如何缓存聊天模型响应
Prerequisites
本指南假设您熟悉以下概念：
LangChain 为 聊天模型 提供了一个可选的缓存层。这主要有两个原因：
- 如果您经常多次请求相同的完成，它可以通过减少您对LLM提供者的API调用来节省资金。这在应用程序开发期间特别有用。
- 它可以通过减少您对LLM提供者的API调用次数来加速您的应用程序。
本指南将引导您如何在您的应用程序中启用此功能。
Select chat model:
pip install -qU langchain-openai
import getpass
import os
if not os.environ.get("OPENAI_API_KEY"):
os.environ["OPENAI_API_KEY"] = getpass.getpass("Enter API key for OpenAI: ")
from langchain_openai import ChatOpenAI
llm = ChatOpenAI(model="gpt-4o-mini")
# <!-- ruff: noqa: F821 -->
from langchain_core.globals import set_llm_cache
API Reference:set_llm_cache
内存缓存
这是一个临时缓存，用于在内存中存储模型调用。当您的环境重新启动时，它将被清除，并且不会在进程之间共享。
%%time
from langchain_core.caches import InMemoryCache
set_llm_cache(InMemoryCache())
# The first time, it is not yet in cache, so it should take longer
llm.invoke("Tell me a joke")
API Reference:InMemoryCache
CPU times: user 645 ms, sys: 214 ms, total: 859 ms
Wall time: 829 ms
AIMessage(content="Why don't scientists trust atoms?\n\nBecause they make up everything!", response_metadata={'token_usage': {'completion_tokens': 13, 'prompt_tokens': 11, 'total_tokens': 24}, 'model_name': 'gpt-3.5-turbo', 'system_fingerprint': 'fp_c2295e73ad', 'finish_reason': 'stop', 'logprobs': None}, id='run-b6836bdd-8c30-436b-828f-0ac5fc9ab50e-0')
%%time
# The second time it is, so it goes faster
llm.invoke("Tell me a joke")
CPU times: user 822 µs, sys: 288 µs, total: 1.11 ms
Wall time: 1.06 ms
AIMessage(content="Why don't scientists trust atoms?\n\nBecause they make up everything!", response_metadata={'token_usage': {'completion_tokens': 13, 'prompt_tokens': 11, 'total_tokens': 24}, 'model_name': 'gpt-3.5-turbo', 'system_fingerprint': 'fp_c2295e73ad', 'finish_reason': 'stop', 'logprobs': None}, id='run-b6836bdd-8c30-436b-828f-0ac5fc9ab50e-0')
SQLite 缓存
此缓存实现使用SQLite数据库来存储响应，并且将在进程重启后持续存在。
!rm .langchain.db
# We can do the same thing with a SQLite cache
from langchain_community.cache import SQLiteCache
set_llm_cache(SQLiteCache(database_path=".langchain.db"))
API Reference:SQLiteCache
%%time
# The first time, it is not yet in cache, so it should take longer
llm.invoke("Tell me a joke")
CPU times: user 9.91 ms, sys: 7.68 ms, total: 17.6 ms
Wall time: 657 ms
AIMessage(content='Why did the scarecrow win an award? Because he was outstanding in his field!', response_metadata={'token_usage': {'completion_tokens': 17, 'prompt_tokens': 11, 'total_tokens': 28}, 'model_name': 'gpt-3.5-turbo', 'system_fingerprint': 'fp_c2295e73ad', 'finish_reason': 'stop', 'logprobs': None}, id='run-39d9e1e8-7766-4970-b1d8-f50213fd94c5-0')
%%time
# The second time it is, so it goes faster
llm.invoke("Tell me a joke")
CPU times: user 52.2 ms, sys: 60.5 ms, total: 113 ms
Wall time: 127 ms
AIMessage(content='Why did the scarecrow win an award? Because he was outstanding in his field!', id='run-39d9e1e8-7766-4970-b1d8-f50213fd94c5-0')
下一步
你现在已经学会了如何缓存模型响应以节省时间和金钱。
接下来，查看本节中的其他操作指南聊天模型，例如如何让模型返回结构化输出或如何创建您自己的自定义聊天模型。