[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"article-turbovec-rust-vector-index-packs-10m-docs-4gb-en":3,"article-related-turbovec-rust-vector-index-packs-10m-docs-4gb-en":29,"series-tools-dc764c2f-e238-47ee-bee8-87b79ffba57d":78},{"id":4,"slug":5,"title":6,"content":7,"summary":8,"source":9,"source_url":10,"author":11,"image_url":12,"cover_image":12,"category":13,"language":14,"translated_content":11,"related_article_id":15,"keywords":16,"key_takeaways":22,"views":26,"created_at":27,"published_at":28,"topic_cluster_id":11},"dc764c2f-e238-47ee-bee8-87b79ffba57d","turbovec-rust-vector-index-packs-10m-docs-4gb-en","turbovec: Rust vector index cuts RAM to 4 GB","\u003Cp>A 10 million document corpus that needs 31 GB as float32 can now fit in 4 GB. RyanCodrai’s \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fryancodrai\u002Fturbovec\" target=\"_blank\" rel=\"noopener\">turbovec\u003C\u002Fa> aims to do that with a \u003Ca href=\"\u002Ftag\u002Frust\">Rust\u003C\u002Fa> vector index and Python bindings.\u003C\u002Fp>\u003Cp data-speakable=\"summary\">turbovec is a Rust vector index with Python bindings that compresses large corpora and speeds up search.\u003C\u002Fp>\u003Ctable>\u003Cthead>\u003Ctr>\u003Cth>項目\u003C\u002Fth>\u003Cth>數值\u003C\u002Fth>\u003C\u002Ftr>\u003C\u002Fthead>\u003Ctbody>\u003Ctr>\u003Ctd>Repository stars\u003C\u002Ftd>\u003Ctd>14.8k\u003C\u002Ftd>\u003C\u002Ftr>\u003Ctr>\u003Ctd>Forks\u003C\u002Ftd>\u003Ctd>1.3k\u003C\u002Ftd>\u003C\u002Ftr>\u003Ctr>\u003Ctd>Commits\u003C\u002Ftd>\u003Ctd>359\u003C\u002Ftd>\u003C\u002Ftr>\u003Ctr>\u003Ctd>RAM for 10M docs as float32\u003C\u002Ftd>\u003Ctd>31 GB\u003C\u002Ftd>\u003C\u002Ftr>\u003Ctr>\u003Ctd>turbovec RAM for same corpus\u003C\u002Ftd>\u003Ctd>4 GB\u003C\u002Ftd>\u003C\u002Ftr>\u003Ctr>\u003Ctd>Search benchmark corpus\u003C\u002Ftd>\u003Ctd>100K vectors, 1K queries, k=64\u003C\u002Ftd>\u003C\u002Ftr>\u003C\u002Ftbody>\u003C\u002Ftable>\u003Ch2>What changed\u003C\u002Fh2>\u003Cp>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fryancodrai\u002Fturbovec\" target=\"_blank\" rel=\"noopener\">turbovec\u003C\u002Fa> packages \u003Ca href=\"\u002Ftag\u002Fgoogle\">Google\u003C\u002Fa> Research’s \u003Ca href=\"\u002Ftag\u002Fturboquant\">TurboQuant\u003C\u002Fa> algorithm into a local vector index written in Rust, with a Python API on top. The project is built for online ingest, incremental saves, filtered search, and offline use.\u003C\u002Fp>\n\u003Cfigure class=\"my-6\">\u003Cimg src=\"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1787043776682-e20z.png\" alt=\"turbovec: Rust vector index cuts RAM to 4 GB\" class=\"rounded-xl w-full\" loading=\"lazy\" \u002F>\u003C\u002Ffigure>\n\u003Cp>The repo says vectors can be added without a training pass, parameter tuning, or rebuilds as the corpus grows. It also adds stable external IDs through \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fryancodrai\u002Fturbovec\" target=\"_blank\" rel=\"noopener\">IdMapIndex\u003C\u002Fa>, plus write\u002Fload snapshots and a sync path that persists only changed data.\u003C\u002Fp>\u003Cul>\u003Cli>Rust core with Python bindings\u003C\u002Fli>\u003Cli>TurboQuant-based compression and search\u003C\u002Fli>\u003Cli>Incremental \u003Ccode>sync(path)\u003C\u002Fcode> for crash-safe saves\u003C\u002Fli>\u003Cli>Allowlist filtering inside the search kernel\u003C\u002Fli>\u003Cli>Local-only deployment for air-gapped RAG stacks\u003C\u002Fli>\u003C\u002Ful>\u003Cp>Benchmarks in the repo compare \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Ffacebookresearch\u002Ffaiss\" target=\"_blank\" rel=\"noopener\">FAISS\u003C\u002Fa> IndexPQFastScan against turbovec on 100K vectors. The project reports faster search on both ARM and x86, with average gains of 3.4x to 3.5x at 4-bit and about 20% to 26% at 2-bit, depending on architecture and test cell.