graph.py

"""
Build a graph to solve gala problems.
"""
import os
from langchain_core.tools import tool
from langchain_groq import ChatGroq
from langchain_community.tools.tavily_search import TavilySearchResults
from langgraph.graph import START, StateGraph, MessagesState, END
from langgraph.prebuilt import tools_condition, ToolNode
from langchain_huggingface import ChatHuggingFace, HuggingFaceEndpoint
from langchain_community.document_loaders import WikipediaLoader, ArxivLoader
from langchain_core.messages import SystemMessage, HumanMessage

@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}

SYSTEM_PROMPT = """
You are a helpful assistant that can solve problems using a set 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 = [multiply, add, subtract, divide, modulus, wiki_search, web_search, arvix_search]
def build_graph():
    """
    Build a graph to solve gala problems.
    """
    model = HuggingFaceEndpoint(
        repo_id="Qwen/QwQ-32B",  # 模型ID
        task="text-generation",   # 任务类型
        temperature=0.7,
        max_new_tokens=512,
        huggingfacehub_api_token=os.getenv('HUGGINGFACE_API_TOKEN'),
        top_p=0.95,
        
    )
    llm = ChatHuggingFace(llm=model)
    # llm = ChatGroq(model="qwen-qwq-32b", temperature=0)
    llm_with_tools = llm.bind_tools(tools)

    # Node
    def assistant(state: MessagesState):
        """Assistant node"""
        print(state["messages"])
        return {"messages": [llm_with_tools.invoke(state["messages"])]}

    def end(state: MessagesState):
        """End node"""
        return {"messages": [HumanMessage(content="FINAL ANSWER: " + state["messages"][-1].content)]}
    
    builder = StateGraph(MessagesState)
    builder.add_node("assistant", assistant)
    builder.add_node("tools", ToolNode(tools))
    builder.add_edge(START, "assistant")
    builder.add_conditional_edges(
        "assistant",
        tools_condition
    )
    builder.add_edge("tools", "assistant")
    builder.add_edge("assistant", END)
    # Compile graph
    return builder.compile()

if __name__ == "__main__":
    from pprint import pprint
    graph = build_graph()
    messages = [SystemMessage(content=SYSTEM_PROMPT), HumanMessage(content="What is the capital of France?")]
    msg = graph.invoke({"messages": messages})
    for m in msg["messages"]:
        m.pretty_print()