piah 0.1.0

automatically parse PDF's and texts to dataclasses

piah

---

Piah automatically parse the data from PDF's or texts based only in the dataclass that you provide and return the same dataclass fullfilled with the values. Piah is based in the OxyParser

Table of Contents

• Installation
• Example
• TODO
• Know Issues
• License

Installation

pip install piah

Example

from piah import Piah
from dataclasses import dataclass

@dataclass
class Person:
  name: str
  age: int

parser = Piah("gpt-3.5-turbo")
result = parser.parse("Hello Iam python and I have 33 years old", Person)

to parse PDF's:

result = parser.parse("example.pdf", Person)
#or
result = parser.parse(Path("example.pdf"), Person)

TODO

• Write docstrings
• Improve allowed types
• Improve system prompt

Know Issues

Seems that piah don't pass every time in the test, because the LLM don't parse correctly every time large PDF's

License

piah is distributed under the terms of the MIT license.