SAATATYA LABS
Enquiry

Case study · Textile manufacturer · name withheld

Point a camera at a saree. Find it.

A leading textile manufacturer needed two answers fast: which catalog design is in this photo, and what do these marketplace settlement files mean. We built a visual search engine and an AI reconciliation layer that answer both.

Delivered · AI systemsDINOv3 ONNXQdrantGroqFastAPISupabase

384

Embedding dimensions

8

Vectors per image

6

Filter tiers

2

Systems, one platform

Station 01 · The problem

Which design is this?

A large catalog of designs, and a photo on a phone. Matching one to the other by eye takes minutes and gets it wrong. Meanwhile, every marketplace sends settlement spreadsheets in a different shape, and someone has to decode each one.

before · search by eye
PHOTOCATALOGMAYBERETRY← by eye
Two slow answers

Station 02 · The search

The camera finds the catalog.

A photo is cleaned of its background, cut into eight crops, and embedded by a vision model into 384 dimensions per crop. A vector database matches against the catalog through six tiers of attribute filters and returns the closest six designs.

pipeline · image to match
REMBG8 CROPSDINOV3 384-DQDRANT
Multi-vector search

Station 03 · The reconciliation

Settlement files, decoded.

Every marketplace names its columns differently. The system retrieves the closest known format, hands that context to a language model, and gets back exactly which columns matter for reconciliation. New formats stop being a research project.

analyze · settlement
$ analyze settlement.xlsx
→ detect header rows
→ retrieve nearest known format
→ LLM maps relevant columns
✓ ready to reconcile
RAG column detection

Station 04 · The evolution

From experiment to instrument.

The first version proved the idea with a heavier model running locally. The shipped system re-architected it: a lighter ONNX model, eight vectors per image, cloud vector search, authentication and a real deployment. Built to be owned, not demoed.

status · shipped
VECTORS 8 / IMAGEDIMS 384-DSTATUS DELIVERED
Delivered

System map · verified

The architecture, on paper.

Users

React 19 app

camera + uploads

Core

FastAPI core

DINOv3 ONNX · rembg · 8 crops

Data

Qdrant

8 vectors / image · 6 tiers

Supabase Postgres

users · mappings

Outside

Groq LLM

column detection

ImageKit CDN

catalog images

Arrived. Now let's chart yours.

Every client gets a new flight path. Bring us the destination and we will engineer the route.