Popular GitHub Repositories for Wikipedia

WIT (Wikipedia-based Image Text) Dataset is a large multimodal multilingual dataset comprising 37M+ image-text sets with 11M+ unique images across 100+ languages.

Retrieve, Read and LinK: Fast and Accurate Entity Linking and Relation Extraction on an Academic Budget (ACL 2024)

ADAM - A Question Answering System. Inspired from IBM Watson

:video_camera: A tool for automatic video creation and uploading on YouTube

CoDEx: A set of knowledge graph Completion Datasets Extracted from Wikidata and Wikipedia

Python Voice Assistant project can: recognize and synthesize speech without Internet access; report the weather forecast anywhere in the world; make a search in the Google; make a video search in the YouTube; make a search for a definition in Wikipedia and read it; translate from the target language to the user's native language, and much more

Generated in real-time from random Wikipedia articles, microscale is a web-based, generative album.

Word2vec (word to vectors) approach for Japanese language using Gensim and Mecab.

A pipeline for training word embeddings using word2vec on wikipedia corpus.

Python Streamlit web app utilizing OpenAI (GPT4) and LangChain LLM tools with access to Wikipedia, DuckDuckgo Search, and a ChromaDB with previous research embeddings. Ultimately delivering a research report for a user-specified input, including an introduction, quantitative facts, as well as relevant publications, books, and youtube links.

?? STREAM: Search with Top Result Extraction & Answer Model ?? SEEKTOPIC ?? Tractor the Text Extractor ???? Tardigrade the Web Crawler

Pull high-quality, efficient embeddings for PubMed, arXiv and Wikipedia from Huggingface and use for local LLM inference/Retrieval Augmented Generation (RAG)

An F/OSS solution combining AI with Wikipedia knowledge via a RAG pipeline

CHOLAN: A Modular Approach for Neural Entity Linking on Wikipedia and Wikidata

Implementation, trained models and result data for the paper "Pairwise Multi-Class Document Classification for Semantic Relations between Wikipedia Articles"

Piazza-Updater automates updates to a Weaviate database with real-time vectorial data. By continuously searching the internet and integrating with Verba repositories, it enhances retrieval-augmented generation (RAG) capabilities, keeping your applications informed and responsive.

A Bert2Bert model which able to summarize articles!

Scraping Wikipedia by combining LangChain's agents and tools with OpenAI's LLMs and function calling

Word2Vec untuk bahasa Indonesia dari korpus Wikipedia ?

利用wikipedia中英文的語料訓練Word2vec模型