Skip to main content
Open In Colab在 GitHub 上打开

如何单独使用提示 （无工具调用） 进行提取

从 LLM 生成结构化输出不需要工具调用功能。能够很好地遵循提示说明的 LLM 可以负责以给定格式输出信息。

这种方法依赖于设计良好的提示，然后解析 LLM 的输出，使其能够很好地提取信息。

要在没有工具调用功能的情况下提取数据，请执行以下作：

  1. 指示 LLM 按照预期的格式（例如，具有特定架构的 JSON）生成文本;
  2. 使用输出解析器将模型响应构建为所需的 Python 对象。

首先我们选择一个 LLM：

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

model = init_chat_model("gpt-4o-mini", model_provider="openai")
提示

本教程旨在简单，但通常应该真正包含参考示例以提高性能！

使用 PydanticOutputParser

以下示例使用内置的PydanticOutputParser来解析聊天模型的输出。

from typing import List, Optional

from langchain_core.output_parsers import PydanticOutputParser
from langchain_core.prompts import ChatPromptTemplate
from pydantic import BaseModel, Field, validator


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

    name: str = Field(..., description="The name of the person")
    height_in_meters: float = Field(
        ..., description="The height of the person expressed in meters."
    )


class People(BaseModel):
    """Identifying information about all people in a text."""

    people: List[Person]


# Set up a parser
parser = PydanticOutputParser(pydantic_object=People)

# Prompt
prompt = ChatPromptTemplate.from_messages(
    [
        (
            "system",
            "Answer the user query. Wrap the output in `json` tags\n{format_instructions}",
        ),
        ("human", "{query}"),
    ]
).partial(format_instructions=parser.get_format_instructions())

我们来看看向模型发送了哪些信息

query = "Anna is 23 years old and she is 6 feet tall"
print(prompt.format_prompt(query=query).to_string())
System: Answer the user query. Wrap the output in `json` tags
The output should be formatted as a JSON instance that conforms to the JSON schema below.

As an example, for the schema {"properties": {"foo": {"title": "Foo", "description": "a list of strings", "type": "array", "items": {"type": "string"}}}, "required": ["foo"]}
the object {"foo": ["bar", "baz"]} is a well-formatted instance of the schema. The object {"properties": {"foo": ["bar", "baz"]}} is not well-formatted.

Here is the output schema:
\`\`\`
{"$defs": {"Person": {"description": "Information about a person.", "properties": {"name": {"description": "The name of the person", "title": "Name", "type": "string"}, "height_in_meters": {"description": "The height of the person expressed in meters.", "title": "Height In Meters", "type": "number"}}, "required": ["name", "height_in_meters"], "title": "Person", "type": "object"}}, "description": "Identifying information about all people in a text.", "properties": {"people": {"items": {"$ref": "#/$defs/Person"}, "title": "People", "type": "array"}}, "required": ["people"]}
\`\`\`
Human: Anna is 23 years old and she is 6 feet tall

定义完 prompt 后，我们只需将 prompt、model 和 output parser 链接在一起：

chain = prompt | model | parser
chain.invoke({"query": query})
People(people=[Person(name='Anna', height_in_meters=1.83)])

查看关联的 Langsmith 跟踪。

请注意，架构显示在两个位置：

  1. 在提示符中，通过parser.get_format_instructions();
  2. 在链中，接收格式化的输出并将其构建为 Python 对象（在本例中为 Pydantic 对象People).

自定义解析

如果需要，可以很容易地使用LangChain和LCEL.

要创建自定义解析器，请定义一个函数，将模型的输出（通常是 AIMessage）解析为您选择的对象。

有关 JSON 解析器的简单实现，请参阅下文。

import json
import re
from typing import List, Optional

from langchain_anthropic.chat_models import ChatAnthropic
from langchain_core.messages import AIMessage
from langchain_core.prompts import ChatPromptTemplate
from pydantic import BaseModel, Field, validator


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

    name: str = Field(..., description="The name of the person")
    height_in_meters: float = Field(
        ..., description="The height of the person expressed in meters."
    )


class People(BaseModel):
    """Identifying information about all people in a text."""

    people: List[Person]


# Prompt
prompt = ChatPromptTemplate.from_messages(
    [
        (
            "system",
            "Answer the user query. Output your answer as JSON that  "
            "matches the given schema: \`\`\`json\n{schema}\n\`\`\`. "
            "Make sure to wrap the answer in \`\`\`json and \`\`\` tags",
        ),
        ("human", "{query}"),
    ]
).partial(schema=People.schema())


# Custom parser
def extract_json(message: AIMessage) -> List[dict]:
    """Extracts JSON content from a string where JSON is embedded between \`\`\`json and \`\`\` tags.

    Parameters:
        text (str): The text containing the JSON content.

    Returns:
        list: A list of extracted JSON strings.
    """
    text = message.content
    # Define the regular expression pattern to match JSON blocks
    pattern = r"\`\`\`json(.*?)\`\`\`"

    # Find all non-overlapping matches of the pattern in the string
    matches = re.findall(pattern, text, re.DOTALL)

    # Return the list of matched JSON strings, stripping any leading or trailing whitespace
    try:
        return [json.loads(match.strip()) for match in matches]
    except Exception:
        raise ValueError(f"Failed to parse: {message}")
query = "Anna is 23 years old and she is 6 feet tall"
print(prompt.format_prompt(query=query).to_string())
System: Answer the user query. Output your answer as JSON that  matches the given schema: \`\`\`json
{'$defs': {'Person': {'description': 'Information about a person.', 'properties': {'name': {'description': 'The name of the person', 'title': 'Name', 'type': 'string'}, 'height_in_meters': {'description': 'The height of the person expressed in meters.', 'title': 'Height In Meters', 'type': 'number'}}, 'required': ['name', 'height_in_meters'], 'title': 'Person', 'type': 'object'}}, 'description': 'Identifying information about all people in a text.', 'properties': {'people': {'items': {'$ref': '#/$defs/Person'}, 'title': 'People', 'type': 'array'}}, 'required': ['people'], 'title': 'People', 'type': 'object'}
\`\`\`. Make sure to wrap the answer in \`\`\`json and \`\`\` tags
Human: Anna is 23 years old and she is 6 feet tall
chain = prompt | model | extract_json
chain.invoke({"query": query})
/Users/bagatur/langchain/.venv/lib/python3.11/site-packages/pydantic/_internal/_fields.py:201: UserWarning: Field name "schema" in "PromptInput" shadows an attribute in parent "BaseModel"
  warnings.warn(
[{'people': [{'name': 'Anna', 'height_in_meters': 1.83}]}]

其他库

如果您正在考虑使用解析方法进行提取，请查看 Kor 库。它是由LangChainmaintainers 和 it 有助于制作一个考虑示例的提示，允许控制格式（例如 JSON 或 CSV）并在 TypeScript 中表达架构。它似乎效果很好！