Build an ONDC Multilingual Routing Assistant with LlamaIndex and Coplay AI
Open Network for Digital Commerce (ONDC) aims to democratize e-commerce across India. To assist rural micro-entrepreneurs and consumers, this challenge requires building an intelligent multilingual service routing agent using LlamaIndex index structures and Coplay AI assistant interfaces. The system will parse localized catalog schemas, index multi-vendor product inventories, and respond to natural language queries in Indic languages (Hindi, Tamil, Marathi) while executing optimal buyer-seller logistics matching.
What you are building
The core problem, expected build, and operating context for this challenge.
Construct an ONDC multilingual service routing system using LlamaIndex indexers and Coplay AI interactive assistant interfaces.
How work is evaluated
Validates retrieval recall and Indic language search accuracy for localized ONDC product queries.
Challenge datasets
Public datasets, plus the private datasets you have access to.
How submissions are scored
These dimensions define what the evaluator checks and which criteria separate a passable run from a strong one.
product_match_test
Validates that relevant organic wheat flour product is returned.
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
relevance_score
Semantic relevance of retrieved items. • target: 0.9 • range: 0-1
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
What you should walk away with
Index ONDC seller catalogs using LlamaIndex vector store indexers.
Implement Indic text normalization and multilingual embedding integration.
Deploy interactive Coplay AI assistant interface configurations.
Execute automated logistics partner capability matching based on delivery SLA.
Reference links and supporting material
Sample ONDC catalog payload containing localized grocery and D2C product descriptions across multiple pincodes.
Challenge setup
Validates retrieval recall and Indic language search accuracy for localized ONDC product queries.
Challenge input
JSON with user_query, language_code, and user_pincode.
LlamaIndex
Required data framework for semantic search across catalogs.
Coplay AI
Required tool for user interaction interface deployment.
Evaluated output
JSON with matched_providers, products, and estimated_delivery_time.
- Validates that relevant organic wheat flour product is returned.
- Semantic relevance of retrieved items. • target: 0.9 • range: 0-1
- Benchmark: Indic RAG Search Benchmark
- Relevance Score target: 0.9
- 1 public reference case
- Python execution harness
- Python sandbox (unavailable on Versalist)
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
- Coplay AI · Required
- Llama Index · Optional
- Exa · Optional
Evaluation contract
- product_match_test · Weight 1
- relevance_score · Weight 1
Metrics
- relevance_score · Target 0.9
Benchmarks
- Indic RAG Search Benchmark
- general
Reference cases
- 1 public reference case
Workflow tasks
- Task 1
Input: JSON with user_query, language_code, and user_pincode.
Output: JSON with matched_providers, products, and estimated_delivery_time.
Execution harness: Python
Evaluation tools
- LlamaIndex · Indexing & Retrieval
- Coplay AI · Assistant Interface
Recipe freeze marker
No recipe freeze time is recorded.