RAG implemented from scratch without using LangChain and LangGraph - designed specifically for processing and querying PDF documents with advanced support for visual content like tables, charts, and mathematical formulas.

An AI-powered crypto analytics platform integrating forecasting, sentiment, and on-chain intelligence, built with FastAPI, MCP protocol, and MLflow in a monolithic architecture.

Java Spring Boot RAG & hybrid search system for graduation projects: Elasticsearch BM25, BGE-M3 vector search, reranker, evidence-grounded QA, book recommendation, Vue 3, offline evaluation.

Self-Evolving RAG System with ChromaDB for continuous knowledge updates (6x daily), designed to overcome Large Language Model data cutoff limitations.

icron YOUR lightweight Personal AI Assistant - permanent Markdown memory with hybrid BM25 + vector search

Turn any LLM into a self-extending knowledge agent powered by a graph-structured memory - complete with PDF-to-graph ingestion, budget-aware optimisation, and dual-engine orchestration.

Terminal-based platform where specialized AI experts (Legal, Tech, Business) engage in real-time debates and collaborative problem-solving to provide multi-perspective analysis for complex decisions.

Retrieval Pivot Attacks in Hybrid RAG (Vector → Graph)

🧮 PINN Enterprise Platform - AI-Powered Physics Simulations with CopilotKit-style Research Canvas UI. Complete serverless architecture with RAG-powered code generation, 3D visualization, and global edge deployment.

Agentic personal medical assistant that reasons over medical data using multi-agent orchestration, with leveraging mutiple ML/DL pre-trained models, with addition to relational and vector databases.

Enterprise-grade AI voice assistant with RAG-powered customer support, real-time phone integration, and advanced conversation management

Production-ready intelligent knowledge management system built with LlamaIndex. Enables organizations to query, analyze, and extract insights from multiple data sources (documents, databases, APIs) through natural language using advanced RAG capabilities, multi-tenant architecture, and specialized query engines: SQL generation /intelligent routing.

Self-hosted, zero-trust RAG with role-based access control enforced at the database level.

ByteShaala 2.0 🚀 More powerful. More unified. Where code meets creativity — now built as one solid system. ⚡💻🔥

A retrieval-augmented generation pipeline in Python with a rigorous offline evaluation harness. Chunks and embeds documents, retrieves by vector similarity, and generates grounded answers — with pluggable LLM providers (including a deterministic local fake for tests) and metrics for retrieval quality and answer faithfulness. No API key required.

ทำนอกเวลา อยากไปสาย AI

Test Ai engineer Skill

Hands-on exercises and real-world projects built while learning the Anthropic Claude API—covering prompt engineering, RAG systems, tool use, MCP, and agent-based AI architectures.

Multi-agent AI system combining RAG, web search, fact-checking, and synthesis to produce well-cited research reports. Demonstrates agentic design patterns in action.

an AI interaction tool with RAG hybrid search, conversation context, web content processing and structured data analysis with LLM / GPT