MantisAI/sieves
Plug-and-play document AI with zero-shot models.
This tool helps non-technical professionals extract specific information from various documents like PDFs, images, and Office files. You provide the documents and describe what data you need (e.g., product names, addresses, or classifications like 'spam' vs. 'not spam'), and it delivers that structured data back to you. This is ideal for anyone who regularly processes large volumes of documents and needs to automate data extraction or categorization without writing complex code.
125 stars. Available on PyPI.
Use this if you need to quickly and accurately pull out structured data from documents or classify text, without having to train a new AI model from scratch.
Not ideal if your primary goal is to build deep learning models from the ground up or if your document processing needs are very simple and can be handled with basic keyword search.
Stars
125
Forks
8
Language
Python
License
MIT
Category
Last pushed
Feb 16, 2026
Commits (30d)
0
Dependencies
20
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/MantisAI/sieves"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
xiaoya-li/Instruction-Tuning-Survey
Project for the paper entitled `Instruction Tuning for Large Language Models: A Survey`
rafaelpierre/bullet
bullet: A Zero-Shot / Few-Shot Learning, LLM Based, text classification framework
TencentARC-QQ/TagGPT
TagGPT: Large Language Models are Zero-shot Multimodal Taggers
amazon-science/adaptive-in-context-learning
AdaICL: Which Examples to Annotate of In-Context Learning? Towards Effective and Efficient Selection
andrewzamai/SLIMER_IT
An Instruction-tuned LLM for zero-shot NER on Italian