The ChatGPT Long Term Memory package is a powerful tool designed to empower your projects with the ability to handle a large number of simultaneous users and external sources.

[ICLR 2025] - Cross the Gap: Exposing the Intra-modal Misalignment in CLIP via Modality Inversion

A Python library for long-term memory in language models. Improve conversational scenarios and create autonomous learning agents with enhanced context.

Python tools to retrieve text from CommonCrawl WARC files based on cdx index.

Spatial Data and Networks, Efficient Text Retrieval Methods, Ultra Fast Database Operators, Top-K Queries

CS336 Final Project - Vietnamese Legal Text Retrieval

This is a docker compose file for running elastic search in a docker container. It is based on the official elastic search docker image

A simple bot for HQ trivia that uses OpenCV.

Natural Language Processing Based Text Retrieval System in Python

A voice based personal assistant which has different functionalities right from voice based text, image retrieval, a chatbot to a text summarizer and an automatic question generator. Made by amalgamating different concepts of NLP and Machine Learning together

Codebase for "Self-supervised context-aware Covid-19 document exploration through atlas grounding" as well as links to the tools mentioned in the paper. Work done within ESAT-PSI at KU Leuven.

This repository contains code for all assignments in the Multimedia Computing and Applications (CSE563) course.

Unsupervised Passage Retrieval for Question Answering, Fact Checking, and Entity Linking on the KILT benchmark using the T5 language model series.

YTQueryBot is a web app that answers questions about YouTube videos. It uses Streamlit for the UI, LangChain for transcript processing, and OpenAI for generating responses from video data.

UHSR (Unified Hyperbolic Spectral Retrieval) is a next-generation hybrid text retrieval framework that combines BM25 (Lexical Search) with FAISS/Pinecone (Semantic Search), enhanced by Spectral Re-Ranking & AI-Powered Reranking. It supports multiple similarity metrics, provides interpretable normalized scores, & is designed for scalability & speed.

Minimal retrieval-augmented reasoning example in Python — pure local demo showing retrieval + summarization logic without APIs.