diff --git a/.gitignore b/.gitignore index 858f560f0b842..b6edbccf71125 100644 --- a/.gitignore +++ b/.gitignore @@ -69,6 +69,7 @@ metadata-ingestion/generated/** # docs docs/generated/ +docs-website/versioned_docs/ tmp* temp/** diff --git a/README.md b/README.md index d2208cf6ced49..951dcebad6498 100644 --- a/README.md +++ b/README.md @@ -80,7 +80,11 @@ Please follow the [DataHub Quickstart Guide](https://datahubproject.io/docs/quic If you're looking to build & modify datahub please take a look at our [Development Guide](https://datahubproject.io/docs/developers). -[![DataHub Demo GIF](docs/imgs/entity.png)](https://demo.datahubproject.io/) +

+ + + +

## Source Code and Repositories diff --git a/datahub-web-react/README.md b/datahub-web-react/README.md index 6c91b169af858..8bf592b11a0ae 100644 --- a/datahub-web-react/README.md +++ b/datahub-web-react/README.md @@ -126,7 +126,9 @@ for functional configurability should reside. to render a view associated with a particular entity type (user, dataset, etc.). -![entity-registry](./entity-registry.png) +

+ +

**graphql** - The React App talks to the `dathub-frontend` server using GraphQL. This module is where the *queries* issued against the server are defined. Once defined, running `yarn run generate` will code-gen TypeScript objects to make invoking diff --git a/docker/airflow/local_airflow.md b/docker/airflow/local_airflow.md index d0a2b18cff2d2..55a64f5c122c5 100644 --- a/docker/airflow/local_airflow.md +++ b/docker/airflow/local_airflow.md @@ -138,25 +138,57 @@ Successfully added `conn_id`=datahub_rest_default : datahub_rest://:@http://data Navigate the Airflow UI to find the sample Airflow dag we just brought in -![Find the DAG](../../docs/imgs/airflow/find_the_dag.png) + +

+ +

+ By default, Airflow loads all DAG-s in paused status. Unpause the sample DAG to use it. -![Paused DAG](../../docs/imgs/airflow/paused_dag.png) -![Unpaused DAG](../../docs/imgs/airflow/unpaused_dag.png) + +

+ +

+ + +

+ +

+ Then trigger the DAG to run. -![Trigger the DAG](../../docs/imgs/airflow/trigger_dag.png) + +

+ +

+ After the DAG runs successfully, go over to your DataHub instance to see the Pipeline and navigate its lineage. -![DataHub Pipeline View](../../docs/imgs/airflow/datahub_pipeline_view.png) -![DataHub Pipeline Entity](../../docs/imgs/airflow/datahub_pipeline_entity.png) +

+ +

+ + + +

+ +

-![DataHub Task View](../../docs/imgs/airflow/datahub_task_view.png) -![DataHub Lineage View](../../docs/imgs/airflow/datahub_lineage_view.png) + +

+ +

+ + + +

+ +

+ ## TroubleShooting @@ -164,9 +196,17 @@ Most issues are related to connectivity between Airflow and DataHub. Here is how you can debug them. -![Find the Task Log](../../docs/imgs/airflow/finding_failed_log.png) -![Inspect the Log](../../docs/imgs/airflow/connection_error.png) +

+ +

+ + + +

+ +

+ In this case, clearly the connection `datahub-rest` has not been registered. Looks like we forgot to register the connection with Airflow! Let's execute Step 4 to register the datahub connection with Airflow. @@ -175,4 +215,8 @@ In case the connection was registered successfully but you are still seeing `Fai After re-running the DAG, we see success! -![Pipeline Success](../../docs/imgs/airflow/successful_run.png) + +

+ +

+ diff --git a/docs-website/build.gradle b/docs-website/build.gradle index 12f37033efc2f..851c10d9ea97f 100644 --- a/docs-website/build.gradle +++ b/docs-website/build.gradle @@ -77,7 +77,12 @@ task yarnGenerate(type: YarnTask, dependsOn: [yarnInstall, args = ['run', 'generate'] } -task yarnStart(type: YarnTask, dependsOn: [yarnInstall, yarnGenerate]) { +task downloadHistoricalVersions(type: Exec) { + workingDir '.' + commandLine 'python3', 'download_historical_versions.py' +} + +task yarnStart(type: YarnTask, dependsOn: [yarnInstall, yarnGenerate, downloadHistoricalVersions]) { args = ['run', 'start'] } task fastReload(type: YarnTask) { @@ -105,7 +110,7 @@ task serve(type: YarnTask, dependsOn: [yarnInstall] ) { } -task yarnBuild(type: YarnTask, dependsOn: [yarnLint, yarnGenerate]) { +task yarnBuild(type: YarnTask, dependsOn: [yarnLint, yarnGenerate, downloadHistoricalVersions]) { inputs.files(projectMdFiles) inputs.file("package.json").withPathSensitivity(PathSensitivity.RELATIVE) inputs.dir("src").withPathSensitivity(PathSensitivity.RELATIVE) diff --git a/docs-website/docusaurus.config.js b/docs-website/docusaurus.config.js index c10c178424b53..df69e8513fbfc 100644 --- a/docs-website/docusaurus.config.js +++ b/docs-website/docusaurus.config.js @@ -69,6 +69,11 @@ module.exports = { label: "Roadmap", position: "right", }, + { + type: 'docsVersionDropdown', + position: 'right', + dropdownActiveClassDisabled: true, + }, { href: "https://slack.datahubproject.io", "aria-label": "Slack", diff --git a/docs-website/download_historical_versions.py b/docs-website/download_historical_versions.py new file mode 100644 index 0000000000000..a005445cb1497 --- /dev/null +++ b/docs-website/download_historical_versions.py @@ -0,0 +1,60 @@ +import os +import tarfile +import urllib.request +import json + +repo_url = "https://api.github.com/repos/datahub-project/static-assets" + + +def download_file(url, destination): + with urllib.request.urlopen(url) as response: + with open(destination, "wb") as f: + while True: + chunk = response.read(8192) + if not chunk: + break + f.write(chunk) + + +def fetch_tar_urls(repo_url, folder_path): + api_url = f"{repo_url}/contents/{folder_path}" + response = urllib.request.urlopen(api_url) + data = response.read().decode('utf-8') + tar_urls = [ + file["download_url"] for file in json.loads(data) if file["name"].endswith(".tar.gz") + ] + print(tar_urls) + return tar_urls + + +def main(): + folder_path = "versioned_docs" + destination_dir = "versioned_docs" + if not os.path.exists(destination_dir): + os.makedirs(destination_dir) + + tar_urls = fetch_tar_urls(repo_url, folder_path) + + for url in tar_urls: + filename = os.path.basename(url) + destination_path = os.path.join(destination_dir, filename) + + version = '.'.join(filename.split('.')[:3]) + extracted_path = os.path.join(destination_dir, version) + print("extracted_path", extracted_path) + if os.path.exists(extracted_path): + print(f"{extracted_path} already exists, skipping downloads") + continue + try: + download_file(url, destination_path) + print(f"Downloaded {filename} to {destination_dir}") + with tarfile.open(destination_path, "r:gz") as tar: + tar.extractall() + os.remove(destination_path) + except urllib.error.URLError as e: + print(f"Error while downloading {filename}: {e}") + continue + + +if __name__ == "__main__": + main() diff --git a/docs-website/src/pages/docs/_components/SearchBar/index.jsx b/docs-website/src/pages/docs/_components/SearchBar/index.jsx index 37f8a5c252aee..054c041d8a9e5 100644 --- a/docs-website/src/pages/docs/_components/SearchBar/index.jsx +++ b/docs-website/src/pages/docs/_components/SearchBar/index.jsx @@ -303,11 +303,16 @@ function SearchBar() { strokeLinejoin="round" > - - {docsSearchVersionsHelpers.versioningEnabled && } - -
{!!searchResultState.totalResults && documentsFoundPlural(searchResultState.totalResults)}
+ {docsSearchVersionsHelpers.versioningEnabled && ( + + )} +
+ {!!searchResultState.totalResults && + documentsFoundPlural(searchResultState.totalResults)} +
{searchResultState.items.length > 0 ? (
@@ -369,4 +374,4 @@ function SearchBar() { ); } -export default SearchBar; +export default SearchBar; \ No newline at end of file diff --git a/docs-website/src/pages/docs/_components/SearchBar/search.module.scss b/docs-website/src/pages/docs/_components/SearchBar/search.module.scss index 17e5f22490664..30a2973384ba6 100644 --- a/docs-website/src/pages/docs/_components/SearchBar/search.module.scss +++ b/docs-website/src/pages/docs/_components/SearchBar/search.module.scss @@ -21,13 +21,21 @@ height: 1.5rem; } +.searchQueryInput { + padding: 0.8rem 0.8rem 0.8rem 3rem; +} + +.searchVersionInput { + padding: 0.8rem 2rem 0.8rem 2rem; + text-align: center; +} + .searchQueryInput, .searchVersionInput { border-radius: 1000em; border-style: solid; border-color: transparent; font: var(--ifm-font-size-base) var(--ifm-font-family-base); - padding: 0.8rem 0.8rem 0.8rem 3rem; width: 100%; background: var(--docsearch-searchbox-background); color: var(--docsearch-text-color); @@ -93,6 +101,7 @@ @media only screen and (max-width: 996px) { .searchVersionColumn { max-width: 40% !important; + margin: auto; } .searchResultsColumn { @@ -113,9 +122,15 @@ .searchVersionColumn { max-width: 100% !important; padding-left: var(--ifm-spacing-horizontal) !important; + margin: auto; } } +.searchVersionColumn { + margin: auto; +} + + .loadingSpinner { width: 3rem; height: 3rem; diff --git a/docs-website/versioned_sidebars/version-0.10.5-sidebars.json b/docs-website/versioned_sidebars/version-0.10.5-sidebars.json new file mode 100644 index 0000000000000..67179075fc994 --- /dev/null +++ b/docs-website/versioned_sidebars/version-0.10.5-sidebars.json @@ -0,0 +1,594 @@ +{ + "overviewSidebar": [ + { + "label": "Getting Started", + "type": "category", + "collapsed": true, + "items": [ + { + "type": "doc", + "label": "Introduction", + "id": "docs/features" + }, + { + "type": "doc", + "label": "Quickstart", + "id": "docs/quickstart" + }, + { + "type": "link", + "label": "Demo", + "href": "https://demo.datahubproject.io/" + }, + "docs/what-is-datahub/datahub-concepts", + "docs/saas" + ] + }, + { + "Integrations": [ + { + "type": "doc", + "label": "Introduction", + "id": "metadata-ingestion/README" + }, + { + "Quickstart Guides": [ + { + "BigQuery": [ + "docs/quick-ingestion-guides/bigquery/overview", + "docs/quick-ingestion-guides/bigquery/setup", + "docs/quick-ingestion-guides/bigquery/configuration" + ] + }, + { + "Redshift": [ + "docs/quick-ingestion-guides/redshift/overview", + "docs/quick-ingestion-guides/redshift/setup", + "docs/quick-ingestion-guides/redshift/configuration" + ] + }, + { + "Snowflake": [ + "docs/quick-ingestion-guides/snowflake/overview", + "docs/quick-ingestion-guides/snowflake/setup", + "docs/quick-ingestion-guides/snowflake/configuration" + ] + }, + { + "Tableau": [ + "docs/quick-ingestion-guides/tableau/overview", + "docs/quick-ingestion-guides/tableau/setup", + "docs/quick-ingestion-guides/tableau/configuration" + ] + }, + { + "PowerBI": [ + "docs/quick-ingestion-guides/powerbi/overview", + "docs/quick-ingestion-guides/powerbi/setup", + "docs/quick-ingestion-guides/powerbi/configuration" + ] + } + ] + }, + { + "Sources": [ + { + "type": "doc", + "id": "docs/lineage/airflow", + "label": "Airflow" + }, + "metadata-integration/java/spark-lineage/README", + "metadata-ingestion/integration_docs/great-expectations", + "metadata-integration/java/datahub-protobuf/README", + { + "type": "autogenerated", + "dirName": "docs/generated/ingestion/sources" + } + ] + }, + { + "Sinks": [ + { + "type": "autogenerated", + "dirName": "metadata-ingestion/sink_docs" + } + ] + }, + { + "Transformers": [ + "metadata-ingestion/docs/transformer/intro", + "metadata-ingestion/docs/transformer/dataset_transformer" + ] + }, + { + "Advanced Guides": [ + { + "Scheduling Ingestion": [ + "metadata-ingestion/schedule_docs/intro", + "metadata-ingestion/schedule_docs/cron", + "metadata-ingestion/schedule_docs/airflow", + "metadata-ingestion/schedule_docs/kubernetes" + ] + }, + "docs/platform-instances", + "metadata-ingestion/docs/dev_guides/stateful", + "metadata-ingestion/docs/dev_guides/classification", + "metadata-ingestion/docs/dev_guides/add_stateful_ingestion_to_source", + "metadata-ingestion/docs/dev_guides/sql_profiles" + ] + } + ] + }, + { + "Deployment": [ + "docs/deploy/aws", + "docs/deploy/gcp", + "docker/README", + "docs/deploy/kubernetes", + "docs/deploy/environment-vars", + { + "Authentication": [ + "docs/authentication/README", + "docs/authentication/concepts", + "docs/authentication/changing-default-credentials", + "docs/authentication/guides/add-users", + { + "Frontend Authentication": [ + "docs/authentication/guides/jaas", + { + "OIDC Authentication": [ + "docs/authentication/guides/sso/configure-oidc-react", + "docs/authentication/guides/sso/configure-oidc-react-google", + "docs/authentication/guides/sso/configure-oidc-react-okta", + "docs/authentication/guides/sso/configure-oidc-react-azure" + ] + } + ] + }, + "docs/authentication/introducing-metadata-service-authentication", + "docs/authentication/personal-access-tokens" + ] + }, + { + "Authorization": [ + "docs/authorization/README", + "docs/authorization/roles", + "docs/authorization/policies", + "docs/authorization/groups" + ] + }, + { + "Advanced Guides": [ + "docs/how/delete-metadata", + "docs/how/configuring-authorization-with-apache-ranger", + "docs/how/backup-datahub", + "docs/how/restore-indices", + "docs/advanced/db-retention", + "docs/advanced/monitoring", + "docs/how/extract-container-logs", + "docs/deploy/telemetry", + "docs/how/kafka-config", + "docs/deploy/confluent-cloud", + "docs/advanced/no-code-upgrade", + "docs/how/jattach-guide" + ] + }, + "docs/how/updating-datahub" + ] + }, + { + "API": [ + "docs/api/datahub-apis", + { + "GraphQL API": [ + { + "label": "Overview", + "type": "doc", + "id": "docs/api/graphql/overview" + }, + { + "Reference": [ + { + "type": "doc", + "label": "Queries", + "id": "graphql/queries" + }, + { + "type": "doc", + "label": "Mutations", + "id": "graphql/mutations" + }, + { + "type": "doc", + "label": "Objects", + "id": "graphql/objects" + }, + { + "type": "doc", + "label": "Inputs", + "id": "graphql/inputObjects" + }, + { + "type": "doc", + "label": "Interfaces", + "id": "graphql/interfaces" + }, + { + "type": "doc", + "label": "Unions", + "id": "graphql/unions" + }, + { + "type": "doc", + "label": "Enums", + "id": "graphql/enums" + }, + { + "type": "doc", + "label": "Scalars", + "id": "graphql/scalars" + } + ] + }, + { + "Guides": [ + { + "type": "doc", + "label": "How To Set Up GraphQL", + "id": "docs/api/graphql/how-to-set-up-graphql" + }, + { + "type": "doc", + "label": "Getting Started With GraphQL", + "id": "docs/api/graphql/getting-started" + }, + { + "type": "doc", + "label": "Access Token Management", + "id": "docs/api/graphql/token-management" + } + ] + } + ] + }, + { + "type": "doc", + "label": "OpenAPI", + "id": "docs/api/openapi/openapi-usage-guide" + }, + "docs/dev-guides/timeline", + { + "Rest.li API": [ + { + "type": "doc", + "label": "Rest.li API Guide", + "id": "docs/api/restli/restli-overview" + }, + { + "type": "doc", + "label": "Restore Indices", + "id": "docs/api/restli/restore-indices" + }, + { + "type": "doc", + "label": "Get Index Sizes", + "id": "docs/api/restli/get-index-sizes" + }, + { + "type": "doc", + "label": "Truncate Timeseries Aspect", + "id": "docs/api/restli/truncate-time-series-aspect" + }, + { + "type": "doc", + "label": "Get ElasticSearch Task Status Endpoint", + "id": "docs/api/restli/get-elastic-task-status" + }, + { + "type": "doc", + "label": "Evaluate Tests", + "id": "docs/api/restli/evaluate-tests" + }, + { + "type": "doc", + "label": "Aspect Versioning and Rest.li Modeling", + "id": "docs/advanced/aspect-versioning" + } + ] + }, + { + "Python SDK": [ + "metadata-ingestion/as-a-library", + { + "Python SDK Reference": [ + { + "type": "autogenerated", + "dirName": "python-sdk" + } + ] + } + ] + }, + "metadata-integration/java/as-a-library", + { + "API and SDK Guides": [ + "docs/advanced/patch", + "docs/api/tutorials/datasets", + "docs/api/tutorials/lineage", + "docs/api/tutorials/tags", + "docs/api/tutorials/terms", + "docs/api/tutorials/owners", + "docs/api/tutorials/domains", + "docs/api/tutorials/deprecation", + "docs/api/tutorials/descriptions", + "docs/api/tutorials/custom-properties", + "docs/api/tutorials/ml" + ] + }, + { + "type": "category", + "label": "DataHub CLI", + "link": { + "type": "doc", + "id": "docs/cli" + }, + "items": [ + "docs/datahub_lite" + ] + }, + { + "type": "category", + "label": "Datahub Actions", + "link": { + "type": "doc", + "id": "docs/act-on-metadata" + }, + "items": [ + "docs/actions/README", + "docs/actions/quickstart", + "docs/actions/concepts", + { + "Sources": [ + { + "type": "autogenerated", + "dirName": "docs/actions/sources" + } + ] + }, + { + "Events": [ + { + "type": "autogenerated", + "dirName": "docs/actions/events" + } + ] + }, + { + "Actions": [ + { + "type": "autogenerated", + "dirName": "docs/actions/actions" + } + ] + }, + { + "Guides": [ + { + "type": "autogenerated", + "dirName": "docs/actions/guides" + } + ] + } + ] + } + ] + }, + { + "Features": [ + "docs/ui-ingestion", + "docs/how/search", + "docs/schema-history", + "docs/domains", + "docs/dataproducts", + "docs/glossary/business-glossary", + "docs/tags", + "docs/ownership/ownership-types", + "docs/browse", + "docs/authorization/access-policies-guide", + "docs/features/dataset-usage-and-query-history", + "docs/posts", + "docs/sync-status", + "docs/lineage/lineage-feature-guide", + { + "type": "doc", + "id": "docs/tests/metadata-tests", + "className": "saasOnly" + }, + "docs/act-on-metadata/impact-analysis", + { + "Observability": [ + "docs/managed-datahub/observe/freshness-assertions" + ] + } + ] + }, + { + "Develop": [ + { + "DataHub Metadata Model": [ + "docs/modeling/metadata-model", + "docs/modeling/extending-the-metadata-model", + "docs/what/mxe", + { + "Entities": [ + { + "type": "autogenerated", + "dirName": "docs/generated/metamodel/entities" + } + ] + } + ] + }, + { + "Architecture": [ + "docs/architecture/architecture", + "docs/components", + "docs/architecture/metadata-ingestion", + "docs/architecture/metadata-serving", + "docs/architecture/docker-containers" + ] + }, + { + "Developing on DataHub": [ + "docs/developers", + "docs/docker/development", + "metadata-ingestion/developing", + "docs/api/graphql/graphql-endpoint-development", + { + "Modules": [ + "datahub-web-react/README", + "datahub-frontend/README", + "datahub-graphql-core/README", + "metadata-service/README", + "metadata-jobs/mae-consumer-job/README", + "metadata-jobs/mce-consumer-job/README" + ] + } + ] + }, + "docs/plugins", + { + "Troubleshooting": [ + "docs/troubleshooting/quickstart", + "docs/troubleshooting/build", + "docs/troubleshooting/general" + ] + }, + { + "Advanced": [ + "metadata-ingestion/docs/dev_guides/reporting_telemetry", + "docs/advanced/mcp-mcl", + "docker/datahub-upgrade/README", + "docs/advanced/no-code-modeling", + "datahub-web-react/src/app/analytics/README", + "docs/how/migrating-graph-service-implementation", + "docs/advanced/field-path-spec-v2", + "metadata-ingestion/adding-source", + "docs/how/add-custom-ingestion-source", + "docs/how/add-custom-data-platform", + "docs/advanced/browse-paths-upgrade", + "docs/browseV2/browse-paths-v2" + ] + } + ] + }, + { + "Community": [ + "docs/slack", + "docs/townhalls", + "docs/townhall-history", + "docs/CODE_OF_CONDUCT", + "docs/CONTRIBUTING", + "docs/links", + "docs/rfc" + ] + }, + { + "Managed DataHub": [ + "docs/managed-datahub/managed-datahub-overview", + "docs/managed-datahub/welcome-acryl", + { + "type": "doc", + "id": "docs/managed-datahub/saas-slack-setup", + "className": "saasOnly" + }, + { + "type": "doc", + "id": "docs/managed-datahub/approval-workflows", + "className": "saasOnly" + }, + { + "Metadata Ingestion With Acryl": [ + "docs/managed-datahub/metadata-ingestion-with-acryl/ingestion" + ] + }, + { + "DataHub API": [ + { + "type": "doc", + "id": "docs/managed-datahub/datahub-api/entity-events-api", + "className": "saasOnly" + }, + { + "GraphQL API": [ + "docs/managed-datahub/datahub-api/graphql-api/getting-started", + { + "type": "doc", + "id": "docs/managed-datahub/datahub-api/graphql-api/incidents-api-beta", + "className": "saasOnly" + } + ] + } + ] + }, + { + "Integrations": [ + { + "type": "doc", + "id": "docs/managed-datahub/integrations/aws-privatelink", + "className": "saasOnly" + }, + { + "type": "doc", + "id": "docs/managed-datahub/integrations/oidc-sso-integration", + "className": "saasOnly" + } + ] + }, + { + "Operator Guide": [ + { + "type": "doc", + "id": "docs/managed-datahub/operator-guide/setting-up-remote-ingestion-executor-on-aws", + "className": "saasOnly" + }, + { + "type": "doc", + "id": "docs/managed-datahub/operator-guide/setting-up-events-api-on-aws-eventbridge", + "className": "saasOnly" + } + ] + }, + { + "type": "doc", + "id": "docs/managed-datahub/chrome-extension", + "className": "saasOnly" + }, + { + "Managed DataHub Release History": [ + "docs/managed-datahub/release-notes/v_0_2_10", + "docs/managed-datahub/release-notes/v_0_2_9", + "docs/managed-datahub/release-notes/v_0_2_8", + "docs/managed-datahub/release-notes/v_0_2_7", + "docs/managed-datahub/release-notes/v_0_2_6", + "docs/managed-datahub/release-notes/v_0_2_5", + "docs/managed-datahub/release-notes/v_0_2_4", + "docs/managed-datahub/release-notes/v_0_2_3", + "docs/managed-datahub/release-notes/v_0_2_2", + "docs/managed-datahub/release-notes/v_0_2_1", + "docs/managed-datahub/release-notes/v_0_2_0", + "docs/managed-datahub/release-notes/v_0_1_73", + "docs/managed-datahub/release-notes/v_0_1_72", + "docs/managed-datahub/release-notes/v_0_1_70", + "docs/managed-datahub/release-notes/v_0_1_69" + ] + } + ] + }, + { + "Release History": [ + "releases" + ] + } + ] +} diff --git a/docs-website/versions.json b/docs-website/versions.json new file mode 100644 index 0000000000000..0b79ac9498e06 --- /dev/null +++ b/docs-website/versions.json @@ -0,0 +1,3 @@ +[ + "0.10.5" +] diff --git a/docs/actions/concepts.md b/docs/actions/concepts.md index 381f2551d2237..5b05a0c586a5d 100644 --- a/docs/actions/concepts.md +++ b/docs/actions/concepts.md @@ -40,7 +40,11 @@ The Actions Framework consists of a few core concepts-- Each of these will be described in detail below. -![](imgs/actions.png) + +

+ +

+ **In the Actions Framework, Events flow continuously from left-to-right.** ### Pipelines diff --git a/docs/advanced/no-code-modeling.md b/docs/advanced/no-code-modeling.md index 9c8f6761a62bc..d76b776d3dddb 100644 --- a/docs/advanced/no-code-modeling.md +++ b/docs/advanced/no-code-modeling.md @@ -159,11 +159,19 @@ along with simplifying the number of raw data models that need defined, includin From an architectural PoV, we will move from a before that looks something like this: -![no-code-before](../imgs/no-code-before.png) + +

+ +

+ to an after that looks like this -![no-code-after](../imgs/no-code-after.png) + +

+ +

+ That is, a move away from patterns of strong-typing-everywhere to a more generic + flexible world. diff --git a/docs/api/graphql/how-to-set-up-graphql.md b/docs/api/graphql/how-to-set-up-graphql.md index 562e8edb9f5d9..584bf34ad3f92 100644 --- a/docs/api/graphql/how-to-set-up-graphql.md +++ b/docs/api/graphql/how-to-set-up-graphql.md @@ -62,7 +62,11 @@ Postman is a popular API client that provides a graphical user interface for sen Within Postman, you can create a `POST` request and set the request URL to the `/api/graphql` endpoint. In the request body, select the `GraphQL` option and enter your GraphQL query in the request body. -![postman-graphql](../../imgs/apis/postman-graphql.png) + +

+ +

+ Please refer to [Querying with GraphQL](https://learning.postman.com/docs/sending-requests/graphql/graphql/) in the Postman documentation for more information. diff --git a/docs/api/tutorials/custom-properties.md b/docs/api/tutorials/custom-properties.md index dbc07bfaa712e..fe0d7e62dcde8 100644 --- a/docs/api/tutorials/custom-properties.md +++ b/docs/api/tutorials/custom-properties.md @@ -34,7 +34,11 @@ In this example, we will add some custom properties `cluster_name` and `retentio After you have ingested sample data, the dataset `fct_users_deleted` should have a custom properties section with `encoding` set to `utf-8`. -![dataset-properties-before](../../imgs/apis/tutorials/dataset-properties-before.png) + +

+ +

+ ```shell datahub get --urn "urn:li:dataset:(urn:li:dataPlatform:hive,fct_users_deleted,PROD)" --aspect datasetProperties @@ -80,7 +84,11 @@ The following code adds custom properties `cluster_name` and `retention_time` to You can now see the two new properties are added to `fct_users_deleted` and the previous property `encoding` is unchanged. -![dataset-properties-added](../../imgs/apis/tutorials/dataset-properties-added.png) + +

+ +

+ We can also verify this operation by programmatically checking the `datasetProperties` aspect after running this code using the `datahub` cli. @@ -130,7 +138,11 @@ The following code shows you how can add and remove custom properties in the sam You can now see the `cluster_name` property is added to `fct_users_deleted` and the `retention_time` property is removed. -![dataset-properties-added-removed](../../imgs/apis/tutorials/dataset-properties-added-removed.png) + +

+ +

+ We can also verify this operation programmatically by checking the `datasetProperties` aspect using the `datahub` cli. @@ -179,7 +191,11 @@ The following code replaces the current custom properties with a new properties You can now see the `cluster_name` and `retention_time` properties are added to `fct_users_deleted` but the previous `encoding` property is no longer present. -![dataset-properties-replaced](../../imgs/apis/tutorials/dataset-properties-replaced.png) + +

+ +

+ We can also verify this operation programmatically by checking the `datasetProperties` aspect using the `datahub` cli. diff --git a/docs/api/tutorials/datasets.md b/docs/api/tutorials/datasets.md index 62b30e97c8020..7c6d4a88d4190 100644 --- a/docs/api/tutorials/datasets.md +++ b/docs/api/tutorials/datasets.md @@ -42,7 +42,11 @@ For detailed steps, please refer to [Datahub Quickstart Guide](/docs/quickstart. You can now see `realestate_db.sales` dataset has been created. -![dataset-created](../../imgs/apis/tutorials/dataset-created.png) + +

+ +

+ ## Delete Dataset @@ -110,4 +114,8 @@ Expected Response: The dataset `fct_users_deleted` has now been deleted, so if you search for a hive dataset named `fct_users_delete`, you will no longer be able to see it. -![dataset-deleted](../../imgs/apis/tutorials/dataset-deleted.png) + +

+ +

+ diff --git a/docs/api/tutorials/deprecation.md b/docs/api/tutorials/deprecation.md index 6a8f7c8a1d2be..73e73f5224cbc 100644 --- a/docs/api/tutorials/deprecation.md +++ b/docs/api/tutorials/deprecation.md @@ -155,4 +155,8 @@ Expected Response: You can now see the dataset `fct_users_created` has been marked as `Deprecated.` -![tag-removed](../../imgs/apis/tutorials/deprecation-updated.png) + +

+ +

+ diff --git a/docs/api/tutorials/descriptions.md b/docs/api/tutorials/descriptions.md index 46f42b7a05be6..27c57309ba76a 100644 --- a/docs/api/tutorials/descriptions.md +++ b/docs/api/tutorials/descriptions.md @@ -275,7 +275,11 @@ Expected Response: You can now see the description is added to `fct_users_deleted`. -![dataset-description-added](../../imgs/apis/tutorials/dataset-description-added.png) + +

+ +

+ ## Add Description on Column @@ -357,4 +361,8 @@ Expected Response: You can now see column description is added to `user_name` column of `fct_users_deleted`. -![column-description-added](../../imgs/apis/tutorials/column-description-added.png) + +

+ +

+ diff --git a/docs/api/tutorials/domains.md b/docs/api/tutorials/domains.md index c8c47f85c570f..617864d233b7a 100644 --- a/docs/api/tutorials/domains.md +++ b/docs/api/tutorials/domains.md @@ -74,7 +74,11 @@ Expected Response: You can now see `Marketing` domain has been created under `Govern > Domains`. -![domain-created](../../imgs/apis/tutorials/domain-created.png) + +

+ +

+ ## Read Domains @@ -209,7 +213,11 @@ Expected Response: You can now see `Marketing` domain has been added to the dataset. -![domain-added](../../imgs/apis/tutorials/domain-added.png) + +

+ +

+ ## Remove Domains @@ -259,4 +267,8 @@ curl --location --request POST 'http://localhost:8080/api/graphql' \ You can now see a domain `Marketing` has been removed from the `fct_users_created` dataset. -![domain-removed](../../imgs/apis/tutorials/domain-removed.png) + +

+ +

+ diff --git a/docs/api/tutorials/lineage.md b/docs/api/tutorials/lineage.md index e37986af7bbbd..ce23a4d274e8e 100644 --- a/docs/api/tutorials/lineage.md +++ b/docs/api/tutorials/lineage.md @@ -112,7 +112,11 @@ Expected Response: You can now see the lineage between `fct_users_deleted` and `logging_events`. -![lineage-added](../../imgs/apis/tutorials/lineage-added.png) + +

+ +

+ ## Add Column-level Lineage @@ -130,7 +134,11 @@ You can now see the lineage between `fct_users_deleted` and `logging_events`. You can now see the column-level lineage between datasets. Note that you have to enable `Show Columns` to be able to see the column-level lineage. -![column-level-lineage-added](../../imgs/apis/tutorials/column-level-lineage-added.png) + +

+ +

+ ## Read Lineage diff --git a/docs/api/tutorials/ml.md b/docs/api/tutorials/ml.md index b16f2669b30c7..cb77556d48ebf 100644 --- a/docs/api/tutorials/ml.md +++ b/docs/api/tutorials/ml.md @@ -94,9 +94,17 @@ Please note that an MlModelGroup serves as a container for all the runs of a sin You can search the entities in DataHub UI. -![feature-table-created](../../imgs/apis/tutorials/feature-table-created.png) -![model-group-created](../../imgs/apis/tutorials/model-group-created.png) +

+ +

+ + + +

+ +

+ ## Read ML Entities @@ -499,6 +507,14 @@ Expected Response: (Note that this entity does not exist in the sample ingestion You can access to `Features` or `Group` Tab of each entity to view the added entities. -![feature-added-to-model](../../imgs/apis/tutorials/feature-added-to-model.png) -![model-group-added-to-model](../../imgs/apis/tutorials/model-group-added-to-model.png) +

+ +

+ + + +

+ +

+ diff --git a/docs/api/tutorials/owners.md b/docs/api/tutorials/owners.md index 3c7a46b136d76..5bc3b95cb5631 100644 --- a/docs/api/tutorials/owners.md +++ b/docs/api/tutorials/owners.md @@ -77,7 +77,11 @@ Update succeeded for urn urn:li:corpuser:datahub. ### Expected Outcomes of Upserting User You can see the user `The bar` has been created and the user `Datahub` has been updated under `Settings > Access > Users & Groups` -![user-upserted](../../imgs/apis/tutorials/user-upserted.png) + +

+ +

+ ## Upsert Group @@ -125,7 +129,11 @@ Update succeeded for group urn:li:corpGroup:foogroup@acryl.io. ### Expected Outcomes of Upserting Group You can see the group `Foo Group` has been created under `Settings > Access > Users & Groups` -![group-upserted](../../imgs/apis/tutorials/group-upserted.png) + +

+ +

+ ## Read Owners @@ -272,7 +280,11 @@ curl --location --request POST 'http://localhost:8080/api/graphql' \ You can now see `bfoo` has been added as an owner to the `fct_users_created` dataset. -![ownership-added](../../imgs/apis/tutorials/owner-added.png) + +

+ +

+ ## Remove Owners @@ -340,4 +352,8 @@ curl --location --request POST 'http://localhost:8080/api/graphql' \ You can now see `John Doe` has been removed as an owner from the `fct_users_created` dataset. -![ownership-removed](../../imgs/apis/tutorials/owner-removed.png) + +

+ +

+ diff --git a/docs/api/tutorials/tags.md b/docs/api/tutorials/tags.md index 2f80a833136c1..b2234bf00bcb9 100644 --- a/docs/api/tutorials/tags.md +++ b/docs/api/tutorials/tags.md @@ -91,7 +91,11 @@ Expected Response: You can now see the new tag `Deprecated` has been created. -![tag-created](../../imgs/apis/tutorials/tag-created.png) + +

+ +

+ We can also verify this operation by programmatically searching `Deprecated` tag after running this code using the `datahub` cli. @@ -307,7 +311,11 @@ Expected Response: You can now see `Deprecated` tag has been added to `user_name` column. -![tag-added](../../imgs/apis/tutorials/tag-added.png) + +

+ +

+ We can also verify this operation programmatically by checking the `globalTags` aspect using the `datahub` cli. @@ -359,7 +367,11 @@ curl --location --request POST 'http://localhost:8080/api/graphql' \ You can now see `Deprecated` tag has been removed to `user_name` column. -![tag-removed](../../imgs/apis/tutorials/tag-removed.png) + +

+ +

+ We can also verify this operation programmatically by checking the `gloablTags` aspect using the `datahub` cli. diff --git a/docs/api/tutorials/terms.md b/docs/api/tutorials/terms.md index 207e14ea4afe8..99acf77d26ab0 100644 --- a/docs/api/tutorials/terms.md +++ b/docs/api/tutorials/terms.md @@ -95,7 +95,11 @@ Expected Response: You can now see the new term `Rate of Return` has been created. -![term-created](../../imgs/apis/tutorials/term-created.png) + +

+ +

+ We can also verify this operation by programmatically searching `Rate of Return` term after running this code using the `datahub` cli. @@ -289,7 +293,11 @@ Expected Response: You can now see `Rate of Return` term has been added to `user_name` column. -![term-added](../../imgs/apis/tutorials/term-added.png) + +

+ +

+ ## Remove Terms @@ -361,4 +369,8 @@ curl --location --request POST 'http://localhost:8080/api/graphql' \ You can now see `Rate of Return` term has been removed to `user_name` column. -![term-removed](../../imgs/apis/tutorials/term-removed.png) + +

+ +

+ diff --git a/docs/architecture/architecture.md b/docs/architecture/architecture.md index 6b76b995cc427..6a9c1860d71b0 100644 --- a/docs/architecture/architecture.md +++ b/docs/architecture/architecture.md @@ -10,8 +10,16 @@ disparate tools & systems. The figures below describe the high-level architecture of DataHub. -![datahub-architecture](../imgs/datahub-architecture.png) -![Acryl DataHub System Architecture ](../managed-datahub/imgs/saas/DataHub-Architecture.png) + +

+ +

+ + +

+ +

+ For a more detailed look at the components that make up the Architecture, check out [Components](../components.md). diff --git a/docs/architecture/metadata-ingestion.md b/docs/architecture/metadata-ingestion.md index 2b60383319c68..abf8fc24d1385 100644 --- a/docs/architecture/metadata-ingestion.md +++ b/docs/architecture/metadata-ingestion.md @@ -6,7 +6,11 @@ title: "Ingestion Framework" DataHub supports an extremely flexible ingestion architecture that can support push, pull, asynchronous and synchronous models. The figure below describes all the options possible for connecting your favorite system to DataHub. -![Ingestion Architecture](../imgs/ingestion-architecture.png) + +

+ +

+ ## Metadata Change Proposal: The Center Piece diff --git a/docs/architecture/metadata-serving.md b/docs/architecture/metadata-serving.md index ada41179af4e0..57194f49d5ea4 100644 --- a/docs/architecture/metadata-serving.md +++ b/docs/architecture/metadata-serving.md @@ -6,7 +6,11 @@ title: "Serving Tier" The figure below shows the high-level system diagram for DataHub's Serving Tier. -![datahub-serving](../imgs/datahub-serving.png) + +

+ +

+ The primary component is called [the Metadata Service](../../metadata-service) and exposes a REST API and a GraphQL API for performing CRUD operations on metadata. The service also exposes search and graph query API-s to support secondary-index style queries, full-text search queries as well as relationship queries like lineage. In addition, the [datahub-frontend](../../datahub-frontend) service expose a GraphQL API on top of the metadata graph. diff --git a/docs/authentication/concepts.md b/docs/authentication/concepts.md index 715e94c7e0380..0940f86a805f1 100644 --- a/docs/authentication/concepts.md +++ b/docs/authentication/concepts.md @@ -11,7 +11,11 @@ We introduced a few important concepts to the Metadata Service to make authentic In following sections, we'll take a closer look at each individually. -![](../imgs/metadata-service-auth.png) + +

+ +

+ *High level overview of Metadata Service Authentication* ## What is an Actor? diff --git a/docs/authentication/guides/sso/configure-oidc-react-azure.md b/docs/authentication/guides/sso/configure-oidc-react-azure.md index d185957967882..177387327c0e8 100644 --- a/docs/authentication/guides/sso/configure-oidc-react-azure.md +++ b/docs/authentication/guides/sso/configure-oidc-react-azure.md @@ -32,7 +32,11 @@ Azure supports more than one redirect URI, so both can be configured at the same At this point, your app registration should look like the following: -![azure-setup-app-registration](img/azure-setup-app-registration.png) + +

+ +

+ e. Click **Register**. @@ -40,7 +44,11 @@ e. Click **Register**. Once registration is done, you will land on the app registration **Overview** tab. On the left-side navigation bar, click on **Authentication** under **Manage** and add extra redirect URIs if need be (if you want to support both local testing and Azure deployments). -![azure-setup-authentication](img/azure-setup-authentication.png) + +

+ +

+ Click **Save**. @@ -51,7 +59,11 @@ Select **Client secrets**, then **New client secret**. Type in a meaningful des **IMPORTANT:** Copy the `value` of your newly create secret since Azure will never display its value afterwards. -![azure-setup-certificates-secrets](img/azure-setup-certificates-secrets.png) + +

+ +

+ ### 4. Configure API permissions @@ -66,7 +78,11 @@ Click on **Add a permission**, then from the **Microsoft APIs** tab select **Mic At this point, you should be looking at a screen like the following: -![azure-setup-api-permissions](img/azure-setup-api-permissions.png) + +

+ +

+ ### 5. Obtain Application (Client) ID diff --git a/docs/authentication/guides/sso/configure-oidc-react-google.md b/docs/authentication/guides/sso/configure-oidc-react-google.md index 474538097aae2..af62185e6e787 100644 --- a/docs/authentication/guides/sso/configure-oidc-react-google.md +++ b/docs/authentication/guides/sso/configure-oidc-react-google.md @@ -31,7 +31,11 @@ Note that in order to complete this step you should be logged into a Google acco c. Fill out the details in the App Information & Domain sections. Make sure the 'Application Home Page' provided matches where DataHub is deployed at your organization. -![google-setup-1](img/google-setup-1.png) + +

+ +

+ Once you've completed this, **Save & Continue**. @@ -70,7 +74,11 @@ f. You will now receive a pair of values, a client id and a client secret. Bookm At this point, you should be looking at a screen like the following: -![google-setup-2](img/google-setup-2.png) + +

+ +

+ Success! diff --git a/docs/authentication/guides/sso/configure-oidc-react-okta.md b/docs/authentication/guides/sso/configure-oidc-react-okta.md index cfede999f1e70..320b887a28f16 100644 --- a/docs/authentication/guides/sso/configure-oidc-react-okta.md +++ b/docs/authentication/guides/sso/configure-oidc-react-okta.md @@ -69,8 +69,16 @@ for example, `https://dev-33231928.okta.com/.well-known/openid-configuration`. At this point, you should be looking at a screen like the following: -![okta-setup-1](img/okta-setup-1.png) -![okta-setup-2](img/okta-setup-2.png) + +

+ +

+ + +

+ +

+ Success! @@ -96,7 +104,11 @@ Replacing the placeholders above with the client id & client secret received fro > > By default, we assume that the groups will appear in a claim named "groups". This can be customized using the `AUTH_OIDC_GROUPS_CLAIM` container configuration. > -> ![okta-setup-2](img/okta-setup-groups-claim.png) +> +

+ +

+ ### 5. Restart `datahub-frontend-react` docker container diff --git a/docs/authentication/guides/sso/img/azure-setup-api-permissions.png b/docs/authentication/guides/sso/img/azure-setup-api-permissions.png deleted file mode 100755 index 4964b7d48ffec..0000000000000 Binary files a/docs/authentication/guides/sso/img/azure-setup-api-permissions.png and /dev/null differ diff --git a/docs/authentication/guides/sso/img/azure-setup-app-registration.png b/docs/authentication/guides/sso/img/azure-setup-app-registration.png deleted file mode 100755 index ffb23a7e3ddec..0000000000000 Binary files a/docs/authentication/guides/sso/img/azure-setup-app-registration.png and /dev/null differ diff --git a/docs/authentication/guides/sso/img/azure-setup-authentication.png b/docs/authentication/guides/sso/img/azure-setup-authentication.png deleted file mode 100755 index 2d27ec88fb40b..0000000000000 Binary files a/docs/authentication/guides/sso/img/azure-setup-authentication.png and /dev/null differ diff --git a/docs/authentication/guides/sso/img/azure-setup-certificates-secrets.png b/docs/authentication/guides/sso/img/azure-setup-certificates-secrets.png deleted file mode 100755 index db6585d84d8ee..0000000000000 Binary files a/docs/authentication/guides/sso/img/azure-setup-certificates-secrets.png and /dev/null differ diff --git a/docs/authentication/guides/sso/img/google-setup-1.png b/docs/authentication/guides/sso/img/google-setup-1.png deleted file mode 100644 index 88c674146f1e4..0000000000000 Binary files a/docs/authentication/guides/sso/img/google-setup-1.png and /dev/null differ diff --git a/docs/authentication/guides/sso/img/google-setup-2.png b/docs/authentication/guides/sso/img/google-setup-2.png deleted file mode 100644 index 850512b891d5f..0000000000000 Binary files a/docs/authentication/guides/sso/img/google-setup-2.png and /dev/null differ diff --git a/docs/authentication/guides/sso/img/okta-setup-1.png b/docs/authentication/guides/sso/img/okta-setup-1.png deleted file mode 100644 index 3949f18657c5e..0000000000000 Binary files a/docs/authentication/guides/sso/img/okta-setup-1.png and /dev/null differ diff --git a/docs/authentication/guides/sso/img/okta-setup-2.png b/docs/authentication/guides/sso/img/okta-setup-2.png deleted file mode 100644 index fa6ea4d991894..0000000000000 Binary files a/docs/authentication/guides/sso/img/okta-setup-2.png and /dev/null differ diff --git a/docs/authentication/guides/sso/img/okta-setup-groups-claim.png b/docs/authentication/guides/sso/img/okta-setup-groups-claim.png deleted file mode 100644 index ed35426685e46..0000000000000 Binary files a/docs/authentication/guides/sso/img/okta-setup-groups-claim.png and /dev/null differ diff --git a/docs/authentication/personal-access-tokens.md b/docs/authentication/personal-access-tokens.md index 0188aab49444e..dc57a989a4e0c 100644 --- a/docs/authentication/personal-access-tokens.md +++ b/docs/authentication/personal-access-tokens.md @@ -71,7 +71,11 @@ curl 'http://localhost:8080/entities/urn:li:corpuser:datahub' -H 'Authorization: Since authorization happens at the GMS level, this means that ingestion is also protected behind access tokens, to use them simply add a `token` to the sink config property as seen below: -![](../imgs/ingestion-with-token.png) + +

+ +

+ :::note diff --git a/docs/components.md b/docs/components.md index ef76729bb37fb..b59dabcf999cc 100644 --- a/docs/components.md +++ b/docs/components.md @@ -6,7 +6,11 @@ title: "Components" The DataHub platform consists of the components shown in the following diagram. -![DataHub Component Overview](./imgs/datahub-components.png) + +

+ +

+ ## Metadata Store diff --git a/docs/demo/DataHub-UIOverview.pdf b/docs/demo/DataHub-UIOverview.pdf deleted file mode 100644 index cd6106e84ac23..0000000000000 Binary files a/docs/demo/DataHub-UIOverview.pdf and /dev/null differ diff --git a/docs/demo/DataHub_-_Powering_LinkedIn_Metadata.pdf b/docs/demo/DataHub_-_Powering_LinkedIn_Metadata.pdf deleted file mode 100644 index 71498045f9b5b..0000000000000 Binary files a/docs/demo/DataHub_-_Powering_LinkedIn_Metadata.pdf and /dev/null differ diff --git a/docs/demo/Data_Discoverability_at_SpotHero.pdf b/docs/demo/Data_Discoverability_at_SpotHero.pdf deleted file mode 100644 index 83e37d8606428..0000000000000 Binary files a/docs/demo/Data_Discoverability_at_SpotHero.pdf and /dev/null differ diff --git a/docs/demo/Datahub_-_Strongly_Consistent_Secondary_Indexing.pdf b/docs/demo/Datahub_-_Strongly_Consistent_Secondary_Indexing.pdf deleted file mode 100644 index 2d6a33a464650..0000000000000 Binary files a/docs/demo/Datahub_-_Strongly_Consistent_Secondary_Indexing.pdf and /dev/null