ProjectIntent Over Keywords: From Stitched Embeddings to a Production Fashion Agent · Module 13: Low-level design: API, sessions and data · part 15 of 26
Part 15 · Module 13: Low-level design: API, sessions and data

Module 13: Low-level design: API, sessions and data

24 min read·
About 55 minutes · Needs: Module 11 (StyleMe: the product problem), Module 12 (high-level design) · Code: part3-styleme/backend/src/styleme/api.py, sessions.py, catalog.py, config.py, agent/state.py

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
This module (highlighted): the API's contract, the sessions behind it and the catalogue the agent searches. Blue marks our own code; amber, used later, marks a model.

Module 12 (high-level design) drew StyleMe as boxes and arrows. This module opens four of those boxes: the chat request and its answer, the error shape, the session that remembers a conversation, the state of one turn, the catalogue and the settings. These are the parts you change most often and break most easily.

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