Buy Okkular if your catalogue is fashion or furniture and the bottleneck is tagging product images for search and filters. Choose Anglera if enrichment must mine supplier documents, cite its sources, and keep working after launch.
Both claim to enrich product data. This page is about where that claim stops.
Product data is a practice, not a project: Okkular's pipeline is built to make an existing catalogue findable from images, feed fields and API data, and the open question next to it is who sources the fields that only exist in a supplier document, and who re-runs them when the mill spec or the taxonomy moves.
Mine every spec from every source.
Every value traced to a document you can open. The catalog is only as honest as what it was built from.
Aim the catalog at the buyer who actually buys.
Grounded data still loses if it answers questions nobody asked. Alignment is what turns specs into conversion.
Product data is a practice, not a project.
Markets move, suppliers reissue, buyers change what they ask for. A catalog that is right in March is wrong by August unless something is watching.
Scored against public documentation. Grouped by the three acts — so you can see which ones Okkular leaves on your desk.
Mines product images, feed fields, API data; no supplier PDFs
PDFs, spec tables, drawings, manuals, images, sites
Fills the taxonomy you configure upfront; proposes no new fields
Proposes fields your schema never had
Per-category attributes, preferred names, synonyms collapse variants
Normalizes and governs allowed values, versioned
Classifies SKUs to your taxonomy; segment attribute hierarchies
Auto-classifies; channel and marketplace mapping
Review queue shows predicted tags; no per-value source citations
Every value cites its source doc and page
Varies copy by product segment and channel, not buyer persona
B2B specifier and B2C shopper enriched differently
Search-term oriented, but synonyms configured by your team
Reviews, search, competitor rails, social — fed back
Description-Gen writes descriptions, channel variants, alt text
Original copy per persona and channel
Ingests and analyses existing images; generates none
Generates studio-grade imagery for photoless SKUs
Tags new products; human review gates each export
Re-enriches on its own after go-live
No catalogue completeness scoring or health tracking published
Scored against your standards; nothing publishes below bar
Direct integration to Shopify, SAP, PIM; CSV/JSON exports
Writes back to PIM, ERP, warehouse, commerce
Public REST API and docs; no webhooks or MCP server found
API, webhooks, and MCP servers
Software tool; your team reviews and approves tags
Anglera owns the work; review is a guardrail
“Buyer signals” is the emptiest phrase in this category, so here is the literal thing. Each of these is an observation from a live market, the gap it exposes, and the field that gets created as a result.
"3 season freestanding 2p tent" returns nothing. The same sessions fall back to browsing by colour, then bounce.
Season rating is not a visual property. It comes off the manufacturer's stated spec, and it is the field the shopper is actually buying on.
tent_season_rating1-season | 2-season | 3-season | 3-4-season | 4-season. Taken from the manufacturer's stated rating, never inferred from fly denier or pole count.Spec sheet reads "cotton drill, 285 gsm, 145 cm usable width, 3% shrinkage after first wash." The PDP reads "cotton fabric, navy."
285 gsm is what tells a customer this is bottomweight: workwear and upholstery, not a summer shirt. It is a number on a PDF, and a swatch photo of navy drill looks like a swatch photo of navy poplin.
fabric_weight_gsmInteger gsm, plus a governed band: lightweight (<150), midweight (150-250), bottomweight (251-400), heavyweight (>400)."Seat height is 47 cm and it won't clear our table apron. Third chair I've sent back."
Oak, tapered leg and mid-century are all on the record. The one measurement driving the return is not a field at all, so it can't be filtered, can't be matched against table clearance, and can't be checked before the chair ships.
seat_height_mmInteger millimetres, floor to front edge of seat. Supplier cm and inch values converted on ingest, not stored as given.Okkular publishes its pipeline: product images, product feed fields and API-provided information run through visual and text analysis, map to your taxonomy, and are reviewed before export ([tag-gen](https://www.okkular.io/tag-gen/)). The outputs it names are discovery attributes — product type, colour, pattern, material, texture, style, silhouette, synonyms, image alt text — aimed at search, filters and recommendations. Fabric weight in gsm, seat height, a season rating: those sit in a mill spec sheet or a supplier PDF that arrived as an email attachment, and nobody re-reads them when the mill changes its yarn. Then the taxonomy drifts: you add a value this season, last season's SKUs keep the old one, and both sit in the same filter. Anglera treats both as standing work: source the fields from the documents, re-derive them when the document changes, re-normalise the back catalogue when the vocabulary moves.
Values are normalized into a governed, versioned set of allowed values — so a filter works, and keeps working after the next import.
3/4 in0.75"3/4"19mm3/4 inchDN200.75 in (DN20)Six suppliers, six spellings, one physical size. Filters only work once they agree.
BlkblackBLACK MATTEMatte BlkRAL 9005Black — MatteFree text makes a colour filter useless. A governed value makes it a facet.
SS316316 StainlessStainless Steel 316A4 StainlessStainless Steel — 316 / A4Same alloy, four vocabularies, plus a trade name. Buyers search all of them.
Filling the fields you defined has an invisible ceiling: a catalog can hit 100% complete and still miss the attribute that loses the sale, because completeness is measured against a schema someone drew years ago. Schema Foundry reads competitor listings, buyer searches, review complaints and your supplier docs, and proposes the fields you never defined — which is where Okkular stops.
How Schema Foundry works
Okkular is an Australia/New Zealand-founded AI product enrichment and discovery platform for retail catalogues. Its core product, Tag-Gen, uses computer vision to turn product images, feed fields, and API data into structured attribute tags — product type, colour, pattern, material, style, occasion — plus search synonyms and image alt text, mapped to the customer's configured taxonomy. Description-Gen then writes SEO product descriptions and channel-tailored variants from that metadata. It also sells visual search and recommendations, targeting fashion, footwear, furniture, craft and DIY, and general merchandise.
Pricing: Partially public. Tag-Gen's Shopify listing publishes usage-based tiers billed in USD every 30 days: Small $80/mo for 100 images ($1.10 per extra), Medium $150/mo for 200 ($1 per extra), Large $350/mo for 500 ($0.90 per extra), each with a 60-day trial. Direct/enterprise, Description-Gen, visual search, and SAP/PIM/API pricing is undisclosed — the site routes to a demo request.
Okkular websiteFashion, footwear and furniture retailers whose products are best described visually — especially Shopify teams wanting image-driven tagging and SEO copy live fast at published, low-entry pricing.
We'd rather tell you here than in month three of an implementation.
Capability verdicts reviewed against Okkular's public documentation on July 14, 2026. Vendors ship quickly — if something here is out of date, tell us and we'll correct it.
Bring one category and your supplier files. In 30 minutes you'll see it enriched — complete, structured, and consistent enough to launch on — plus the attributes your schema didn't have yet.
Book a demo