A Docker-powered service for PDF document layout analysis. This service provides a powerful and flexible PDF analysis service. The service allows for the segmentation and classification of differen…

LOTUS: The semantic query engine - process data with LMs as easily as writing pandas code

PDF Table Extractor is an innovative Python project designed to tackle the challenge of extracting tables from scanned PDF documents. Leveraging advanced optical character recognition (OCR) and ima…

Table Transformer (TATR) is a deep learning model for extracting tables from unstructured documents (PDFs and images). This is also the official repository for the PubTables-1M dataset and GriTS ev…

Distributed Training Over-The-Internet

A library for company name parsing based on cleanco

BluOS API client

Qdrant - High-performance, massive-scale Vector Database for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/

tiktoken is a fast BPE tokeniser for use with OpenAI's models.

DSPy: The framework for programming—not prompting—foundation models

Pydantic extension for annotating autocorrecting fields.

A RDF-based representation of the HTML-vocabulary to express HTML-documents in RDF, rendering them semantic.

Tools for reading and fusing live data streams from Polar OH1 (PPG) and H10 (ECG) sensors. pip install polarpy.

Python client for Polar AccessLink API.

Python client for Polar web API.

A free, opensource, multiplatform, universal viewer and toolbox intended for, but not limited to, timeseries storage files like EEG, EMG, ECG, BioImpedance, etc.

Developer APIs to Accelerate LLM Projects

Full text search in your Pandas dataframe

Open source libraries and APIs to build custom preprocessing pipelines for labeling, training, or production machine learning pipelines.

Fast and robust date extraction from web pages, with Python or on the command-line

Heuristic based boilerplate removal tool

fast python port of arc90's readability tool, updated to match latest readability.js!

A Python 3 compatible version of goose http://goose3.readthedocs.io/en/latest/index.html

img2table is a table identification and extraction Python Library for PDF and images, based on OpenCV image processing

Camelot: PDF Table Extraction for Humans

Plumb a PDF for detailed information about each char, rectangle, line, et cetera — and easily extract text and tables.

Fork of https://github.com/infoscout/weighted-levenshtein

A collection of 24 x 24 dp SVG spinners! (CSS & SMIL)

borb is a library for reading, creating and manipulating PDF files in python.