{"adoption": {"forks": 197, "observed_at": "2026-08-28T04:07:30.051502+00:00", "stars": 2917}, "canonical_url": "https://ross.abutalabs.com/products/michaelfeil-infinity", "card": {"archived": false, "artifact_type": "service", "description": "Infinity is a high-throughput, low-latency serving engine for text-embeddings, reranking models, clip, clap and colpali", "domain": ["machine-learning", "large-language-models", "apis", "self-hosted", "backend"], "enriched": true, "function": ["llm-inference", "http-server", "api-framework", "machine-learning", "rag"], "health_score": 78, "homepage": "https://michaelfeil.github.io/infinity/", "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "active", "member_repos": ["michaelfeil/infinity"], "name": "michaelfeil/infinity", "platform": ["python", "windows", "self-hosted", "cross-platform"], "pushed_at": "2026-03-24T03:59:47+00:00", "repo": "michaelfeil/infinity", "stars": 2917, "tags": ["embeddings", "reranking", "clip", "sentence-transformers", "openai-compatible-api", "text-embeddings-inference", "fastapi", "docker", "linux", "macos", "gpu"], "topics": ["llm", "text-embeddings", "bert-embeddings"], "urls": [], "use_cases": ["self-host an OpenAI-compatible embeddings API", "serve sentence-transformer models for a RAG pipeline", "deploy reranking models behind a REST endpoint", "run CLIP image and text embeddings on GPU", "batch-serve multiple embedding models from one server", "host ColPali vision retrieval models"], "what_it_is": "Infinity is a high-throughput, low-latency serving engine that exposes text-embedding, reranking, CLIP, CLAP and ColPali models via an OpenAI-compatible REST API. It is built on FastAPI with PyTorch, ONNX/TensorRT and CTranslate2 backends, supporting dynamic batching across CUDA, ROCm, CPU, AWS Inf2 and Apple MPS.", "when_to_avoid": ["you only need embeddings inside a single Python app without a server", "you need full LLM text generation, not embeddings or reranking", "you want a fully managed hosted service rather than self-hosting"], "when_to_choose": ["you need a self-hosted, OpenAI-spec-compatible embedding server", "you want to mix multiple embedding/reranking/multimodal models in one service", "you need high throughput with dynamic batching and hardware acceleration", "you want an MIT-licensed alternative to proprietary embedding APIs"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/michaelfeil-infinity", "repo": "michaelfeil/infinity", "role": "main", "score": 63}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:07:30.051502+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T07:34:04.975419+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "816365ff1961ef84738af699bdabdad39cd9839baa99edefad274d9a3eb7fd0b", "fetched_at": "2026-08-28T04:07:30.051502+00:00", "kind": "readme", "missing": false, "url": "https://github.com/michaelfeil/infinity"}, {"content_hash": "6c24e505942a0b4ef69f107651e85bb7e0be4bfbd1421c8cda578801375c7e8a", "fetched_at": "2026-08-29T09:49:18.713466+00:00", "kind": "homepage", "missing": false, "url": "https://michaelfeil.github.io/infinity/"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:07:30.051502+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T07:34:04.975419+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "816365ff1961ef84738af699bdabdad39cd9839baa99edefad274d9a3eb7fd0b", "fetched_at": "2026-08-28T04:07:30.051502+00:00", "kind": "readme", "missing": false, "url": "https://github.com/michaelfeil/infinity"}, {"content_hash": "6c24e505942a0b4ef69f107651e85bb7e0be4bfbd1421c8cda578801375c7e8a", "fetched_at": "2026-08-29T09:49:18.713466+00:00", "kind": "homepage", "missing": false, "url": "https://michaelfeil.github.io/infinity/"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T07:34:04.975419+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "816365ff1961ef84738af699bdabdad39cd9839baa99edefad274d9a3eb7fd0b", "fetched_at": "2026-08-28T04:07:30.051502+00:00", "kind": "readme", "missing": false, "url": "https://github.com/michaelfeil/infinity"}, {"content_hash": "6c24e505942a0b4ef69f107651e85bb7e0be4bfbd1421c8cda578801375c7e8a", "fetched_at": "2026-08-29T09:49:18.713466+00:00", "kind": "homepage", "missing": false, "url": "https://michaelfeil.github.io/infinity/"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:07:30.051502+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:07:30.051502+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:07:30.051502+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T07:34:04.