如何为查询分析添加示例到提示中

# %pip install -qU langchain-core langchain-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["LANGCHAIN_TRACING_V2"] = "true"
# os.environ["LANGCHAIN_API_KEY"] = getpass.getpass()

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")

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

query_analyzer.invoke(
    "what's the difference between web voyager and reflection agents? do both use langgraph?"
)

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]})

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
)

query_analyzer_with_examples.invoke(
    "what's the difference between web voyager and reflection agents? do both use langgraph?"
)