在提取时如何使用参考示例

通过向 LLM 提供参考示例，通常可以提高提取的质量。

数据提取尝试生成在文本和其他非结构化或半结构化格式中找到的信息的结构化表示。工具调用 LLM 功能通常在此上下文中使用。本指南演示如何构建工具调用的少量示例，以帮助指导提取和类似应用程序的行为。

提示

虽然本指南侧重于如何将示例与工具调用模型一起使用，但此技术通常适用，并且也适用于 JSON 或更多基于提示的技术。

LangChain 在来自 LLM 的消息上实现了工具调用属性，其中包括工具调用。有关更多详细信息，请参阅我们的关于工具调用的操作指南。为了构建数据提取的参考示例，我们构建了一个聊天历史记录，其中包含以下序列：

• HumanMessage，包含示例输入；
• AIMessage，包含示例工具调用；
• ToolMessage，包含示例工具输出。

LangChain 采用此约定来跨 LLM 模型提供商构建工具调用到对话中。

首先，我们构建一个提示模板，其中包含这些消息的占位符

from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder

# Define a custom prompt to provide instructions and any additional context.
# 1) You can add examples into the prompt template to improve extraction quality
# 2) Introduce additional parameters to take context into account (e.g., include metadata
#    about the document from which the text was extracted.)
prompt = ChatPromptTemplate.from_messages(
    [
        (
            "system",
            "You are an expert extraction algorithm. "
            "Only extract relevant information from the text. "
            "If you do not know the value of an attribute asked "
            "to extract, return null for the attribute's value.",
        ),
        # ↓↓↓↓↓↓↓↓↓↓↓↓↓↓↓↓↓↓↓↓↓↓↓↓↓↓↓↓
        MessagesPlaceholder("examples"),  # <-- EXAMPLES!
        # ↑↑↑↑↑↑↑↑↑↑↑↑↑↑↑↑↑↑↑↑↑↑↑↑↑↑↑↑↑
        ("human", "{text}"),
    ]
)

API 参考：ChatPromptTemplate | MessagesPlaceholder

测试模板

from langchain_core.messages import (
    HumanMessage,
)

prompt.invoke(
    {"text": "this is some text", "examples": [HumanMessage(content="testing 1 2 3")]}
)

API 参考：HumanMessage

ChatPromptValue(messages=[SystemMessage(content="You are an expert extraction algorithm. Only extract relevant information from the text. If you do not know the value of an attribute asked to extract, return null for the attribute's value.", additional_kwargs={}, response_metadata={}), HumanMessage(content='testing 1 2 3', additional_kwargs={}, response_metadata={}), HumanMessage(content='this is some text', additional_kwargs={}, response_metadata={})])

定义模式

让我们重用提取教程中的人员模式。

from typing import List, Optional

from langchain_openai import ChatOpenAI
from pydantic import BaseModel, Field


class Person(BaseModel):
    """Information about a person."""

    # ^ Doc-string for the entity Person.
    # This doc-string is sent to the LLM as the description of the schema Person,
    # and it can help to improve extraction results.

    # Note that:
    # 1. Each field is an `optional` -- this allows the model to decline to extract it!
    # 2. Each field has a `description` -- this description is used by the LLM.
    # Having a good description can help improve extraction results.
    name: Optional[str] = Field(..., description="The name of the person")
    hair_color: Optional[str] = Field(
        ..., description="The color of the person's hair if known"
    )
    height_in_meters: Optional[str] = Field(..., description="Height in METERs")


class Data(BaseModel):
    """Extracted data about people."""

    # Creates a model so that we can extract multiple entities.
    people: List[Person]

API 参考：ChatOpenAI

定义参考示例

示例可以定义为输入-输出对的列表。

每个示例都包含示例 input 文本和一个示例 output，显示应从文本中提取的内容。

重要提示

这有点深入细节，所以可以随意跳过。

示例的格式需要与使用的 API 相匹配（例如，工具调用或 JSON 模式等）。

在这里，格式化的示例将与工具调用 API 期望的格式相匹配，因为这就是我们正在使用的。

import uuid
from typing import Dict, List, TypedDict

from langchain_core.messages import (
    AIMessage,
    BaseMessage,
    HumanMessage,
    SystemMessage,
    ToolMessage,
)
from pydantic import BaseModel, Field


class Example(TypedDict):
    """A representation of an example consisting of text input and expected tool calls.

    For extraction, the tool calls are represented as instances of pydantic model.
    """

    input: str  # This is the example text
    tool_calls: List[BaseModel]  # Instances of pydantic model that should be extracted


def tool_example_to_messages(example: Example) -> List[BaseMessage]:
    """Convert an example into a list of messages that can be fed into an LLM.

    This code is an adapter that converts our example to a list of messages
    that can be fed into a chat model.

    The list of messages per example corresponds to:

    1) HumanMessage: contains the content from which content should be extracted.
    2) AIMessage: contains the extracted information from the model
    3) ToolMessage: contains confirmation to the model that the model requested a tool correctly.

