Create GaiaAgent and use it to answer the GAIA questions

app.py

@@ -1,23 +1,113 @@
 import os
 import gradio as gr
 import requests
-import inspect
 import pandas as pd
 
+from smolagents import (
+    CodeAgent,
+    DuckDuckGoSearchTool,
+    LiteLLMModel,
+    ToolCallingAgent,
+)
+
+from tools.text_inspector_tool import TextInspectorTool
+from tools.text_web_browser import (
+    ArchiveSearchTool,
+    FinderTool,
+    FindNextTool,
+    PageDownTool,
+    PageUpTool,
+    SimpleTextBrowser,
+    VisitTool,
+)
+from tools.visual_qa import visualizer
+
+
 # (Keep Constants as is)
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
-# --- Basic Agent Definition ---
+# --- Gaia Agent Definition ---
 # ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
-class BasicAgent:
-    def __init__(self):
-        print("BasicAgent initialized.")
+class GaiaAgent:
+    def __init__(self, model_id: str = "o3"):
+        self._model = self._create_model(model_id)
+        self._text_limit = 100000
+        text_webbrowser_agent = self._create_text_webbrowser_agent()
+        self._manager_agent = CodeAgent(
+            model=self._model,
+            tools=[visualizer, TextInspectorTool(self._model, self._text_limit)],
+            max_steps=12,
+            verbosity_level=2,
+            additional_authorized_imports=["*"],
+            planning_interval=4,
+            managed_agents=[text_webbrowser_agent],
+        )
+
+        print("GaiaAgent initialized.")
+
+    def _create_model(self, model_id):
+        custom_role_conversions = {"tool-call": "assistant", "tool-response": "user"}
+        model_params = {
+            "model_id": model_id,
+            "custom_role_conversions": custom_role_conversions,
+            "max_completion_tokens": 8192,
+            "reasoning_effort": "high",
+        }
+        return LiteLLMModel(**model_params)
+    
+    def _create_text_webbrowser_agent(self):
+        user_agent = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/119.0.0.0 Safari/537.36 Edg/119.0.0.0"
+
+        BROWSER_CONFIG = {
+            "viewport_size": 1024 * 5,
+            "downloads_folder": "downloads_folder",
+            "request_kwargs": {
+                "headers": {"User-Agent": user_agent},
+                "timeout": 300,
+            },
+            "serpapi_key": os.getenv("SERPAPI_API_KEY"),
+        }
+
+        os.makedirs(f"./{BROWSER_CONFIG['downloads_folder']}", exist_ok=True)
+
+        browser = SimpleTextBrowser(**BROWSER_CONFIG)
+        WEB_TOOLS = [
+            DuckDuckGoSearchTool(),
+            VisitTool(browser),
+            PageUpTool(browser),
+            PageDownTool(browser),
+            FinderTool(browser),
+            FindNextTool(browser),
+            ArchiveSearchTool(browser),
+            TextInspectorTool(self._model, self._text_limit),
+        ]
+        text_webbrowser_agent = ToolCallingAgent(
+            model=self._model,
+            tools=WEB_TOOLS,
+            max_steps=20,
+            verbosity_level=2,
+            planning_interval=4,
+            name="search_agent",
+            description="""A team member that will search the internet to answer your question.
+        Ask him for all your questions that require browsing the web.
+        Provide him as much context as possible, in particular if you need to search on a specific timeframe!
+        And don't hesitate to provide him with a complex search task, like finding a difference between two webpages.
+        Your request must be a real sentence, not a google search! Like "Find me this information (...)" rather than a few keywords.
+        """,
+            provide_run_summary=True,
+        )
+        text_webbrowser_agent.prompt_templates["managed_agent"]["task"] += """You can navigate to .txt online files.
+        If a non-html page is in another format, especially .pdf or a Youtube video, use tool 'inspect_file_as_text' to inspect it.
+        Additionally, if after some searching you find out that you need more information to answer the question, you can use `final_answer` with your request for clarification as argument to request for more information."""
+
+        return text_webbrowser_agent
+    
     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
+        answer = self._manager_agent.run(question)
+        print(f"Agent returning fixed answer: {answer}")
+        return answer
 
 def run_and_submit_all( profile: gr.OAuthProfile | None):
     """
@@ -38,9 +128,13 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
     questions_url = f"{api_url}/questions"
     submit_url = f"{api_url}/submit"
 
+    # 0. Create the model
+    
+
+
     # 1. Instantiate Agent ( modify this part to create your agent)
     try:
-        agent = BasicAgent()
+        agent = GaiaAgent()
     except Exception as e:
         print(f"Error instantiating agent: {e}")
         return f"Error initializing agent: {e}", None