Skip to main content

structured llm outputs

Project description

struct-gpt

Features

  • Easy creation of custom models using the OpenAI API
  • Integration with Pydantic for model validation and serialization
  • Flexible configuration with retries and temperature settings

Usage

pip install struct-gpt


Template variables in the class' docstring are replaced with the keyword arguments passed to create.

from struct_gpt import OpenAiBase
from pydantic import Field

class SentimentSchema(OpenAiBase):
    """
    Determine the sentiment of the given text:

    {content}
    """

    sentiment: str = Field(description="Either -1, 0, or 1.")

print(SentimentSchema.create(content="I love pizza!").json())

outputs:

{
  "sentiment": "1"
}

Your classes can reference one another. You can also use the OpenAiMixin to add functionality to your own classes.

from struct_gpt import OpenAiBase, OpenAiMixin
from pydantic import Field, BaseModel
from typing import Mapping

class SentimentSchema(OpenAiBase):
    """
    Determine the sentiment of the given text:

    {content}
    """

    sentiment: str = Field(description="Either -1, 0, or 1.")

# you can use the OpenAiMixin to add functionality to your own classes
class SentimentAnalysis(BaseModel, OpenAiMixin):
    """
    Determine the sentiment of each word in the following: {text}

    Also determine the overall sentiment of the text and who the narrator is.
    """

    words_to_sentiment: Mapping[str, SentimentSchema]
    overall_sentiment: SentimentSchema
    narrator: str


print(
    SentimentAnalysis.create(
        text="As president, I loved the beautiful scenery, but the long hike was exhausting."
    ).json(indent=2)
)
outputs
{
  "words_to_sentiment": {
    "As": {
      "sentiment": "0"
    },
    "president,": {
      "sentiment": "1"
    },
    "I": {
      "sentiment": "0"
    },
    "loved": {
      "sentiment": "1"
    },
    "the": {
      "sentiment": "0"
    },
    "beautiful": {
      "sentiment": "1"
    },
    "scenery,": {
      "sentiment": "1"
    },
    "but": {
      "sentiment": "-1"
    },
    "long": {
      "sentiment": "-1"
    },
    "hike": {
      "sentiment": "-1"
    },
    "was": {
      "sentiment": "0"
    },
    "exhausting.": {
      "sentiment": "-1"
    }
  },
  "overall_sentiment": {
    "sentiment": "0"
  },
  "narrator": "president"
}

Improving reliability with examples

create can accept a list of examples to guide the model and improve its accuracy. Each example is a dictionary containing an input and output key. The input is the user message and the output is the expected assistant message, which should be a valid instance of the schema serialized as a string.

In this example, we are providing the model with examples of positive and negative sentiments:

from struct_gpt import OpenAiBase
from pydantic import Field

class SentimentSchema(OpenAiBase):
    """
    Determine the sentiment of the given text:

    {content}
    """

    sentiment: str = Field(description="Either -1, 0, or 1.")

examples = [
    {
        "input": "this library is neat!",
        "output": SentimentSchema(sentiment="1").json(),
    },
    {
        "input": "don't touch that",
        "output": SentimentSchema(sentiment="-1").json(),
    },
]

print(SentimentSchema.create(content="I love pizza!", examples=examples).json())

outputs:

{
  "sentiment": "1"
}

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

struct_gpt-1.0.0.tar.gz (4.1 kB view hashes)

Uploaded Source

Built Distribution

struct_gpt-1.0.0-py3-none-any.whl (3.8 kB view hashes)

Uploaded Python 3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page