| title: QMD Web Demo | |
| emoji: 🔍 | |
| colorFrom: blue | |
| colorTo: green | |
| sdk: static | |
| pinned: false | |
| license: mit | |
| # QMD Web Demo | |
| In-browser hybrid search pipeline using WebGPU + Transformers.js v4. | |
| Demonstrates the full QMD search pipeline running entirely in your browser: | |
| 1. **Query Expansion** — Qwen3 1.7B generates HyDE, semantic, and keyword variants | |
| 2. **Parallel Search** — BM25 keyword search + vector similarity search | |
| 3. **Reciprocal Rank Fusion** — Merges results from multiple search backends | |
| 4. **LLM Reranking** — Qwen3 Reranker 0.6B scores document relevance | |
| 5. **Score Blending** — Position-aware combination of RRF and reranker scores | |
| ## Requirements | |
| - Chrome 113+ or Edge 113+ (WebGPU required) | |
| - ~2.5GB model download on first visit (cached for subsequent visits) | |
| ## Models | |
| - [embeddinggemma-300M](https://huggingface.co/onnx-community/embeddinggemma-300m-ONNX) — Embeddings | |
| - [Qwen3-Reranker-0.6B](https://huggingface.co/onnx-community/Qwen3-Reranker-0.6B-ONNX) — Reranking | |
| - [qmd-query-expansion-1.7B](https://huggingface.co/shreyask/qmd-query-expansion-1.7B-ONNX) — Query expansion | |
| Based on [QMD](https://github.com/tobi/qmd) by Tobi Lütke. | |