Update app.py

app.py

@@ -1,19 +1,43 @@
 import os
+from dotenv import load_dotenv
 import gradio as gr
 import requests
 import inspect
 import pandas as pd
+import re as re
+
 
 # rulo additionally
-from langchain_core.messages import HumanMessage
-from agent import build_graph
+#from langchain_core.messages import HumanMessage
+#from agent import build_graph
+from langgraph.prebuilt import create_react_agent
+from langchain_core.prompts import ChatPromptTemplate
+from langchain_google_genai import ChatGoogleGenerativeAI
+from langchain_community.tools.tavily_search import TavilySearchResults
+from langchain_community.tools import DuckDuckGoSearchResults
+from langgraph.graph import START, StateGraph, MessagesState
+from langchain_core.messages import SystemMessage, HumanMessage
+from langgraph.prebuilt import tools_condition
+from langgraph.prebuilt import ToolNode
+from langchain_core.tools import tool
+from langchain_huggingface import ChatHuggingFace, HuggingFaceEndpoint, HuggingFaceEmbeddings
+from langchain_community.document_loaders import WikipediaLoader
+from langchain_community.document_loaders import ArxivLoader
+
+load_dotenv()
 
-# Rulo
 
 # (Keep Constants as is)
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
+# load the system prompt from the file
+with open("system_prompt.txt", "r", encoding="utf-8") as f:
+    system_prompt = f.read()
+
+# System message
+system_prompt = SystemMessage(content=system_prompt)
+
 # --- Basic Agent Definition ---
 # ----- THIS IS WHERE YOU CAN BUILD WHAT YOU WANT ------
 
@@ -22,17 +46,85 @@ class BasicAgent:
     def __init__(self):
         print("BasicAgent initialized.")
         #self.graph = build_graph("huggingface")
-        self.graph = build_graph()
+        #self.graph = build_graph()
         
     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
         # Wrap the question in a HumanMessage from langchain_core
-        messages = [HumanMessage(content=question)]
-        messages = self.graph.invoke({"messages": messages})
-        answer = messages['messages'][-1].content
+        #messages = [HumanMessage(content=question)]
+        #messages = self.graph.invoke({"messages": messages})
+        #answer = messages['messages'][-1].content
+        #return answer[14:]
+
+class AssignmentAgent:
+    def __init__(self, system_prompt):
+        #if "ANTHROPIC_API_KEY" not in os.environ:
+        #  raise Exception("No Anthropic API key in environment")
         
+        """
+        llm = ChatAnthropic(
+            model="claude-3-5-sonnet-20240620",
+            temperature=0,
+            max_tokens=1024,
+            timeout=None,
+            max_retries=2
+        )
+        """
+
+        llm = ChatGoogleGenerativeAI(
+            model="gemini-2.0-flash", 
+            temperature=0,
+            max_retries=2,
+        )
+        #llm = ChatGoogleGenerativeAI(model="gemini-1.5-flash", temperature=0)
+
+        
+        web_search = DuckDuckGoSearchResults()
+
+        @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}
+
+        tools =[
+            web_search,
+            wiki_search,
+        ]
+            
+        agent = create_react_agent(llm, tools, prompt=system_prompt)
+        self.llm = llm
+        self.tool = tool    
+        self.agent = agent
+        print("AssignmentAgent initialized.")
+    
+    def __call__(self, question: str) -> str:
+        print(f"AssignmentAgent received question (first 50 chars): {question[:50]}...")
+        # Wrap the question in a HumanMessage from Langchain_core
+        messages = [HumanMessage(content=question)]
+        result = self.agent.invoke({"messages":messages})
+        #pattern = re.compile(".*<answer>(.*)</answer>")
+        #regex_result = pattern.search(result['messages'][-1].content)
+        #answer = regex_result.group(1)
+        #print(f"AssignmentAgent returning answer: {answer}")
+        #return answer
+        answer = result['messages'][-1].content
         return answer[14:]
-                
+          
         
 def run_and_submit_all( profile: gr.OAuthProfile | None):
     """