|
|
--- |
|
|
title: UB Virtual Student Assistant (UB-VSA) |
|
|
emoji: 🎓 |
|
|
colorFrom: pink |
|
|
colorTo: blue |
|
|
sdk: docker |
|
|
pinned: false |
|
|
short_description: AI assistant for University at Buffalo students. |
|
|
--- |
|
|
|
|
|
# UB Virtual Student Assistant (UB-VSA) |
|
|
**RAG-powered chatbot for UB admissions, visa & campus life questions** |
|
|
|
|
|
|
|
|
UB-VSA is a **retrieval-augmented conversational agent** that gives accurate, source-grounded answers about the University at Buffalo, with special focus on the needs of international students (F-1/OPT, I-20, course selection, housing, etc.). |
|
|
It combines: |
|
|
|
|
|
| Layer | Tech | |
|
|
|-------|------| |
|
|
| **Retriever** | FAISS dense vectors (`BAAI/bge-small-en-v1.5`) + keyword hybrid search | |
|
|
| **Reranker** | `cross-encoder/ms-marco-MiniLM-L-6-v2` | |
|
|
| **Fine-tuning** | LoRA / QLoRA adapters on `microsoft/phi-1_5` with RAFT | |
|
|
| **API** | Flask (backend) | |
|
|
| **UI** | Flask (+ vanilla JS) single-page chat | |
|
|
--- |
|
|
|
|
|
## ✨ Features |
|
|
* **Context-aware chat** – tracks the last few turns for coherent follow-ups. |
|
|
* **Grounded citations** – every answer lists clickable sources. |
|
|
* **Lightweight adapters** – fine-tuned with LoRA/QLoRA; base model stays frozen. |
|
|
* **One-click deploy** – Dockerfile + `start.sh` spin up scraper, vector-store, API & UI. |
|
|
* **Scalable vector DB** – FAISS index stored in `data/embeddings/`. |
|
|
|
|
|
--- |
|
|
|
|
|
## 🖥️ Online Demo |
|
|
> 👉 **Try it live:** https://huggingface.co/spaces/TeamSAS/UB_VSA |
|
|
|
|
|
We’re on the free HF hardware tier; first response may take ~30 s while the container wakes up. |
|
|
|
|
|
--- |
|
|
|
|
|
## 🏗️ Project Structure |
|
|
``` |
|
|
buffalo_rag/ |
|
|
├── api/ # FastAPI routes & schemas |
|
|
├── embeddings/ # Chunker + sentence‑transformer encoder |
|
|
├── frontend/ # Flask templates & static JS/CSS |
|
|
├── model/ # BuffaloRAG orchestration |
|
|
├── scraper/ # Playwright / BeautifulSoup crawler |
|
|
└── vector_store/ # FAISS DB + hybrid search logic |
|
|
data/ |
|
|
└── embeddings/ # .pkl embeddings + faiss_index.pkl (generated) |
|
|
Dockerfile |
|
|
start.sh |
|
|
main.py # CLI pipeline entry‑point |
|
|
``` |
|
|
|
|
|
## Quick Start (Local) |
|
|
|
|
|
```bash |
|
|
git clone https://huggingface.co/spaces/TeamSAS/UB_VSA |
|
|
cd UB_VSA |
|
|
|
|
|
# 1. Python deps |
|
|
python -m venv .venv && source .venv/bin/activate |
|
|
pip install -r requirements.txt |
|
|
|
|
|
export HUGGINGFACEHUB_API_TOKEN=hf_your_token_here |
|
|
|
|
|
# 3. Build embeddings (only first time, ~5 min) |
|
|
python main.py --build |
|
|
|
|
|
# 4. Launch backend + frontend |
|
|
python main.py --run |
|
|
``` |
|
|
|
