LangChain v0.3 langchain.chat_models.init_chat_model调用现成大模型接口进行智能问答教程

原创已于 2025-02-21 16:28:04 修改 · 1.1k 阅读

5 ·

CC 4.0 BY-SA版权

文章标签：

#langchain #人工智能 #python

于 2025-02-21 11:31:51 首次发布

人工智能学习笔记专栏收录该内容

277 篇文章

订阅专栏

诸神缄默不语-个人技术博文与视频目录

langchain.chat_models.init_chat_model()函数事实上跟单独使用langchain-openai、langchain-deepseek性质一样的。
（所以需要提前安装对应的包，如pip install langchain-openai）

文章目录

1. 使用OpenAI接口的示例
2. 另一种格式的示例，在init_chat_model函数里加参数
3. 在`invoke()`中才指定参数的示例
4. 在`init_chat_model()`指定参数默认值，在`invoke()`中可以使用默认值也可以修改的示例
5. 带工具调用功能的示例
6. advanced使用参考资料

1. 使用OpenAI接口的示例

import os

os.environ["OPENAI_API_KEY"] = OPENAI_KEY

from langchain.chat_models import init_chat_model

model = init_chat_model("gpt-4o-mini", model_provider="openai")

response = model.invoke("Hello, world!")
print(response.content)

打印内容：Hello! How can I assist you today?

2. 另一种格式的示例，在init_chat_model函数里加参数

import os

os.environ["OPENAI_API_KEY"] = OPENAI_KEY

from langchain.chat_models import init_chat_model

o4_mini = init_chat_model("openai:gpt-4o-mini", temperature=0)

response = o4_mini.invoke("what's your name")
print(response.content)

打印内容：I’m called ChatGPT. How can I assist you today?

3. 在`invoke()`中才指定参数的示例

↓这里面不用指定openai因为langchain会自己infer

import os

os.environ["OPENAI_API_KEY"] = OPENAI_KEY

from langchain.chat_models import init_chat_model

configurable_model = init_chat_model(temperature=0)

response=configurable_model.invoke(
    "what's your name",
    config={"configurable": {"model": "gpt-4o-mini"}}
)
print(response.content)

4. 在`init_chat_model()`指定参数默认值，在`invoke()`中可以使用默认值也可以修改的示例

# pip install langchain langchain-openai langchain-anthropic
from langchain.chat_models import init_chat_model

configurable_model_with_default = init_chat_model(
    "openai:gpt-4o",
    configurable_fields="any",  # this allows us to configure other params like temperature, max_tokens, etc at runtime.
    config_prefix="foo",
    temperature=0
)

configurable_model_with_default.invoke("what's your name")
# GPT-4o response with temperature 0

configurable_model_with_default.invoke(
    "what's your name",
    config={
        "configurable": {
            "foo_model": "anthropic:claude-3-5-sonnet-20240620",
            "foo_temperature": 0.6
        }
    }
)
# Claude-3.5 sonnet response with temperature 0.6

5. 带工具调用功能的示例

# pip install langchain langchain-openai langchain-anthropic
from langchain.chat_models import init_chat_model
from pydantic import BaseModel, Field

class GetWeather(BaseModel):
    '''Get the current weather in a given location'''

    location: str = Field(..., description="The city and state, e.g. San Francisco, CA")

class GetPopulation(BaseModel):
    '''Get the current population in a given location'''

    location: str = Field(..., description="The city and state, e.g. San Francisco, CA")

configurable_model = init_chat_model(
    "gpt-4o",
    configurable_fields=("model", "model_provider"),
    temperature=0
)

configurable_model_with_tools = configurable_model.bind_tools([GetWeather, GetPopulation])
configurable_model_with_tools.invoke(
    "Which city is hotter today and which is bigger: LA or NY?"
)
# GPT-4o response with tool calls

configurable_model_with_tools.invoke(
    "Which city is hotter today and which is bigger: LA or NY?",
    config={"configurable": {"model": "claude-3-5-sonnet-20240620"}}
)
# Claude-3.5 sonnet response with tools