Open Source AI Made Simple

Client-side retrieval firewall for RAG systems — blocks prompt injection and secret leaks, re-ranks stale or untrusted content, and keeps all data inside your environment.

js client for R2R: production-ready RAG engine with a sh*t ton of features.

Implementation of MLLM-based Self-Vision-RAG models

Perform intelligent research over document collections using hybrid search and LLMs.

A collection of 10+ chatbot types, from keyword-based and rule-based to AI-powered models. Explore various implementations for building intelligent chat interfaces and virtual assistants.

Pattern Based Question and Answer

This project applies AI techniques including LLMs, retrieval-augmented generation, prompt engineering, and distillation to understand unstructured text and generate structured, readable output. It focuses on extracting, organizing, and clarifying complex content using applied NLP techniques.

A robust Retrieval-Augmented Generation (RAG) system for noisy, multi-intent queries using LLM-based query understanding. Implemented in Python with PostgreSQL and OpenSearch for retrieval and storage.

Implementação de um pipeline de Retrieval-Augmented Generation (RAG) com Node.js, React e LanceDB.

Hybrid RAG Travel Assistant for Vietnam - Blue Enigma AI Challenge Submission

Customized LangChain Azure Document Intelligence loader for table extraction and summarization