    The ToolMessage is required because some of the chat models are hyper-optimized for agents
    rather than for an extraction use case.
    """
    messages: List[BaseMessage] = [HumanMessage(content=example["input"])]
    tool_calls = []
    for tool_call in example["tool_calls"]:
        tool_calls.append(
            {
                "id": str(uuid.uuid4()),
                "args": tool_call.dict(),
                # The name of the function right now corresponds
                # to the name of the pydantic model
                # This is implicit in the API right now,
                # and will be improved over time.
                "name": tool_call.__class__.__name__,
            },
        )
    messages.append(AIMessage(content="", tool_calls=tool_calls))
    tool_outputs = example.get("tool_outputs") or [
        "You have correctly called this tool."
    ] * len(tool_calls)
    for output, tool_call in zip(tool_outputs, tool_calls):
        messages.append(ToolMessage(content=output, tool_call_id=tool_call["id"]))
    return messages

API 参考：AIMessage | BaseMessage | HumanMessage | SystemMessage | ToolMessage

接下来，让我们定义我们的示例，然后将它们转换为消息格式。

examples = [
    (
        "The ocean is vast and blue. It's more than 20,000 feet deep. There are many fish in it.",
        Data(people=[]),
    ),
    (
        "Fiona traveled far from France to Spain.",
        Data(people=[Person(name="Fiona", height_in_meters=None, hair_color=None)]),
    ),
]


messages = []

for text, tool_call in examples:
    messages.extend(
        tool_example_to_messages({"input": text, "tool_calls": [tool_call]})
    )

让我们测试一下提示

example_prompt = prompt.invoke({"text": "this is some text", "examples": messages})

for message in example_prompt.messages:
    print(f"{message.type}: {message}")

system: content="You are an expert extraction algorithm. Only extract relevant information from the text. If you do not know the value of an attribute asked to extract, return null for the attribute's value." additional_kwargs={} response_metadata={}
human: content="The ocean is vast and blue. It's more than 20,000 feet deep. There are many fish in it." additional_kwargs={} response_metadata={}
ai: content='' additional_kwargs={} response_metadata={} tool_calls=[{'name': 'Data', 'args': {'people': []}, 'id': '240159b1-1405-4107-a07c-3c6b91b3d5b7', 'type': 'tool_call'}]
tool: content='You have correctly called this tool.' tool_call_id='240159b1-1405-4107-a07c-3c6b91b3d5b7'
human: content='Fiona traveled far from France to Spain.' additional_kwargs={} response_metadata={}
ai: content='' additional_kwargs={} response_metadata={} tool_calls=[{'name': 'Data', 'args': {'people': [{'name': 'Fiona', 'hair_color': None, 'height_in_meters': None}]}, 'id': '3fc521e4-d1d2-4c20-bf40-e3d72f1068da', 'type': 'tool_call'}]
tool: content='You have correctly called this tool.' tool_call_id='3fc521e4-d1d2-4c20-bf40-e3d72f1068da'
human: content='this is some text' additional_kwargs={} response_metadata={}

创建一个提取器

让我们选择一个 LLM。因为我们正在使用工具调用，所以我们需要一个支持工具调用功能的模型。请参阅此表以获取可用的 LLM。

选择聊天模型

OpenAI

Anthropic

Azure

Google Vertex

AWS

Groq

Cohere

NVIDIA

Fireworks AI

Mistral AI

Together AI

IBM watsonx

Databricks

xAI

pip install -qU "langchain[openai]"

import getpass
import os

if not os.environ.get("OPENAI_API_KEY"):
  os.environ["OPENAI_API_KEY"] = getpass.getpass("Enter API key for OpenAI: ")

from langchain.chat_models import init_chat_model

llm = init_chat_model("gpt-4-0125-preview", model_provider="openai", temperature=0)

按照提取教程，我们使用 .with_structured_output 方法根据所需的模式结构化模型输出

runnable = prompt | llm.with_structured_output(
    schema=Data,
    method="function_calling",
    include_raw=False,
)

没有示例 😿

请注意，即使是功能强大的模型也可能在非常简单的测试用例中失败！

for _ in range(5):
    text = "The solar system is large, but earth has only 1 moon."
    print(runnable.invoke({"text": text, "examples": []}))

people=[Person(name='earth', hair_color='null', height_in_meters='null')]
``````output
people=[Person(name='earth', hair_color='null', height_in_meters='null')]
``````output
people=[]
``````output
people=[Person(name='earth', hair_color='null', height_in_meters='null')]
``````output
people=[]

有示例 😻

参考示例有助于修复失败！

for _ in range(5):
    text = "The solar system is large, but earth has only 1 moon."
    print(runnable.invoke({"text": text, "examples": messages}))

people=[]
``````output
people=[]
``````output
people=[]
``````output
people=[]
``````output
people=[]

请注意，我们可以在Langsmith 追踪中将少量示例视为工具调用。

我们在正面样本上保持性能

runnable.invoke(
    {
        "text": "My name is Harrison. My hair is black.",
        "examples": messages,
    }
)

Data(people=[Person(name='Harrison', hair_color='black', height_in_meters=None)])