975419+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "816365ff1961ef84738af699bdabdad39cd9839baa99edefad274d9a3eb7fd0b", "fetched_at": "2026-08-28T04:07:30.051502+00:00", "kind": "readme", "missing": false, "url": "https://github.com/michaelfeil/infinity"}, {"content_hash": "6c24e505942a0b4ef69f107651e85bb7e0be4bfbd1421c8cda578801375c7e8a", "fetched_at": "2026-08-29T09:49:18.713466+00:00", "kind": "homepage", "missing": false, "url": "https://michaelfeil.github.io/infinity/"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:07:30.051502+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:07:30.051502+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T07:34:04.975419+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "816365ff1961ef84738af699bdabdad39cd9839baa99edefad274d9a3eb7fd0b", "fetched_at": "2026-08-28T04:07:30.051502+00:00", "kind": "readme", "missing": false, "url": "https://github.com/michaelfeil/infinity"}, {"content_hash": "6c24e505942a0b4ef69f107651e85bb7e0be4bfbd1421c8cda578801375c7e8a", "fetched_at": "2026-08-29T09:49:18.713466+00:00", "kind": "homepage", "missing": false, "url": "https://michaelfeil.github.io/infinity/"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:07:30.051502+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:07:30.051502+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:07:30.051502+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T07:34:04.975419+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "816365ff1961ef84738af699bdabdad39cd9839baa99edefad274d9a3eb7fd0b", "fetched_at": "2026-08-28T04:07:30.051502+00:00", "kind": "readme", "missing": false, "url": "https://github.com/michaelfeil/infinity"}, {"content_hash": "6c24e505942a0b4ef69f107651e85bb7e0be4bfbd1421c8cda578801375c7e8a", "fetched_at": "2026-08-29T09:49:18.713466+00:00", "kind": "homepage", "missing": false, "url": "https://michaelfeil.github.io/infinity/"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:07:30.051502+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:07:30.051502+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T07:34:04.975419+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "816365ff1961ef84738af699bdabdad39cd9839baa99edefad274d9a3eb7fd0b", "fetched_at": "2026-08-28T04:07:30.051502+00:00", "kind": "readme", "missing": false, "url": "https://github.com/michaelfeil/infinity"}, {"content_hash": "6c24e505942a0b4ef69f107651e85bb7e0be4bfbd1421c8cda578801375c7e8a", "fetched_at": "2026-08-29T09:49:18.713466+00:00", "kind": "homepage", "missing": false, "url": "https://michaelfeil.github.io/infinity/"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T07:34:04.975419+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "816365ff1961ef84738af699bdabdad39cd9839baa99edefad274d9a3eb7fd0b", "fetched_at": "2026-08-28T04:07:30.051502+00:00", "kind": "readme", "missing": false, "url": "https://github.com/michaelfeil/infinity"}, {"content_hash": "6c24e505942a0b4ef69f107651e85bb7e0be4bfbd1421c8cda578801375c7e8a", "fetched_at": "2026-08-29T09:49:18.713466+00:00", "kind": "homepage", "missing": false, "url": "https://michaelfeil.github.io/infinity/"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T07:34:04.975419+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "816365ff1961ef84738af699bdabdad39cd9839baa99edefad274d9a3eb7fd0b", "fetched_at": "2026-08-28T04:07:30.051502+00:00", "kind": "readme", "missing": false, "url": "https://github.com/michaelfeil/infinity"}, {"content_hash": "6c24e505942a0b4ef69f107651e85bb7e0be4bfbd1421c8cda578801375c7e8a", "fetched_at": "2026-08-29T09:49:18.713466+00:00", "kind": "homepage", "missing": false, "url": "https://michaelfeil.github.io/infinity/"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T07:34:04.975419+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "816365ff1961ef84738af699bdabdad39cd9839baa99edefad274d9a3eb7fd0b", "fetched_at": "2026-08-28T04:07:30.051502+00:00", "kind": "readme", "missing": false, "url": "https://github.com/michaelfeil/infinity"}, {"content_hash": "6c24e505942a0b4ef69f107651e85bb7e0be4bfbd1421c8cda578801375c7e8a", "fetched_at": "2026-08-29T09:49:18.713466+00:00", "kind": "homepage", "missing": false, "url": "https://michaelfeil.github.io/infinity/"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 73, "longevity": 75, "rhythm": 44}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 1057, "days_push": 162, "days_rel": 376, "gap_med": 3.5, "n_releases_24m": 23}, "score": 63, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}