Back to evaluations
Public evaluation
structural_extraction_eval
Evaluates accuracy of extracted structural parameters and feasibility classification against ground truth engineering specs.
Evaluation type
task based
Challenge
Office Conversion Feasibility RAG Pipeline with LlamaIndex & Fiddler AI
Difficulty
Advanced
Rigor
Unspecified
Evaluation overview
How the linked challenge is judged: tasks, benchmarks, and criteria count.
Tasks
1
Benchmarks
0
Criteria
0
Task templates
Inputs and expected outputs.
Task 1
structural_extraction_eval
Parses blueprint text and computes floorplate viability metric.
Input format
JSON containing document_id and blueprint_text
Output format
JSON with core_to_window_dist_ft, mechanical_shaft_capacity, conversion_viable boolean