{"adoption": {"forks": 312, "observed_at": "2026-08-28T04:06:15.831491+00:00", "stars": 2115}, "canonical_url": "https://ross.abutalabs.com/products/datafusion-ballista", "card": {"archived": false, "artifact_type": "framework", "description": "Apache DataFusion Ballista Distributed Query Engine", "domain": ["big-data", "microservices", "databases"], "enriched": true, "function": ["database", "etl", "streaming"], "health_score": 100, "homepage": "https://datafusion.apache.org/ballista", "language": "Rust", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["apache/datafusion-ballista"], "name": "apache/datafusion-ballista", "platform": ["rust", "python", "cross-platform", "cli"], "pushed_at": "2026-08-26T11:21:55+00:00", "repo": "apache/datafusion-ballista", "stars": 2115, "tags": ["distributed-query-engine", "apache-arrow", "datafusion", "olap", "sql", "dataframe", "spark-alternative", "data-engineering"], "topics": ["arrow", "big-data", "dataframe", "olap", "python", "query-engine", "rust", "sql", "distributed"], "urls": [], "use_cases": ["run SQL queries across a distributed cluster", "scale DataFusion DataFrame workloads to multiple nodes", "execute large batch ETL jobs in parallel", "query Parquet and CSV files distributedly from Python", "replace Spark with a Rust-native query engine", "run distributed OLAP analytics on Arrow data"], "what_it_is": "Apache DataFusion Ballista is a distributed query execution engine built on Apache DataFusion that parallelizes SQL and DataFrame workloads across multiple nodes. It offers Rust, Python, SQL, and CLI clients with a scheduler/executor architecture and blocking shuffle similar to Apache Spark.", "when_to_avoid": ["your queries are interactive, short, and produce small intermediate results where a pipelined engine is faster", "you need full Apache Spark API compatibility rather than Spark-compatible functions", "your workload fits comfortably in a single process with DataFusion alone", "you need streaming shuffles between query stages"], "when_to_choose": ["you already use DataFusion and need distributed execution with minimal code changes", "you run large, long-running batch or ETL jobs, especially on preemptible nodes", "you want a lightweight Rust-based alternative to Apache Spark", "you need Python bindings similar to PySpark for distributed queries"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/datafusion-ballista", "repo": "apache/datafusion-ballista", "role": "main", "score": 98}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:06:15.831491+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T02:53:21.550888+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d126042f90e5008347351e45747a0ee6a04a96738fd7d27aabf530a19cce7504", "fetched_at": "2026-08-28T04:06:15.831491+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apache/datafusion-ballista"}, {"content_hash": "8d4dd28c757bf363f14fe93761949140d7512e1207553cc8f5a045d6e78a3eed", "fetched_at": "2026-08-29T10:33:27.425745+00:00", "kind": "homepage", "missing": false, "url": "https://datafusion.apache.org/ballista"}, {"content_hash": "d3ad84df69f445b347a08dc8e9c03f0ea5c246c222c5304adcfc6c4b62903e46", "fetched_at": "2026-08-29T10:33:27.435597+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/user-guide/deployment/cargo-install.html"}, {"content_hash": "045601be01819f2e1c32b1e47c70a8a1a85c711c6c8cd3c15a368cad6f0a578b", "fetched_at": "2026-08-29T10:33:27.438466+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/user-guide/python/quickstart.html"}, {"content_hash": "1fc0b50b199e37b2faf6afa85247dcad5bcd05e92583000e69bc780520030dcd", "fetched_at": "2026-08-29T10:33:27.440955+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/user-guide/faq.html"}, {"content_hash": "b7d335764d974aa1304bd3085ba32cde527f93bda4cffec9fea0eb7ad5690322", "fetched_at": "2026-08-29T10:33:27.442993+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/changelog/index.html"}, {"content_hash": "67b964a2eacc0ca53f941b969eee374e4dc994f35072a46de423347e3c22f175", "fetched_at": "2026-08-29T10:33:27.444788+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/changelog/54.1.0.html"}, {"content_hash": "3ac4f5bb7e6e95a9ef0504a140153d35a18123b55a98f4021a7f4d0ded4ebd91", "fetched_at": "2026-08-29T10:33:27.446664+