jndiogo/sibila

Extract structured data from local or remote LLM models

47
/ 100
Emerging

This project helps you reliably extract specific pieces of information from text or images using large language models (LLMs). You provide a text prompt or an image, along with a clear description of the data you need (like a list of items or a receipt's total), and it outputs that exact data structure. This is for developers, data scientists, or MLOps engineers who want predictable, structured output from LLMs for integration into applications.

No commits in the last 6 months. Available on PyPI.

Use this if you need to consistently get structured data, like Pydantic objects or dataclasses, from diverse LLMs, whether they are running locally or are remote APIs.

Not ideal if you only need unstructured text generation or freeform JSON from LLMs and don't require strict schema adherence for your outputs.

data-extraction LLM-integration structured-output receipt-processing image-analysis
Stale 6m
Maintenance 0 / 25
Adoption 8 / 25
Maturity 25 / 25
Community 14 / 25

How are scores calculated?

Stars

54

Forks

8

Language

Python

License

MIT

Category

rag-qa-systems

Last pushed

Jun 21, 2024

Commits (30d)

0

Dependencies

11

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/jndiogo/sibila"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.