Index live
§ 01 · Premise

Search for parts
the way a workshop
actually talks.

A domain-specific embedding model trained on India's auto-part catalogs, OEM cross-references, and the Hinglish a mechanic actually uses. Because "Swift dicky strut" should find the tailgate gas spring — not nothing at all.

Parts indexed1.2M
p95 latency42 ms
PreviewQ2 2026
Built byThe night shift
§ 02 · The gap

A buyer asks for a "Scorpio dicky wala strut, 2015, diesel ka". The catalog lists it as Tailgate Lift Support · 0609AA0044N. Keyword search misses. Fuzzy match misses worse.

General-purpose embedding models (OpenAI, Cohere, Gemini) were trained on the open web. They don't know that a dicky is a boot, a silencer is an exhaust muffler, or that Alto K10 parts interchange with Maruti 800 on 60% of SKUs. PartIndex is trained on that language.

§ 03 · On record

Live against a 1.2 M-part index.

idx.srch
p95 42ms
Clutch disc assembly
0602AA0050NScorpio mHawk 2.2L 2014–17·Valeo
0.94
match
Clutch plate 310 mm
DWF-0310-V2Scorpio · XUV500 diesel·Valeo
0.91
match
Pressure plate cover assy
0602AA0048NScorpio Getrag 2014–17·Mahindra OEM
0.87
match
Sampled from production index, anonymized.Rotates every few seconds
§ 04 · How it works

A compact bi-encoder, fine-tuned on triplets of query, matching part, and near-miss — with a vehicle-compatibility graph underneath.

260M parameters, runs on a single A10 at under 50 ms p95. No LLM round-trip in the hot path. Every SKU is bound to the vehicles it fits — so "will this clutch work on my Scorpio?" gets a straight yes or no, not a confidence score dressed up as one.

§ 05 · Early access

Shipping to ten partners in Q2 2026.

If you run an auto-parts marketplace, a distributor network, a workshop-facing app, or an OEM e-commerce surface — one line about your use case is enough.