How aroojkhan192/university-rag-recommender works
This is a compact RAG university recommender: a student query enters through the Streamlit demo or command line, retrieves relevant university records from a FAISS index, and produces a language-model recommendation grounded in retrieved context. Index construction is a separate data-preparation stage. The README documents these stages and dependencies, but no source excerpts were available, so the Streamlit-to-pipeline connection is shown as unverified.
Components 9
User interfaces
- Streamlit demo
Recommendation pipeline
- RAG recommender
- RAG orchestration
- Flan-T5 model
University knowledge
- University dataset
- Index builder
- Sentence embedder
- FAISS vector index
Other components
- Student
Connections 9
- Student → Streamlit demo: enters query
README.md - Student → RAG recommender: runs command
README.md - Streamlit demo → RAG recommender: submits query
- University dataset → Index builder: provides records
README.md - Index builder → Sentence embedder: embeds records
README.md - Index builder → FAISS vector index: stores vectors
README.md - RAG recommender → FAISS vector index: retrieves matches
README.md - RAG recommender → RAG orchestration: uses orchestration
README.md - RAG recommender → Flan-T5 model: generates from context
README.md