update agent

agent.py

@@ -1,213 +1,120 @@
-"""LangGraph Agent"""
 import os
 from dotenv import load_dotenv
 from langgraph.graph import START, StateGraph, MessagesState
-from langgraph.prebuilt import tools_condition
-from langgraph.prebuilt import ToolNode
+from langgraph.prebuilt import tools_condition, ToolNode
 from langchain_google_genai import ChatGoogleGenerativeAI
 from langchain_groq import ChatGroq
-from langchain_huggingface import ChatHuggingFace, HuggingFaceEndpoint, HuggingFaceEmbeddings
+from langchain_huggingface import ChatHuggingFace, HuggingFaceEndpoint
 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_community.document_loaders import WikipediaLoader, ArxivLoader
 from langchain_core.messages import SystemMessage, HumanMessage
 from langchain_core.tools import tool
-from langchain.tools.retriever import create_retriever_tool
-# from supabase.client import Client, create_client
 
 load_dotenv()
 
+# ------------------- TOOL DEFINITIONS -------------------
+
 @tool
 def multiply(a: int, b: int) -> int:
-    """Multiply two numbers.
-    Args:
-        a: first int
-        b: second int
-    """
+    """Multiply two numbers."""
     return a * b
 
 @tool
 def add(a: int, b: int) -> int:
-    """Add two numbers.
-    
-    Args:
-        a: first int
-        b: second int
-    """
+    """Add two numbers."""
     return a + b
 
 @tool
 def subtract(a: int, b: int) -> int:
-    """Subtract two numbers.
-    
-    Args:
-        a: first int
-        b: second int
-    """
+    """Subtract two numbers."""
     return a - b
 
 @tool
-def divide(a: int, b: int) -> int:
-    """Divide two numbers.
-    
-    Args:
-        a: first int
-        b: second int
-    """
+def divide(a: int, b: int) -> float:
+    """Divide two numbers."""
     if b == 0:
         raise ValueError("Cannot divide by zero.")
     return a / b
 
 @tool
 def modulus(a: int, b: int) -> int:
-    """Get the modulus of two numbers.
-    
-    Args:
-        a: first int
-        b: second int
-    """
+    """Get the modulus of two numbers."""
     return a % b
 
 @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}
+    """Search Wikipedia for a query (max 2 results)."""
+    docs = WikipediaLoader(query=query, load_max_docs=2).load()
+    return "\n\n".join([doc.page_content for doc in docs])
 
 @tool
 def web_search(query: str) -> str:
-    """Search Tavily for a query and return maximum 3 results.
-    
-    Args:
-        query: The search query."""
-    search_docs = TavilySearchResults(max_results=3).invoke(query=query)
-    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 {"web_results": formatted_search_docs}
+    """Search the web using Tavily (max 3 results)."""
+    docs = TavilySearchResults(max_results=3).invoke(query)
+    return "\n\n".join([doc.page_content for doc in docs])
 
 @tool
 def arvix_search(query: str) -> str:
-    """Search Arxiv for a query and return maximum 3 result.
-    
-    Args:
-        query: The search query."""
-    search_docs = ArxivLoader(query=query, load_max_docs=3).load()
-    formatted_search_docs = "\n\n---\n\n".join(
-        [
-            f'<Document source="{doc.metadata["source"]}" page="{doc.metadata.get("page", "")}"/>\n{doc.page_content[:1000]}\n</Document>'
-            for doc in search_docs
-        ])
-    return {"arvix_results": formatted_search_docs}
-
-
-
-# load the system prompt from the file
-with open("system_prompt.txt", "r", encoding="utf-8") as f:
-    system_prompt = f.read()
-
-# System message
+    """Search Arxiv for academic papers (max 3)."""
+    docs = ArxivLoader(query=query, load_max_docs=3).load()
+    return "\n\n".join([doc.page_content[:1000] for doc in docs])
+
+tools = [multiply, add, subtract, divide, modulus, wiki_search, web_search, arvix_search]
+
+# ------------------- SYSTEM PROMPT -------------------
+
+system_prompt_path = "system_prompt.txt"
+if os.path.exists(system_prompt_path):
+    with open(system_prompt_path, "r", encoding="utf-8") as f:
+        system_prompt = f.read()
+else:
+    system_prompt = (
+        "You are an intelligent AI agent who can solve math, science, factual, and research-based problems. "
+        "You can use tools like Wikipedia, Web search, or Arxiv when needed. Always give precise and helpful answers."
+    )
 sys_msg = SystemMessage(content=system_prompt)
 
