mirror of
https://github.com/hwchase17/langchain
synced 2024-10-29 17:07:25 +00:00
10dab053b4
This pull request adds an enum class for the various types of agents used in the project, located in the `agent_types.py` file. Currently, the project is using hardcoded strings for the initialization of these agents, which can lead to errors and make the code harder to maintain. With the introduction of the new enums, the code will be more readable and less error-prone. The new enum members include: - ZERO_SHOT_REACT_DESCRIPTION - REACT_DOCSTORE - SELF_ASK_WITH_SEARCH - CONVERSATIONAL_REACT_DESCRIPTION - CHAT_ZERO_SHOT_REACT_DESCRIPTION - CHAT_CONVERSATIONAL_REACT_DESCRIPTION In this PR, I have also replaced the hardcoded strings with the appropriate enum members throughout the codebase, ensuring a smooth transition to the new approach.
140 lines
3.0 KiB
Plaintext
140 lines
3.0 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "052dfe58",
|
|
"metadata": {},
|
|
"source": [
|
|
"# How (and why) to use the 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.agent_types 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=[\n",
|
|
" \"Action: Python REPL\\nAction Input: print(2 + 2)\",\n",
|
|
" \"Final Answer: 4\"\n",
|
|
"]\n",
|
|
"llm = FakeListLLM(responses=responses)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 17,
|
|
"id": "da226d02",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"agent = initialize_agent(tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True)"
|
|
]
|
|
},
|
|
{
|
|
"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": "3.9.1"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 5
|
|
}
|