A sophisticated RAG (Retrieval-Augmented Generation) Telegram bot that transforms articles and documents into interactive knowledge bases. Upload PDFs/URLs and get AI-powered answers with source citations.

Sovereign AI for Saudi MOI Services | ALLaM-7B · Judge 9.03/10 · 8 Languages · 95.8% Price Accuracy | Cross-Lingual Hybrid RAG + KG Price Bypass + T-S-T Translation + 5-Layer Safety

Prizolov Agent OS: The Open-Source Orchestration Framework for Autonomous AI Empires. Built by Dm.Andreyanov for RAG-driven business automation.

Production-Ready AI Systems • Enterprise Architecture • Azure & Beyond

High-density RAG Semantic Search Engine & Quran Corpus (GEO/SEO Architecture)

🛡️ Context-Aware AI SRE & Code Review Agent. Omni-SRE uses institutional memory (Supabase pgvector) and Groq (Llama-3.1) to find security vulnerabilities and architectural debt in Pull Requests with real-time GitHub Webhook synchronization

AI-First Full-Stack Engineer building production LLM systems. 3 years shipping RAG architecture, multi-model orchestration, real-time AI. Open to remote roles.

Juro: A Retrieval-Augmented Generation AI Chatbot for Enhancing Legal Information Access in Resource-Constrained Settings

Chatbot de IA que responde a perguntas sobre meu currículo, utilizando Python, FastAPI, Streamlit e a arquitetura RAG com a API do Google Gemini.

An AI-powered RAG SaaS that transforms static PDFs into interactive, voice-synthesized personas. Features real-time ultra-low latency conversations using Vapi and 11 Labs, built with a secure Next.js 15+ architecture, MongoDB indexing, and Clerk billing.

A feature-rich knowledge sharing platform for companies, featuring blogs, technical documents, notifications, and a full admin panel.

A next-gen AI/ML interview preparation platform featuring a secure Python code sandbox, dependency-graph learning paths, and RAG-based mock interview agents.

A Retrieval-Augmented Generation (RAG) chatbot designed to ingest custom knowledge bases. Built with Python, it utilizes Groq for high-speed LLM inference and Pinecone for vector storage to process text data and deliver precise, context-aware conversational AI.

An AI-powered financial monitoring system utilizing RAG (Retrieval-Augmented Generation) with Weaviate and LangChain to analyze currency fluctuations and generate intelligent, context-aware alerts.

A Green AI Knowledge Governance Engine for Enterprise RAG. Features FinOps-driven ingestion, PII redaction middleware, and strict lifecycle management to ensure zero-trust, cost-optimized AI. Built with FastAPI, React, Qdrant, and GPT-4o.

An enterprise-grade orchestrator for multilingual AI voice agents. Powered by Azure Speech and GPT-4o RAG to deliver zero-latency, hallucination-free support in any language.

Designing and building scalable AI systems - from deep neural networks to production-ready LLM applications.

AI inference platform architecture lab demonstrating admission control, fairness scheduling, bounded queues, and graceful degradation under burst traffic.

The project is designed as a practical introduction to RAG systems, showing how retrieval and generation can be orchestrated to answer user queries using only relevant document chunks. It is well-suited for learners and portfolio use, highlighting modern AI patterns like embeddings, vector search, and LLM integration.