MTEB: Massive Text Embedding Benchmark

Generative Representational Instruction Tuning

Detect AI generated coding answers

Generative AI & Recommendation Engine --- Firat University / Faculty of Technology / Software Engineering / Final Project

Using machine learning on your anki collection to enhance the scheduling via semantic clustering and semantic similarity

Building a Medical chatbot using SBERT model. Dataset used was MEDQUAD

emoji_finder

This project demonstrates text clustering using SBERT embeddings. Includes text preprocessing, K-Means and DBSCAN clustering, and visualization of clusters. See scripts/ for detailed implementation.

Rust port of sentence-transformers (https://github.com/UKPLab/sentence-transformers)

Search in youtube channel

A GUI-based tool to calculate cosine similarity between two texts. It uses SBERT models from the sentence-transformers library for text encoding and tkinter for the interface.

Livebook to run a Phoenix_LiveView documentation Retrieval-Augmented Generation (RAG) enhanced LLM

Search with BERT vectors in Solr, Elasticsearch, OpenSearch and GSI APU

Embedding Representation for Indonesian Sentences!

A tool for performing semantic search within pdf documents leveraging sentence transformers.

A Heterogeneous Benchmark for Information Retrieval. Easy to use, evaluate your models across 15+ diverse IR datasets.

Forecasting the Adoption Process of Technology Using AI Methods

An implementation of the TaxRetrievalBenchmark task for the 🤗 Massive Text Embedding Benchmark (MTEB) framework.

This project is a corporate partnership with the online bookstore platform 'YES24', where we collect data from various platforms such as YouTube to analyze the latest trends and develop a service that recommends books matching these trends.