{"slug": "show-hn-lance-bundle-portable-embeddings-to-embed-once-query-forever", "title": "Show HN: Lance-bundle – Portable embeddings to embed once, query forever", "summary": "Developer cloudkj released lance-bundle, an open-source library that packages precomputed embedding vectors with their embedding model into a single file for fast, local semantic queries, using LanceDB and ONNX for a low dependency footprint. The project includes precomputed datasets hosted on Hugging Face, such as lance-bundle/berkshire-hathaway-letters, which can be loaded and searched directly. The library aims to help local-first AI enthusiasts avoid regenerating embeddings across environments.", "body_md": "Hello,\n\nWhile experimenting with personal, local RAG app setups, I kept having to (re)generate embeddings and really wanted precomputed embedding datasets that I could quickly pull and use in various environments.\n\nI built a library to test out the idea: lance-bundle lets you package precomputed embedding vectors alongside the actual embedding model so that everything can be loaded from a single file for querying against the vectors; initial version uses LanceDB + ONNX for low dependency footprint and fast cold start to vector queries.\n\n[https://github.com/cloudkj/lance-bundle](https://github.com/cloudkj/lance-bundle)\n\nAs part of this, a few datasets that might be of interest to this audience have been precomputed as embedding vectors and hosted on a Hugging Face dataset hub and can be directly loaded and queried against:\n\n[https://huggingface.co/lance-bundle/datasets](https://huggingface.co/lance-bundle/datasets)\n\nWith these datasets, you can simply load directly and run semantic queries to retrieve the nearest documents/embeddings:\n\n``` python\n    from lance_bundle import load_dataset\n    bundle = load_dataset(\"lance-bundle/berkshire-hathaway-letters\")\n    bundle.search(\"What does Warren Buffett think of passive index funds?\")\n```\n\nLooking to share to see if anyone actually finds it useful, and to gather feedback on whether it makes sense for the local-first AI enthusiasts. Let me know what you think!Comments URL: [https://news.ycombinator.com/item?id=49259385](https://news.ycombinator.com/item?id=49259385)\n\nPoints: 1\n\n# Comments: 0", "url": "https://wpnews.pro/news/show-hn-lance-bundle-portable-embeddings-to-embed-once-query-forever", "canonical_source": "https://github.com/cloudkj/lance-bundle", "published_at": "2026-08-11 14:53:41+00:00", "updated_at": "2026-08-11 15:12:47.362132+00:00", "lang": "en", "topics": ["ai-tools", "developer-tools", "machine-learning"], "entities": ["cloudkj", "lance-bundle", "LanceDB", "ONNX", "Hugging Face"], "alternates": {"html": "https://wpnews.pro/news/show-hn-lance-bundle-portable-embeddings-to-embed-once-query-forever", "markdown": "https://wpnews.pro/news/show-hn-lance-bundle-portable-embeddings-to-embed-once-query-forever.md", "text": "https://wpnews.pro/news/show-hn-lance-bundle-portable-embeddings-to-embed-once-query-forever.txt", "jsonld": "https://wpnews.pro/news/show-hn-lance-bundle-portable-embeddings-to-embed-once-query-forever.jsonld"}}