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/changelog/54.0.0.html"}, {"content_hash": "e3c79bb6c5a09a4c6bc33b06c989dc8c0657e4275b9f58b324f9983c4cca526f", "fetched_at": "2026-08-29T10:33:27.449449+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/changelog/53.0.0.html"}, {"content_hash": "2051e77995c0d828545df5e46858173e7796f36b8ea43d61268b612dcff7d461", "fetched_at": "2026-08-29T10:33:27.452218+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/changelog/52.0.0.html"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:06:15.831491+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T02:53:21.550888+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d126042f90e5008347351e45747a0ee6a04a96738fd7d27aabf530a19cce7504", "fetched_at": "2026-08-28T04:06:15.831491+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apache/datafusion-ballista"}, {"content_hash": "8d4dd28c757bf363f14fe93761949140d7512e1207553cc8f5a045d6e78a3eed", "fetched_at": "2026-08-29T10:33:27.425745+00:00", "kind": "homepage", "missing": false, "url": "https://datafusion.apache.org/ballista"}, {"content_hash": "d3ad84df69f445b347a08dc8e9c03f0ea5c246c222c5304adcfc6c4b62903e46", "fetched_at": "2026-08-29T10:33:27.435597+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/user-guide/deployment/cargo-install.html"}, {"content_hash": "045601be01819f2e1c32b1e47c70a8a1a85c711c6c8cd3c15a368cad6f0a578b", "fetched_at": "2026-08-29T10:33:27.438466+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/user-guide/python/quickstart.html"}, {"content_hash": "1fc0b50b199e37b2faf6afa85247dcad5bcd05e92583000e69bc780520030dcd", "fetched_at": "2026-08-29T10:33:27.440955+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/user-guide/faq.html"}, {"content_hash": "b7d335764d974aa1304bd3085ba32cde527f93bda4cffec9fea0eb7ad5690322", "fetched_at": "2026-08-29T10:33:27.442993+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/changelog/index.html"}, {"content_hash": "67b964a2eacc0ca53f941b969eee374e4dc994f35072a46de423347e3c22f175", "fetched_at": "2026-08-29T10:33:27.444788+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/changelog/54.1.0.html"}, {"content_hash": "3ac4f5bb7e6e95a9ef0504a140153d35a18123b55a98f4021a7f4d0ded4ebd91", "fetched_at": "2026-08-29T10:33:27.446664+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/changelog/54.0.0.html"}, {"content_hash": "e3c79bb6c5a09a4c6bc33b06c989dc8c0657e4275b9f58b324f9983c4cca526f", "fetched_at": "2026-08-29T10:33:27.449449+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/changelog/53.0.0.html"}, {"content_hash": "2051e77995c0d828545df5e46858173e7796f36b8ea43d61268b612dcff7d461", "fetched_at": "2026-08-29T10:33:27.452218+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/changelog/52.0.0.html"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T02:53:21.550888+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d126042f90e5008347351e45747a0ee6a04a96738fd7d27aabf530a19cce7504", "fetched_at": "2026-08-28T04:06:15.831491+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apache/datafusion-ballista"}, {"content_hash": "8d4dd28c757bf363f14fe93761949140d7512e1207553cc8f5a045d6e78a3eed", "fetched_at": "2026-08-29T10:33:27.425745+00:00", "kind": "homepage", "missing": false, "url": "https://datafusion.apache.org/ballista"}, {"content_hash": "d3ad84df69f445b347a08dc8e9c03f0ea5c246c222c5304adcfc6c4b62903e46", "fetched_at": "2026-08-29T10:33:27.435597+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/user-guide/deployment/cargo-install.html"}, {"content_hash": "045601be01819f2e1c32b1e47c70a8a1a85c711c6c8cd3c15a368cad6f0a578b", "fetched_at": "2026-08-29T10:33:27.438466+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/user-guide/python/quickstart.html"}, {"content_hash": "1fc0b50b199e37b2faf6afa85247dcad5bcd05e92583000e69bc780520030dcd", "fetched_at": "2026-08-29T10:33:27.440955+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/user-guide/faq.html"}, {"content_hash": "b7d335764d974aa1304bd3085ba32cde527f93bda4cffec9fea0eb7ad5690322", "fetched_at": "2026-08-29T10:33:27.442993+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/changelog/index.html"}, {"content_hash": "67b964a2eacc0ca53f941b969eee374e4dc994f35072a46de423347e3c22f175", "fetched_at": "2026-08-29T10:33:27.444788+