kor
Text extractor
An open-source wrapper around LLMs to extract structured data from text
LLM(😽)
2k stars
15 watching
91 forks
Language: Python
last commit: about 2 months ago information-extractionllmnatural-languagenatural-language-processingnatural-language-understanding
Related projects:
| Repository | Description | Stars |
|---|---|---|
 geeks-of-data/knowledge-gpt | Extracts and stores information from various sources using AI models to generate answers. | 283 |
 cognesy/instructor-php | A PHP library that simplifies the integration of Large Language Models into applications by providing structured data extraction and validation. | 230 |
 karlicoss/kobuddy | Extracts data from Kobo eReader databases for analysis and backup | 152 |
 recrm/archivetools | A collection of tools for extracting and analyzing data from web archives | 71 |
 monarch-initiative/ontogpt | An LLM-based tool for extracting structured information from text with ontology-based grounding. | 626 |
 bikash/documentunderstanding | Research and development of tools and techniques for extracting information from images and PDFs using deep learning and graph neural networks. | 96 |
 wse-research/loris-llm-generated-representations-of-sparql-queries | Generates natural language representations of SPARQL queries for knowledge graphs | 3 |
 quanteda/spacyr | An R wrapper around spaCy for natural language processing tasks | 251 |
 nikolamilosevic86/tabinout | A framework for extracting information from tables in scientific literature using a rule-based approach. | 42 |
 richardlitt/lrl | Developing tools and scripts to extract data from low-resource languages, focusing on language processing and machine learning applications. | 2 |
 koraykv/fex | A Lua-based library for feature extraction in computer vision applications using the SIFT algorithm | 10 |
 philipperemy/stanford-openie-python | Provides a Python interface to extract structured relation triples from plain text using CoreNLP's open information extraction system. | 639 |
 microsoft/unicoder | This repository provides pre-trained models and code for understanding and generation tasks in multiple languages. | 89 |
 stephenbrannon/iocextractor | Extracts and organizes Indicators of Compromise from unstructured text files into structured formats. | 135 |
 lang-uk/ner-uk | A Ukrainian NER corpus and annotation dataset for training and evaluating named entity recognition models. | 90 |