Healthcare pack

Supplier inventory CSV import API

Import a supplier catalog from CSV with GTIN, GLN and IBAN validation built in.

low risksupplier_inventory_v1
30-second curl
curl -X POST https://api.adaptivmapr.com/v1/uploads \
  -H "Authorization: Bearer $ADAPTIVMAPR_API_KEY" \
  -F "template=supplier_inventory_v1" \
  -F "file=@your_data.csv"
→ 5 canonical fields · 3 validated · low risk

Canonical columns

The whole schema, printed as it ships.

Every canonical column, the type each row carries, whether it is required, the field-level validators that fire on commit, and the multilingual header hints the cascade resolves against. This is the shipped definition, not a summary of it.

supplier_inventory_v1
fields
5
required
2
validated
3
hints
8
Canonical columnTypeRequiredValidatorsHeader hints the cascade matches
skustringyesskuartikelnrréférencecodigo
namestringyesmatched on the column name
gtinstringgtingtinean
glnstringglngln
ibanstringibaniban

Read the same definition as JSON at GET /v1/templates/supplier_inventory_v1. A hint match resolves on layer 2 — no LLM call, no token spend, just the flat per-map fee. Hover a validator id to see what it checks.

  • 5 canonical fields
  • 2 required
  • 3 validated
  • 8 header hints, 5 languages

Why it exists

Written for the file you actually receive.

The Supplier inventory template is the canonical schema for a clinic or hospital's supplier catalogue — SKUs, names, the GTIN that identifies the product to GS1, the GLN that identifies the supplier as a global location, and the IBAN that identifies the bank account you pay them at. Five fields covers the row. The template is `low` risk because suppliers are not patients. Customers use it when onboarding a new procurement system, when consolidating after a group purchasing organisation switch, or when running a quarterly catalog refresh against the latest GS1 directory. The IBAN validator runs mod-97 with a country restriction (CH, LI, DE, FR, IT by default) — fork and extend the country list for cross-border procurement. The cascade catches "référence" and "código" without an LLM call.

GTIN and GLN both run through the same GS1 mod-10 checksum — they share the algorithm because they share the encoding rules. IBAN runs mod-97 in 7-character chunks so the math stays inside JavaScript number precision; this matters because the validator runs in a Cloudflare Worker without BigInt available cheap.

Migration scenarios & the foreign headers they ship

Migration scenarios for Supplier inventory: switching a hospital's procurement system and porting the full vendor master, consolidating after a group-purchasing-organisation change, quarterly catalogue refreshes against the published GS1 directory, and ad-hoc imports for tender comparisons. Foreign headers we see weekly: "SKU / Artikelnummer / Référence / Codice articolo / Código / Bezeichnung / Désignation / Descrizione / GTIN / EAN / Barcode / GLN / Globale Standortnummer / IBAN / Compte bancaire / Konto / Bank Account". The checksum validators are load-bearing — supplier files are notorious for typos and pasted-from-Excel mishaps where a leading zero gets stripped; the GS1 mod-10 catches the corruption before it lands in the procurement database.

The cascade

Five layers, and the cheapest one wins.

Layers run in order and stop the moment a column resolves. That is the single biggest cost lever in the system: a column caught on layer 2 never reaches the metered layer 5.

  1. L1Statisticsno LLM

    Auto-accepts a header that past confirmations already resolved the same way, at {minN:100, minRatio:0.95} or {minN:20, minRatio:1.00}.

  2. L2Heuristicno LLM

    Normalises accents, punctuation and whitespace, then compares against the column name, the label, and every registered hint (DE / FR / IT / EN / ES).

  3. L3Fuzzyno LLM

    Token-set ratio plus Levenshtein over the normalised strings. Auto-accepts at 0.80 — it absorbs typos and reordered words.

  4. L4Semanticcheap, cached

    Embedding cosine between the header and the field’s label + hints. Catches the long tail of paraphrases.

  5. L5LLMmetered

    Everything still unresolved goes up in ONE batched, collision-aware call, constrained to this template’s column set so it cannot invent a field.

Try it

One template id, two ways in.

REST for your import pipeline, MCP for your editor. Both run the same cascade and both honour the same schema-only clamp.

REST · POST /v1/uploads

Name the template; the cascade picks up the rest. The canonical definition is read-only at GET /v1/templates/supplier_inventory_v1.

bash
curl -X POST https://api.adaptivmapr.com/v1/uploads \
  -H "Authorization: Bearer $ADAPTIVMAPR_API_KEY" \
  -F "template=supplier_inventory_v1" \
  -F "file=@your_data.csv"
→ upload created · mappings ready · confirm before commit

MCP · Cursor / Claude Desktop

Drop AdaptivMapr into your editor and call the same cascade as a tool. Schema-only calls leave only column names and up to three clamped sample rows.

mcp
// In Cursor or Claude Desktop with the AdaptivMapr MCP server installed:
adaptivmapr.match_headers({
  template_id: "supplier_inventory_v1",
  headers: ["sku", "name", "gtin", "gln"]
})
schema-only · headers and ≤3 rows, 80 chars each
MCP install instructions

Questions

Supplier inventory CSV import — FAQ

Fork the template and add a `price` field with type number. The canonical shape is identifier-focused (SKU / GTIN / GLN / IBAN) because prices change per contract and live elsewhere.
Fork the template and broaden the `countries` array in the IBAN validator. The validator otherwise treats the country as a hard reject.
No — only the checksum is verified locally. Registry lookup is a separate, paid GS1 service; we keep the cascade offline-safe.
Add them via a fork. The canonical row is identifier-shaped (SKU / GTIN / GLN / IBAN) because identifiers are stable; commercial terms shift contract-by-contract and belong in a separate table.

Ready when you are

Map supplier inventory in production — without shipping raw records.

Schema-only mode leaves only headers and a handful of clamped samples. Add full-data when you need row-level AI, routed in-region under a BAA.

No free tier · $10 prepaid wallet to start · every map draws a small flat fee, deterministic ones included