langchain/docs/modules/models/llms/examples/fake_llm.ipynb

How (and why) to use the 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.

In [1]:

from langchain.llms.fake import FakeListLLM

In [2]:

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

In [3]:

tools = load_tools(["python_repl"])

In [16]:

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

In [17]:

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

In [18]:

agent.run("whats 2 + 2")

Out [18]:

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

Thought:Final Answer: 4

> Finished chain.

'4'

In [ ]: