{"adoption": {"forks": 1111, "observed_at": "2026-08-28T04:04:19.935400+00:00", "stars": 1310}, "canonical_url": "https://ross.abutalabs.com/products/dataflowtemplates", "card": {"archived": false, "artifact_type": "framework", "description": "Cloud Dataflow Google-provided templates for solving in-Cloud data tasks", "domain": ["big-data", "cloud-computing", "databases", "analytics"], "enriched": true, "function": ["etl", "streaming", "data-science", "workflow-automation"], "health_score": 100, "homepage": "https://cloud.google.com/dataflow/docs/guides/templates/provided-templates", "language": "Java", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["GoogleCloudPlatform/DataflowTemplates"], "name": "GoogleCloudPlatform/DataflowTemplates", "platform": ["cloud", "jvm"], "pushed_at": "2026-08-26T15:41:15+00:00", "repo": "GoogleCloudPlatform/DataflowTemplates", "stars": 1310, "tags": ["google-cloud-dataflow", "apache-beam", "pipeline-templates", "bigquery", "bigtable", "cloud-spanner", "gcp", "batch-processing", "change-data-capture", "data-engineering", "docker"], "topics": ["apache-beam", "dataflow-templates", "google-cloud-dataflow", "google-cloud-storage", "google-cloud-spanner", "bigquery", "bigtable"], "urls": [], "use_cases": ["stream data from Kafka or Pub/Sub into BigQuery", "run change data capture from MySQL to BigQuery", "migrate data from Datastream into Spanner or BigQuery", "export BigQuery tables to Cloud Storage", "bulk copy or backup data between Google Cloud databases", "mask or tokenize data with Cloud DLP while loading into BigQuery", "process MongoDB or JMS data streams without writing pipeline code"], "what_it_is": "A collection of Google-provided Apache Beam pipeline templates for Google Cloud Dataflow that solve common in-cloud data tasks like import/export, backup/restore, and bulk API operations without writing pipeline code. The templates are open source Java pipelines that can be run as-is or customized and extended by developers.", "when_to_avoid": ["your data workloads run outside Google Cloud", "you need highly custom transformation logic that doesn't fit any template", "you prefer lightweight local ETL tools rather than managed cloud dataflow jobs"], "when_to_choose": ["you need prebuilt, production-ready pipelines for common GCP data movement tasks", "you want to run batch or streaming ETL on Dataflow without a development environment", "you need a customizable starting point for Apache Beam pipelines on Google Cloud"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/dataflowtemplates", "repo": "GoogleCloudPlatform/DataflowTemplates", "role": "main", "score": 95}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:04:19.935400+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T04:49:53.257060+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ec414145bfb604297e70393ad96a2b8f5ef32d98579b7336187c6152b72eae2b", "fetched_at": "2026-08-28T04:04:19.935400+00:00", "kind": "readme", "missing": false, "url": "https://github.com/GoogleCloudPlatform/DataflowTemplates"}, {"content_hash": "0f2472d7a113c33e3187088ddd09afe3a4affd6d1de2e6d11b377aba27bf65c4", "fetched_at": "2026-08-29T12:07:51.063283+00:00", "kind": "homepage", "missing": false, "url": "https://cloud.google.com/dataflow/docs/guides/templates/provided-templates"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:04:19.935400+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T04:49:53.257060+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ec414145bfb604297e70393ad96a2b8f5ef32d98579b7336187c6152b72eae2b", "fetched_at": "2026-08-28T04:04:19.935400+00:00", "kind": "readme", "missing": false, "url": "https://github.com/GoogleCloudPlatform/DataflowTemplates"}, {"content_hash": "0f2472d7a113c33e3187088ddd09afe3a4affd6d1de2e6d11b377aba27bf65c4", "fetched_at": "2026-08-29T12:07:51.063283+00:00", "kind": "homepage", "missing": false, "url": "https://cloud.google.com/dataflow/docs/guides/templates/provided-templates"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T04:49:53.257060+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ec414145bfb604297e70393ad96a2b8f5ef32d98579b7336187c6152b72eae2b", "fetched_at": "2026-08-28T04:04:19.935400+00:00", "kind": "readme", "missing": false, "url": "https://github.com/GoogleCloudPlatform/DataflowTemplates"}, {"content_hash": "0f2472d7a113c33e3187088ddd09afe3a4affd6d1de2e6d11b377aba27bf65c4", "fetched_at": "2026-08-29T12:07:51.063283+00:00", "kind": "homepage", "missing": false, "url": "https://cloud.google.com/dataflow/docs/guides/templates/provided-templates"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:04:19.935400+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:04:19.935400+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:04:19.935400+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T04:49:53.257060+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