{"adoption": {"forks": 2343, "observed_at": "2026-08-28T04:10:28.872638+00:00", "stars": 9202}, "canonical_url": "https://ross.abutalabs.com/products/datafusion", "card": {"archived": false, "artifact_type": "library", "description": "Apache DataFusion SQL Query Engine", "domain": ["databases", "analytics", "big-data", "data-science"], "enriched": true, "function": ["database", "parser", "cli", "data-science"], "health_score": 80, "homepage": "https://datafusion.apache.org/", "language": "Rust", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["apache/datafusion"], "name": "apache/datafusion", "platform": ["rust", "python", "cli", "cross-platform"], "pushed_at": "2026-08-26T21:06:13+00:00", "repo": "apache/datafusion", "stars": 9202, "tags": ["sql", "query-engine", "dataframe", "apache-arrow", "columnar", "olap", "parquet", "in-process", "embeddable", "streaming-execution", "query-optimizer"], "topics": ["arrow", "big-data", "dataframe", "datafusion", "olap", "python", "query-engine", "rust", "sql"], "urls": [], "use_cases": ["run SQL queries directly on parquet files", "embed a SQL query engine in my Rust application", "build a custom database or analytics product without writing an execution engine", "query CSV and JSON files with SQL from the command line", "use a DataFrame API for analytics in Rust or Python", "fast in-process OLAP analytics on columnar data"], "what_it_is": "Apache DataFusion is an extensible query engine written in Rust that uses Apache Arrow as its in-memory columnar format. It provides SQL and DataFrame APIs with a full query planner and a vectorized, multi-threaded, streaming execution engine designed to be embedded into custom database and analytics systems, with Python bindings and a datafusion-cli binary.", "when_to_avoid": ["You want an end-user ready serverless analytical database to use directly, where DuckDB is a better fit", "You want a batteries-included DataFrame library aimed at data scientists like Polars", "You need distributed multi-node execution out of the box, which is handled by the separate Ballista project", "You need a transactional OLTP database rather than an analytical query engine"], "when_to_choose": ["You are a developer building a database, analytics platform, or query system and want reusable SQL parsing, planning, and vectorized execution rather than starting from scratch", "You need fast single-process queries over Parquet, CSV, JSON, or Avro using the Apache Arrow memory model", "You need deep customization points such as custom data sources, operators, functions, window/aggregate functions, or alternative query languages", "You prefer an Apache Software Foundation-governed, actively developed engine with an active community and Python bindings"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/datafusion", "repo": "apache/datafusion", "role": "main", "score": 77}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:10:28.872638+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T17:23:17.980699+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "06a614fee7fc2261c4d96197a7f159033a6c0f8f8005450fc2e3f8465ea12176", "fetched_at": "2026-08-28T04:10:28.872638+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apache/datafusion"}, {"content_hash": "25e945e4ad2d6dd139e50495cdd267d0cfd7cf57edc29948e1e7990ee072fb51", "fetched_at": "2026-08-29T08:23:13.919786+00:00", "kind": "homepage", "missing": false, "url": "https://datafusion.apache.org/"}, {"content_hash": "21693b9b77f0f70f7768a721271e3087cda6dcc579c7e3d10120f87308fb2c6f", "fetched_at": "2026-08-29T08:23:13.928935+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/user-guide/features.html"}, {"content_hash": "dd28e4dec4ab5cda9c73c9452dbdd423f81e3ae38ee816541a0d48a2da13c508", "fetched_at": "2026-08-29T08:23:13.931092+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/user-guide/cli/installation.html"}, {"content_hash": "aa71679b0111487daaaebcb0d3b584efe42bd86a59cfead7f9df0d3622128fde", "fetched_at": "2026-08-29T08:23:13.933342+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/user-guide/faq.html"}, {"content_hash": "d9825b58ceddd14a942f3157df77657e364dfec14a8d35dd62b19704312c641c", "fetched_at": "2026-08-29T08:23:13.935189+00:00", "kind": "registry_crates", "missing": false, "url": "https://crates.io/api/v1/crates/datafusion"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:10:28.872638+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T17:23:17.980699+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "06a614fee7fc2261c4d96197a7f159033a6c0f8f8005450fc2e3f8465ea12176", "fetched_at": "2026-08-28T04:10:28.872638+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apache/datafusion"}, {"content_hash": "25e945e4ad2d6dd139e50495cdd267d0cfd7cf57edc29948e1e7990ee072fb51", "fetched_at": "2026-08-29T08:23:13.919786+00:00", "kind": "homepage", "missing": false, "url": "https://datafusion.apache.org/"}, {"content_hash": "21693b9b77f0f70f7768a721271e3087cda6dcc579c7e3d10120f87308fb2c6f", "fetched_at": "2026-08-29T08:23:13.928935+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/user-guide/features.html"}, {"content_hash": "dd28e4dec4ab5cda9c73c9452dbdd423f81e3ae38ee816541a0d48a2da13c508", "fetched_at": "2026-08-29T08:23:13.931092+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/user-guide/cli/installation.html"}, {"content_hash": "aa71679b0111487daaaebcb0d3b584efe42bd86a59cfead7f9df0d3622128fde", "fetched_at": "2026-08-29T08:23:13.933342+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/user-guide/faq.html"}, {"content_hash": "d9825b58ceddd14a942f3157df77657e364dfec14a8d35dd62b19704312c641c", "fetched_at": "2026-08-29T08:23:13.935189+00:00", "kind": "registry_crates", "missing": false, "url": "https://crates.io/api/v1/crates/datafusion"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T17:23:17.980699+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "06a614fee7fc2261c4d96197a7f159033a6c0f8f8005450fc2e3f8465ea12176", "fetched_at": "2026-08-28T04:10:28.872638+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apache/datafusion"}, {"content_hash": "25e945e4ad2d6dd139e50495cdd267d0cfd7cf57edc29948e1e7990ee072fb51", "fetched_at": "2026-08-29T08:23:13.919786+00:00", "kind": "homepage", "missing": false, "url": "https://datafusion.apache.org/"}, {"content_hash": "21693b9b77f0f70f7768a721271e3087cda6dcc579c7e3d10120f87308fb2c6f", "fetched_at": "2026-08-29T08:23:13.928935+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/user-guide/features.html"}, {"content_hash": "dd28e4dec4ab5cda9c73c9452dbdd423f81e3ae38ee816541a0d48a2da13c508", "fetched_at": "2026-08-29T08:23:13.931092+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/user-guide/cli/installation.html"}, {"content_hash": "aa71679b0111487daaaebcb0d3b584efe42bd86a59cfead7f9df0d3622128fde", "fetched_at": "2026-08-29T08:23:13.933342+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/user-guide/faq.html"}, {"content_hash": "d9825b58ceddd14a942f3157df77657e364dfec14a8d35dd62b19704312c641c", "fetched_at": "2026-08-29T08:23:13.935189+00:00", "kind": "registry_crates", "missing": false, "url": "https://crates.io/api/v1/crates/datafusion"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:10:28.872638+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:10:28.872638+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:10:28.872638+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T17:23:17.980699+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "06a614fee7fc2261c4d96197a7f159033a6c0f8f8005450fc2e3f8465ea12176", "fetched_at": "2026-08-28T04:10:28.872638+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apache/datafusion"}, {"content_hash": "25e945e4ad2d6dd139e50495cdd267d0cfd7cf57edc29948e1e7990ee072fb51", "fetched_at": "2026-08-29T08:23:13.919786+00:00", "kind": "homepage", "missing": false, "url": "https://datafusion.apache.org/"}, {"content_hash": "21693b9b77f0f70f7768a721271e3087cda6dcc579c7e3d10120f87308fb2c6f", "fetched_at": "2026-08-29T08:23:13.928935+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/user-guide/features.html"}, {"content_hash": "dd28e4dec4ab5cda9c73c9452dbdd423f81e3ae38ee816541a0d48a2da13c508", "fetched_at": "2026-08-29T08:23:13.931092+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/user-guide/cli/installation.html"}, {"content_hash": "aa71679b0111487daaaebcb0d3b584efe42bd86a59cfead7f9df0d3622128fde", "fetched_at": "2026-08-29T08:23:13.933342+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/user-guide/faq.html"}, {"content_hash": "d9825b58ceddd14a942f3157df77657e364dfec14a8d35dd62b19704312c641c", "fetched_at": "2026-08-29T08:23:13.935189+00:00", "kind": "registry_crates", "missing": false, "url": "https://crates.io/api/v1/crates/datafusion"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:10:28.872638+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:10:28.872638+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T17:23:17.980699+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "06a614fee7fc2261c4d96197a7f159033a6c0f8f8005450fc2e3f8465ea12176", "fetched_at": "2026-08-28T04:10:28.872638+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apache/datafusion"}, {"content_hash": "25e945e4ad2d6dd139e50495cdd267d0cfd7cf57edc29948e1e7990ee072fb51", "fetched_at": "2026-08-29T08:23:13.919786+00:00", "kind": "homepage", "missing": false, "url": "https://datafusion.apache.org/"}, {"content_hash": "21693b9b77f0f70f7768a721271e3087cda6dcc579c7e3d10120f87308fb2c6f", "fetched_at": "2026-08-29T08:23:13.928935+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/user-guide/features.html"}, {"content_hash": "dd28e4dec4ab5cda9c73c9452dbdd423f81e3ae38ee816541a0d48a2da13c508", "fetched_at": "2026-08-29T08:23:13.931092+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/user-guide/cli/installation.html"}, {"content_hash": "aa71679b0111487daaaebcb0d3b584efe42bd86a59cfead7f9df0d3622128fde", "fetched_at": "2026-08-29T08:23:13.933342+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/user-guide/faq.html"}, {"content_hash": "d9825b58ceddd14a942f3157df77657e364dfec14a8d35dd62b19704312c641c", "fetched_at": "2026-08-29T08:23:13.935189+00:00", "kind": "registry_crates", "missing": false, "url": "https://crates.io/api/v1/crates/datafusion"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:10:28.872638+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:10:28.872638+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:10:28.872638+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T17:23:17.980699+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "06a614fee7fc2261c4d96197a7f159033a6c0f8f8005450fc2e3f8465ea12176", "fetched_at": "2026-08-28T04:10:28.872638+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apache/datafusion"}, {"content_hash": "25e945e4ad2d6dd139e50495cdd267d0cfd7cf57edc29948e1e7990ee072fb51", "fetched_at": "2026-08-29T08:23:13.919786+00:00", "kind": "homepage", "missing": false, "url": "https://datafusion.apache.org/"}, {"content_hash": "21693b9b77f0f70f7768a721271e3087cda6dcc579c7e3d10120f87308fb2c6f", "fetched_at": "2026-08-29T08:23:13.928935+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/user-guide/features.html"}, {"content_hash": "dd28e4dec4ab5cda9c73c9452dbdd423f81e3ae38ee816541a0d48a2da13c508", "fetched_at": "2026-08-29T08:23:13.931092+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/user-guide/cli/installation.html"}, {"content_hash": "aa71679b0111487daaaebcb0d3b584efe42bd86a59cfead7f9df0d3622128fde", "fetched_at": "2026-08-29T08:23:13.933342+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/user-guide/faq.html"}, {"content_hash": "d9825b58ceddd14a942f3157df77657e364dfec14a8d35dd62b19704312c641c", "fetched_at": "2026-08-29T08:23:13.935189+00:00", "kind": "registry_crates", "missing": false, "url": "https://crates.io/api/v1/crates/datafusion"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:10:28.872638+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:10:28.872638+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T17:23:17.980699+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "06a614fee7fc2261c4d96197a7f159033a6c0f8f8005450fc2e3f8465ea12176", "fetched_at": "2026-08-28T04:10:28.872638+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apache/datafusion"}, {"content_hash": "25e945e4ad2d6dd139e50495cdd267d0cfd7cf57edc29948e1e7990ee072fb51", "fetched_at": "2026-08-29T08:23:13.919786+00:00", "kind": "homepage", "missing": false, "url": "https://datafusion.apache.org/"}, {"content_hash": "21693b9b77f0f70f7768a721271e3087cda6dcc579c7e3d10120f87308fb2c6f", "fetched_at": "2026-08-29T08:23:13.928935+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/user-guide/features.html"}, {"content_hash": "dd28e4dec4ab5cda9c73c9452dbdd423f81e3ae38ee816541a0d48a2da13c508", "fetched_at": "2026-08-29T08:23:13.931092+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/user-guide/cli/installation.html"}, {"content_hash": "aa71679b0111487daaaebcb0d3b584efe42bd86a59cfead7f9df0d3622128fde", "fetched_at": "2026-08-29T08:23:13.933342+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/user-guide/faq.html"}, {"content_hash": "d9825b58ceddd14a942f3157df77657e364dfec14a8d35dd62b19704312c641c", "fetched_at": "2026-08-29T08:23:13.935189+00:00", "kind": "registry_crates", "missing": false, "url": "https://crates