Implement CustomAgent and CustomToolNode; refactor tools and agent initialization

app.py

@@ -4,9 +4,9 @@ import requests
 import inspect
 import pandas as pd
 from langchain_core.messages import HumanMessage, SystemMessage
+from src.
 
-
-from src.my_app import build_graph, get_prompt
+from src.agent import CustomAgent
 import json
 
 # (Keep Constants as is)
@@ -15,22 +15,22 @@ DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
 # --- Basic Agent Definition ---
 # ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
-class BasicAgent:
-    def __init__(self):
-        print("BasicAgent initialized.")
-        self.graph = build_graph()  # Build the state graph for the agent
-    def __call__(self, question: str, task_id: str) -> str:
-        print(f"Agent received question (first 50 chars): {question[:50]}...")
-        system_prompt = SystemMessage(content=get_prompt())
-        messages = self.graph.invoke({
-            "messages": [
-                system_prompt,
-                {"role": "user", "content": question}
-            ],
-        "task_id": task_id
-    })
-        answer = messages['messages'][-1].content
-        return answer[14:]
+# class BasicAgent:
+#     def __init__(self):
+#         print("BasicAgent initialized.")
+#         self.graph = build_graph()  # Build the state graph for the agent
+#     def __call__(self, question: str, task_id: str) -> str:
+#         print(f"Agent received question (first 50 chars): {question[:50]}...")
+#         system_prompt = SystemMessage(content=get_prompt())
+#         messages = self.graph.invoke({
+#             "messages": [
+#                 system_prompt,
+#                 {"role": "user", "content": question}
+#             ],
+#         "task_id": task_id
+#     })
+#         answer = messages['messages'][-1].content
+#         return answer[14:]
 
 def run_and_submit_all( profile: gr.OAuthProfile | None):
     """
@@ -53,7 +53,7 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
 
     # 1. Instantiate Agent ( modify this part to create your agent)
     try:
-        agent = BasicAgent()
+        agent = CustomAgent()
     except Exception as e:
         print(f"Error instantiating agent: {e}")
         return f"Error initializing agent: {e}", None

src/{my_app.py → agent.py}

@@ -1,32 +1,36 @@
 import os
-from typing import List, Dict, Any, Optional
-from langgraph.graph import StateGraph, START, END
-from langchain_openai import ChatOpenAI
-from langchain_core.messages import HumanMessage
 from IPython.display import Image, display
-
-from langchain_openai import AzureChatOpenAI
-from langgraph.prebuilt import ToolNode, tools_condition
-from langgraph.prebuilt import tools_condition
-
-from .tools import reverse_text, is_question_reversed, route_question, avaiable_tools, CustomToolNode
 from langchain_core.messages import SystemMessage
+from langchain_openai import AzureChatOpenAI
+from langgraph.graph import StateGraph, START, END
+from langgraph.prebuilt import  tools_condition
 from .state import State
-# from langgraph.prebuilt import create_react_agent
-from langchain.agents import create_tool_calling_agent
-from langchain_core.runnables import Runnable
+from .custom_tool_node import CustomToolNode
+from .tools import get_avaiable_tools
+
+
+class CustomAgent:
+    def __init__(self):
+        print("CustomAgent initialized.")
+        self.graph = build_graph()  # Build the state graph for the agent
+
+    def __call__(self, question: str, task_id: str) -> str:
+        print(f"Agent received question (first 50 chars): {question[:50]}...")
+        system_prompt = SystemMessage(content=get_prompt())
+        messages = self.graph.invoke({
+            "messages": [
+                system_prompt,
+                {"role": "user", "content": question}
+            ],
+        "task_id": task_id
+    })
+        answer = messages['messages'][-1].content
+        return answer[14:]
 
