Fake LLM

We expose a fake LLM class that can be used for testing. This allows you to mock out calls to the LLM and simulate what would happen if the LLM responded in a certain way.

In this notebook we go over how to use this.

We start this with using the FakeLLM in an agent.

from langchain.llms.fake import FakeListLLM

API Reference:

• FakeListLLM from langchain.llms.fake

from langchain.agents import load_tools
from langchain.agents import initialize_agent
from langchain.agents import AgentType

API Reference:

• load_tools from langchain.agents
• initialize_agent from langchain.agents
• AgentType from langchain.agents

tools = load_tools(["python_repl"])

responses = ["Action: Python REPL\nAction Input: print(2 + 2)", "Final Answer: 4"]
llm = FakeListLLM(responses=responses)

agent = initialize_agent(
    tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True
)

agent.run("whats 2 + 2")

    
    
    > Entering new AgentExecutor chain...
    Action: Python REPL
    Action Input: print(2 + 2)
    Observation: 4
    
    Thought:Final Answer: 4
    
    > Finished chain.





    '4'