Back to Prompt Library
implementation
Build the application
Inspect the original prompt language first, then copy or adapt it once you know how it fits your workflow.
Linked challenge: Build a Vernacular Artisan Catalog Story and Beckn Item Formatter
Format
Code-aware
Lines
86
Sections
11
Linked challenge
Build a Vernacular Artisan Catalog Story and Beckn Item Formatter
Prompt source
Original prompt text with formatting preserved for inspection.
86 lines
11 sections
No variables
1 code block
## Build
Convert vernacular voice descriptions from rural craft producers into structured product listings. Validate geographical indication claims and format items for open commerce discovery.
## User
Handicraft cooperative facilitator
## Workflow
1. Transcribe regional artisan voice recordings into vernacular text using mock Bhashini ASR pipelines.
2. Translate cultural craft specifications and materials into English catalog metadata via Bhashini NMT.
3. Extract raw material dimensions, care instructions, and geographical origin claims into structured records.
4. Assemble compliant Beckn Core 1.0.0 catalog items for human verification and publication.
## Interface
Voice recording upload pane, bilingual side-by-side translation editor, and Beckn catalog preview.
## Data
Synthesize artisan voice transcripts and regional craft profiles based on open handicraft directory attributes.
Starter examples below are synthetic. They are not downloaded records.
## Source
[Bhashini documentation](https://bhashini.gitbook.io/bhashini-apis)
Adopts Bhashini ULCA pipeline sequence conventions (ASR + NMT) with ISO-639 regional language codes.
## Tools
dspy, pydantic, fastapi.
Optimizes prompt chains for extracting standardized product attributes from dialect-heavy artisan speech.
Local Ollama instance or Claude API capable of zero-shot structured information extraction.
## Deliverables
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.
## Acceptance
- Translate regional audio transcripts to English while retaining cultural craft terminologies.
- Produce standardized Beckn item objects containing descriptor, price, and category_id.
- Flag unverified geographical indication references for artisan cooperative review.
- Validate final catalog document against Beckn schema version 1.0.0.
## Starter Examples
```json
[
{
"input": {
"artisan_id": "art-punjab-04",
"voice_transcript": "Ehe hath naal baniya phulkari dupatta hai pure georgette utte reshmi dhage da kamm",
"language_code": "pa"
},
"expected_output": {
"title_en": "Handmade Phulkari Dupatta",
"material": "Pure Georgette with Silk Embroidery",
"craft_style": "Phulkari",
"beckn_item": {
"descriptor": {
"name": "Handmade Phulkari Dupatta",
"short_desc": "Traditional hand-embroidered georgette dupatta"
},
"tags": [
{
"code": "craft_type",
"value": "phulkari"
}
]
},
"requires_origin_check": false
}
},
{
"input": {
"artisan_id": "art-rajasthan-12",
"voice_transcript": "Kala mitti da bartan bina stamp da par kishangarh da daawa",
"language_code": "hi"
},
"expected_output": {
"title_en": "Black Clay Pottery Vessel",
"material": "Terracotta Clay",
"craft_style": "Black Pottery",
"beckn_item": {
"descriptor": {
"name": "Black Clay Pottery Vessel",
"short_desc": "Handcrafted earthen vessel"
},
"tags": [
{
"code": "craft_type",
"value": "earthenware"
}
]
},
"requires_origin_check": true
}
}
]
```
## Safety
Does not publish unverified commercial claims to active networks; simulates Beckn registry interactions.
Use mock external writes. Require human review before any real deployment.Adaptation plan
Keep the source stable, then change the prompt in a predictable order so the next run is easier to evaluate.
Keep stable
Hold the task contract and output shape stable so generated implementations remain comparable.
Tune next
Update libraries, interfaces, and environment assumptions to match the stack you actually run.
Verify after
Test failure handling, edge cases, and any code paths that depend on hidden context or secrets.