agent.py

# """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 langchain_google_genai import ChatGoogleGenerativeAI
# from langchain_groq import ChatGroq
# from langchain_huggingface import ChatHuggingFace, HuggingFaceEndpoint, HuggingFaceEmbeddings
# 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
# from supabase.client import Client, create_client
# from langchain_core.documents import Document
# #load_dotenv()

# load_dotenv(".env") 

# @tool
# def multiply(a: int, b: int) -> int:
#     """Multiply two numbers.
#     Args:
#         a: first int
#         b: second int
#     """
#     return a * b

# @tool
# def add(a: int, b: int) -> int:
#     """Add two numbers.
    
#     Args:
#         a: first int
#         b: second int
#     """
#     return a + b

# @tool
# def subtract(a: int, b: int) -> int:
#     """Subtract two numbers.
    
#     Args:
#         a: first int
#         b: second int
#     """
#     return a - b

# @tool
# def divide(a: int, b: int) -> int:
#     """Divide two numbers.
    
#     Args:
#         a: first int
#         b: second int
#     """
#     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
#     """
#     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}

# @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}

# @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
# 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"))
# supabase_url = os.getenv("SUPABASE_URL")
# supabase_key = os.getenv("SUPABASE_KEY")

# if not supabase_url or not supabase_key:
#     raise ValueError("SUPABASE_URL and SUPABASE_KEY must be set in environment variables.")

# supabase: Client = create_client(supabase_url, supabase_key)
# docs = [Document(page_content="This is a test about AI.")]
# vector_store = SupabaseVectorStore(
#     client=supabase,  # should be your `supabase` client instance
#     embedding=embeddings,
#     table_name="documents",
#     query_name="match_documents_langchain",
# )

# # Add documents
# vector_store.add_documents(docs)

# print("🔍 Testing similarity_search with: 'What is AI?'")
# results = vector_store.similarity_search("What is AI?")
# print(f"✅ Got {len(results)} results.")
# if results:
#     print("First result content:\n", results[0].page_content)
# 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
# def build_graph(provider: str = "groq"):
#     """Build the graph"""
#     # Load environment variables from .env file
#     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
#     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,
#             ),
#         )
#     else:
#         raise ValueError("Invalid provider. Choose 'google', 'groq' or 'huggingface'.")
#     # Bind tools to LLM
#     llm_with_tools = llm.bind_tools(tools)

#     def assistant(state: MessagesState):
#         """Assistant node"""
#         print("\n🧠 Final prompt to model:")
#         for m in state["messages"]:
#             print(f"{m.type.upper()}: {m.content[:300]}...\n")  # truncate for readability
        
#         response = llm_with_tools.invoke(state["messages"])
        
#         print("💬 Model response:", response.content[:500], "\n")
#         return {"messages": [response]}

#     # 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]}

#     def retriever(state: MessagesState):
#         """Retriever node"""
#         messages = state.get("messages", [])
#         if not messages:
#             print("⚠️ No messages received in retriever node.")
#             return {"messages": []}
        
#         query = messages[0].content
#         print(f"\n🔍 Query to vector store: {query}")
        
#         try:
#             similar_question = vector_store.similarity_search(query)
#         except Exception as e:
#             print(f"❌ similarity_search failed: {e}")
#             return {"messages": messages}
        
#         if not similar_question:
#             print("⚠️ No similar questions found.")
#             return {"messages": messages}
        
#         print(f"✅ Found {len(similar_question)} similar question(s).")
#         print("📄 First retrieved doc:\n", similar_question[0].page_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] + messages + [example_msg]}




#     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")

#     # Compile graph
#     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?"
#     # Build the graph
#     graph = build_graph(provider="groq")
#     # Run the graph
#     messages = [HumanMessage(content=question)]
#     messages = graph.invoke({"messages": messages})
#     for m in messages["messages"]:
#         m.pretty_print()

"""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 langchain_google_genai import ChatGoogleGenerativeAI
from langchain_groq import ChatGroq
from langchain_huggingface import ChatHuggingFace, HuggingFaceEndpoint, HuggingFaceEmbeddings
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
from supabase.client import Client, create_client

load_dotenv()

@tool
def multiply(a: int, b: int) -> int:
    """Multiply two numbers.
    Args:
        a: first int
        b: second int
    """
    return a * b

@tool
def add(a: int, b: int) -> int:
    """Add two numbers.
    
    Args:
        a: first int
        b: second int
    """
    return a + b

@tool
def subtract(a: int, b: int) -> int:
    """Subtract two numbers.
    
    Args:
        a: first int
        b: second int
    """
    return a - b

@tool
def divide(a: int, b: int) -> int:
    """Divide two numbers.
    
    Args:
        a: first int
        b: second int
    """
    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
    """
    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}

@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}

@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
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
def build_graph(provider: str = "google"):
    """Build the graph"""
    # Load environment variables from .env file
    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
    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,
            ),
        )
    else:
        raise ValueError("Invalid provider. Choose 'google', 'groq' or 'huggingface'.")
    # Bind tools to LLM
    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]}

    from langchain_core.messages import AIMessage

    def retriever(state: MessagesState):
        query = state["messages"][-1].content
        similar_doc = vector_store.similarity_search(query, k=1)[0]

        content = similar_doc.page_content
        if "Final answer :" in content:
            answer = content.split("Final answer :")[-1].strip()
        else:
            answer = content.strip()

        return {"messages": [AIMessage(content=answer)]}

   # 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")

    builder = StateGraph(MessagesState)
    builder.add_node("retriever", retriever)

    # Retriever ist Start und Endpunkt
    builder.set_entry_point("retriever")
    builder.set_finish_point("retriever")

    # Compile graph
    return builder.compile()