1) add agent, tool, and system prompt

Agents/agent.py

@@ -0,0 +1,115 @@
+import os
+from Tools.tools import webSearch, arxivSearch, wikiSearch,add,multiply,divide,substract, remainder
+from langchain_core.messages import SystemMessage, HumanMessage
+from dotenv import load_dotenv
+from supabase.client import Client, create_client
+from langchain_groq import ChatGroq
+from langgraph.graph import START, StateGraph, MessagesState
+from langgraph.prebuilt import ToolNode, tools_condition
+from langchain_huggingface import ChatHuggingFace, HuggingFaceEndpoint, HuggingFaceEmbeddings
+from langchain.tools.retriever import create_retriever_tool
+from langchain_community.vectorstores import SupabaseVectorStore
+from langfuse.langchain import CallbackHandler
+
+load_dotenv()
+
+langfuse_handler = CallbackHandler()
+
+with open("Prompt/SystemPrompt.txt","r",encoding="utf-8") as f:
+    systemPrompt = f.read()
+print(systemPrompt)
+
+sysMsg = SystemMessage(content=systemPrompt)
+
+embeddings = HuggingFaceEmbeddings(
+    model_name = "sentence-transformers/all-mpnet-base-v2"
+)
+
+supabase: Client = create_client(
+    os.environ.get("SUPABASE_URL"),os.environ.get("SUPABASE_SERVICE_KEY")
+)
+
+vector_store = SupabaseVectorStore(
+    client=supabase,
+    embeddings=embeddings,
+    table_name="documents",
+    query_name="match_documents",
+)
+
+create_retriever_tool = create_retriever_tool(
+    retriever=vector_store.as_retriever(),
+    name="Question Search",
+    description="A tool to retrieve similar questions from a vector store.",
+)
+
+tools = [
+    webSearch,
+    wikiSearch,
+    arxivSearch,
+    multiply,
+    add,
+    substract,
+    divide,
+    remainder
+]
+
+def build_graph(provider: str="groq"):
+    if provider== "groq":
+        llm=ChatGroq(model="qwen/qwen3-32b",temperature=0)
+    elif provider == "huggingface":
+        llm = ChatHuggingFace(
+            llm=HuggingFaceEndpoint(
+                repo_id="TinyLlama/TinyLlama-1.1B-Chat-v1.0",
+                task="text-generation",
+                max_new_tokens=1024,
+                do_sample=False,
+                repetition_penalty=1.03,
+                temperature=0,
+            ),
+            verbose=True,
+        )
+    else:
+        raise ValueError("Invalid Provider. Choose 'groq or 'huggingface'")
+    llmWithTools = llm.bind_tools(tools)
+
+    def assistant(state: MessagesState):
+        return {"message": [llmWithTools.invoke(state["messages"])]}
+    
+    def retriever(state: MessagesState):
+        similiarQuestion = vector_store.similarity_search(state["message"][0].content)
+
+        if similiarQuestion:
+            exampleMessage = HumanMessage(
+                content=f"Here i provide a similiar question and answer for reference: \n\n{similiarQuestion[0].page_content}",
+            )
+            return {"messages": [sysMsg] + state["messages"] + [exampleMessage]}
+        else:
+            return {"message": [sysMsg] + state["messages"]}
+        
+    builder = StateGraph(MessagesState)
+    builder.add_node("retriever",retriever)
+    builder.add_node("assistant",assistant)
+    builder.add_node("tools", ToolNode(tools))
+    builder.add_edge(START,"retriever")
+    builder.add_edge("retriever","assistant")
+    builder.add_conditional_edges(
+        "assistant",
+        tools_condition,
+    )
+    builder.add_edge("tools","assistant")
+    return builder.compile()
+
+
+#test
+if __name__ == "__main__":
+    question = "When was a picture of St. Thomas Aquinas first added to the wikipedia page on the principle of double effect?"
+    graph = build_graph(provider="groq")
+    messages = [HumanMessage(content=question)]
+    messages = graph.invoke(
+        input= {"messages": messages},
+        config={"callbacks": [langfuse_handler]}
+    )
+    graph.get_graph().draw_mermaid_png()
+
+    for m in messages["messages"]:
+        m.pretty_print()

Prompts/SystemPrompt.txt

@@ -0,0 +1,5 @@
+You are a helpful assistant tasked with answering question using sets of tools.
+Now i will ask you a question. Report your thoughts 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. 