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/changelog/54.1.0.html"}, {"content_hash": "3ac4f5bb7e6e95a9ef0504a140153d35a18123b55a98f4021a7f4d0ded4ebd91", "fetched_at": "2026-08-29T10:33:27.446664+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/changelog/54.0.0.html"}, {"content_hash": "e3c79bb6c5a09a4c6bc33b06c989dc8c0657e4275b9f58b324f9983c4cca526f", "fetched_at": "2026-08-29T10:33:27.449449+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/changelog/53.0.0.html"}, {"content_hash": "2051e77995c0d828545df5e46858173e7796f36b8ea43d61268b612dcff7d461", "fetched_at": "2026-08-29T10:33:27.452218+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/changelog/52.0.0.html"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:06:15.831491+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:06:15.831491+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:06:15.831491+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T02:53:21.550888+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d126042f90e5008347351e45747a0ee6a04a96738fd7d27aabf530a19cce7504", "fetched_at": "2026-08-28T04:06:15.831491+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apache/datafusion-ballista"}, {"content_hash": "8d4dd28c757bf363f14fe93761949140d7512e1207553cc8f5a045d6e78a3eed", "fetched_at": "2026-08-29T10:33:27.425745+00:00", "kind": "homepage", "missing": false, "url": "https://datafusion.apache.org/ballista"}, {"content_hash": "d3ad84df69f445b347a08dc8e9c03f0ea5c246c222c5304adcfc6c4b62903e46", "fetched_at": "2026-08-29T10:33:27.435597+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/user-guide/deployment/cargo-install.html"}, {"content_hash": "045601be01819f2e1c32b1e47c70a8a1a85c711c6c8cd3c15a368cad6f0a578b", "fetched_at": "2026-08-29T10:33:27.438466+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/user-guide/python/quickstart.html"}, {"content_hash": "1fc0b50b199e37b2faf6afa85247dcad5bcd05e92583000e69bc780520030dcd", "fetched_at": "2026-08-29T10:33:27.440955+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/user-guide/faq.html"}, {"content_hash": "b7d335764d974aa1304bd3085ba32cde527f93bda4cffec9fea0eb7ad5690322", "fetched_at": "2026-08-29T10:33:27.442993+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/changelog/index.html"}, {"content_hash": "67b964a2eacc0ca53f941b969eee374e4dc994f35072a46de423347e3c22f175", "fetched_at": "2026-08-29T10:33:27.444788+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/changelog/54.1.0.html"}, {"content_hash": "3ac4f5bb7e6e95a9ef0504a140153d35a18123b55a98f4021a7f4d0ded4ebd91", "fetched_at": "2026-08-29T10:33:27.446664+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/changelog/54.0.0.html"}, {"content_hash": "e3c79bb6c5a09a4c6bc33b06c989dc8c0657e4275b9f58b324f9983c4cca526f", "fetched_at": "2026-08-29T10:33:27.449449+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/changelog/53.0.0.html"}, {"content_hash": "2051e77995c0d828545df5e46858173e7796f36b8ea43d61268b612dcff7d461", "fetched_at": "2026-08-29T10:33:27.452218+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/changelog/52.0.0.html"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:06:15.831491+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:06:15.831491+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T02:53:21.550888+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d126042f90e5008347351e45747a0ee6a04a96738fd7d27aabf530a19cce7504", "fetched_at": "2026-08-28T04:06:15.831491+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apache/datafusion-ballista"}, {"content_hash": "8d4dd28c757bf363f14fe93761949140d7512e1207553cc8f5a045d6e78a3eed", "fetched_at": "2026-08-29T10:33:27.425745+00:00", "kind": "homepage", "missing": false, "url": "https://datafusion.apache.org/ballista"}, {"content_hash": "d3ad84df69f445b347a08dc8e9c03f0ea5c246c222c5304adcfc6c4b62903e46", "fetched_at": "2026-08-29T10:33:27.435597+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/user-guide/deployment/cargo-install.html"}, {"content_hash": "045601be01819f2e1c32b1e47c70a8a1a85c711c6c8cd3c15a368cad6f0a578b", "fetched_at": "2026-08-29T10:33:27.438466+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/user-guide/python/quickstart.html"}, {"content_hash": "1fc0b50b199e37b2faf6afa85247dcad5bcd05e92583000e69bc780520030dcd", "