{"id":13477987,"url":"https://github.com/m1guelpf/tinyvector","last_synced_at":"2025-10-23T19:02:53.844Z","repository":{"id":178388882,"uuid":"661792195","full_name":"m1guelpf/tinyvector","owner":"m1guelpf","description":"A tiny embedding database in pure Rust.","archived":false,"fork":false,"pushed_at":"2023-12-28T08:45:39.000Z","size":124,"stargazers_count":398,"open_issues_count":8,"forks_count":20,"subscribers_count":8,"default_branch":"main","last_synced_at":"2025-03-30T00:11:08.600Z","etag":null,"topics":["embeddings","embeddings-similarity","machine-learning","rust","search-engines","similarity-search","vector-database","vector-search"],"latest_commit_sha":null,"homepage":"https://crates.io/crates/tinyvector","language":"Rust","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/m1guelpf.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null},"funding":{"github":"m1guelpf"}},"created_at":"2023-07-03T16:53:18.000Z","updated_at":"2025-03-19T02:28:27.000Z","dependencies_parsed_at":"2024-01-13T19:40:12.207Z","dependency_job_id":"d806b1e1-f81e-4bcb-b58e-17de52e1c0dd","html_url":"https://github.com/m1guelpf/tinyvector","commit_stats":null,"previous_names":["m1guelpf/tinyvector-rs"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/m1guelpf%2Ftinyvector","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/m1guelpf%2Ftinyvector/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/m1guelpf%2Ftinyvector/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/m1guelpf%2Ftinyvector/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/m1guelpf","download_url":"https://codeload.github.com/m1guelpf/tinyvector/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247419861,"owners_count":20936012,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["embeddings","embeddings-similarity","machine-learning","rust","search-engines","similarity-search","vector-database","vector-search"],"created_at":"2024-07-31T16:01:50.905Z","updated_at":"2025-10-23T19:02:53.737Z","avatar_url":"https://github.com/m1guelpf.png","language":"Rust","readme":"\u003cp align=\"center\"\u003e\n  \u003cimg src=\"https://github.com/m1guelpf/tinyvector/assets/23558090/512ff4ad-49fd-43ec-b3bd-57365b920078\" alt=\"tinyvector logo\"\u003e\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n    \u003cb\u003etinyvector - a tiny embedding database in pure Rust\u003c/b\u003e \u003cbr /\u003e\u003cbr /\u003e\n    \u003ca href=\"https://crates.io/crates/tinyvector\"\u003e\u003cimg src=\"https://img.shields.io/crates/v/tinyvector\" \u003e\u003c/a\u003e \u003ca href=\"https://github.com/m1guelpf/tinyvector/actions/workflows/build\"\u003e\u003cimg src=\"https://github.com/m1guelpf/tinyvector/actions/workflows/build.yaml/badge.svg\" \u003e\u003c/a\u003e  \u003ca href=\"LICENSE\"\u003e\u003cimg src=\"https://img.shields.io/badge/license-MIT-blue.svg\" \u003e\u003c/a\u003e\n\u003c/p\u003e\n\u003chr /\u003e\n\n## ✨ Features\n- **Tiny**: It's in the name. It's literally just an axum server. Extremely easy to customize, around 600 lines of code.\n- **Fast**: Tinyvector _should_ have comparable speed to advanced vector databases when it comes on small to medium datasets, and slightly better accuracy.\n- **Vertically Scales**: Tinyvector stores all indexes in memory for fast querying. Very easy to scale up to 100 million+ vector dimensions without issue.\n- **Open Source**: MIT Licensed, free forever.\n\n### Soon\n- **Powerful Queries**: Allow filtering by the provided vector metadata without slowing the search down.\n- **Integrated Models**: Soon you won't have to bring your own vectors, just generate them on the server automaticaly. Aiming to support support SBert, Hugging Face models, OpenAI, Cohere, etc.\n- **Typescript/Python Libraries**: Should be able to auto-generate pretty good clients using the included OpenAPI schema.\n\n## 🚀 Getting Started\n\n### 🐳 Docker\n\nWe provide a lightweight Docker container that you can run anywhere. It only takes one command to get up and running with the latest changes:\n\n```sh\ndocker run \\\n  -p 8000:8000 \\\n  ghcr.io/m1guelpf/tinyvector:edge\n```\n\n\u003e **Note**\n\u003e When running via Docker Compose or Kubernetes, make sure to bind a volume to `/tinyvector/storage` for persistence. This is handled automatically in the command above.\n\n### 🛠️ Building from scratch\n\nYou can build tinyvector from the latest tagged release by running `cargo install tinyvector` (you might need to [install Rust](https://rustup.rs/) first). Then, run `tinyvector` to start up the server.\n \nYou can also build it from the latest commit by cloning the repo and running `cargo build --release`, and run it with `./target/release/tinyvector`.\n\n## 💡 Why use tinyvector?\n\nMost vector databases are overkill for simple setups. For example:\n- Using embeddings to chat with your documents. Most document search is nowhere close to what you'd need to justify accelerating search speed with [HNSW](https://github.com/nmslib/hnswlib) or [FAISS](https://github.com/facebookresearch/faiss).\n- Doing search for your website or store. Unless you're selling 1,000,000 items, you don't need Pinecone.\n\n## 🧩 Embeddings?\n\nEmbeddings are a way to compare similar things, in the same way humans compare similar things, by converting text into a small list of numbers. Similar pieces of text will have similar numbers, different ones have very different numbers.\n\nRead OpenAI's [explanation](https://platform.openai.com/docs/guides/embeddings/what-are-embeddings).\n\n## 🙏 Acknowledgements\n\n- Will Depue's [tinyvector](https://twitter.com/willdepue/status/1675796236304252928) (python+sqlite+numpy) inspired me to build a vector database from scratch (and borrow the name). Will also contributed plenty of ideas to optimize performance.\n\n## 📄 License\n\nThis project is open-sourced under the MIT license. See [the License file](LICENSE) for more information.\n","funding_links":["https://github.com/sponsors/m1guelpf"],"categories":["Rust","vector-database","\u003ca name=\"Rust\"\u003e\u003c/a\u003eRust"],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fm1guelpf%2Ftinyvector","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fm1guelpf%2Ftinyvector","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fm1guelpf%2Ftinyvector/lists"}