{"adoption": {"forks": 29348, "observed_at": "2026-08-28T04:12:09.166108+00:00", "stars": 43882}, "canonical_url": "https://ross.abutalabs.com/products/spark", "card": {"archived": false, "artifact_type": "framework", "description": "Apache Spark - A unified analytics engine for large-scale data processing", "domain": ["big-data", "data-science", "machine-learning", "analytics", "microservices"], "enriched": true, "function": ["etl", "streaming", "machine-learning", "data-science", "search-engine"], "health_score": 80, "homepage": "https://spark.apache.org/", "language": "Scala", "license": "Apache-2.0", "license_family": "permissive", "maturity": "stable", "member_repos": ["apache/spark"], "name": "apache/spark", "platform": ["jvm", "python", "cross-platform", "cloud", "windows"], "pushed_at": "2026-08-27T00:33:15+00:00", "repo": "apache/spark", "stars": 43882, "tags": ["spark", "pyspark", "dataframes", "spark-sql", "mllib", "structured-streaming", "graphx", "distributed-computing", "apache", "scala", "sql", "data-engineering", "docker", "kubernetes", "linux", "macos"], "topics": ["python", "scala", "r", "java", "big-data", "jdbc", "sql", "spark"], "urls": [], "use_cases": ["process petabyte-scale datasets across a cluster", "run distributed SQL queries for analytics and reporting", "build ETL pipelines over batch and streaming data", "train machine learning models at scale with MLlib", "analyze large JSON, CSV, or Parquet files with DataFrames", "perform exploratory data analysis on big data", "process real-time event streams with Structured Streaming", "run graph analytics on large graphs with GraphX"], "what_it_is": "Apache Spark is a unified analytics engine for large-scale data processing, providing high-level APIs in Scala, Java, Python, and R over an optimized distributed execution engine. It bundles higher-level tools including Spark SQL and DataFrames, a pandas API, MLlib for machine learning, GraphX for graph processing, and Structured Streaming for real-time stream processing.", "when_to_avoid": ["your datasets fit comfortably in memory on one machine - pandas or DuckDB are simpler", "you need low-latency per-event stream processing rather than micro-batch", "you want lightweight ad-hoc analytics without cluster infrastructure overhead", "you need a small-footprint embedded database rather than a distributed engine"], "when_to_choose": ["you need to process data too large for a single machine", "you want one engine for batch, streaming, SQL, and ML workloads", "you need a mature, battle-tested big data framework with a large ecosystem", "your team works in Python, Scala, Java, or SQL and wants pandas-like or SQL interfaces", "you need to query data in HDFS, S3, Hive, Cassandra, or JDBC databases"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/spark", "repo": "apache/spark", "role": "main", "score": 77}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:12:09.166108+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T16:22:16.377639+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "70f6be2e8ea1c97059a6cd739d6b5c293223ecde078e7c5169eabaa49263d839", "fetched_at": "2026-08-28T04:12:09.166108+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apache/spark"}, {"content_hash": "a291a9d9a45259f24fe179935d2c7e66246a015e65938349ed55c762f35fdcde", "fetched_at": "2026-08-29T07:46:06.703555+00:00", "kind": "homepage", "missing": false, "url": "https://spark.apache.org/"}, {"content_hash": "07bd3c2857f40b9c05064f005155e893c88013ac17cf6877dc73287a8d594365", "fetched_at": "2026-08-29T07:46:06.712911+00:00", "kind": "site_page", "missing": false, "url": "https://