\u003C\u002Fp>\u003Ch2>Why it matters\u003C\u002Fh2>\u003Cp>For developers building RAG or similarity search systems, the pitch is simple: less memory, no training step, and faster local retrieval. That matters when embeddings must stay on-device, inside a VPC, or under tight latency budgets.\u003C\u002Fp>\n\u003Cfigure class=\"my-6\">\u003Cimg src=\"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1787043773374-io2o.png\" alt=\"turbovec: Rust vector index cuts RAM to 4 GB\" class=\"rounded-xl w-full\" loading=\"lazy\" \u002F>\u003C\u002Ffigure>\n\u003Cp>The Python API also lowers the barrier for teams already using \u003Ca href=\"\u002Ftag\u002Flangchain\">LangChain\u003C\u002Fa>, LlamaIndex, Haystack, or Agno. turbovec ships drop-in replacements for in-tree memory stores, so teams can swap the backend without rewriting the rest of the pipeline.\u003C\u002Fp>\u003Cp>The bigger signal is operational. Incremental sync and allowlist filtering are the kinds of details that decide whether a vector index is convenient in a demo or usable in production.\u003C\u002Fp>\u003Cp>The open question is not whether compression works, but how well this approach holds up once indexes get larger, filters get more selective, and workloads move beyond the repo’s \u003Ca href=\"\u002Ftag\u002Fbenchmark\">benchmark\u003C\u002Fa> set.\u003C\u002Fp>","RyanCodrai’s turbovec brings TurboQuant to Rust and Python, shrinking a 10M-document index from 31 GB to 4 GB with faster search.","github.com","https:\u002F\u002Fgithub.com\u002Fryancodrai\u002Fturbovec",null,"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1787043776682-e20z.png","tools","en","74f789e9-29e4-4d7a-a142-5d3b54346d86",[17,18,19,20,21],"Rust","vector search","TurboQuant","Python bindings","RAG",[23,24,25],"Compresses a 10M-document corpus from 31 GB to 4 GB in the repo’s benchmark claim.","Adds online ingest, incremental sync, and filtered search without a separate training phase.","Reports faster search than FAISS IndexPQFastScan on both ARM and x86 tests.",0,"2026-08-18T09:02:28.418851+00:00","2026-08-18T09:02:28.413+00:00",{"tags":30,"relatedLang":37,"relatedPosts":41},[31,33,35],{"name":17,"slug":32},"rust",{"name":21,"slug":34},"rag",{"name":19,"slug":36},"turboquant",{"id":15,"slug":38,"title":39,"language":40},"turbovec-rust-vector-index-packs-10m-docs-4gb-zh","turbovec：Rust 向量索引把 10M 文件壓到 4GB","zh",[42,48,54,60,66,72],{"id":43,"slug":44,"title":45,"cover_image":46,"image_url":46,"created_at":47,"category":13},"fb7100e3-ce80-48cc-a74e-2eafe65c9b54","install-rust-on-windows-and-verify-rustc-en","Install Rust on Windows and verify rustc","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1787040168017-youp.png","2026-08-18T08:02:23.659088+00:00",{"id":49,"slug":50,"title":51,"cover_image":52,"image_url":52,"created_at":53,"category":13},"fa7cb9a9-5b63-4da7-9def-f3872490c821","claude-code-desktop-ships-inside-one-app-en","Claude Code Desktop lets you ship inside one app","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1786952008135-zrjx.png","2026-08-17T07:32:57.721723+00:00",{"id":55,"slug":56,"title":57,"cover_image":58,"image_url":58,"created_at":59,"category":13},"3cf08a14-7ed0-4328-af1f-bf3a2b9f328a","cursors-iphone-app-brings-coding-agents-mobile-en","Cursor’s