如何為查詢分析的提示添加範例
隨著我們的查詢分析變得更加複雜，LLM 可能難以理解在某些情境下應該如何回應。為了提高此處的效能，我們可以添加範例到提示中以引導 LLM。
讓我們看看如何為 LangChain YouTube 影片查詢分析器添加範例。
設定
安裝依賴項
# %pip install -qU langchain-core langchain-openai
設定環境變數
在此範例中，我們將使用 OpenAI
import getpass
import os
if "OPENAI_API_KEY" not in os.environ:
os.environ["OPENAI_API_KEY"] = getpass.getpass()
# Optional, uncomment to trace runs with LangSmith. Sign up here: https://smith.langchain.com.
# os.environ["LANGSMITH_TRACING"] = "true"
# os.environ["LANGSMITH_API_KEY"] = getpass.getpass()
查詢架構
我們將定義一個我們希望模型輸出的查詢架構。為了使我們的查詢分析更有趣，我們將添加一個 sub_queries 字段，其中包含從頂層問題衍生的更精確的問題。
from typing import List, Optional
from pydantic 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")
查詢生成
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-4o-mini", temperature=0)
structured_llm = llm.with_structured_output(Search)
query_analyzer = {"question": RunnablePassthrough()} | prompt | structured_llm
讓我們在提示中不使用任何範例的情況下試用我們的查詢分析器
query_analyzer.invoke(
"what's the difference between web voyager and reflection agents? do both use langgraph?"
)
Search(query='difference between web voyager and reflection agents', sub_queries=['what is web voyager', 'what are reflection agents', 'do both web voyager and reflection agents use langgraph?'], publish_year=None)
添加範例並調整提示
這效果很好，但我們可能希望它進一步分解問題，以分離關於 Web Voyager 和 Reflection Agents 的查詢。
為了調整我們的查詢生成結果，我們可以添加一些輸入問題和黃金標準輸出查詢的範例到我們的提示中。
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]})
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 from multi-agent system",
"How to stream intermediate steps",
],
)
examples.append({"input": question, "tool_calls": [query]})
question = "LangChain agents vs LangGraph?"
query = Search(
query="What's the difference between LangChain agents and LangGraph? How do you deploy them?",
sub_queries=[
"What are LangChain agents",
"What is LangGraph",
"How do you deploy LangChain agents",
"How do you deploy LangGraph",
],
)
examples.append({"input": question, "tool_calls": [query]})
現在我們需要更新我們的提示範本和鏈，以便範例包含在每個提示中。由於我們正在使用 OpenAI 函數調用，我們需要做一些額外的結構化工作，以將範例輸入和輸出發送到模型。我們將建立一個 tool_example_to_messages 輔助函數來為我們處理這個問題
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)]
from langchain_core.prompts import MessagesPlaceholder
query_analyzer_with_examples = (
{"question": RunnablePassthrough()}
| prompt.partial(examples=example_msgs)
| structured_llm
)
API 參考：MessagesPlaceholder
query_analyzer_with_examples.invoke(
"what's the difference between web voyager and reflection agents? do both use langgraph?"
)
Search(query="What's the difference between web voyager and reflection agents? Do both use langgraph?", sub_queries=['What is web voyager', 'What are reflection agents', 'Do web voyager and reflection agents use langgraph?'], publish_year=None)
感謝我們的範例，我們獲得了稍微更分解的搜尋查詢。透過更多提示工程和調整我們的範例，我們可以進一步改進查詢生成。
您可以看到範例作為訊息傳遞到模型中，如 LangSmith 追蹤所示。