Semantic Drift Media Engine (SDME)

Heramb Vengurlekar Thadomal Shahani Engineering College vengurlekarheramb19@gmail.com
Code

Keywords: FastAPI, Celery, Redis, Whisper, Docker, Gemini API

Overview

The Semantic Drift Media Engine (SDME) is a production-ready asynchronous media processing backend designed to handle audio/video ingestion, speech transcription, and contextual synthesis.

Key Architecture & Decisions

  1. Microservices with FastAPI & Next.js: Decoupled client interactions from heavy CPU/GPU processing pipelines.
  2. Distributed Queue with Celery & Redis: Long-running transcription and analysis tasks are offloaded asynchronously, keeping web API response latencies minimal.
  3. Local Whisper Optimization: Implemented lazy-loading and quantization strategies to run speech-to-text transcription within strict 512MB RAM constraints.
  4. LLM Synthesis & BYOK Security: Automated topic extraction and academic reference indexing via Google Gemini API with a Bring Your Own Key (BYOK) paradigm.
  5. Container Orchestration: Deployed using Docker Compose with isolated networks and health-checked workers.