 
-# llm_with_tools = llm.bind_tools(avaiable_tools, parallel_tool_calls=False)
 def get_prompt() -> str:
     with open("system_prompt.txt", "r", encoding="utf-8") as f:
         return f.read()
-    # return """You are a helpful assistant tasked with answering questions using a set of tools. 
-    #         Now, I will ask you a question. Report your thoughts, show the task_id and finish your answer with the following template: 
-    #         FINAL ANSWER: [YOUR FINAL ANSWER]. 
-    #         YOUR FINAL ANSWER should be a number OR as few words as possible OR a comma separated list of numbers and/or strings. If you are asked for a number, don't use comma to write your number neither use units such as $ or percent sign unless specified otherwise. If you are asked for a string, don't use articles, neither abbreviations (e.g. for cities), and write the digits in plain text unless specified otherwise. If you are asked for a comma separated list, apply the above rules depending of whether the element to be put in the list is a number or a string.
-    #         Your answer should only start with "FINAL ANSWER: ", then follows with the answer. 
-    # """
 
 
 def build_graph():
@@ -39,6 +43,7 @@ def build_graph():
         openai_api_key=os.getenv("AZURE_OPENAI_API_KEY"),
         temperature=0.0,
     )
+    avaiable_tools = get_avaiable_tools()
     llm_with_tools = llm.bind_tools(avaiable_tools)
 
 
@@ -59,8 +64,8 @@ def build_graph():
     graph_builder = StateGraph(State)
 
     # Add nodes
-    graph_builder.add_node("check_question_reversed", is_question_reversed)
-    graph_builder.add_node("reverse_text", reverse_text)
+    # graph_builder.add_node("check_question_reversed", is_question_reversed)
+    # graph_builder.add_node("reverse_text", reverse_text)
     graph_builder.add_node("assistant", assistant)
     tools_dict = {tool.name: tool for tool in avaiable_tools}
 
@@ -100,7 +105,7 @@ if __name__ == "__main__":
     #question = """Examine the video at https://www.youtube.com/watch?v=1htKBjuUWec.\n\nWhat does Teal'c say in response to the question \"Isn't that hot?\""""
     # question = """Hi, I was out sick from my classes on Friday, so I'm trying to figure out what I need to study for my Calculus mid-term next week. My friend from class sent me an audio recording of Professor Willowbrook giving out the recommended reading for the test, but my headphones are broken :(\n\nCould you please listen to the recording for me and tell me the page numbers I'm supposed to go over? I've attached a file called Homework.mp3 that has the recording. Please provide just the page numbers as a comma-delimited list. And please provide the list in ascending order."""
     # question = """The attached Excel file contains the sales of menu items for a local fast-food chain. What were the total sales that the chain made from food (not including drinks)? Express your answer in USD with two decimal places."""
-    question = """What is the first name of the only Malko Competition recipient from the 20th Century (after 1977) whose nationality on record is a country that no longer exists?"""
+    question = """What country had the least number of athletes at the 1928 Summer Olympics? If there's a tie for a number of athletes, return the first in alphabetical order. Give the IOC country code as your answer."""
     task_id = "7bd855d8-463d-4ed5-93ca-5fe35145f733"
     system_prompt = SystemMessage(content=get_prompt())
     messages = react_graph.invoke({

src/custom_tool_node.py

@@ -0,0 +1,45 @@
+
+class CustomToolNode:
+    """Tool node personalizzato che può accedere allo stato completo"""
+    
+    def __init__(self, tools_dict):
+        self.tools_dict = tools_dict
+    
+    def __call__(self, state):
+        messages = state["messages"]
+        last_message = messages[-1]
+        
+        # Estrai i tool calls dall'ultimo messaggio
+        if hasattr(last_message, 'tool_calls') and last_message.tool_calls:
+            results = []
+            for tool_call in last_message.tool_calls:
+                tool_name = tool_call["name"]
+                tool_args = tool_call["args"]
+                
+                # Aggiungi task_id agli argomenti del tool
+                tool_args_with_state = {
+                    **tool_args,
+                    "task_id": state["task_id"],
+                    "state": state  # Opzionale: passa tutto lo stato
+                }
+                
+                if tool_name in self.tools_dict:
+                    try:
+                        result = self.tools_dict[tool_name].invoke(tool_args_with_state)
+                        results.append({
+                            "type": "tool",
+                            "name": tool_name,
+                            "tool_call_id": tool_call["id"],
+                            "content": str(result)
+                        })
+                    except Exception as e:
+                        results.append({
+                            "type": "tool",
+                            "name": tool_name,
+                            "tool_call_id": tool_call["id"],
+                            "content": f"Error: {str(e)}"
+                        })
+            
+            return {"messages": results}
+        
+        return {"messages": []}