Tools/tools.py

@@ -0,0 +1,104 @@
+from langchain_community.tools.tavily_search import TavilySearchResults
+from langchain_community.document_loaders import WikipediaLoader
+from langchain_community.document_loaders import ArxivLoader
+from langchain_community.vectorstores import SupabaseVectorStore
+from langchain_core.messages import SystemMessage, HumanMessage
+from langchain_core.tools import tool
+from langchain.tools.retriever import create_retriever_tool
+
+@tool
+def add(a: int, b:int) -> int:
+    """ add two integer 
+    Args:
+        a: first integer
+        b: second integer
+    """
+    return a + b
+
+@tool
+def substract(a: int, b:int) -> int:
+    """ substract two integer
+    Args:
+        a : first integer
+        b : second integer
+    """
+    return a - b
+
+@tool
+def multiply(a: int, b: int) -> int:
+    """multiply two integer
+    Args:
+        a: first integer
+        b: second integer
+    """
+    return a * b
+
+@tool
+def divide(a: int, b: int) -> int:
+    """ divide two integer
+    args:
+        a: first integer
+        b: second integer
+    """
+    return a / b
+
+@tool
+def remainder(a: int, b: int) -> int:
+    """ left over of division
+    args: 
+        a: first integer
+        b: second integer
+    """
+    return a % b
+
+@tool
+def wikiSearch(searchQuery:str) -> str:
+    """ search wikipedia to get three matching results
+    
+    args: 
+        searchQuery: the search query
+    """
+    search_results = WikipediaLoader(query=searchQuery, load_max_docs=3).load()
+    formatted_results = "\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_results
+        ])
+    return {"wiki_results": formatted_results}
+
+@tool
+def arxivSearch(searchQuery:str) -> str:
+    """
+        search arxiv to get three matching results
+
+        args:
+            searchQuery: the search query
+    """ 
+    search_results = ArxivLoader(query=searchQuery, load_max_docs=3).load()
+    formatted_results = "\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_results
+        ])
+    return {"arxiv_result": formatted_results}
+
+@tool
+def webSearch(searchQuery:str) -> str:
+    """
+      search the web using Tavily to get three matching results
+
+      args: 
+        searchQuery: search query
+    """
+    search_results = TavilySearchResults(max_results=3).invoke(query=searchQuery)
+    formatted_results = "\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_results
+        ]
+    )
+    return {"web_search": formatted_results}
+
+
+
+    

agent.py

@@ -0,0 +1,8 @@
+from tools import webSearch, arxivSearch, wikiSearch,add,multiply,divide,substract, remainder
+from dotenv import load_dotenv
+
+load_dotenv()
+
+
+
+

app.py

@@ -3,21 +3,29 @@ import gradio as gr
 import requests
 import inspect
 import pandas as pd
+from langchain_core.messages import HumanMessage
+from agent import build_graph
+from langfuse.langchain import CallbackHandler
 
 # (Keep Constants as is)
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
+langfuse_handler = CallbackHandler()
 
 # --- Basic Agent Definition ---
 # ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
 class BasicAgent:
     def __init__(self):
         print("BasicAgent initialized.")
+        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
+        messages = [HumanMessage(content=question)]
+        messages = self.graph.invoke({"messages": messages})
+        messages = self.graph.invoke({"messages": messages},config={"callbacks": [langfuse_handler]})
+        self.graph.get_graph().draw_mermaid_png()
+        answer = messages['messages'][-1].content
+        return answer[14:]
 
 def run_and_submit_all( profile: gr.OAuthProfile | None):
     """