Chat Models
聊天模型使用LLM(大型语言模型)进行操作,但具有不同的接口,使用"消息"而不是原始文本输入/输出。LangChain 提供了与这些模型轻松交互的功能。
在聊天模型中,支持三种类型的消息:
- SystemMessage(系统消息) - 这设置了LLM的行为和目标。您可以在这里给出具体的指示,如:"扮演市场经理。" 或 "只返回JSON响应,不返回说明文本"
- HumanMessage(人类消息) - 这是您将用户提示输入并发送给LLM的地方
- AIMessage(AI消息) - 当将聊天记录传回LLM以供将来请求时,您可以在这里存储来自LLM的响应。
还有一个通用的 ChatMessage,它接受一个任意的"角色"输入,可以在需要除系统/人类/AI之外的其他内容的情况下使用。但通常情况下,您会使用上面提到的三种类型。
要使用它,您需要导入所使用集成的聊天模型。
python
from langchain.chat_models import ChatOpenAI
from langchain.schema import (
AIMessage,
HumanMessage,
SystemMessage
)
然后,您需要初始化聊天代理。这个示例使用了 OpenAI 的聊天模型。
python
chat = ChatOpenAI(temperature=0)
与LLM模型一样,这也有多个可以调整的设置,例如:
model
(模型) - 默认为 "gpt-3.5-turbo"temperature
(温度) - 参见上面的解释max_tokens
(最大令牌数) - 设置LLM在响应中生成的令牌数量的限制 然后,您需要将一系列消息传递给聊天代理以生成响应。在关于LangChain的"Memory"(记忆)的未来文章中,我们将讨论用于存储和应用聊天记录的ChatMessageHistory类,它可以使代理记住聊天的上下文并在未来的响应中使用它,从而产生"对话"的好处。
python
messages = [
SystemMessage(content="Return only a JSON object as a response with no explanation text"),
HumanMessage(content="Generate a JSON response object containing a brief description and release year for the movie 'Inception'")
]
chat(messages)
# AIMessage(content='{\\n "title": "Inception",\\n "description": "A skilled thief is given a final chance at redemption which involves executing his toughest job yet: Inception. The idea of planting an idea into someone\\'s mind is deemed impossible by most, but Cobb and his team of specialists must accomplish this task to save their lives.",\\n "release_year": 2010\\n}', additional_kwargs={})
聊天模型(Chat Model)和LLM模型一样,也有一个生成函数,您可以在其中传入多个消息集合。与前述类似,它还包括有用的信息,如令牌使用情况。
python
batch_messages = [
[
SystemMessage(content="Return only a JSON object as a response with no explanation text"),
HumanMessage(content="Generate a JSON response object containing a brief description and release year for the movie 'Inception'")
],
[
SystemMessage(content="Return only a JSON object as a response with no explanation text"),
HumanMessage(content="Generate a JSON response object containing a brief description and release year for the movie 'Avatar'")
]
]
result = chat.generate(batch_messages)
print(result.generations[1])
# ChatGeneration(text='{\\n "title": "Avatar",\\n "description": "A paraplegic marine dispatched to the moon Pandora on a unique mission becomes torn between following his orders and protecting the world he feels is his home.",\\n "release_year": 2009\\n}', generation_info=None, message=AIMessage(content='{\\n "title": "Avatar",\\n "description": "A paraplegic marine dispatched to the moon Pandora on a unique mission becomes torn between following his orders and protecting the world he feels is his home.",\\n "release_year": 2009\\n}', additional_kwargs={}))
print(result.llm_outout)
# {'token_usage': {'prompt_tokens': 91, 'completion_tokens': 151, 'total_tokens': 242}, 'model_name': 'gpt-3.5-turbo'}