MohammedAly22/GenQuest-RAG

A Question Generation Application leveraging RAG and Weaviate vector store to be able to retrieve relative contexts and generate a more useful answer-aware questions

20
/ 100
Experimental

Implements answer-aware question generation by fine-tuning T5 models on SQuAD with answer-highlighting tokens, then augmenting generation through semantic retrieval from Wikipedia via Weaviate's vector search. The system uses LangChain to orchestrate the RAG pipeline, combining retrieved contextual passages with an instruction-based prompt format to generate topic-specific, answer-grounded questions evaluated against BLEU, ROUGE, METEOR, and BERTScore metrics.

No commits in the last 6 months.

No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 1 / 25
Community 13 / 25

How are scores calculated?

Stars

17

Forks

3

Language

Jupyter Notebook

License

Last pushed

Feb 03, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/MohammedAly22/GenQuest-RAG"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.