Pydantic程序指南¶

使用guidance通过LlamaIndex生成结构化数据。

使用guidance，您可以通过强制LLM输出所需的标记来确保输出结构是正确的。 当您使用容量较低的模型（例如当前的开源模型）时，这将特别有帮助，否则模型可能难以生成符合所需输出模式的有效输出。

如果您在colab上打开这个笔记本，您可能需要安装LlamaIndex 🦙。

In [ ]:

%pip install llama-index-program-guidance

%pip install llama-index-program-guidance

In [ ]:

!pip install llama-index

!pip install llama-index

In [ ]:

from pydantic import BaseModel
from typing import List
from guidance.llms import OpenAI

from llama_index.program.guidance import GuidancePydanticProgram

from pydantic import BaseModel from typing import List from guidance.llms import OpenAI from llama_index.program.guidance import GuidancePydanticProgram

定义输出模式

In [ ]:

class Song(BaseModel):
    title: str
    length_seconds: int


class Album(BaseModel):
    name: str
    artist: str
    songs: List[Song]

class Song(BaseModel): title: str length_seconds: int class Album(BaseModel): name: str artist: str songs: List[Song]

定义指导pydantic程序

from pydantic import BaseModel

class Guidance(BaseModel):
    title: str
    description: str
    steps: List[str]

In [ ]:

program = GuidancePydanticProgram(
    output_cls=Album,
    prompt_template_str=(
        "Generate an example album, with an artist and a list of songs. Using"
        " the movie {{movie_name}} as inspiration"
    ),
    guidance_llm=OpenAI("text-davinci-003"),
    verbose=True,
)

program = GuidancePydanticProgram( output_cls=Album, prompt_template_str=( "Generate an example album, with an artist and a list of songs. Using" " the movie {{movie_name}} as inspiration" ), guidance_llm=OpenAI("text-davinci-003"), verbose=True, )

运行程序以获得结构化输出。 蓝色突出显示的文本是我们指定的变量，绿色突出显示的文本是由LLM生成的。

In [ ]:

output = program(movie_name="The Shining")

output = program(movie_name="The Shining")

Stop program

Generate an example album, with an artist and a list of songs. Using the movie The Shining as inspiration
```json
{
  "name": "The Shining",
  "artist": "Jack Torrance",
  "songs": [{
  "title": "All Work and No Play",
  "length_seconds": "180",
}, {
  "title": "The Overlook Hotel",
  "length_seconds": "240",
}, {
  "title": "The Shining",
  "length_seconds": "210",
}],
}
```

输出是一个有效的Pydantic对象，我们可以使用它来调用函数/API。

In [ ]:

output

output

Out[ ]:

Album(name='The Shining', artist='Jack Torrance', songs=[Song(title='All Work and No Play', length_seconds=180), Song(title='The Overlook Hotel', length_seconds=240), Song(title='The Shining', length_seconds=210)])