src/tools.py

@@ -8,7 +8,7 @@ from dotenv import load_dotenv
 from langchain_openai import AzureChatOpenAI
 from langchain_perplexity import ChatPerplexity
 from langchain_core.tools import tool
-from langchain_community.tools.tavily_search.tool import TavilySearchResults
+from langchain_tavily import TavilySearchResults
 
 from langchain_huggingface import HuggingFaceEndpoint, ChatHuggingFace
 from youtube_transcript_api import YouTubeTranscriptApi
@@ -27,8 +27,6 @@ from .state import State
 
 load_dotenv()
 
-# Set your OpenAI API key here
-# os.environ["OPENAI_API_KEY"] = "sk-xxxxx"  # Replace with your actual API key
 
 # Initialize our LLM
 llm = AzureChatOpenAI(
@@ -142,94 +140,17 @@ def route_question(state: State) -> str:
     else:
         return "question_not_reversed"
     
-# web_search_tool = DuckDuckGoSearchRun()
-web_search_tool = TavilySearchResults()
-arxiv_search_tool = ArxivQueryRun()
-wikipedia_tool = WikipediaQueryRun(api_wrapper=WikipediaAPIWrapper())
 
-
-class CustomToolNode:
-    """Tool node personalizzato che può accedere allo stato completo"""
-    
-    def __init__(self, tools_dict):
-        self.tools_dict = tools_dict
-    
-    def __call__(self, state):
-        messages = state["messages"]
-        last_message = messages[-1]
-        
-        # Estrai i tool calls dall'ultimo messaggio
-        if hasattr(last_message, 'tool_calls') and last_message.tool_calls:
-            results = []
-            for tool_call in last_message.tool_calls:
-                tool_name = tool_call["name"]
-                tool_args = tool_call["args"]
-                
-                # Aggiungi task_id agli argomenti del tool
-                tool_args_with_state = {
-                    **tool_args,
-                    "task_id": state["task_id"],
-                    "state": state  # Opzionale: passa tutto lo stato
-                }
-                
-                if tool_name in self.tools_dict:
-                    try:
-                        result = self.tools_dict[tool_name].invoke(tool_args_with_state)
-                        results.append({
-                            "type": "tool",
-                            "name": tool_name,
-                            "tool_call_id": tool_call["id"],
-                            "content": str(result)
-                        })
-                    except Exception as e:
-                        results.append({
-                            "type": "tool",
-                            "name": tool_name,
-                            "tool_call_id": tool_call["id"],
-                            "content": f"Error: {str(e)}"
-                        })
-            
-            return {"messages": results}
-        
-        return {"messages": []}
-
-
-
-avaiable_tools = [
-    wikipedia_tool,
-    arxiv_search_tool,
-    web_search_tool,
-    get_youtube_transcript,
-    transcript_mp3_audio,
-    load_and_analyze_excel_file
-]
-# response = wikipedia_tool.run("HUNTER X HUNTER")
-# print(response)
-
-# 1) tool_for_fetch_wikipedia_data
-
-# 2) fetch youtube video data
-
-# 3 ) reverse del testo
-
-# 4 ) tool/agente che valuta se la domanda è sensata o è scritta al contrario
-
-# 5) chess-image-to-dict
-
-# 6) chess agent
-
-# 7) general python code execution tool
-
-# 8) get trascript from youtube video
-
-# 9) web-search tool
-
-# 10) fetch page content
-
-# 11) trascribe mp3 audio file
-
-# 12) read mp3 audio file
-
-# 13) Research paper MCP
-
-# 14) read excel file
+def get_avaiable_tools():
+    """Returns a list of available tools."""
+    web_search_tool = TavilySearchResults()
+    arxiv_search_tool = ArxivQueryRun()
+    wikipedia_tool = WikipediaQueryRun(api_wrapper=WikipediaAPIWrapper())
+    return [
+        wikipedia_tool,
+        arxiv_search_tool,
+        web_search_tool,
+        get_youtube_transcript,
+        transcript_mp3_audio,
+        load_and_analyze_excel_file
+    ]