{"slug":"infinity","name":"infinity","nameZh":"michaelfeil/infinity","category":"retrieval","categoryName":"Retrieval, vector DBs & embeddings","audience":["for-ai"],"primary":"for-ai","openClosed":"open","pricing":"open-source","license":"MIT","maintained":"yes","officialUrl":"https://michaelfeil.github.io/infinity/","repo":"https://github.com/michaelfeil/infinity","latestVersion":"0.0.78","latestRelease":"2026-10-20","stars":2966,"starsAsOf":"2026-10-22","description":"Infinity is a high-throughput, low-latency serving engine for text-embeddings, reranking models, clip, clap and colpali","descriptionZh":"嵌入/重排模型高吞吐服务","callMethods":["API"],"platforms":[],"addedAt":"2026-10-10","updatedAt":"2026-10-22","topics":["bert-embeddings","llm","text-embeddings"],"language":"Python","lastPush":"2026-10-22","formerly":null,"packages":[],"recentVersions":[{"version":"0.0.77","date":"2025-08-22","prerelease":false,"url":"https://github.com/michaelfeil/infinity/releases/tag/0.0.77","source":"GitHub Release"},{"version":"0.0.76","date":"2025-03-16","prerelease":false,"url":"https://github.com/michaelfeil/infinity/releases/tag/0.0.76","source":"GitHub Release"},{"version":"0.0.75","date":"2025-01-22","prerelease":false,"url":"https://github.com/michaelfeil/infinity/releases/tag/0.0.75","source":"GitHub Release"},{"version":"0.0.74","date":"2025-01-03","prerelease":false,"url":"https://github.com/michaelfeil/infinity/releases/tag/0.0.74","source":"GitHub Release"},{"version":"0.0.73","date":"2024-12-10","prerelease":false,"url":"https://github.com/michaelfeil/infinity/releases/tag/0.0.73","source":"GitHub Release"}],"alternatives":["llm-app","quivr","onyx","txtai","deeplake","gptcache","elasticsearch","redis"],"stacks":[],"scenarios":["rag-and-documents"],"problems":[],"reasonZh":"开源大库收录：嵌入/重排模型高吞吐服务","sources":["oss","github-oss","github-pool"],"record":"https://aimap.page/api/v1/software/infinity.json","pages":{"en":"https://aimap.page/en/software/infinity/","zh-hans":"https://aimap.page/zh-hans/software/infinity/"}}