spark.apache.org/docs/latest"}, {"content_hash": "731c16e1c2dfa2196421f6392a310ba228c7c06572b4a8e470e2ef7f354cde21", "fetched_at": "2026-08-29T07:46:06.715172+00:00", "kind": "site_page", "missing": false, "url": "https://spark.apache.org/documentation.html"}, {"content_hash": "e471ff56458498ee0a53b7360a58b777c3ff006a5c42d5c9139c0fa89a796823", "fetched_at": "2026-08-29T07:46:06.719573+00:00", "kind": "site_page", "missing": false, "url": "https://spark.apache.org/docs/latest/quick-start.html"}, {"content_hash": "ad4596579581b3d2cd59b01e1a20dd86874b7537f56d94ae87b573a9ab3d7b18", "fetched_at": "2026-08-29T07:46:06.722015+00:00", "kind": "site_page", "missing": false, "url": "https://spark.apache.org/docs/latest/sql-performance-tuning.html"}, {"content_hash": "647aec5b39fa8cf1f3f071b52a459efa8b5083b9359ef4bea4f7cf10d133a057", "fetched_at": "2026-08-29T07:46:06.724560+00:00", "kind": "site_page", "missing": false, "url": "https://spark.apache.org/docs/latest/sql-ref-ansi-compliance.html"}, {"content_hash": "dde447752a9437a5f61740b592a52aa55681e3f9d479038c3fa00f04b19feda1", "fetched_at": "2026-08-29T07:46:06.727458+00:00", "kind": "site_page", "missing": false, "url": "https://spark.apache.org/docs/latest/sql-data-sources-json.html"}, {"content_hash": "707d496b95982233c9c507acedaaf90956e3bba663b813f7f3abcfb93889bb06", "fetched_at": "2026-08-29T07:46:06.717494+00:00", "kind": "site_page", "missing": false, "url": "https://spark.apache.org/faq.html"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:12:09.166108+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T16:22:16.377639+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "70f6be2e8ea1c97059a6cd739d6b5c293223ecde078e7c5169eabaa49263d839", "fetched_at": "2026-08-28T04:12:09.166108+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apache/spark"}, {"content_hash": "a291a9d9a45259f24fe179935d2c7e66246a015e65938349ed55c762f35fdcde", "fetched_at": "2026-08-29T07:46:06.703555+00:00", "kind": "homepage", "missing": false, "url": "https://spark.apache.org/"}, {"content_hash": "07bd3c2857f40b9c05064f005155e893c88013ac17cf6877dc73287a8d594365", "fetched_at": "2026-08-29T07:46:06.712911+00:00", "kind": "site_page", "missing": false, "url": "https://spark.apache.org/docs/latest"}, {"content_hash": "731c16e1c2dfa2196421f6392a310ba228c7c06572b4a8e470e2ef7f354cde21", "fetched_at": "2026-08-29T07:46:06.715172+00:00", "kind": "site_page", "missing": false, "url": "https://spark.apache.org/documentation.html"}, {"content_hash": "e471ff56458498ee0a53b7360a58b777c3ff006a5c42d5c9139c0fa89a796823", "fetched_at": "2026-08-29T07:46:06.719573+00:00", "kind": "site_page", "missing": false, "url": "https://spark.apache.org/docs/latest/quick-start.html"}, {"content_hash": "ad4596579581b3d2cd59b01e1a20dd86874b7537f56d94ae87b573a9ab3d7b18", "fetched_at": "2026-08-29T07:46:06.722015+00:00", "kind": "site_page", "missing": false, "url": "https://spark.apache.org/docs/latest/sql-performance-tuning.html"}, {"content_hash": "647aec5b39fa8cf1f3f071b52a459efa8b5083b9359ef4bea4f7cf10d133a057", "fetched_at": "2026-08-29T07:46:06.724560+00:00", "kind": "site_page", "missing": false, "url": "https://spark.apache.org/docs/latest/sql-ref-ansi-compliance.html"}, {"content_hash": "dde447752a9437a5f61740b592a52aa55681e3f9d479038c3fa00f04b19feda1", "fetched_at": "2026-08-29T07:46:06.727458+00:00", "kind": "site_page", "missing": false, "url": "https://spark.apache.org/docs/latest/sql-data-sources-json.html"}, {"content_hash": "707d496b95982233c9c507acedaaf90956e3bba663b813f7f3abcfb93889bb06", "fetched_at": "2026-08-29T07:46:06.717494+00:00", "kind": "site_page", "missing": false, "url": "https://spark.apache.org/faq.html"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T16:22:16.377639+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "70f6be2e8ea1c97059a6cd739d6b5c293223ecde078e7c5169eabaa49263d839", "fetched_at": "2026-08-28T04:12:09.166108+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apache/spark"}, {"content_hash": "a291a9d9a45259f24fe179935d2c7e66246a015e65938349ed55c762f35fdcde", "fetched_at": "2026-08-29T07:46:06.703555+00:00", "kind": "homepage", "missing": false, "url": "https://spark.apache.org/"}, {"content_hash": "07bd3c2857f40b9c05064f005155e893c88013ac17cf6877dc73287a8d594365", "fetched_at": "2026-08-29T07:46:06.712911+00:00", "kind": "site_page", "missing": false, "url": "https://spark.apache.org/docs/latest"}, {"content_hash": "731c16e1c2dfa2196421f6392a310ba228c7c06572b4a8e470e2ef7f354cde21", "fetched_at": "2026-08-29T07:46:06.715172+00:00", "kind": "site_page", "missing": false, "url": "https://spark.apache.org/documentation.html"}, {"content_hash": "e471ff56458498ee0a53b7360a58b777c3ff006a5c42d5c9139c0fa89a796823", "fetched_at": "2026-08-29T07:46:06.719573+00:00", "kind": "site_page", "missing": false, "url": "https://spark.apache.org/docs/latest/quick-start.html"}, {"content_hash": "ad4596579581b3d2cd59b01e1a20dd86874b7537f56d94ae87b573a9ab3d7b18", "fetched_at": "2026-08-29T07:46:06.722015+00:00", "kind": "site_page", "missing": false, "url": "https://spark.apache.org/docs/latest/sql-performance-tuning.html"}, {"content_hash": "647aec5b39fa8cf1f3f071b52a459efa8b5083b9359ef4bea4f7cf10d133a057", "fetched_at": "2026-08-29T07:46:06.724560+00:00", "kind": "site_page", "missing": false, "url": "https://spark.apache.org/docs/latest/sql-ref-ansi-compliance.html"}, {"content_hash": "dde447752a9437a5f61740b592a52aa55681e3f9d479038c3fa00f04b19feda1", "fetched_at": "2026-08-29T07:46:06.727458+00:00", "kind": "site_page", "missing": false, "url": "https://spark.apache.org/docs/latest/sql-data-sources-json.html"}, {"content_hash": "707d496b95982233c9c507acedaaf90956e3bba663b813f7f3abcfb93889bb06", "fetched_at": "2026-08-29T07:46:06.717494+00:00", "kind": "site_page", "missing": false, "url": "https://spark.apache.org/faq.html"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:12:09.166108+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:12:09.166108+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:12:09.166108+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T16:22:16.377639+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "70f6be2e8ea1c97059a6cd739d6b5c293223ecde078e7c5169eabaa49263d839", "fetched_at": "2026-08-28T04:12:09.166108+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apache/spark"}, {"content_hash": "a291a9d9a45259f24fe179935d2c7e66246a015e65938349ed55c762f35fdcde", "fetched_at": "2026-08-29T07:46:06.703555+00:00", "kind": "homepage", "missing": false, "url": "https://spark.apache.org/"}, {"content_hash": "07bd3c2857f40b9c05064f005155e893c88013ac17cf6877dc73287a8d594365", "fetched_at": "2026-08-29T07:46:06.712911+00:00", "kind": "site_page", "missing": false, "url": "https://spark.apache.org/docs/latest"}, {"content_hash": "731c16e1c2dfa2196421f6392a310ba228c7c06572b4a8e470e2ef7f354cde21", "fetched_at": "2026-08-29T07:46:06.715172+00:00", "kind": "site_page", "missing": false, "url": "https://spark.apache.org/documentation.html"}, {"content_hash": "e471ff56458498ee0a53b7360a58b777c3ff006a5c42d5c9139c0fa89a796823", "fetched_at": "2026-08-29T07:46:06.719573+00:00", "kind": "site_page", "missing": false, "url": "https://spark.apache.org/docs/latest/quick-start.html"}, {"content