Advanced RAG pipeline using Re-Ranking after initial retrieval

Enhance the performance and cost-efficiency of large-scale Retrieval Augmented Generation (RAG) applications. Learn to integrate vector search with traditional database operations and apply techniques like prefiltering, postfiltering, projection, and prompt compression.

The phenomenon refers to the degradation of model performance on tokens in the middle of long sequences, where the model tends to focus more on the beginning and end tokens, losing context in the middle.

This repository is dedicated to exploring and implementing vector-based retrieval methods and reranking algorithms. It includes Jupyter notebooks with practical examples and code snippets that demonstrate how these techniques can be applied for efficient information retrieval in various datasets.

predicting a movie list with Two-sided Fairness-aware Recommendation Model (accotding to TFROM_A article) dataset : https://grouplens.org/datasets/movielens/100k/

Reranking from scratch using sentence-transformer, BM25, Cohere and Cross-Encoders !!!

A Java implementation of the classical Information Retrieval models in the TREC-COVID Challenge with the CORD19 Dataset

An LLM app leveraging RAG with LangChain and GPT-4 mini to analyze earnings call transcripts, assess company performance, using natural language queries (NLP), FAISS (vector database), and Hugging Face re-ranking models.

Exploring search relevance techniques.

Assignment on Information Retrieval course, implementing ranking algorithms with Lucene.

Frontend for comic book semantic search engine. Renders explanations along with search results

Library for plotting multiple ranks evolved over processing steps - draw a rankflow/bump chart

Multi-stage Retrieval using SPLADE or RM3 and T5.

Information Retrieval using KoSentence-BERT

Chroma DB vector database, with embedding and reranker models to implement a Retrieval Augmented Generation (RAG) system.

임베딩(SentenceTransformer) 및 재순위화(Re-Ranking)

Smart Untact Meeting / 전문가추천시스템 APP

This repository showcases a comprehensive approach to information retrieval, document re-ranking, and language model integration. It incorporates techniques such as document chunking, embedding projection, and automatic query expansion to enhance the effectiveness of information retrieval systems.

Training a customized dataset on fast-reid, evaluation and visualization

Alpaca, Bloom, DeciLM, Falcon, Vicuna, Llama2, Zephyr, Mistral(MoE), RAG, Reranking, Langchain, Langsmith..