LangChain使用Parser控制输出

1.导包

from langchain_openai import ChatOpenAI
from langchain.output_parsers import CommaSeparatedListOutputParser
from langchain.prompts import ChatPromptTemplate

2.设置提示模板

prompt = ChatPromptTemplate.from_messages([
    ("system", "{parser_instructions}"),
    ("human", "列出5个{subject}色系的十六进制颜色码。")
])

3.对提示规范化

output_parser = CommaSeparatedListOutputParser()
parser_instructions = output_parser.get_format_instructions()
print(parser_instructions)

输出：
Your response should be a list of comma separated values, eg: foo, bar, baz or foo,bar,baz

4.设置最终模板

final_prompt = prompt.invoke({"subject": "莫兰迪", "parser_instructions": parser_instructions})

5.输出最终模板

final_prompt

ChatPromptValue(messages=[SystemMessage(content=‘Your response should be a list of comma separated values, eg: foo, bar, baz or foo,bar,baz’), HumanMessage(content=‘列出5个莫兰迪色系的十六进制颜色码。’)])

6.输入模型

model = ChatOpenAI(model="gpt-3.5-turbo",base_url="https://api.chatanywhere.tech/v1")
response = model.invoke(final_prompt)
print(response.content)

#FF6F61, #FFCC5C, #FFE066, #6B705C, #546E7A