Update app.py

app.py

@@ -3,21 +3,133 @@ import gradio as gr
 import requests
 import inspect
 import pandas as pd
+from langchain_google_genai import ChatGoogleGenerativeAI
+from langgraph.graph import StateGraph, MessagesState, START
+from langchain_core.messages import SystemMessage, HumanMessage
+from langchain_community.document_loaders import WikipediaLoader
+from langchain_community.tools import TavilySearchResults, DuckDuckGoSearchRun
+from dotenv import load_dotenv
+import operator
+from typing import Annotated
+from typing_extensions import TypedDict
 
+load_dotenv()
 # (Keep Constants as is)
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
+SYSTEM_MESSAGE = """You are a general AI assistant. I will ask you a question. Report your thoughts, and finish your answer with the following template:[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.
+"""
+
 # --- Basic Agent Definition ---
 # ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
 class BasicAgent:
-    def __init__(self):
+    def __init__(self, graph):
+        self.graph = graph
         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
+        input_state = {"question": question}
+        # Run the graph
+        answer = self.graph.invoke(input_state)
+        print(f"Agent returning fixed answer: {answer}")
+        return answer
+
+class State(TypedDict):
+    question: str
+    answer: str
+    context: Annotated[list, operator.add]
+
+    def search_tavily(state):
+    
+        """ Retrieve docs from web search """
+
+        # Search
+        tavily_search = TavilySearchResults(max_results=2)
+        search_docs = tavily_search.invoke(state['question'])
+
+         # Format
+        formatted_search_docs = "\n\n---\n\n".join(
+            [
+                f'<Document href="{doc["url"]}"/>\n{doc["content"]}\n</Document>'
+                for doc in search_docs
+            ]
+        )
+
+        return {"context": [formatted_search_docs]}
+
+    def search_wikipedia(state):
+    
+    """ Retrieve docs from wikipedia """
+
+        # Search
+        search_docs = WikipediaLoader(query=state['question'], 
+                                  load_max_docs=2).load()
+
+         # Format
+        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 {"context": [formatted_search_docs]}
+
+    def search_DuckDuckGo(state):
+
+        """ Retrive answer from DuckDuckGoSearch."""
+
+        ddg_search = DuckDuckGoSearchRun(max_results=2)
+        search_docs = ddg_search.invoke(state['question'])
+
+         # Format
+        formatted_search_docs = "\n\n---\n\n".join(
+            [
+                f'<Document href="{doc["url"]}"/>\n{doc["content"]}\n</Document>'
+                for doc in search_docs
+            ]
+        )
+
+        return {"context": [formatted_search_docs]}
+
+    def generate_answer(state):
+
+        """Node to give answer to the question"""
+
+        context = state["context"]
+        question = state["question"]
+
+        additional_context_template = """Here are some contexts about the question you can use if you find it helpful: {context}"""
+        additional_context = additional_context_template.format(context=context)
+        final_instruction = SYSTEM_MESSAGE + additional_context
+
+        #answer
+        answer = llm.invoke([SystemMessage(content=final_instruction)] + [HumanMessage(content=f"Answer the question: {question}")])
+
+        # Append it to state
+        return {"answer": answer}
+
+
+builder = StateGraph(State)
+
+builder.add_node("search_tavily",search_tavily)
+builder.add_node("search_wikipedia", search_wikipedia)
+builder.add_node("search_DuckDuckGo", search_DuckDuckGo)
+builder.add_node("generate_answer", generate_answer)
+
+builder.add_edge(START, "search_wikipedia")
+builder.add_edge(START, "search_tavily")
+builder.add_edge(START, "search_DuckDuckGo")
+builder.add_edge("search_wikipedia", "generate_answer")
+builder.add_edge("search_tavily", "generate_answer")
+builder.add_edge("search_DuckDuckGo", "generate_answer")
+graph = builder.compile()
+
 
 def run_and_submit_all( profile: gr.OAuthProfile | None):
     """
@@ -40,7 +152,7 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
 
     # 1. Instantiate Agent ( modify this part to create your agent)
     try:
-        agent = BasicAgent()
+        agent = BasicAgent(graph)
     except Exception as e:
         print(f"Error instantiating agent: {e}")
         return f"Error initializing agent: {e}", None