metadata

title: Sentence Transformers
emoji: 📚
colorFrom: yellow
colorTo: blue
sdk: gradio
sdk_version: 5.31.0
app_file: app.py
pinned: false
license: apache-2.0
short_description: Small CNN

🔍 MiniLM Semantic FAQ Search — Smart, Lightning-Fast Knowledge Retrieval

🚀 TL;DR

Ask a question → get the three most relevant answers from a curated FAQ — all in real time on a free CPU-only Hugging Face Space.
Powered by the all-MiniLM-L6-v2 sentence-transformer (∼90 MB, < 1 GB RAM) and a minimalist Gradio 5 UI.

✨ Why You’ll Love It

·	Capability	Why It Matters
⚡	Instant Retrieval	50-200 ms response time even on CPU-only hardware.
🧠	Semantic Matching	Goes beyond keywords; understands intent and phrasing.
📈	Live Similarity Scores	Transparent confidence metrics for every hit.
🎛️	Interactive Slider	Choose 1-5 results in a single drag.
🎨	Sleek Gradio GUI	No setup friction — just open a browser and explore.
💸	Free-Tier Friendly	Fits comfortably inside Hugging Face Spaces’ 2 vCPU / 16 GB RAM limit.
🛠️	Drop-in Dataset Swap	Replace `faqs.csv` with thousands of your own Q-A pairs — no retraining required.

🏗️ How It Works

Vectorisation
Every FAQ question is embedded with sentence-transformers/all-MiniLM-L6-v2 into a 384-dimensional vector (done once at start-up).
Inference
A user query is embedded on the fly and cosine-compared with all FAQ vectors via 🤗 util.cos_sim.
Ranking
Top-k indices are extracted with PyTorch’s efficient topk, then mapped back to the original FAQ rows.
Presentation
Gradio displays the question, answer and similarity score in a responsive dataframe.

No database, no external search engine, just straight Python & PyTorch embeddings.

🖥️ Quick Start (Local Dev, Optional)

git clone https://github.com/your-username/minilm-semantic-search.git
cd minilm-semantic-search
python -m venv venv && source venv/bin/activate  # Windows: venv\Scripts\activate
pip install -r requirements.txt
python app.py