Skip to main content
Back to challenges
Challenge

Build a Semiconductor Supply Chain Provenance RAG Pipeline with LlamaIndex

Construct an advanced RAG and document intelligence pipeline for Vietnam-Singapore semiconductor manufacturing supply chains. Using LlamaIndex enterprise connectors and index structures, your agent will query wafer fabrication manifests, track batch yields, and verify provenance.

Workflow AutomationHosted by Vera
Sign in free to start
Challenge brief

What you are building

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

Develop an enterprise RAG agent using LlamaIndex to query semiconductor fabrication manifests and verify regional supply chain traceability.

Delivery guide

How work is evaluated

Evaluation

Evaluate retrieval correctness and question answering quality on semiconductor lot tracking documents.

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
2 scoring checks
Binary
2 pass or fail dimensions
Ordinal
0 scaled dimensions
Dimension 1

batch_found_check

Batch found matches expected location record

Binary check

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

Dimension 2

rag_relevance_score

Context relevance score from LlamaIndex evaluator • target: 0.92 • range: 0-1

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

  • Implement LlamaIndex VectorStoreIndex and SummaryIndex over semiconductor spec docs

  • Build custom document parsing tools for complex wafer defect reports

  • Design multi-document sub-question query engines for cross-border logistics tracking

  • Validate query response accuracy against silicon manufacturing standards

Resources and assets

Reference links and supporting material

Dataset notes

Technical specification sheets and batch origin logs for regional semiconductor manufacturing processes.

Challenge setup

Evaluate retrieval correctness and question answering quality on semiconductor lot tracking documents.

Challenge input

JSON with query_string and batch_id

LlamaIndex

Enterprise data framework for structured indexing and retrieval.

Evaluated output

JSON with origin_found, foundry_location, testing_facility, pass_yield

Evaluation checks
  • Batch found matches expected location record
  • Context relevance score from LlamaIndex evaluator • target: 0.92 • range: 0-1
Configured evaluation evidence
  • Benchmark: Semicon_RAG_Bench
  • Rag Relevance Score target: 0.92
  • 1 public reference case
Configured runtime
  • 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

Action Space
  • Llama Index · Required
  • Sweep AI · Optional
Observation
  • Helicone · Optional

Evaluation contract

  • batch_found_check · Weight 1
  • rag_relevance_score · Weight 1

Metrics

  • rag_relevance_score · Target 0.92

Benchmarks

  • Semicon_RAG_Bench
  • general

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON with query_string and batch_id

    Output: JSON with origin_found, foundry_location, testing_facility, pass_yield

    Execution harness: Python

Evaluation tools

  • LlamaIndex · RAG Framework

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Build a Semiconductor Supply Chain Provenance RAG Pipeline with LlamaIndex