Catalog PyPI
PACKAGE EXPLORERView in registry

ai-alchemy

PyPI

Lightweight package for arbitrary data transformation and validation using AI models and first class python libraries like Pandas and Pydantic.

Versions collected1
Direct dependencies4From release 1.0.1
Last observed21 Oct, 09:55 UTC

README

Version 1.0.1 documentation

AI Alchemy

AI Alchemy is a Python library that provides a convenient way to interact with AI models, such as OpenAI's GPT-3.5 Turbo, and perform transformations on data.

Getting Started

These instructions will get you a copy of the project up and running on your local machine for development and testing purposes.

Prerequisites

You need to have Python installed on your machine. You can download Python here.

Installation

You can install AI Alchemy via pip:

pip install ai_alchemy

Usage

Here's a basic example of how to use AI Alchemy:

# Import necessary libraries
import os
import ai_alchemy
from ai_alchemy.ai import OpenAIWrapper
from pydantic import BaseModel

# Instantiate a wrapper for an AI model
openai = OpenAIWrapper(api_key=os.environ["OPENAI_API_KEY"], model="gpt-3.5-turbo")

# Define a Pydantic model
class User(BaseModel):
    name: str
    age: int

# Input data
data = "John Smith is 25 years old, five foot ten inches tall, and weighs 150 pounds."

# Use AI Alchemy to transform the data into a Pydantic model
model = ai_alchemy.cast.str_to_pydantic_model(data, openai, User)

# Now `model` is a `User` instance with `name` and `age` populated from `data`

Downloads & popularity

Awaiting observations

No metric observations yet

Download counts and popularity will appear here as the collector receives them.

Versions 1

Collected releases
VersionPublishedDirect dependenciesOpen version
1.0.13 Jun 20244

Package advisories

0
No matching advisories collected

This describes our collected data; it is not a security assessment.

Metadata history

Meaningful changes
Current collected state Current

Observed since 21 Oct, 09:55 UTC

No superseded metadata states collected. Unchanged observations do not create new revisions.

Record identity

package:6599b5fa5309dbc26c94f2e794bd026bee82d784ebb94e6b031fe014064ce98a