ec414145bfb604297e70393ad96a2b8f5ef32d98579b7336187c6152b72eae2b", "fetched_at": "2026-08-28T04:04:19.935400+00:00", "kind": "readme", "missing": false, "url": "https://github.com/GoogleCloudPlatform/DataflowTemplates"}, {"content_hash": "0f2472d7a113c33e3187088ddd09afe3a4affd6d1de2e6d11b377aba27bf65c4", "fetched_at": "2026-08-29T12:07:51.063283+00:00", "kind": "homepage", "missing": false, "url": "https://cloud.google.com/dataflow/docs/guides/templates/provided-templates"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:04:19.935400+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:04:19.935400+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T04:49:53.257060+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ec414145bfb604297e70393ad96a2b8f5ef32d98579b7336187c6152b72eae2b", "fetched_at": "2026-08-28T04:04:19.935400+00:00", "kind": "readme", "missing": false, "url": "https://github.com/GoogleCloudPlatform/DataflowTemplates"}, {"content_hash": "0f2472d7a113c33e3187088ddd09afe3a4affd6d1de2e6d11b377aba27bf65c4", "fetched_at": "2026-08-29T12:07:51.063283+00:00", "kind": "homepage", "missing": false, "url": "https://cloud.google.com/dataflow/docs/guides/templates/provided-templates"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:04:19.935400+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:04:19.935400+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:04:19.935400+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T04:49:53.257060+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ec414145bfb604297e70393ad96a2b8f5ef32d98579b7336187c6152b72eae2b", "fetched_at": "2026-08-28T04:04:19.935400+00:00", "kind": "readme", "missing": false, "url": "https://github.com/GoogleCloudPlatform/DataflowTemplates"}, {"content_hash": "0f2472d7a113c33e3187088ddd09afe3a4affd6d1de2e6d11b377aba27bf65c4", "fetched_at": "2026-08-29T12:07:51.063283+00:00", "kind": "homepage", "missing": false, "url": "https://cloud.google.com/dataflow/docs/guides/templates/provided-templates"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:04:19.935400+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:04:19.935400+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T04:49:53.257060+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ec414145bfb604297e70393ad96a2b8f5ef32d98579b7336187c6152b72eae2b", "fetched_at": "2026-08-28T04:04:19.935400+00:00", "kind": "readme", "missing": false, "url": "https://github.com/GoogleCloudPlatform/DataflowTemplates"}, {"content_hash": "0f2472d7a113c33e3187088ddd09afe3a4affd6d1de2e6d11b377aba27bf65c4", "fetched_at": "2026-08-29T12:07:51.063283+00:00", "kind": "homepage", "missing": false, "url": "https://cloud.google.com/dataflow/docs/guides/templates/provided-templates"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T04:49:53.257060+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ec414145bfb604297e70393ad96a2b8f5ef32d98579b7336187c6152b72eae2b", "fetched_at": "2026-08-28T04:04:19.935400+00:00", "kind": "readme", "missing": false, "url": "https://github.com/GoogleCloudPlatform/DataflowTemplates"}, {"content_hash": "0f2472d7a113c33e3187088ddd09afe3a4affd6d1de2e6d11b377aba27bf65c4", "fetched_at": "2026-08-29T12:07:51.063283+00:00", "kind": "homepage", "missing": false, "url": "https://cloud.google.com/dataflow/docs/guides/templates/provided-templates"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T04:49:53.257060+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ec414145bfb604297e70393ad96a2b8f5ef32d98579b7336187c6152b72eae2b", "fetched_at": "2026-08-28T04:04:19.935400+00:00", "kind": "readme", "missing": false, "url": "https://github.com/GoogleCloudPlatform/DataflowTemplates"}, {"content_hash": "0f2472d7a113c33e3187088ddd09afe3a4affd6d1de2e6d11b377aba27bf65c4", "fetched_at": "2026-08-29T12:07:51.063283+00:00", "kind": "homepage", "missing": false, "url": "https://cloud.google.com/dataflow/docs/guides/templates/provided-templates"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T04:49:53.257060+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ec414145bfb604297e70393ad96a2b8f5ef32d98579b7336187c6152b72eae2b", "fetched_at": "2026-08-28T04:04:19.935400+00:00", "kind": "readme", "missing": false, "url": "https://github.com/GoogleCloudPlatform/DataflowTemplates"}, {"content_hash": "0f2472d7a113c33e3187088ddd09afe3a4affd6d1de2e6d11b377aba27bf65c4", "fetched_at": "2026-08-29T12:07:51.063283+00:00", "kind": "homepage", "missing": false, "url": "https://cloud.google.com/dataflow/docs/guides/templates/provided-templates"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 99, "longevity": 100, "rhythm": 87}, "computed_at": "2026-09-03T02:39:23.370411+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 3127, "days_push": 7, "days_rel": 7, "gap_med": 6, "n_releases_24m": 100}, "score": 95, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}