fetched_at": "2026-08-29T10:33:27.440955+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/user-guide/faq.html"}, {"content_hash": "b7d335764d974aa1304bd3085ba32cde527f93bda4cffec9fea0eb7ad5690322", "fetched_at": "2026-08-29T10:33:27.442993+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/changelog/index.html"}, {"content_hash": "67b964a2eacc0ca53f941b969eee374e4dc994f35072a46de423347e3c22f175", "fetched_at": "2026-08-29T10:33:27.444788+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/changelog/54.1.0.html"}, {"content_hash": "3ac4f5bb7e6e95a9ef0504a140153d35a18123b55a98f4021a7f4d0ded4ebd91", "fetched_at": "2026-08-29T10:33:27.446664+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/changelog/54.0.0.html"}, {"content_hash": "e3c79bb6c5a09a4c6bc33b06c989dc8c0657e4275b9f58b324f9983c4cca526f", "fetched_at": "2026-08-29T10:33:27.449449+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/changelog/53.0.0.html"}, {"content_hash": "2051e77995c0d828545df5e46858173e7796f36b8ea43d61268b612dcff7d461", "fetched_at": "2026-08-29T10:33:27.452218+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/changelog/52.0.0.html"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:06:15.831491+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:06:15.831491+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:06:15.831491+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T02:53:21.550888+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d126042f90e5008347351e45747a0ee6a04a96738fd7d27aabf530a19cce7504", "fetched_at": "2026-08-28T04:06:15.831491+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apache/datafusion-ballista"}, {"content_hash": "8d4dd28c757bf363f14fe93761949140d7512e1207553cc8f5a045d6e78a3eed", "fetched_at": "2026-08-29T10:33:27.425745+00:00", "kind": "homepage", "missing": false, "url": "https://datafusion.apache.org/ballista"}, {"content_hash": "d3ad84df69f445b347a08dc8e9c03f0ea5c246c222c5304adcfc6c4b62903e46", "fetched_at": "2026-08-29T10:33:27.435597+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/user-guide/deployment/cargo-install.html"}, {"content_hash": "045601be01819f2e1c32b1e47c70a8a1a85c711c6c8cd3c15a368cad6f0a578b", "fetched_at": "2026-08-29T10:33:27.438466+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/user-guide/python/quickstart.html"}, {"content_hash": "1fc0b50b199e37b2faf6afa85247dcad5bcd05e92583000e69bc780520030dcd", "fetched_at": "2026-08-29T10:33:27.440955+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/user-guide/faq.html"}, {"content_hash": "b7d335764d974aa1304bd3085ba32cde527f93bda4cffec9fea0eb7ad5690322", "fetched_at": "2026-08-29T10:33:27.442993+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/changelog/index.html"}, {"content_hash": "67b964a2eacc0ca53f941b969eee374e4dc994f35072a46de423347e3c22f175", "fetched_at": "2026-08-29T10:33:27.444788+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/changelog/54.1.0.html"}, {"content_hash": "3ac4f5bb7e6e95a9ef0504a140153d35a18123b55a98f4021a7f4d0ded4ebd91", "fetched_at": "2026-08-29T10:33:27.446664+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/changelog/54.0.0.html"}, {"content_hash": "e3c79bb6c5a09a4c6bc33b06c989dc8c0657e4275b9f58b324f9983c4cca526f", "fetched_at": "2026-08-29T10:33:27.449449+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/changelog/53.0.0.html"}, {"content_hash": "2051e77995c0d828545df5e46858173e7796f36b8ea43d61268b612dcff7d461", "fetched_at": "2026-08-29T10:33:27.452218+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/changelog/52.0.0.html"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:06:15.831491+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:06:15.831491+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T02:53:21.550888+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d126042f90e5008347351e45747a0ee6a04a96738fd7d27aabf530a19cce7504", "fetched_at": "2026-08-28T04:06:15.831491+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apache/datafusion-ballista"}, {"content_hash": "8d4dd28c757bf363f14fe93761949140d7512e1207553cc8f5a045d6e78a3eed", "fetched_at": "2026-08-29T10:33:27.425745+00:00", "kind": "homepage", "missing": false, "url": "https://datafusion.apache.org/ballista"}, {"content_hash": "d3ad84df69f445b347a08dc8e9c03f0ea5c246c222