langchain1.2学习笔记（一）：安装langchain

SCBAiotAigc2025-12-28 15:17

https://docs.langchain.com/oss/python/langchain/install

bash 复制代码

uv add langchain[openai]
uv add dotenv

集成厂商：

pyproject.toml：

bash 复制代码

[project]
name = "langchain_demo"
version = "0.1.0"
description = "langchain demo"
readme = "README.md"
requires-python = ">=3.13, < 3.14"
dependencies = [
    "dotenv>=0.9.9",
    "langchain[openai]>=1.2.0",
]

聊天调用：

python 复制代码

from envs.envs import OPENAI_BASE_URL, OPENAI_API_KEY, OPENAI_BASE_MODEL
from langchain_openai import ChatOpenAI
import asyncio

llm = ChatOpenAI(
    model=OPENAI_BASE_MODEL,
    openai_api_key=OPENAI_API_KEY,
    openai_api_base=OPENAI_BASE_URL,
)


async def main():
    response = await llm.ainvoke("请帮我生成一个关于人工智能的报告")

    print(type(response))
    print(response)


if __name__ == "__main__":
    asyncio.run(main())

流式输出：

python 复制代码

from envs.envs import OPENAI_BASE_URL, OPENAI_API_KEY, OPENAI_BASE_MODEL
from langchain_openai import ChatOpenAI
import asyncio

llm = ChatOpenAI(
    model=OPENAI_BASE_MODEL,
    openai_api_key=OPENAI_API_KEY,
    openai_api_base=OPENAI_BASE_URL,
)


async def main():
    stream = llm.astream("请帮我生成一个关于人工智能的报告")

    async for chunk in stream:
        print(chunk.content, end="", flush=True)

    print()


if __name__ == "__main__":
    asyncio.run(main())