rag-pipelines

Full-stack LLM Engineering Lab. Features: Autonomous Agents (ReAct/AutoGPT) | Fine-Tuning Llama/Mistral (SFT/DPO) | Large Model Deployment (DeepSeek 671B / 2.5-bit) | Advanced RAG (Hybrid Search) | Function Calling (Stream/Text-to-SQL/External APIs) | Frameworks (LangChain, Semantic Kernel, OpenAI) | Daily SOTA Paper Tracking. From theory to 0-to-1

Built a Retrieval-Augmented Generation (RAG) chatbot using LangChain and OpenAI models.

RAG-based conversational AI for Superior University — 4,750+ pages indexed using LangChain, FAISS, and Groq LLM

This course is designed to teach you how to QUICKLY harness the power of the LangChain library for LLM applications. Build 3 end-to-end working LangChain based generative AI applications with no fluff, no toy examples - just real projects using real APIs and real-world skills.

Smart text chunker for LLM preprocessing (sections → paragraphs → sentences → hard splits).

Persistent memory and context management for AI agents. Enable long-term recall, session continuity, and consistent behavior across conversations and workflows.

An advanced Agentic AI Orchestrator disguised as a Microsoft Outlook Add-in. It intercepts communications and schedules tasks using a Multi-Tier Semantic Router, a specialized Physics Engine, and an asynchronous Two-Phase RAG pipeline to protect deep work.

Official MCP Server for Agent-Commerce-OS. Enables AI agents (Claude, etc.) to autonomously normalize web data via our Zero-Trust and Metered Billing infrastructure.

Track member activity, popular channels, peak times, and growth trends. Community data without expensive analytics platforms.

Decentralized Web3 security protocol for protecting crypto assets from rug pulls and malicious activities using smart contracts, anomaly detection, automated fund recovery, and real-time transaction monitoring. Built at Hackspire 1.0.

Built and benchmarked a scalable semantic retrieval pipeline comparing lightweight bi-encoders and QLoRA-tuned large cross-encoders under real-world efficiency constraints

AI-powered loyalty program plugin for RAG pipelines. Automate rewards, boost retention, and maximize customer lifetime value on WordPress.

Full-Stack Developer | Blockchain & Cybersecurity Enthusiast | Building scalable and secure digital solutions.

A simple RAG project to fetch answers from Wikipedia/Research papers

A high-performance, production-grade pre-LLM document intelligence operating system that transforms unstructured documents into synchronized mathematical representations to build budget-aware, optimized context for AI agents.

Agentic RAG (Retrieval-Augmented Generation) system using LangGraph with minimal code. Most RAG tutorials show basic concepts but lack production readiness — this repo bridges that gap by providing both learning materials and deployable code.

Gate RAG pipelines by membership tier. Monetize AI access, control permissions instantly, sync with WordPress membership—no coding.

A/B test RAG & AI pipelines in WordPress. Optimize prompts, retrieval, and responses to maximize conversions with statistical validation.

WordPress plugin for indexing, organizing, and showcasing RAG pipelines. Searchable directory with filtering, automation integration, and SEO built-in.

A robust, production-grade pipeline converting complex Medical PDFs into structured, RAG-ready JSONL datasets. Features smart table merging, multimodal extraction, and dynamic layout analysis using Detectron2 & PaddleOCR.