c5304adcfc6c4b62903e46", "fetched_at": "2026-08-29T10:33:27.435597+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/user-guide/deployment/cargo-install.html"}, {"content_hash": "045601be01819f2e1c32b1e47c70a8a1a85c711c6c8cd3c15a368cad6f0a578b", "fetched_at": "2026-08-29T10:33:27.438466+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/user-guide/python/quickstart.html"}, {"content_hash": "1fc0b50b199e37b2faf6afa85247dcad5bcd05e92583000e69bc780520030dcd", "fetched_at": "2026-08-29T10:33:27.440955+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/user-guide/faq.html"}, {"content_hash": "b7d335764d974aa1304bd3085ba32cde527f93bda4cffec9fea0eb7ad5690322", "fetched_at": "2026-08-29T10:33:27.442993+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/changelog/index.html"}, {"content_hash": "67b964a2eacc0ca53f941b969eee374e4dc994f35072a46de423347e3c22f175", "fetched_at": "2026-08-29T10:33:27.444788+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/changelog/54.1.0.html"}, {"content_hash": "3ac4f5bb7e6e95a9ef0504a140153d35a18123b55a98f4021a7f4d0ded4ebd91", "fetched_at": "2026-08-29T10:33:27.446664+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/changelog/54.0.0.html"}, {"content_hash": "e3c79bb6c5a09a4c6bc33b06c989dc8c0657e4275b9f58b324f9983c4cca526f", "fetched_at": "2026-08-29T10:33:27.449449+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/changelog/53.0.0.html"}, {"content_hash": "2051e77995c0d828545df5e46858173e7796f36b8ea43d61268b612dcff7d461", "fetched_at": "2026-08-29T10:33:27.452218+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/changelog/52.0.0.html"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T02:53:21.550888+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d126042f90e5008347351e45747a0ee6a04a96738fd7d27aabf530a19cce7504", "fetched_at": "2026-08-28T04:06:15.831491+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apache/datafusion-ballista"}, {"content_hash": "8d4dd28c757bf363f14fe93761949140d7512e1207553cc8f5a045d6e78a3eed", "fetched_at": "2026-08-29T10:33:27.425745+00:00", "kind": "homepage", "missing": false, "url": "https://datafusion.apache.org/ballista"}, {"content_hash": "d3ad84df69f445b347a08dc8e9c03f0ea5c246c222c5304adcfc6c4b62903e46", "fetched_at": "2026-08-29T10:33:27.435597+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/user-guide/deployment/cargo-install.html"}, {"content_hash": "045601be01819f2e1c32b1e47c70a8a1a85c711c6c8cd3c15a368cad6f0a578b", "fetched_at": "2026-08-29T10:33:27.438466+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/user-guide/python/quickstart.html"}, {"content_hash": "1fc0b50b199e37b2faf6afa85247dcad5bcd05e92583000e69bc780520030dcd", "fetched_at": "2026-08-29T10:33:27.440955+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/user-guide/faq.html"}, {"content_hash": "b7d335764d974aa1304bd3085ba32cde527f93bda4cffec9fea0eb7ad5690322", "fetched_at": "2026-08-29T10:33:27.442993+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/changelog/index.html"}, {"content_hash": "67b964a2eacc0ca53f941b969eee374e4dc994f35072a46de423347e3c22f175", "fetched_at": "2026-08-29T10:33:27.444788+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/changelog/54.1.0.html"}, {"content_hash": "3ac4f5bb7e6e95a9ef0504a140153d35a18123b55a98f4021a7f4d0ded4ebd91", "fetched_at": "2026-08-29T10:33:27.446664+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/changelog/54.0.0.html"}, {"content_hash": "e3c79bb6c5a09a4c6bc33b06c989dc8c0657e4275b9f58b324f9983c4cca526f", "fetched_at": "2026-08-29T10:33:27.449449+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/changelog/53.0.0.html"}, {"content_hash": "2051e77995c0d828545df5e46858173e7796f36b8ea43d61268b612dcff7d461", "fetched_at": "2026-08-29T10:33:27.452218+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/changelog/52.0.0.html"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T02:53:21.550888+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d126042f90e5008347351e45747a0ee6a04a96738fd7d27aabf530a19cce7504", "fetched_at": "2026-08-28T04:06:15.831491+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apache/datafusion-ballista"}, {"content_hash": "8d4dd28c757bf363f14fe93761949140d7512e1207553cc8f5a045d6e78a3eed", "fetched_at": "2026-08-29T10:33:27.425745+00:00", "kind": "homepage", "missing": false, "url": "https://datafusion.apache.org/ballista"}, {"content_hash": "d3ad84df69f445b347a08dc8e9c03f0ea5c246c222c5304adcfc6c4b62903e46", "fetched_at": "2026-08-29T10:33:27.435597+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/user-guide/deployment/cargo-install.html"}, {"content_hash": "045601be01819f2e1c32b1e47c70a8a1a85c711c6c8cd3c15a368cad6f0a578b", "fetched_at": "2026-08-29T10:33:27.438466+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/user-guide/python/quickstart.html"}, {"content_hash": "1fc0b50b199e37b2faf6afa85247dcad5bcd05e92583000e69bc780520030dcd", "fetched_at": "2026-08-29T10:33:27.440955+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/user-guide/faq.html"}, {"content_hash": "b7d335764d974aa1304bd3085ba32cde527f93bda4cffec9fea0eb7ad5690322", "fetched_at": "2026-08-29T10:33:27.442993+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/changelog/index.html"}, {"content_hash": "67b964a2eacc0ca53f941b969eee374e4dc994f35072a46de423347e3c22f175", "fetched_at": "2026-08-29T10:33:27.444788+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/changelog/54.1.0.html"}, {"content_hash": "3ac4f5bb7e6e95a9ef0504a140153d35a18123b55a98f4021a7f4d0ded4ebd91", "fetched_at": "2026-08-29T10:33:27.446664+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/changelog/54.0.0.html"}, {"content_hash": "e3c79bb6c5a09a4c6bc33b06c989dc8c0657e4275b9f58b324f9983c4cca526f", "fetched_at": "2026-08-29T10:33:27.449449+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/changelog/53.0.0.html"}, {"content_hash": "2051e77995c0d828545df5e46858173e7796f36b8ea43d61268b612dcff7d461", "fetched_at": "2026-08-29T10:33:27.452218+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/changelog/52.0.0.html"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T02:53:21.550888+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d126042f90e5008347351e45747a0ee6a04a96738fd7d27aabf530a19cce7504", "fetched_at": "2026-08-28T04:06:15.831491+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apache/datafusion-ballista"}, {"content_hash": "8d4dd28c757bf363f14fe93761949140d7512e1207553cc8f5a045d6e78a3eed", "fetched_at": "2026-08-29T10:33:27.425745+00:00", "kind": "homepage", "missing": false, "url": "https://datafusion.apache.org/ballista"}, {"content_hash": "d3ad84df69f445b347a08dc8e9c03f0ea5c246c222c5304adcfc6c4b62903e46", "fetched_at": "2026-08-29T10:33:27.435597+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/user-guide/deployment/cargo-install.html"}, {"content_hash": "045601be01819f2e1c32b1e47c70a8a1a85c711c6c8cd3c15a368cad6f0a578b", "fetched_at": "2026-08-29T10:33:27.438466+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/user-guide/python/quickstart.html"}, {"content_hash": "1fc0b50b199e37b2faf6afa85247dcad5bcd05e92583000e69bc780520030dcd", "fetched_at": "2026-08-29T10:33:27.440955+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/user-guide/faq.html"}, {"content_hash": "b7d335764d974aa1304bd3085ba32cde527f93bda4cffec9fea0eb7ad5690322", "fetched_at": "2026-08-29T10:33:27.442993+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/changelog/index.html"}, {"content_hash": "67b964a2eacc0ca53f941b969eee374e4dc994f35072a46de423347e3c22f175", "fetched_at": "2026-08-29T10:33:27.444788+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/changelog/54.1.0.html"}, {"content_hash": "3ac4f5bb7e6e95a9ef0504a140153d35a18123b55a98f4021a7f4d0ded4ebd91", "fetched_at": "2026-08-29T10:33:27.446664+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/changelog/54.0.0.html"}, {"content_hash": "e3c79bb6c5a09a4c6bc33b06c989dc8c0657e4275b9f58b324f9983c4cca526f", "fetched_at": "2026-08-29T10:33:27.449449+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/changelog/53.0.0.html"}, {"content_hash": "2051e77995c0d828545df5e46858173e7796f36b8ea43d61268b612dcff7d461", "fetched_at": "2026-08-29T10:33:27.452218+00:00", "kind": "site_page", "missing": false, "url": "https://datafusion.apache.org/ballista/changelog/52.0.0.html"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 99, "longevity": 100, "rhythm": 96}, "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": 1567, "days_push": 7, "days_rel": 24, "gap_med": 0.0, "n_releases_24m": 13}, "score": 98, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}