langchain/docs/extras/modules/model_io/models/llms/fake_llm.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "052dfe58",
   "metadata": {},
   "source": [
    "# Fake LLM\n",
    "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.\n",
    "\n",
    "In this notebook we go over how to use this.\n",
    "\n",
    "We start this with using the FakeLLM in an agent."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "ef97ac4d",
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.llms.fake import FakeListLLM"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "9a0a160f",
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.agents import load_tools\n",
    "from langchain.agents import initialize_agent\n",
    "from langchain.agents import AgentType"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "b272258c",
   "metadata": {},
   "outputs": [],
   "source": [
    "tools = load_tools([\"python_repl\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "94096c4c",
   "metadata": {},
   "outputs": [],
   "source": [
    "responses = [\"Action: Python REPL\\nAction Input: print(2 + 2)\", \"Final Answer: 4\"]\n",
    "llm = FakeListLLM(responses=responses)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "da226d02",
   "metadata": {},
   "outputs": [],
   "source": [
    "agent = initialize_agent(\n",
    "    tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "44c13426",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
      "\u001b[32;1m\u001b[1;3mAction: Python REPL\n",
      "Action Input: print(2 + 2)\u001b[0m\n",
      "Observation: \u001b[36;1m\u001b[1;3m4\n",
      "\u001b[0m\n",
      "Thought:\u001b[32;1m\u001b[1;3mFinal Answer: 4\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "'4'"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "agent.run(\"whats 2 + 2\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "814c2858",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.11.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}