Back to evaluations
Draft evaluation
Riyadh Expo Substation RAG Assistant with LlamaIndex & ElevenLabs — evaluation
Measures response context recall and correctness for substation technical questions.
Evaluation type
task based
Challenge
Riyadh Expo Substation RAG Assistant with LlamaIndex & ElevenLabs
Difficulty
Intermediate
Rigor
Not declared
The author has not specified a rigor level.
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
substation_spec_query
Tests accurate specification lookup and voice synthesis output formatting.
Input format
JSON with query string and project_code
Output format
JSON with answer text and audio_stream_url