sivakum4 commited on
Commit
41b319d
Β·
verified Β·
1 Parent(s): 9e89ad1

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +35 -2
README.md CHANGED
@@ -11,8 +11,6 @@ short_description: AI assistant for University at Buffalo students.
11
  # UB Virtual Student Assistant (UB-VSA)
12
  **RAG-powered chatbot for UB admissions, visa & campus life questions**
13
 
14
- [![HF Space Status](https://img.shields.io/badge/πŸ€— Spaces-Live-brightgreen.svg)](https://huggingface.co/spaces/TeamSAS/UB_VSA)
15
- [![Docker](https://img.shields.io/badge/docker-ready-blue)](Dockerfile) [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](#license)
16
 
17
  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.).
18
  It combines:
@@ -26,4 +24,39 @@ It combines:
26
  | **UI** | Flask (+ vanilla JS) single-page chat |
27
  ---
28
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
29
  Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
 
11
  # UB Virtual Student Assistant (UB-VSA)
12
  **RAG-powered chatbot for UB admissions, visa & campus life questions**
13
 
 
 
14
 
15
  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.).
16
  It combines:
 
24
  | **UI** | Flask (+ vanilla JS) single-page chat |
25
  ---
26
 
27
+ ## ✨ Features
28
+ * **Context-aware chat** – tracks the last few turns for coherent follow-ups.
29
+ * **Grounded citations** – every answer lists clickable sources.
30
+ * **Lightweight adapters** – fine-tuned with LoRA/QLoRA; base model stays frozen.
31
+ * **One-click deploy** – Dockerfile + `start.sh` spin up scraper, vector-store, API & UI.
32
+ * **Scalable vector DB** – FAISS index stored in `data/embeddings/`.
33
+
34
+ ---
35
+
36
+ ## πŸ–₯️ Online Demo
37
+ > πŸ‘‰ **Try it live:** https://huggingface.co/spaces/TeamSAS/UB_VSA
38
+
39
+ We’re on the free HF hardware tier; first response may take ~30 s while the container wakes up.
40
+
41
+ ---
42
+
43
+ ## πŸš€ Quick Start (Local)
44
+
45
+ ```bash
46
+ git clone https://huggingface.co/spaces/TeamSAS/UB_VSA
47
+ cd UB_VSA
48
+
49
+ # 1. Python deps
50
+ python -m venv .venv && source .venv/bin/activate
51
+ pip install -r requirements.txt
52
+
53
+ # 2. Set your HF token (needed for Cerebras Inference API)
54
+ export HUGGINGFACEHUB_API_TOKEN=hf_your_token_here
55
+
56
+ # 3. Build embeddings (only first time, ~5 min)
57
+ python main.py --build
58
+
59
+ # 4. Launch backend + frontend
60
+ python main.py --run
61
+
62
  Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference