LangChain中使用Chain

1.导包

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

2.设置提示

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

3.设置格式

output_parser = CommaSeparatedListOutputParser()
parser_instructions = output_parser.get_format_instructions()
model = ChatOpenAI(model="gpt-3.5-turbo",base_url="https://api.chatanywhere.tech/v1")

4.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)

5.得到结果

result = output_parser.invoke(model.invoke(prompt.invoke({"subject": "莫兰迪", "parser_instructions": parser_instructions})))
result

输出：
[‘#FF6F61’, ‘#FFCC5C’, ‘#88D8B0’, ‘#4BE2C8’, ‘#A8ADD3’]

6.使用chain输出

chat_model_chain = prompt | model | output_parser
result = chat_model_chain.invoke({"subject": "莫兰迪", "parser_instructions": parser_instructions})
result

输出：
[‘#FF6F61’, ‘#FFCC5C’, ‘#FFE4B5’, ‘#778899’, ‘#ADD8E6’]