EdoardoBotta / RQ-VAE-Recommender
[Pytorch] Generative retrieval model using semantic IDs from "Recommender Systems with Generative Retrieval"
Why this job: matched by what the repo talks about: retrieval, semantic, generative, system
What it does
- Residual quantization with K-means initialization and Euclidean or cosine
- Gumbel-Softmax, straight-through, and rotation-trick gradient estimators.
- Semantic-ID collision disambiguation and corpus-prefix-constrained generation.
- A T5 encoder-decoder retrieval model with hit-rate and NDCG evaluation.
- Automatic preprocessing for Amazon Reviews and MovieLens datasets.
Get started
python -m pip install -e ".[test]"
pytest- Maintenance
- Active
- Last commit 2 months ago
- Stars
- 858
- +2 this week
- Licence
- MIT
- Allows business use
- Downloads for
- None listed
- No release files
- Latest tag
- v1_0_2
- Released 2 months ago
- Built with
- Python
- 95% of the code
Is it looked after?
- Contributors
- Not stated
- Last 90 days
- Issues
- 20% closed
- 41 still open
- Pull requests
- 21 merged
- 3 waiting
- Releases
- 3
- 3 in the last year
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| volcengine / SearchCLI | 1,192 | yesterday | Apache-2.0 | No downloads |
More: languages, topics and project record
Languages
- Python 95%
- TeX 5%
Topics
- generative
- generative-ai
- generative-retrieval
- gumbel
- recommendation
- recommendation-system
- recommender
- recommender-system
- recommendersystems
- retrieval
- retrieval-systems
- semantic-id
Project record
- JobRAG and search
- StatusListed
- Commits191
- Forks128
- Watching3
- Stars in 28 days+9
- CreatedJun 17, 2024
- First seen by usNov 7, 2026
- CheckedNov 8, 2026