] if response.ok else ""
+            except Exception as e:
+                print(f"File fetch error for {task_id}: {e}")
+                pass
+        
+        try:
+            response = self.agent_executor.invoke({"question": question, "file_content": file_content})
+            # Parse to ensure shortness
+            short_answer = re.search(r'(?s)(.*)', response["output"]).group(1).strip()
+            if len(short_answer) > 50:  # Enforce brevity
+                short_answer = short_answer[:50] + "... (truncated)"
+            print(f"Agent returning short answer: {short_answer}")
+            return short_answer
+        except Exception as e:
+            print(f"Agent error: {e}")
+            return "Error"
 
 def run_and_submit_all( profile: gr.OAuthProfile | None):
     """
@@ -80,7 +177,8 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
             print(f"Skipping item with missing task_id or question: {item}")
             continue
         try:
-            submitted_answer = agent(question_text)
+            #submitted_answer = agent(question_text)
+            submitted_answer = agent(question_text, task_id=task_id)
             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: