{"adoption": {"forks": 390, "observed_at": "2026-08-28T04:08:05.530718+00:00", "stars": 3457}, "canonical_url": "https://ross.abutalabs.com/products/smart_open", "card": {"archived": false, "artifact_type": "library", "description": "Utils for streaming large files (S3, HDFS, gzip, bz2...)", "domain": ["files", "cloud-computing", "developer-tools"], "enriched": true, "function": ["file-system", "compression", "http-client", "streaming", "etl"], "health_score": 98, "homepage": null, "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "stable", "member_repos": ["piskvorky/smart_open"], "name": "piskvorky/smart_open", "platform": ["python", "cross-platform"], "pushed_at": "2026-08-04T08:34:12+00:00", "repo": "piskvorky/smart_open", "stars": 3457, "tags": ["s3", "gcs", "azure-blob", "hdfs", "sftp", "gzip", "bzip2", "zstd", "drop-in-open-replacement", "remote-storage", "data-engineering"], "topics": ["python", "s3", "hdfs", "webhdfs", "boto", "streaming", "file", "streaming-data", "gzip-stream", "bz2", "hacktoberfest"], "urls": [], "use_cases": ["stream large files from s3 in python", "read gzip files line by line without extracting", "replace boto3 upload_fileobj boilerplate", "write files to hdfs or webhdfs from python", "stream data over http or sftp like a local file", "convert between compressed file formats on the fly", "process huge remote datasets without downloading them fully"], "what_it_is": "A Python library for efficiently streaming very large files to and from remote storages like S3, GCS, Azure Blob Storage, HDFS, WebHDFS, HTTP, and SFTP, with transparent on-the-fly compression/decompression. It is a drop-in replacement for Python's built-in open() with a unified Pythonic API.", "when_to_avoid": ["you only work with local files and don't need remote storage or compression", "you need fine-grained control over multipart upload tuning that boto3 exposes directly", "you need a non-Python solution"], "when_to_choose": ["you need a unified open()-like API across S3, GCS, Azure, HDFS, HTTP, and SFTP", "you want transparent gzip/bz2/zstd compression while streaming", "you're tired of boto3 file-like object boilerplate for large files"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/smart_open", "repo": "piskvorky/smart_open", "role": "main", "score": 96}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:08:05.530718+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T18:37:29.491074+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "902d462a59095bc7e4c76dc29f6f92ac63e0d5b6f00218efee27211b4198fbb3", "fetched_at": "2026-08-28T04:08:05.530718+00:00", "kind": "readme", "missing": false, "url": "https://github.com/piskvorky/smart_open"}, {"content_hash": "e01d5f1d34171c803f6f29a90699cbbeee926a2aa056e61b3e77711f376697ac", "fetched_at": "2026-08-29T09:31:08.634533+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/smart_open/json"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:08:05.530718+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T18:37:29.491074+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "902d462a59095bc7e4c76dc29f6f92ac63e0d5b6f00218efee27211b4198fbb3", "fetched_at": "2026-08-28T04:08:05.530718+00:00", "kind": "readme", "missing": false, "url": "https://github.com/piskvorky/smart_open"}, {"content_hash": "e01d5f1d34171c803f6f29a90699cbbeee926a2aa056e61b3e77711f376697ac", "fetched_at": "2026-08-29T09:31:08.634533+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/smart_open/json"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T18:37:29.491074+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "902d462a59095bc7e4c76dc29f6f92ac63e0d5b6f00218efee27211b4198fbb3", "fetched_at": "2026-08-28T04:08:05.530718+00:00", "kind": "readme", "missing": false, "url": "https://github.com/piskvorky/smart_open"}, {"content_hash": "e01d5f1d34171c803f6f29a90699cbbeee926a2aa056e61b3e77711f376697ac", "fetched_at": "2026-08-29T09:31:08.634533+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/smart_open/json"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:08:05.530718+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:08:05.530718+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:08:05.530718+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T18:37:29.491074+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "902d462a59095bc7e4c76dc29f6f92ac63e0d5b6f00218efee27211b4198fbb3", "fetched_at": "2026-08-28T04:08:05.530718+00:00", "kind": "readme", "missing": false, "url": "https://github.com/piskvorky/smart_open"}, {"content_hash": "e01d5f1d34171c803f6f29a90699cbbeee926a2aa056e61b3e77711f376697ac", "fetched_at": "2026-08-29T09:31:08.634533+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/smart_open/json"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:08:05.530718+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:08:05.530718+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T18:37:29.491074+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "902d462a59095bc7e4c76dc29f6f92ac63e0d5b6f00218efee27211b4198fbb3", "fetched_at": "2026-08-28T04:08:05.530718+00:00", "kind": "readme", "missing": false, "url": "https://github.com/piskvorky/smart_open"}, {"content_hash": "e01d5f1d34171c803f6f29a90699cbbeee926a2aa056e61b3e77711f376697ac", "fetched_at": "2026-08-29T09:31:08.634533+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/smart_open/json"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:08:05.530718+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:08:05.530718+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:08:05.530718+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T18:37:29.491074+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "902d462a59095bc7e4c76dc29f6f92ac63e0d5b6f00218efee27211b4198fbb3", "fetched_at": "2026-08-28T04:08:05.530718+00:00", "kind": "readme", "missing": false, "url": "https://github.com/piskvorky/smart_open"}, {"content_hash": "e01d5f1d34171c803f6f29a90699cbbeee926a2aa056e61b3e77711f376697ac", "fetched_at": "2026-08-29T09:31:08.634533+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/smart_open/json"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:08:05.530718+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:08:05.530718+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T18:37:29.491074+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "902d462a59095bc7e4c76dc29f6f92ac63e0d5b6f00218efee27211b4198fbb3", "fetched_at": "2026-08-28T04:08:05.530718+00:00", "kind": "readme", "missing": false, "url": "https://github.com/piskvorky/smart_open"}, {"content_hash": "e01d5f1d34171c803f6f29a90699cbbeee926a2aa056e61b3e77711f376697ac", "fetched_at": "2026-08-29T09:31:08.634533+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/smart_open/json"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T18:37:29.491074+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "902d462a59095bc7e4c76dc29f6f92ac63e0d5b6f00218efee27211b4198fbb3", "fetched_at": "2026-08-28T04:08:05.530718+00:00", "kind": "readme", "missing": false, "url": "https://github.com/piskvorky/smart_open"}, {"content_hash": "e01d5f1d34171c803f6f29a90699cbbeee926a2aa056e61b3e77711f376697ac", "fetched_at": "2026-08-29T09:31:08.634533+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/smart_open/json"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T18:37:29.491074+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "902d462a59095bc7e4c76dc29f6f92ac63e0d5b6f00218efee27211b4198fbb3", "fetched_at": "2026-08-28T04:08:05.530718+00:00", "kind": "readme", "missing": false, "url": "https://github.com/piskvorky/smart_open"}, {"content_hash": "e01d5f1d34171c803f6f29a90699cbbeee926a2aa056e61b3e77711f376697ac", "fetched_at": "2026-08-29T09:31:08.634533+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/smart_open/json"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T18:37:29.491074+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "902d462a59095bc7e4c76dc29f6f92ac63e0d5b6f00218efee27211b4198fbb3", "fetched_at": "2026-08-28T04:08:05.530718+00:00", "kind": "readme", "missing": false, "url": "https://github.com/piskvorky/smart_open"}, {"content_hash": "e01d5f1d34171c803f6f29a90699cbbeee926a2aa056e61b3e77711f376697ac", "fetched_at": "2026-08-29T09:31:08.634533+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/smart_open/json"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 96, "longevity": 100, "rhythm": 93}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 4261, "days_push": 29, "days_rel": 49, "gap_med": 21.0, "n_releases_24m": 19}, "score": 96, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}