如何僅使用提示 (不使用工具呼叫) 進行提取

工具呼叫 功能並非從 LLM 產生結構化輸出所必需。能夠良好遵循提示指示的 LLM 可以被委託以給定格式輸出資訊。

此方法依賴於設計良好的提示，然後解析 LLM 的輸出，使其能夠良好地提取資訊。

若要在不使用工具呼叫功能的情況下提取資料

1. 指示 LLM 產生遵循預期格式的文字 (例如，具有特定結構描述的 JSON)；
2. 使用輸出解析器將模型回應結構化為所需的 Python 物件。

首先，我們選擇一個 LLM

選擇聊天模型

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

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

提示

本教學旨在簡潔明瞭，但通常應包含參考範例以發揮效能！

使用 PydanticOutputParser

以下範例使用內建的 PydanticOutputParser 來解析聊天模型的輸出。

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())

API 參考：PydanticOutputParser | ChatPromptTemplate

讓我們看看發送到模型的資訊

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

定義提示後，我們只需將提示、模型和輸出解析器鏈接在一起

chain = prompt | model | parser
chain.invoke({"query": query})

People(people=[Person(name='Anna', height_in_meters=1.83)])

查看相關的 Langsmith 追蹤。

請注意，結構描述顯示在兩個位置

1. 在提示中，透過 parser.get_format_instructions()；
2. 在鏈中，接收格式化的輸出並將其結構化為 Python 物件 (在本例中為 Pydantic 物件 People)。

自訂解析

如果需要，可以使用 LangChain 和 LCEL 輕鬆建立自訂提示和解析器。

若要建立自訂解析器，請定義一個函數來解析模型的輸出 (通常是 AIMessage) 為您選擇的物件。

請參閱下方 JSON 解析器的簡單實作。

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}")

API 參考：ChatAnthropic | AIMessage | ChatPromptTemplate

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}]}]

其他函式庫

如果您正在尋找使用解析方法進行提取，請查看 Kor 函式庫。它由 LangChain 維護者之一編寫，它有助於製作考慮到範例的提示，允許控制格式 (例如 JSON 或 CSV) 並以 TypeScript 表示結構描述。它似乎運作良好！