Skip to main content
Challenge

Build a Multilingual Catalog Onboarding and Evidence Synthesizer

Extract product details and compliance evidence from regional supplier invoices and informal notes. Map attributes into Beckn schema catalogs with automated multilingual translations for onboarding.

Workflow AutomationHosted by Vera
Challenge brief

What you are building

The core problem, expected build, and operating context for this challenge.

Extract product details and compliance evidence from regional supplier invoices and informal notes. Map attributes into Beckn schema catalogs with automated multilingual translations for onboarding.

Catalog Operations Specialist

Ingest supplier item drafts and receipt images with regional text annotations.

Normalize extracted attributes into structured catalog items referencing Beckn Core schemas.

Invoke Bhashini pipeline mock to generate translated titles and descriptions across target languages.

Generate a verified Beckn catalog JSON payload ready for staging import.

Web dashboard showing raw supplier notes, side-by-side multilingual item cards, and catalog export status.

Generate synthetic Kirana supplier invoices and product spec sheets using local fixture scripts. Starter examples below are synthetic. They are not downloaded records.

Beckn protocol specifications Implements Beckn Core discovery packet structures with context and item message catalog payloads.

pydantic-ai, fastapi, uvicorn. Ensures strict type validation across multi-attribute Beckn catalog payloads and nested descriptors. Local open weights or hosted LLM with multilingual instruction-following capability.

Submit runnable source, pinned dependencies, setup commands, a working interface, example outputs, and a recorded end-to-end demo. Include tests and an action log.

Correctly parses supplier attributes into Beckn descriptor, price, and category schemas.

Translates catalog entries into at least two target Indian language codes using ISO-639 tags.

Flags missing mandatory evidence fields including net weight and manufacturer declarations.

Exports compliant Beckn discovery message payloads without execution errors.

```json [ { "input": { "supplier_id": "SUP-701", "source_lang": "hi", "raw_text": "Kalonji seed 200g, MRP 120 INR, FSSAI lic 10012000000123", "target_langs": [ "ta" ] }, "expected_output": { "catalog_item": { "id": "ITEM-SUP701-01", "descriptor": { "name": "Kalonji Seeds 200g", "translations": [ { "code": "ta", "name": "கருஞ்சீரகம் 200g" } ] }, "price": { "currency": "INR", "value": "120.00" }, "evidence": { "fssai_license": "10012000000123", "verified": true } }, "status": "READY_FOR_STAGING" } }, { "input": { "supplier_id": "SUP-702", "source_lang": "hi", "raw_text": "Loose mustard oil, price 90", "target_langs": [ "bn" ] }, "expected_output": { "catalog_item": null, "status": "REJECTED_MISSING_EVIDENCE", "missing_fields": [ "fssai_license", "net_quantity", "packaged_date" ] } } ] ```

Uses synthetic merchant listings; enforces mock simulation of regulatory verifications without live API calls. Use mock external writes. Require human review before any real deployment.

Rules

Participation guide

Uses synthetic merchant listings; enforces mock simulation of regulatory verifications without live API calls. Use mock external writes and human review.

Delivery guide

How work is evaluated

Evaluation

Correctly parses supplier attributes into Beckn descriptor, price, and category schemas. Translates catalog entries into at least two target Indian language codes using ISO-639 tags. Flags missing mandatory evidence fields including net weight and manufacturer declarations. Exports compliant Beckn discovery message payloads without execution errors.

Submission format

Runnable source, pinned dependencies, setup commands, working interface, example outputs, recorded demo, tests, and action logs.

Datasets

Challenge datasets

Public datasets, plus the private datasets you have access to.

Evaluation rubric

How submissions are scored

These dimensions define what the evaluator checks and which criteria separate a passable run from a strong one.

Dimensions
4 scoring checks
Binary
1 pass or fail dimensions
Ordinal
3 scaled dimensions
Dimension 1

Complete workflow

Ingest supplier item drafts and receipt images with regional text annotations. Normalize extracted attributes into structured catalog items referencing Beckn Core schemas. Invoke Bhashini pipeline mock to generate translated titles and descriptions across target languages. Generate a verified Beckn catalog JSON payload ready for staging import.

Score scale
012
Score 0

Missing or incorrect.

Score 1

Partly complete, with documented gaps.

Score 2

Complete, with reproducible evidence.

Dimension 2

Correctness and evidence

Correctly parses supplier attributes into Beckn descriptor, price, and category schemas. Translates catalog entries into at least two target Indian language codes using ISO-639 tags. Flags missing mandatory evidence fields including net weight and manufacturer declarations. Exports compliant Beckn discovery message payloads without execution errors.

Score scale
012
Score 0

Missing or incorrect.

Score 1

Partly complete, with documented gaps.

Score 2

Complete, with reproducible evidence.

Dimension 3

Review interface

Web dashboard showing raw supplier notes, side-by-side multilingual item cards, and catalog export status.

Score scale
012
Score 0

Missing or incorrect.

Score 1

Partly complete, with documented gaps.

Score 2

Complete, with reproducible evidence.

Dimension 4

Safe execution

Uses synthetic merchant listings; enforces mock simulation of regulatory verifications without live API calls.

Binary check

This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.

Learning goals

What you should walk away with

  • Ingest supplier item drafts and receipt images with regional text annotations.

  • Normalize extracted attributes into structured catalog items referencing Beckn Core schemas.

  • Invoke Bhashini pipeline mock to generate translated titles and descriptions across target languages.

  • Generate a verified Beckn catalog JSON payload ready for staging import.

Resources and assets

Reference links and supporting material

Dataset notes

Generate synthetic Kirana supplier invoices and product spec sheets using local fixture scripts. Supplied starter examples are synthetic, not source extracts.

Challenge setup

Configuration summary for this challenge.

Challenge input

Input details are not configured.

Pydantic AI

Typed Python agent framework.

Evaluated output

No output checks are configured.

Evaluation checks
  • Ingest supplier item drafts and receipt images with regional text annotations. Normalize extracted attribut...
  • Correctly parses supplier attributes into Beckn descriptor, price, and category schemas. Translates catalog...
  • Web dashboard showing raw supplier notes, side-by-side multilingual item cards, and catalog export status.
Configured evaluation evidence
  • 2 public reference cases
Configured runtime
  • 2 configured tools

Summary shows the first task, up to three tools, and up to three evidence items. Open the technical recipe to view all configured items.

View technical recipe

Configured tools

Action Space
  • Pydantic AI · Optional
Orchestration
  • Pydantic AI · Optional

Evaluation contract

  • Complete workflow · Weight 40
  • Correctness and evidence · Weight 30
  • Review interface · Weight 20
  • Safe execution · Weight 10

Reference cases

  • 2 public reference cases

Workflow tasks

No workflow tasks are configured.

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Build a Multilingual Catalog Onboarding and Evidence Synthesizer