Go to example tasks
Systra Ai Rag Evaluation Dataset Generator Task
Created by
Troy Hendrick
The Systra AI RAG Evaluation Dataset Generator creates in-depth, citation-grounded evaluation datasets from specified sources. This task generates 80 test cases, including factual, procedural, and unanswerable questions, complete with reference answers and evidence quotes. Ideal for validating RAG models with credible data, it exports in JSONL, CSV, or RAGAS formats.
Rag Evaluation Dataset Generatorsystra_ai/systra-ai-rag-evaluation-dataset-generator
Question
Expected answer
Answerability
Question type
+3 fieldsTextNumberBooleanListObject
Input
Source URLs:https://rafflex.io/
Inline documents
Crawl mode:sitemap
JavaScript rendering:auto
Maximum pages:50
Maximum crawl depth:3
Target evaluation cases:80
Question types:factual+4
Question language:English
OpenAI model:gpt-5.6-luna
Maximum chunk characters:5000
Chunk overlap characters:400
Cases per model call:6
Maximum bytes per source:10000000
Output fields
Question
Expected answer
Answerability
Question type
Difficulty
Source references
Grading guidance
Sign up on Apify01
Create your Apify account to access the Rag Evaluation Dataset Generator.
Start the run02
The Actor will start running based on the input automatically.
Receive the output03
Monitor the progress in real-time. You will be notified as soon as your dataset is complete and ready for review.
Integrate into your workflow04
The final output is delivered in JSON, CSV, or Excel format, ready to be plugged into your workflow.
