{"adoption": {"forks": 455, "observed_at": "2026-08-28T04:09:04.481381+00:00", "stars": 5000}, "canonical_url": "https://ross.abutalabs.com/products/smallpond", "card": {"archived": false, "artifact_type": "framework", "description": "A lightweight data processing framework built on DuckDB and 3FS.", "domain": ["big-data", "data-science"], "enriched": true, "function": ["etl", "data-science", "database", "streaming"], "health_score": 26, "homepage": null, "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "active", "member_repos": ["deepseek-ai/smallpond"], "name": "deepseek-ai/smallpond", "platform": ["python"], "pushed_at": "2025-03-05T18:23:54+00:00", "repo": "deepseek-ai/smallpond", "stars": 5000, "tags": ["duckdb", "distributed-data-processing", "parquet", "sql", "3fs", "dataframe", "data-engineering", "linux", "docker"], "topics": ["data-processing", "duckdb"], "urls": [], "use_cases": ["process large parquet datasets with SQL", "sort terabytes of data across a cluster", "run distributed group-by aggregations on parquet files", "batch ETL over a shared filesystem", "repartition and transform big datasets in Python"], "what_it_is": "Smallpond is a lightweight distributed data processing framework built on DuckDB and DeepSeek's 3FS shared file system. It lets users process petabyte-scale datasets with SQL and dataframe-style operations without running long-lived services.", "when_to_avoid": ["you need streaming or real-time processing", "you want a full Spark/Flink ecosystem with rich connectors", "you only process small datasets that fit on one machine"], "when_to_choose": ["you need DuckDB-style SQL processing scaled to many nodes", "you have a shared filesystem like 3FS and want no long-running services", "you want lightweight batch processing of parquet data at PB scale"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/smallpond", "repo": "deepseek-ai/smallpond", "role": "main", "score": 24}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:09:04.481381+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T18:17:35.630232+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8ad6562a5fec22837fbab87a5047d66acd2b31f5901e9e1221daade507c1af4e", "fetched_at": "2026-08-28T04:09:04.481381+00:00", "kind": "readme", "missing": false, "url": "https://github.com/deepseek-ai/smallpond"}, {"content_hash": "a0658b59a795375d28dfb806f8bd1bd76f3f676d54c4eeba9db53f8cad46601f", "fetched_at": "2026-08-29T08:58:30.049877+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/smallpond/json"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:09:04.481381+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T18:17:35.630232+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8ad6562a5fec22837fbab87a5047d66acd2b31f5901e9e1221daade507c1af4e", "fetched_at": "2026-08-28T04:09:04.481381+00:00", "kind": "readme", "missing": false, "url": "https://github.com/deepseek-ai/smallpond"}, {"content_hash": "a0658b59a795375d28dfb806f8bd1bd76f3f676d54c4eeba9db53f8cad46601f", "fetched_at": "2026-08-29T08:58:30.049877+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/smallpond/json"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T18:17:35.630232+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8ad6562a5fec22837fbab87a5047d66acd2b31f5901e9e1221daade507c1af4e", "fetched_at": "2026-08-28T04:09:04.481381+00:00", "kind": "readme", "missing": false, "url": "https://github.com/deepseek-ai/smallpond"}, {"content_hash": "a0658b59a795375d28dfb806f8bd1bd76f3f676d54c4eeba9db53f8cad46601f", "fetched_at": "2026-08-29T08:58:30.049877+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/smallpond/json"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:09:04.481381+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:09:04.481381+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:09:04.481381+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T18:17:35.630232+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8ad6562a5fec22837fbab87a5047d66acd2b31f5901e9e1221daade507c1af4e", "fetched_at": "2026-08-28T04:09:04.481381+00:00", "kind": "readme", "missing": false, "url": "https://github.com/deepseek-ai/smallpond"}, {"content_hash": "a0658b59a795375d28dfb806f8bd1bd76f3f676d54c4eeba9db53f8cad46601f", "fetched_at": "2026-08-29T08:58:30.049877+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/smallpond/json"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:09:04.481381+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:09:04.481381+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T18:17:35.630232+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8ad6562a5fec22837fbab87a5047d66acd2b31f5901e9e1221daade507c1af4e", "fetched_at": "2026-08-28T04:09:04.481381+00:00", "kind": "readme", "missing": false, "url": "https://github.com/deepseek-ai/smallpond"}, {"content_hash": "a0658b59a795375d28dfb806f8bd1bd76f3f676d54c4eeba9db53f8cad46601f", "fetched_at": "2026-08-29T08:58:30.049877+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/smallpond/json"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:09:04.481381+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:09:04.481381+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:09:04.481381+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T18:17:35.630232+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8ad6562a5fec22837fbab87a5047d66acd2b31f5901e9e1221daade507c1af4e", "fetched_at": "2026-08-28T04:09:04.481381+00:00", "kind": "readme", "missing": false, "url": "https://github.com/deepseek-ai/smallpond"}, {"content_hash": "a0658b59a795375d28dfb806f8bd1bd76f3f676d54c4eeba9db53f8cad46601f", "fetched_at": "2026-08-29T08:58:30.049877+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/smallpond/json"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:09:04.481381+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:09:04.481381+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T18:17:35.630232+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8ad6562a5fec22837fbab87a5047d66acd2b31f5901e9e1221daade507c1af4e", "fetched_at": "2026-08-28T04:09:04.481381+00:00", "kind": "readme", "missing": false, "url": "https://github.com/deepseek-ai/smallpond"}, {"content_hash": "a0658b59a795375d28dfb806f8bd1bd76f3f676d54c4eeba9db53f8cad46601f", "fetched_at": "2026-08-29T08:58:30.049877+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/smallpond/json"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T18:17:35.630232+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8ad6562a5fec22837fbab87a5047d66acd2b31f5901e9e1221daade507c1af4e", "fetched_at": "2026-08-28T04:09:04.481381+00:00", "kind": "readme", "missing": false, "url": "https://github.com/deepseek-ai/smallpond"}, {"content_hash": "a0658b59a795375d28dfb806f8bd1bd76f3f676d54c4eeba9db53f8cad46601f", "fetched_at": "2026-08-29T08:58:30.049877+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/smallpond/json"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T18:17:35.630232+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8ad6562a5fec22837fbab87a5047d66acd2b31f5901e9e1221daade507c1af4e", "fetched_at": "2026-08-28T04:09:04.481381+00:00", "kind": "readme", "missing": false, "url": "https://github.com/deepseek-ai/smallpond"}, {"content_hash": "a0658b59a795375d28dfb806f8bd1bd76f3f676d54c4eeba9db53f8cad46601f", "fetched_at": "2026-08-29T08:58:30.049877+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/smallpond/json"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T18:17:35.630232+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8ad6562a5fec22837fbab87a5047d66acd2b31f5901e9e1221daade507c1af4e", "fetched_at": "2026-08-28T04:09:04.481381+00:00", "kind": "readme", "missing": false, "url": "https://github.com/deepseek-ai/smallpond"}, {"content_hash": "a0658b59a795375d28dfb806f8bd1bd76f3f676d54c4eeba9db53f8cad46601f", "fetched_at": "2026-08-29T08:58:30.049877+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/smallpond/json"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 9, "longevity": 39, "rhythm": 35}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 555, "days_push": 546, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 24, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}