英文:
In LangChain, how to save the verbose output to a variable?
问题
我尝试执行一个langchain代理。我想将verbose的输出保存到一个变量中，但我只能从agent.run中访问最终答案。
如何将verbose输出保存到一个变量中，以便我以后可以使用它？
我的代码：
import json
from langchain.agents import load_tools
from langchain.agents import initialize_agent
from langchain.agents import AgentType
from langchain.llms import OpenAI
from langchain.agents import Tool
from langchain.utilities import PythonREPL
llm = OpenAI(temperature=0.1)
## 定义工具
python_repl = PythonREPL()
tools = load_tools(["python_repl", "llm-math"], llm=llm)
agent = initialize_agent(tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True)
response = agent.run("What is 3^2. Use calculator to solve.")
我尝试访问来自代理的响应，但它只是最终答案，而不是verbose输出。
打印response只会输出9。但我想要像下面这样的verbose过程：
> 进入新的AgentExecutor链...
我需要使用计算器来解决这个问题。
动作：计算器
动作输入：3^2
观察：答案：9
思考：我现在知道了最终答案。
最终答案：9
英文:
I tried executing a langchain agent. I want to save the output from verbose into a variable, but all I can access from the agent.run is only the final answer.
How can I save the verbose output to a variable so that I can use later?
My code:
import json
from langchain.agents import load_tools
from langchain.agents import initialize_agent
from langchain.agents import AgentType
from langchain.llms import OpenAI
from langchain.agents import Tool
from langchain.utilities import PythonREPL
llm = OpenAI(temperature=0.1)
## Define Tools
python_repl = PythonREPL()
tools = load_tools(["python_repl", "llm-math"], llm=llm)
agent = initialize_agent(tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True)
response = agent.run("What is 3^2. Use calculator to solve.")
I tried accessing the response from the agent, but it's only the final answer instead of the verbose output.
printing response gives only 9. But I would like the verbose process like:
> Entering new AgentExecutor chain...
I need to use the calculator to solve this.
Action: Calculator
Action Input: 3^2
Observation: Answer: 9
Thought: I now know the final answer.
Final Answer: 9
答案1
得分: 3
I don't find any API to save verbose output as a variable.
However, I think an alternative solution to the question can be achieved by accessing intermediate steps in this link.
That is set return_intermediate_steps=True,
agent = initialize_agent(
tools,
llm,
agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION,
verbose=True,
return_intermediate_steps=True
)
and use response = agent({"input":"What is 3^2. Use calculator to solve"}) instead of agent.run.
Finally, you can access the intermediate steps in response["intermediate_steps"]
Hope this will help.
英文:
I don't find any API to save verbose output as a variable.
However, I think an alternative solution to the question can be achieved by access intermediate steps in this link.
That is set return_intermediate_steps=True,
agent = initialize_agent(
tools,
llm,
agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION,
verbose=True,
return_intermediate_steps=True
)
and use response = agent({"input":"What is 3^2. Use calculator to solve"}) instead of agent.run.
Finally, you can access the intermediate steps in response["intermediate_steps"]
Hope this will help.
通过集体智慧和协作来改善编程学习和解决问题的方式。致力于成为全球开发者共同参与的知识库，让每个人都能够通过互相帮助和分享经验来进步。
评论