iPhone app brings coding agents mobile","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1786933983162-lma8.png","2026-08-17T02:32:34.225742+00:00",{"id":61,"slug":62,"title":63,"cover_image":64,"image_url":64,"created_at":65,"category":13},"7126b4be-9068-4743-b266-aa5f5aae862b","deepseek-plugin-harness-turns-agents-into-tools-en","DeepSeek’s plugin harness turns agents into tools","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1786779186305-8ppa.png","2026-08-15T07:32:43.83464+00:00",{"id":67,"slug":68,"title":69,"cover_image":70,"image_url":70,"created_at":71,"category":13},"c3952c24-178c-4cb8-a1f8-a54a740f870e","claude-code-sessions-message-each-other-en","Claude Code lets sessions message each other","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1786753979904-qpen.png","2026-08-15T00:32:41.517992+00:00",{"id":73,"slug":74,"title":75,"cover_image":76,"image_url":76,"created_at":77,"category":13},"5dd1b059-52b0-4714-8ccd-212e0a0a4c53","10-ai-github-repos-that-actually-save-time-en","10 AI GitHub repos that actually save time","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1786712619804-x8qp.png","2026-08-14T13:03:15.028729+00:00",[79,84,89,94,99,104,109,114,119,124],{"id":80,"slug":81,"title":82,"created_at":83},"8008f1a9-7a00-4bad-88c9-3eedc9c6b4b1","surepath-ai-mcp-policy-controls-en","SurePath AI's New MCP Policy Controls Enhance AI Security","2026-03-26T01:26:52.222015+00:00",{"id":85,"slug":86,"title":87,"created_at":88},"27e39a8f-b65d-4f7b-a875-859e2b210156","mcp-standard-ai-tools-2026-en","MCP Standard in 2026: Integrating AI Tools","2026-03-26T01:27:43.127519+00:00",{"id":90,"slug":91,"title":92,"created_at":93},"165f9a19-c92d-46ba-b3f0-7125f662921d","rag-2026-transforming-enterprise-ai-en","How RAG in 2026 is Transforming Enterprise AI","2026-03-26T01:28:11.485236+00:00",{"id":95,"slug":96,"title":97,"created_at":98},"6a2a8e6e-b956-49d8-be12-cc47bdc132b2","mastering-ai-prompts-2026-guide-en","Mastering AI Prompts: A 2026 Guide for Developers","2026-03-26T01:29:07.835148+00:00",{"id":100,"slug":101,"title":102,"created_at":103},"3ab2c67e-4664-4c67-a013-687a2f605814","garry-tan-open-sources-claude-code-toolkit-en","Garry Tan Open-Sources a Claude Code Toolkit","2026-03-26T08:26:20.245934+00:00",{"id":105,"slug":106,"title":107,"created_at":108},"66a7cbf8-7e76-41d4-9bbf-eaca9761bf69","github-ai-projects-to-watch-in-2026-en","20 GitHub AI Projects to Watch in 2026","2026-03-26T08:28:09.752027+00:00",{"id":110,"slug":111,"title":112,"created_at":113},"9f332fda-eace-448a-a292-2283951eee71","practical-github-guide-learning-ml-2026-en","A Practical GitHub Guide to Learning ML in 2026","2026-03-27T01:16:50.125678+00:00",{"id":115,"slug":116,"title":117,"created_at":118},"1b1f637d-0f4d-42bd-974b-07b53829144d","aiml-2026-student-ai-ml-lab-repo-review-en","AIML-2026 Is a Bare-Bones Student Lab Repo","2026-03-27T01:21:51.661231+00:00",{"id":120,"slug":121,"title":122,"created_at":123},"6d1bf3f6-e191-4d30-b55b-8a0722fa6afe","ai-trending-github-repos-and-research-feeds-en","AI Trending Tracks Repos and Research Feeds","2026-03-27T01:31:35.709532+00:00",{"id":125,"slug":126,"title":127,"created_at":128},"010539a1-4c3a-4bd3-937a-26616422ee0d","awesome-ai-for-science-research-tools-map-en","Awesome AI for Science Is Becoming a Real Research Map","2026-03-27T01:46:50.89513+00:00"]