Skip to main content

No project description provided

Project description

Lazy OpenAI

Lazy OpenAI is a Python library that simplifies interaction with OpenAI's API. It provides easy-to-use functions to generate text and structured outputs using Pydantic models.

Installation

To install Lazy OpenAI, run the following command:

pip install lazyopenai

Usage

from lazyopenai import generate

print(generate("Hi"))

Structured Outputs

from pydantic import BaseModel
from rich import print

from lazyopenai import generate


class Step(BaseModel):
    explanation: str
    output: str


class MathReasoning(BaseModel):
    steps: list[Step]
    final_answer: str


# https://platform.openai.com/docs/guides/structured-outputs?context=ex1#chain-of-thought
resp = generate("how can I solve 8x + 7 = -23", response_format=MathReasoning)
print(resp)

Function Calling

from pydantic import Field

from lazyopenai import generate
from lazyopenai.types import LazyTool


class AddNumbers(LazyTool):
    a: float = Field(..., description="First number to add")
    b: float = Field(..., description="Second number to add")

    def __call__(self) -> float:
        print("function called")
        return self.a + self.b


resp = generate(
    "100 + 10 = ?",
    tools=[AddNumbers],
)
print(resp)

TODO

  • Function calling
  • Memory
  • Async

Project details


Download files

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

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distribution

lazyopenai-0.1.1-py3-none-any.whl (6.4 kB view details)

Uploaded Python 3

File details

Details for the file lazyopenai-0.1.1-py3-none-any.whl.

File metadata

File hashes

Hashes for lazyopenai-0.1.1-py3-none-any.whl
Algorithm Hash digest
SHA256 ab5045cf39c122dfd53ada7748bd11ed2a9c5b4c04abdea820ed1c7a729425b0
MD5 ee8bcf20ef857cae71a52e1db1031592
BLAKE2b-256 d312a2a89ed4ee5ea4961c46778933a3345f0e952ddaa8400f9585d066242fd7

See more details on using hashes here.

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