Last updated: Mar 25, 2026

NGUYEN NHAT HUY

Ho Chi Minh City, Vietnam

System Architecture

Building an Agentic RAG System for Enterprise Documents

May 6, 2026 5 min read

Retrieval-Augmented Generation (RAG) has become the standard for grounding Large Language Models (LLMs) in proprietary data. However, standard RAG pipelines often struggle with complex, multi-hop reasoning queries. Learn how an Agentic approach solves this.

Deep Learning

Scaling Bilingual Speech-to-Text on Serverless GPUs

Apr 15, 2026 7 min read

Exploring the challenges and solutions in deploying WhisperX and NLLB models on Modal for real-time Vietnamese/English lecture translation. We achieved significant latency reduction using Silero VAD for segmentation.