LangChain Agent与工具：如何向工具传递input外的额外参数（如userId）

针对你需要将userId传递给getPrice工具的需求，有两种实用的实现方式，结合你的代码示例具体说明：

方法一：通过偏函数绑定固定参数（适合单用户独立会话） #

如果每个用户维护独立的Agent实例，可以用functools.partial把userId预先绑定到工具函数上，工具调用时会自动带上该参数。

修改后的代码： #

from langchain import hub
from langchain.agents import AgentExecutor, create_react_agent
from langchain.tools import Tool
from langchain_openai import ChatOpenAI
from langchain.memory import ConversationBufferMemory
import requests
from functools import partial

llm = ChatOpenAI()
prompt = hub.pull("hwchase17/react-chat")

def getPrice(input, extra):
    print("input +++", input, extra)
    url = f"https://api.coincap.io/v2/assets/{input.lower()}"
    response = requests.get(url)
    price = response.json()["data"]["priceUsd"]
    return price

# 假设当前会话的userId为user_123
current_user_id = "user_123"
# 用partial将userId绑定到getPrice的extra参数
bound_getPrice = partial(getPrice, extra=current_user_id)

# 创建绑定后的工具
apicall = Tool(
    name="getCryptoPrice",
    func=bound_getPrice,
    description="use to get the price for any given crypto from user input"
)
tools = [apicall]

agent = create_react_agent(llm, tools, prompt)
agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True)
memory = ConversationBufferMemory(
    memory_key="chat_history", return_messages=True
)

# 正常调用即可，无需在invoke中额外传userId
agent_executor.invoke(
    {
        "input": "what is the price of cardano",
        "chat_history": "Human: Hi! My name is Bob\nAI: Hello Bob! Nice to meet you",
    }
)

方法二：动态传递参数（适合多用户共享Agent实例） #

如果需要在每次调用时动态传入userId，可以使用StructuredTool定义多参数工具，并修改Prompt让Agent识别并传递userId参数。

修改后的代码： #

from langchain import hub
from langchain.agents import AgentExecutor, create_react_agent
from langchain.tools import StructuredTool
from langchain_openai import ChatOpenAI
from langchain.memory import ConversationBufferMemory
from langchain_core.prompts import PromptTemplate
import requests

llm = ChatOpenAI()

# 自定义Prompt，添加user_id变量供Agent使用
custom_prompt = PromptTemplate.from_template("""
Answer the following questions as best you can. You have access to the following tools:

{tools}

Use the following format:

Question: the input question you must answer
Thought: you should always think about what to do
Action: the action to take, should be one of [{tool_names}]
Action Input: a dictionary containing the required parameters for the tool
Observation: the result of the action
... (this Thought/Action/Action Input/Observation can repeat N times)
Thought: I now know the final answer
Final Answer: the final answer to the original input question

Begin!

Question: {input}
Chat History: {chat_history}
User ID: {user_id}
Thought:""")

# 修改工具函数，明确接收crypto和user_id两个参数
def getPrice(crypto: str, user_id: str):
    print("crypto +++", crypto, "user_id +++", user_id)
    url = f"https://api.coincap.io/v2/assets/{crypto.lower()}"
    response = requests.get(url)
    price = response.json()["data"]["priceUsd"]
    return f"{crypto}的价格为{price}美元（查询用户：{user_id}）"

# 用StructuredTool定义多参数工具
apicall = StructuredTool.from_function(
    func=getPrice,
    name="getCryptoPrice",
    description="用于获取加密货币价格，需要传入两个参数：crypto（加密货币名称）和user_id（当前用户ID）"
)
tools = [apicall]

agent = create_react_agent(llm, tools, custom_prompt)
agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True)
memory = ConversationBufferMemory(
    memory_key="chat_history", return_messages=True
)

# 在invoke中直接传入user_id
agent_executor.invoke(
    {
        "input": "what is the price of cardano",
        "chat_history": "Human: Hi! My name is Bob\nAI: Hello Bob! Nice to meet you",
        "user_id": "user_123"
    }
)

选择建议 #

• 若每个用户有独立的Agent实例，优先用方法一，实现简单且无需修改Prompt。
• 若多用户共享Agent实例，需要动态传递参数，用方法二，通过StructuredTool和自定义Prompt实现参数传递。

内容的提问来源于stack exchange，提问作者tejaswi avhad