.io/api/v1/crates/datafusion"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T17:23:17.980699+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "06a614fee7fc2261c4d96197a7f159033a6c0f8f8005450fc2e3f8465ea12176", "fetched_at": "2026-08-28T04:10:28.872638+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apache/datafusion"}, {"content_hash": "25e945e4ad2d6dd139e50495cdd267d0cfd7cf57edc29948e1e7990ee072fb51", "fetched_at": "2026-08-29T08:23:13.919786+00:00", "kind": "homepage", "missing": false, "url": "https://datafusion.apache.org/"}, {"content_hash": "21693b9b77f0f70f7768a721271e3087cda6dcc579c7e3d10120f87308fb2c6f", "fetched_at": "2026-08-29T08:23:13.928935+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/user-guide/features.html"}, {"content_hash": "dd28e4dec4ab5cda9c73c9452dbdd423f81e3ae38ee816541a0d48a2da13c508", "fetched_at": "2026-08-29T08:23:13.931092+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/user-guide/cli/installation.html"}, {"content_hash": "aa71679b0111487daaaebcb0d3b584efe42bd86a59cfead7f9df0d3622128fde", "fetched_at": "2026-08-29T08:23:13.933342+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/user-guide/faq.html"}, {"content_hash": "d9825b58ceddd14a942f3157df77657e364dfec14a8d35dd62b19704312c641c", "fetched_at": "2026-08-29T08:23:13.935189+00:00", "kind": "registry_crates", "missing": false, "url": "https://crates.io/api/v1/crates/datafusion"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T17:23:17.980699+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "06a614fee7fc2261c4d96197a7f159033a6c0f8f8005450fc2e3f8465ea12176", "fetched_at": "2026-08-28T04:10:28.872638+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apache/datafusion"}, {"content_hash": "25e945e4ad2d6dd139e50495cdd267d0cfd7cf57edc29948e1e7990ee072fb51", "fetched_at": "2026-08-29T08:23:13.919786+00:00", "kind": "homepage", "missing": false, "url": "https://datafusion.apache.org/"}, {"content_hash": "21693b9b77f0f70f7768a721271e3087cda6dcc579c7e3d10120f87308fb2c6f", "fetched_at": "2026-08-29T08:23:13.928935+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/user-guide/features.html"}, {"content_hash": "dd28e4dec4ab5cda9c73c9452dbdd423f81e3ae38ee816541a0d48a2da13c508", "fetched_at": "2026-08-29T08:23:13.931092+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/user-guide/cli/installation.html"}, {"content_hash": "aa71679b0111487daaaebcb0d3b584efe42bd86a59cfead7f9df0d3622128fde", "fetched_at": "2026-08-29T08:23:13.933342+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/user-guide/faq.html"}, {"content_hash": "d9825b58ceddd14a942f3157df77657e364dfec14a8d35dd62b19704312c641c", "fetched_at": "2026-08-29T08:23:13.935189+00:00", "kind": "registry_crates", "missing": false, "url": "https://crates.io/api/v1/crates/datafusion"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T17:23:17.980699+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "06a614fee7fc2261c4d96197a7f159033a6c0f8f8005450fc2e3f8465ea12176", "fetched_at": "2026-08-28T04:10:28.872638+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apache/datafusion"}, {"content_hash": "25e945e4ad2d6dd139e50495cdd267d0cfd7cf57edc29948e1e7990ee072fb51", "fetched_at": "2026-08-29T08:23:13.919786+00:00", "kind": "homepage", "missing": false, "url": "https://datafusion.apache.org/"}, {"content_hash": "21693b9b77f0f70f7768a721271e3087cda6dcc579c7e3d10120f87308fb2c6f", "fetched_at": "2026-08-29T08:23:13.928935+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/user-guide/features.html"}, {"content_hash": "dd28e4dec4ab5cda9c73c9452dbdd423f81e3ae38ee816541a0d48a2da13c508", "fetched_at": "2026-08-29T08:23:13.931092+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/user-guide/cli/installation.html"}, {"content_hash": "aa71679b0111487daaaebcb0d3b584efe42bd86a59cfead7f9df0d3622128fde", "fetched_at": "2026-08-29T08:23:13.933342+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/user-guide/faq.html"}, {"content_hash": "d9825b58ceddd14a942f3157df77657e364dfec14a8d35dd62b19704312c641c", "fetched_at": "2026-08-29T08:23:13.935189+00:00", "kind": "registry_crates", "missing": false, "url": "https://crates.io/api/v1/crates/datafusion"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 99, "longevity": 100, "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": 1964, "days_push": 7, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 77, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}