information-retrieval

Train linear embedding adapters with triplet loss to align retrieval embeddings with your queries (RAG).

Experimental RAG playground for exploring retrieval quality, corpus construction, and filter-chain design. Features configurable ranking and filtering pipelines, visual document grounding, chat interfaces, web search, Open WebUI integration, and rich debugging insights. Ollama and vLLM, running in Dev Containers or natively on Linux and Windows.

[ISSTA 2024] PatchFinder: A Two-Phase Approach to Security Patch Tracing for Disclosed Vulnerabilities in Open Source Software

Serverless, lightweight, and fast vector database on top of DynamoDB

Training-free ordinal & sign quantization for compressed nearest-neighbour retrieval over high-dimensional embeddings. Pure Rust, zero system dependencies.

ABC: Achieving Better Control of Multimodal Embeddings using VLMs [TMLR2025]

Near-optimal vector quantization from Google's ICLR 2026 paper — 95% recall, 5x compression, zero preprocessing, pure Python FAISS replacement

Evals framework for Information Retrieval Systems

A Question Generation Application leveraging RAG and Weaviate vector store to be able to retrieve relative contexts and generate a more useful answer-aware questions

Source code of CIKM2021 Paper 'Pre-training for Ad-hoc Retrieval: Hyperlink is Also You Need'

LangGraphRAG: A terminal-based Retrieval-Augmented Generation system using LangGraph. Features include message history caching, query transformation, and vector database retrieval. Ideal for NLP researchers and developers working on advanced conversational AI and information retrieval systems.

Implements a framework to build Generative AI applications.

Recurrence Meets Transformers for Universal Multimodal Retrieval

PostgreSQL TurboQuant Index for PGVector

This project implements 30+ variants of ANN algorithms to find the K nearest neighbors in high-dimensional vector spaces. It is meant as a convenient sandbox: drop in your own ANN code, run a one-liner, and instantly compare build/search speed and recall against the bundled baselines.

An AI-powered search engine to interact with documentation using RAG and local LLMs. Privately deployable with vector search and a modern frontend.

[ACL 2026 Oral] Official code, UIQ benchmark, and pretrained checkpoints for "Omni-Embed-Audio: Leveraging Multimodal LLMs for Robust Audio-Text Retrieval" (Yoo et al., Sogang University)

Advance information retrieval system that combines advanced indexing, machine learning, and personalized search to enhance academic research and document discovery.