-# # build a retriever
-# embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-mpnet-base-v2") #  dim=768
-# supabase: Client = create_client(
-#     os.environ.get("SUPABASE_URL"), 
-#     os.environ.get("SUPABASE_SERVICE_KEY"))
-# vector_store = SupabaseVectorStore(
-#     client=supabase,
-#     embedding= embeddings,
-#     table_name="documents",
-#     query_name="match_documents_langchain",
-# )
-# 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 = [
-    multiply,
-    add,
-    subtract,
-    divide,
-    modulus,
-    wiki_search,
-    web_search,
-    arvix_search,
-]
-
-# Build graph function
+# ------------------- GRAPH CONSTRUCTION -------------------
+
 def build_graph(provider: str = "groq"):
-    """Build the graph"""
-    # Load environment variables from .env file
+    """Build the LangGraph with tool-use."""
+    # Select LLM provider
     if provider == "google":
-        # Google Gemini
         llm = ChatGoogleGenerativeAI(model="gemini-2.0-flash", temperature=0)
     elif provider == "groq":
-        # Groq https://console.groq.com/docs/models
-        llm = ChatGroq(model="qwen-qwq-32b", temperature=0) # optional : qwen-qwq-32b gemma2-9b-it
+        llm = ChatGroq(model="qwen-qwq-32b", temperature=0)
     elif provider == "huggingface":
-        # TODO: Add huggingface endpoint
         llm = ChatHuggingFace(
             llm=HuggingFaceEndpoint(
                 url="https://api-inference.huggingface.co/models/Meta-DeepLearning/llama-2-7b-chat-hf",
-                temperature=0,
-            ),
+                temperature=0
+            )
         )
     else:
-        raise ValueError("Invalid provider. Choose 'google', 'groq' or 'huggingface'.")
-    # Bind tools to LLM
+        raise ValueError("Invalid provider")
+
     llm_with_tools = llm.bind_tools(tools)
 
-    # Node
     def assistant(state: MessagesState):
-        """Assistant node"""
-        return {"messages": [llm_with_tools.invoke(state["messages"])]}
-    
-    # def retriever(state: MessagesState):
-    #     """Retriever node"""
-    #     similar_question = vector_store.similarity_search(state["messages"][0].content)
-    #     example_msg = HumanMessage(
-    #         content=f"Here I provide a similar question and answer for reference: \n\n{similar_question[0].page_content}",
-    #     )
-    #     return {"messages": [sys_msg] + state["messages"] + [example_msg]}
+        return {"messages": [sys_msg] + [llm_with_tools.invoke(state["messages"])]}
 
+    # Build the graph with assistant and tools
     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(START, "assistant")
+    builder.add_conditional_edges("assistant", tools_condition)
     builder.add_edge("tools", "assistant")
 
-    # Compile graph
     return builder.compile()
 
-# test
+# ------------------- LOCAL 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?"
-    # Build the graph
+    question = "What is 17 * 23?"
     graph = build_graph(provider="groq")
-    # Run the graph
-    messages = [HumanMessage(content=question)]
-    messages = graph.invoke({"messages": messages})
+    messages = graph.invoke({"messages": [HumanMessage(content=question)]})
+    print("=== AI Agent Response ===")
     for m in messages["messages"]:
         m.pretty_print()