_hash": "ad4596579581b3d2cd59b01e1a20dd86874b7537f56d94ae87b573a9ab3d7b18", "fetched_at": "2026-08-29T07:46:06.722015+00:00", "kind": "site_page", "missing": false, "url": "https://spark.apache.org/docs/latest/sql-performance-tuning.html"}, {"content_hash": "647aec5b39fa8cf1f3f071b52a459efa8b5083b9359ef4bea4f7cf10d133a057", "fetched_at": "2026-08-29T07:46:06.724560+00:00", "kind": "site_page", "missing": false, "url": "https://spark.apache.org/docs/latest/sql-ref-ansi-compliance.html"}, {"content_hash": "dde447752a9437a5f61740b592a52aa55681e3f9d479038c3fa00f04b19feda1", "fetched_at": "2026-08-29T07:46:06.727458+00:00", "kind": "site_page", "missing": false, "url": "https://spark.apache.org/docs/latest/sql-data-sources-json.html"}, {"content_hash": "707d496b95982233c9c507acedaaf90956e3bba663b813f7f3abcfb93889bb06", "fetched_at": "2026-08-29T07:46:06.717494+00:00", "kind": "site_page", "missing": false, "url": "https://spark.apache.org/faq.html"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:12:09.166108+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:12:09.166108+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T16:22:16.377639+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "70f6be2e8ea1c97059a6cd739d6b5c293223ecde078e7c5169eabaa49263d839", "fetched_at": "2026-08-28T04:12:09.166108+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apache/spark"}, {"content_hash": "a291a9d9a45259f24fe179935d2c7e66246a015e65938349ed55c762f35fdcde", "fetched_at": "2026-08-29T07:46:06.703555+00:00", "kind": "homepage", "missing": false, "url": "https://spark.apache.org/"}, {"content_hash": "07bd3c2857f40b9c05064f005155e893c88013ac17cf6877dc73287a8d594365", "fetched_at": "2026-08-29T07:46:06.712911+00:00", "kind": "site_page", "missing": false, "url": "https://spark.apache.org/docs/latest"}, {"content_hash": "731c16e1c2dfa2196421f6392a310ba228c7c06572b4a8e470e2ef7f354cde21", "fetched_at": "2026-08-29T07:46:06.715172+00:00", "kind": "site_page", "missing": false, "url": "https://spark.apache.org/documentation.html"}, {"content_hash": "e471ff56458498ee0a53b7360a58b777c3ff006a5c42d5c9139c0fa89a796823", "fetched_at": "2026-08-29T07:46:06.719573+00:00", "kind": "site_page", "missing": false, "url": "https://spark.apache.org/docs/latest/quick-start.html"}, {"content_hash": "ad4596579581b3d2cd59b01e1a20dd86874b7537f56d94ae87b573a9ab3d7b18", "fetched_at": "2026-08-29T07:46:06.722015+00:00", "kind": "site_page", "missing": false, "url": "https://spark.apache.org/docs/latest/sql-performance-tuning.html"}, {"content_hash": "647aec5b39fa8cf1f3f071b52a459efa8b5083b9359ef4bea4f7cf10d133a057", "fetched_at": "2026-08-29T07:46:06.724560+00:00", "kind": "site_page", "missing": false, "url": "https://spark.apache.org/docs/latest/sql-ref-ansi-compliance.html"}, {"content_hash": "dde447752a9437a5f61740b592a52aa55681e3f9d479038c3fa00f04b19feda1", "fetched_at": "2026-08-29T07:46:06.727458+00:00", "kind": "site_page", "missing": false, "url": "https://spark.apache.org/docs/latest/sql-data-sources-json.html"}, {"content_hash": "707d496b95982233c9c507acedaaf90956e3bba663b813f7f3abcfb93889bb06", "fetched_at": "2026-08-29T07:46:06.717494+00:00", "kind": "site_page", "missing": false, "url": "https://spark.apache.org/faq.html"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:12:09.166108+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:12:09.166108+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:12:09.166108+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T16:22:16.377639+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "70f6be2e8ea1c97059a6cd739d6b5c293223ecde078e7c5169eabaa49263d839", "fetched_at": "2026-08-28T04:12:09.166108+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apache/spark"}, {"content_hash": "a291a9d9a45259f24fe179935d2c7e66246a015e65938349ed55c762f35fdcde", "fetched_at": "2026-08-29T07:46:06.703555+00:00", "kind": "homepage", "missing": false, "url": "https://spark.apache.org/"}, {"content_hash": "07bd3c2857f40b9c05064f005155e893c88013ac17cf6877dc73287a8d594365", "fetched_at": "2026-08-29T07:46:06.712911+00:00", "kind": "site_page", "missing": false, "url": "https://spark.apache.org/docs/latest"}, {"content_hash": "731c16e1c2dfa2196421f6392a310ba228c7c06572b4a8e470e2ef7f354cde21", "fetched_at": "2026-08-29T07:46:06.715172+00:00", "kind": "site_page", "missing": false, "url": "https://spark.apache.org/documentation.html"}, {"content_hash": "e471ff56458498ee0a53b7360a58b777c3ff006a5c42d5c9139c0fa89a796823", "fetched_at": "2026-08-29T07:46:06.719573+00:00", "kind": "site_page", "missing": false, "url": "https://spark.apache.org/docs/latest/quick-start.html"}, {"content_hash": "ad4596579581b3d2cd59b01e1a20dd86874b7537f56d94ae87b573a9ab3d7b18", "fetched_at": "2026-08-29T07:46:06.722015+00:00", "kind": "site_page", "missing": false, "url": "https://spark.apache.org/docs/latest/sql-performance-tuning.html"}, {"content_hash": "647aec5b39fa8cf1f3f071b52a459efa8b5083b9359ef4bea4f7cf10d133a057", "fetched_at": "2026-08-29T07:46:06.724560+00:00", "kind": "site_page", "missing": false, "url": "https://spark.apache.org/docs/latest/sql-ref-ansi-compliance.html"}, {"content_hash": "dde447752a9437a5f61740b592a52aa55681e3f9d479038c3fa00f04b19feda1", "fetched_at": "2026-08-29T07:46:06.727458+00:00", "kind": "site_page", "missing": false, "url": "https://spark.apache.org/docs/latest/sql-data-sources-json.html"}, {"content_hash": "707d496b95982233c9c507acedaaf90956e3bba663b813f7f3abcfb93889bb06", "fetched_at": "2026-08-29T07:46:06.717494+00:00", "kind": "site_page", "missing": false, "url": "https://spark.apache.org/faq.html"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:12:09.166108+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:12:09.166108+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T16:22:16.377639+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "70f6be2e8ea1c97059a6cd739d6b5c293223ecde078e7c5169eabaa49263d839", "fetched_at": "2026-08-28T04:12:09.166108+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apache/spark"}, {"content_hash": "a291a9d9a45259f24fe179935d2c7e66246a015e65938349ed55c762f35fdcde", "fetched_at": "2026-08-29T07:46:06.703555+00:00", "kind": "homepage", "missing": false, "url": "https://spark.apache.org/"}, {"content_hash": "07bd3c2857f40b9c05064f005155e893c88013ac17cf6877dc73287a8d594365", "fetched_at": "2026-08-29T07:46:06.712911+00:00", "kind": "site_page", "missing": false, "url": "https://spark.apache.org/docs/latest"}, {"content_hash": "731c16e1c2dfa2196421f6392a310ba228c7c06572b4a8e470e2ef7f354cde21", "fetched_at": "2026-08-29T07:46:06.715172+00:00", "kind": "site_page", "missing": false, "url": "https://spark.apache.org/documentation.html"}, {"content_hash": "e471ff56458498ee0a53b7360a58b777c3ff006a5c42d5c9139c0fa89a796823", "fetched_at": "2026-08-29T07:46:06.719573+00:00", "kind": "site_page", "missing": false, "url": "https://spark.apache.org/docs/latest/quick-start.html"}, {"content_hash": "ad4596579581b3d2cd59b01e1a20dd86874b7537f56d94ae87b573a9ab3d7b18", "fetched_at": "2026-08-29T07:46:06.722015+00:00", "kind": "site_page", "missing": false, "url": "https://spark.apache.org/docs/latest/sql-performance-tuning.html"}, {"content_hash": "647aec5b39fa8cf1f3f071b52a459efa8b5083b9359ef4