Skip to main content
Back to challenges
Challenge

Sensor Datasheet Vector Search Engine with LlamaIndex

Control engineers frequently need fast reference lookup tools to query pH, temperature, and pressure sensor limits across large PDF specification libraries. In this challenge, developers will construct a vector-based document search engine using LlamaIndex to query Emerson Rosemount 350A sensor PDF manuals.

EngineeringHosted 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 a lightweight vector document search engine using LlamaIndex to query Rosemount sensor specifications.

Delivery guide

How work is evaluated

Evaluation

Evaluates document lookup precision on technical hardware questions.

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

Pressure Spec Retrieval

Retrieved answer must state 100 psig

Binary check

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

Dimension 2

RAG Precision

Exact spec numerical match score • target: 1 • 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

  • Load PDF document manuals using LlamaIndex document readers

  • Construct a `VectorStoreIndex` for fast similarity search

  • Formulate a retriever query engine with customized `top_k` chunk selection

  • Output precise answer text with document page numbers

Resources and assets

Reference links and supporting material

Dataset notes

Synthetic PDF spec sheets for industrial pH and temperature transmitters.

Challenge setup

Evaluates document lookup precision on technical hardware questions.

Challenge input

Query text string

LlamaIndex

Assigned framework

Evaluated output

JSON with answer, matching_score

Evaluation checks
  • Retrieved answer must state 100 psig
  • Exact spec numerical match score • target: 1 • range: 0-1
Configured evaluation evidence
  • Benchmark: Document Retrieval QA Benchmark
  • RAG Precision target: 1
  • 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
  • LlamaIndex · Optional
  • Llama 3.2 · Optional

Evaluation contract

  • Pressure Spec Retrieval · Weight 1
  • RAG Precision · Weight 1

Metrics

  • RAG Precision · Target 1

Benchmarks

  • Document Retrieval QA Benchmark
  • general

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: Query text string

    Output: JSON with answer, matching_score

    Execution harness: Python

Evaluation tools

  • LlamaIndex · Vector index framework

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Sensor Datasheet Vector Search Engine with LlamaIndex