Efficient Retrieval Augmentation and Generation Framework

Simple customizable evaluation for text retrieval performance of Sentence Transformers embedders on PDFs

The Fastest State-of-the-Art Static Embeddings in the World

MTEB: Massive Text Embedding Benchmark

Manage a songs database using an HTTPS REST API supporting natural language searches.

Similarity detection for Github Issues + AI code reviews

ML Bot is a RAG Application built using google/gemma-2b-it local LLM

Language Models as Hierarchy Encoders

Pipeline to embed .txt documents and cluster them according to their topic.

Machine Learning and NLP models for improving text-based recommendations on TripAdvisor, using BM25, TF-IDF, embeddings, and a Hybrid approach.

A starting take on a fast and fully local NLP file organizer that organizes files based on their content.

Sentence-transformer model for payments classification. Fine-tuned from rubert-tiny-turbo

Booked is an intuitive app providing personalized book recommendations using vector search, connecting readers in a clean, community-driven space for all their book needs.

Top2Vec learns jointly embedded topic, document and word vectors.

AI-Powered Developer Search helps find top developers by skills, experience, and location using a MongoDB database. It utilizes GPT-4 for query refinement and cosine similarity for matching. AI-Powered Resume Search quickly finds matching resumes with vector embeddings and FAISS, optimizing candidate selection.

MINERS Fork⛏️: OTU CSCI 6720 - Extending on ICL and DPR

Simple API to upload images, store them in S3 and find other similar images among the uploaded ones. Created for a take home interview assignment.

Developing a retrieval system using semantic vector search.

Detect AI generated coding answers

AI Portfolio ? True : False