bea4f7cf10d133a057", "fetched_at": "2026-08-29T07:46:06.724560+00:00", "kind": "site_page", "missing": false, "url": "https://spark.apache.org/docs/latest/sql-ref-ansi-compliance.html"}, {"content_hash": "dde447752a9437a5f61740b592a52aa55681e3f9d479038c3fa00f04b19feda1", "fetched_at": "2026-08-29T07:46:06.727458+00:00", "kind": "site_page", "missing": false, "url": "https://spark.apache.org/docs/latest/sql-data-sources-json.html"}, {"content_hash": "707d496b95982233c9c507acedaaf90956e3bba663b813f7f3abcfb93889bb06", "fetched_at": "2026-08-29T07:46:06.717494+00:00", "kind": "site_page", "missing": false, "url": "https://spark.apache.org/faq.html"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T16:22:16.377639+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "70f6be2e8ea1c97059a6cd739d6b5c293223ecde078e7c5169eabaa49263d839", "fetched_at": "2026-08-28T04:12:09.166108+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apache/spark"}, {"content_hash": "a291a9d9a45259f24fe179935d2c7e66246a015e65938349ed55c762f35fdcde", "fetched_at": "2026-08-29T07:46:06.703555+00:00", "kind": "homepage", "missing": false, "url": "https://spark.apache.org/"}, {"content_hash": "07bd3c2857f40b9c05064f005155e893c88013ac17cf6877dc73287a8d594365", "fetched_at": "2026-08-29T07:46:06.712911+00:00", "kind": "site_page", "missing": false, "url": "https://spark.apache.org/docs/latest"}, {"content_hash": "731c16e1c2dfa2196421f6392a310ba228c7c06572b4a8e470e2ef7f354cde21", "fetched_at": "2026-08-29T07:46:06.715172+00:00", "kind": "site_page", "missing": false, "url": "https://spark.apache.org/documentation.html"}, {"content_hash": "e471ff56458498ee0a53b7360a58b777c3ff006a5c42d5c9139c0fa89a796823", "fetched_at": "2026-08-29T07:46:06.719573+00:00", "kind": "site_page", "missing": false, "url": "https://spark.apache.org/docs/latest/quick-start.html"}, {"content_hash": "ad4596579581b3d2cd59b01e1a20dd86874b7537f56d94ae87b573a9ab3d7b18", "fetched_at": "2026-08-29T07:46:06.722015+00:00", "kind": "site_page", "missing": false, "url": "https://spark.apache.org/docs/latest/sql-performance-tuning.html"}, {"content_hash": "647aec5b39fa8cf1f3f071b52a459efa8b5083b9359ef4bea4f7cf10d133a057", "fetched_at": "2026-08-29T07:46:06.724560+00:00", "kind": "site_page", "missing": false, "url": "https://spark.apache.org/docs/latest/sql-ref-ansi-compliance.html"}, {"content_hash": "dde447752a9437a5f61740b592a52aa55681e3f9d479038c3fa00f04b19feda1", "fetched_at": "2026-08-29T07:46:06.727458+00:00", "kind": "site_page", "missing": false, "url": "https://spark.apache.org/docs/latest/sql-data-sources-json.html"}, {"content_hash": "707d496b95982233c9c507acedaaf90956e3bba663b813f7f3abcfb93889bb06", "fetched_at": "2026-08-29T07:46:06.717494+00:00", "kind": "site_page", "missing": false, "url": "https://spark.apache.org/faq.html"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T16:22:16.377639+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "70f6be2e8ea1c97059a6cd739d6b5c293223ecde078e7c5169eabaa49263d839", "fetched_at": "2026-08-28T04:12:09.166108+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apache/spark"}, {"content_hash": "a291a9d9a45259f24fe179935d2c7e66246a015e65938349ed55c762f35fdcde", "fetched_at": "2026-08-29T07:46:06.703555+00:00", "kind": "homepage", "missing": false, "url": "https://spark.apache.org/"}, {"content_hash": "07bd3c2857f40b9c05064f005155e893c88013ac17cf6877dc73287a8d594365", "fetched_at": "2026-08-29T07:46:06.712911+00:00", "kind": "site_page", "missing": false, "url": "https://spark.apache.org/docs/latest"}, {"content_hash": "731c16e1c2dfa2196421f6392a310ba228c7c06572b4a8e470e2ef7f354cde21", "fetched_at": "2026-08-29T07:46:06.715172+00:00", "kind": "site_page", "missing": false, "url": "https://spark.apache.org/documentation.html"}, {"content_hash": "e471ff56458498ee0a53b7360a58b777c3ff006a5c42d5c9139c0fa89a796823", "fetched_at": "2026-08-29T07:46:06.719573+00:00", "kind": "site_page", "missing": false, "url": "https://spark.apache.org/docs/latest/quick-start.html"}, {"content_hash": "ad4596579581b3d2cd59b01e1a20dd86874b7537f56d94ae87b573a9ab3d7b18", "fetched_at": "2026-08-29T07:46:06.722015+00:00", "kind": "site_page", "missing": false, "url": "https://spark.apache.org/docs/latest/sql-performance-tuning.html"}, {"content_hash": "647aec5b39fa8cf1f3f071b52a459efa8b5083b9359ef4bea4f7cf10d133a057", "fetched_at": "2026-08-29T07:46:06.724560+00:00", "kind": "site_page", "missing": false, "url": "https://spark.apache.org/docs/latest/sql-ref-ansi-compliance.html"}, {"content_hash": "dde447752a9437a5f61740b592a52aa55681e3f9d479038c3fa00f04b19feda1", "fetched_at": "2026-08-29T07:46:06.727458+00:00", "kind": "site_page", "missing": false, "url": "https://spark.apache.org/docs/latest/sql-data-sources-json.html"}, {"content_hash": "707d496b95982233c9c507acedaaf90956e3bba663b813f7f3abcfb93889bb06", "fetched_at": "2026-08-29T07:46:06.717494+00:00", "kind": "site_page", "missing": false, "url": "https://spark.apache.org/faq.html"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T16:22:16.377639+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "70f6be2e8ea1c97059a6cd739d6b5c293223ecde078e7c5169eabaa49263d839", "fetched_at": "2026-08-28T04:12:09.166108+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apache/spark"}, {"content_hash": "a291a9d9a45259f24fe179935d2c7e66246a015e65938349ed55c762f35fdcde", "fetched_at": "2026-08-29T07:46:06.703555+00:00", "kind": "homepage", "missing": false, "url": "https://spark.apache.org/"}, {"content_hash": "07bd3c2857f40b9c05064f005155e893c88013ac17cf6877dc73287a8d594365", "fetched_at": "2026-08-29T07:46:06.712911+00:00", "kind": "site_page", "missing": false, "url": "https://spark.apache.org/docs/latest"}, {"content_hash": "731c16e1c2dfa2196421f6392a310ba228c7c06572b4a8e470e2ef7f354cde21", "fetched_at": "2026-08-29T07:46:06.715172+00:00", "kind": "site_page", "missing": false, "url": "https://spark.apache.org/documentation.html"}, {"content_hash": "e471ff56458498ee0a53b7360a58b777c3ff006a5c42d5c9139c0fa89a796823", "fetched_at": "2026-08-29T07:46:06.719573+00:00", "kind": "site_page", "missing": false, "url": "https://spark.apache.org/docs/latest/quick-start.html"}, {"content_hash": "ad4596579581b3d2cd59b01e1a20dd86874b7537f56d94ae87b573a9ab3d7b18", "fetched_at": "2026-08-29T07:46:06.722015+00:00", "kind": "site_page", "missing": false, "url": "https://spark.apache.org/docs/latest/sql-performance-tuning.html"}, {"content_hash": "647aec5b39fa8cf1f3f071b52a459efa8b5083b9359ef4bea4f7cf10d133a057", "fetched_at": "2026-08-29T07:46:06.724560+00:00", "kind": "site_page", "missing": false, "url": "https://spark.apache.org/docs/latest/sql-ref-ansi-compliance.html"}, {"content_hash": "dde447752a9437a5f61740b592a52aa55681e3f9d479038c3fa00f04b19feda1", "fetched_at": "2026-08-29T07:46:06.727458+00:00", "kind": "site_page", "missing": false, "url": "https://spark.apache.org/docs/latest/sql-data-sources-json.html"}, {"content_hash": "707d496b95982233c9c507acedaaf90956e3bba663b813f7f3abcfb93889bb06", "fetched_at": "2026-08-29T07:46:06.717494+00:00", "kind": "site_page", "missing": false, "url": "https://spark.apache.org/faq.html"}], "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": 4572, "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}}