ProjectIntent Over Keywords: From Stitched Embeddings to a Production Fashion Agent · Module 22: Containers and the local stack · part 24 of 26
Part 24 · Module 22: Containers and the local stack

Module 22: Containers and the local stack

24 min read·
About 40 minutes · Needs: Module 2 (the stitched architecture), Module 12 (the high-level design of StyleMe), Module 21 (security: uploads, rate limits, the proxy secret) · Code: docker-compose.yml, Makefile, .env.example, part1-video-rag-stitched/Dockerfile, part2-video-rag-unified/Dockerfile, part3-styleme/backend/Dockerfile, part3-styleme/frontend/Dockerfile, part3-styleme/frontend/nginx.conf.template, originals/styleme/fashion-agent/Dockerfile

Where this fits

WHERE THIS FITS Intent Over Keywords this module PART 1: STITCHED VIDEO RAG three models, two spaces, RRF PART 2: UNIFIED VIDEO RAG one model, one space PART 3: STYLEME FastAPI, LangGraph, React QUALITY AND OPERATIONS evals, Docker, Cloud Run Frames ffmpeg, one per 5 s CLIP ViT-B/32 frames + text, 512 d Whisper base speech to text MiniLM 64-word chunks, 384 d Two collections p1_visual, p1_text Rank fusion RRF, k = 60 Gemini answer from transcript text API + Streamlit upload, ask, sources Windows ffmpeg, video + audio Embedding 2 Gemini, one vector One collection p2_unified, no fusion Notes + answer Gemini, cited times React web chat, photo, chips nginx one URL, /api proxy FastAPI /api/chat, limits Sessions in memory, cap of 3 Planner intent before retrieval Implementer batched embed, search Generator stylist reply, ids Grounding check no LLM, drops invented Gemini flash-lite, embedding 2 Qdrant styleme_products Catalogue ingest image + title vectors Langfuse optional traces Test video 26 questions, 4 kinds Video eval Part 1 vs Part 2 Agent evals intent, grounding Guards uploads, limits, secrets Containers compose profiles Cloud Run StyleMe only CI/CD GitHub Actions, WIF Original code v1, v2, fashion-agent
The parts this module packs and starts (blue): the compose stack of all three parts, the Part 1 API and UI, StyleMe's FastAPI service and the nginx front door.

Every earlier module described code. This one packs all three parts into containers, so that one command starts any of them on a laptop with the same operating system, Python, ffmpeg, model weights and nginx that the author tested. The StyleMe images built here are the exact images that Module 23 deploys to Cloud Run; the Part 1 and Part 2 images stay on your machine.

The rest of this project is yours to keep

This project is bought on its own, once, and stays readable afterwards, including the parts added to it later.

Buy this project · ₹799See what is inside

Or open everything with a plan