differ diff --git a/docs/demo/Datahub_at_Grofers.pdf b/docs/demo/Datahub_at_Grofers.pdf deleted file mode 100644 index c29cece9e250a..0000000000000 Binary files a/docs/demo/Datahub_at_Grofers.pdf and /dev/null differ diff --git a/docs/demo/Designing_the_next_generation_of_metadata_events_for_scale.pdf b/docs/demo/Designing_the_next_generation_of_metadata_events_for_scale.pdf deleted file mode 100644 index 0d067eef28d03..0000000000000 Binary files a/docs/demo/Designing_the_next_generation_of_metadata_events_for_scale.pdf and /dev/null differ diff --git a/docs/demo/Metadata_Use-Cases_at_LinkedIn_-_Lightning_Talk.pdf b/docs/demo/Metadata_Use-Cases_at_LinkedIn_-_Lightning_Talk.pdf deleted file mode 100644 index 382754f863c8a..0000000000000 Binary files a/docs/demo/Metadata_Use-Cases_at_LinkedIn_-_Lightning_Talk.pdf and /dev/null differ diff --git a/docs/demo/Saxo Bank Data Workbench.pdf b/docs/demo/Saxo Bank Data Workbench.pdf deleted file mode 100644 index c43480d32b8f2..0000000000000 Binary files a/docs/demo/Saxo Bank Data Workbench.pdf and /dev/null differ diff --git a/docs/demo/Taming the Data Beast Using DataHub.pdf b/docs/demo/Taming the Data Beast Using DataHub.pdf deleted file mode 100644 index d0062465d9220..0000000000000 Binary files a/docs/demo/Taming the Data Beast Using DataHub.pdf and /dev/null differ diff --git a/docs/demo/Town_Hall_Presentation_-_12-2020_-_UI_Development_Part_2.pdf b/docs/demo/Town_Hall_Presentation_-_12-2020_-_UI_Development_Part_2.pdf deleted file mode 100644 index fb7bd2b693e87..0000000000000 Binary files a/docs/demo/Town_Hall_Presentation_-_12-2020_-_UI_Development_Part_2.pdf and /dev/null differ diff --git a/docs/demo/ViasatMetadataJourney.pdf b/docs/demo/ViasatMetadataJourney.pdf deleted file mode 100644 index ccffd18a06d18..0000000000000 Binary files a/docs/demo/ViasatMetadataJourney.pdf and /dev/null differ diff --git a/docs/deploy/aws.md b/docs/deploy/aws.md index 7b01ffa02a744..228fcb51d1a28 100644 --- a/docs/deploy/aws.md +++ b/docs/deploy/aws.md @@ -201,7 +201,11 @@ Provision a MySQL database in AWS RDS that shares the VPC with the kubernetes cl the VPC of the kubernetes cluster. Once the database is provisioned, you should be able to see the following page. Take a note of the endpoint marked by the red box. -![AWS RDS](../imgs/aws/aws-rds.png) + +

+ +

+ First, add the DB password to kubernetes by running the following. @@ -234,7 +238,11 @@ Provision an elasticsearch domain running elasticsearch version 7.10 or above th cluster or has VPC peering set up between the VPC of the kubernetes cluster. Once the domain is provisioned, you should be able to see the following page. Take a note of the endpoint marked by the red box. -![AWS Elasticsearch Service](../imgs/aws/aws-elasticsearch.png) + +

+ +

+ Update the elasticsearch settings under global in the values.yaml as follows. @@ -330,7 +338,11 @@ Provision an MSK cluster that shares the VPC with the kubernetes cluster or has the kubernetes cluster. Once the domain is provisioned, click on the “View client information” button in the ‘Cluster Summary” section. You should see a page like below. Take a note of the endpoints marked by the red boxes. -![AWS MSK](../imgs/aws/aws-msk.png) + +

+ +

+ Update the kafka settings under global in the values.yaml as follows. diff --git a/docs/deploy/confluent-cloud.md b/docs/deploy/confluent-cloud.md index d93ffcceaecee..794b55d4686bf 100644 --- a/docs/deploy/confluent-cloud.md +++ b/docs/deploy/confluent-cloud.md @@ -24,7 +24,11 @@ decommissioned. To create the topics, navigate to your **Cluster** and click "Create Topic". Feel free to tweak the default topic configurations to match your preferences. -![CreateTopic](../imgs/confluent-create-topic.png) + +

+ +

+ ## Step 2: Configure DataHub Container to use Confluent Cloud Topics @@ -140,12 +144,20 @@ and another for the user info used for connecting to the schema registry. You'll select "Clients" -> "Configure new Java Client". You should see a page like the following: -![Config](../imgs/confluent-cloud-config.png) + +

+ +

+ You'll want to generate both a Kafka Cluster API Key & a Schema Registry key. Once you do so,you should see the config automatically populate with your new secrets: -![Config](../imgs/confluent-cloud-config-2.png) + +

+ +

+ You'll need to copy the values of `sasl.jaas.config` and `basic.auth.user.info` for the next step. diff --git a/docs/deploy/gcp.md b/docs/deploy/gcp.md index 3713d69f90636..0cd3d92a8f3cd 100644 --- a/docs/deploy/gcp.md +++ b/docs/deploy/gcp.md @@ -65,16 +65,28 @@ the GKE page on [GCP website](https://console.cloud.google.com/kubernetes/discov Once all deploy is successful, you should see a page like below in the "Services & Ingress" tab on the left. -![Services and Ingress](../imgs/gcp/services_ingress.png) + +

+ +

+ Tick the checkbox for datahub-datahub-frontend and click "CREATE INGRESS" button. You should land on the following page. -![Ingress1](../imgs/gcp/ingress1.png) + +

+ +

+ Type in an arbitrary name for the ingress and click on the second step "Host and path rules". You should land on the following page. -![Ingress2](../imgs/gcp/ingress2.png) + +

+ +

+ Select "datahub-datahub-frontend" in the dropdown menu for backends, and then click on "ADD HOST AND PATH RULE" button. In the second row that got created, add in the host name of choice (here gcp.datahubproject.io) and select @@ -83,14 +95,22 @@ In the second row that got created, add in the host name of choice (here gcp.dat This step adds the rule allowing requests from the host name of choice to get routed to datahub-frontend service. Click on step 3 "Frontend configuration". You should land on the following page. -![Ingress3](../imgs/gcp/ingress3.png) + +

+ +

+ Choose HTTPS in the dropdown menu for protocol. To enable SSL, you need to add a certificate. If you do not have one, you can click "CREATE A NEW CERTIFICATE" and input the host name of choice. GCP will create a certificate for you. Now press "CREATE" button on the left to create ingress! After around 5 minutes, you should see the following. -![Ingress Ready](../imgs/gcp/ingress_ready.png) + +

+ +

+ In your domain provider, add an A record for the host name set above using the IP address on the ingress page (noted with the red box). Once DNS updates, you should be able to access DataHub through the host name!! @@ -98,5 +118,9 @@ with the red box). Once DNS updates, you should be able to access DataHub throug Note, ignore the warning icon next to ingress. It takes about ten minutes for ingress to check that the backend service is ready and show a check mark as follows. However, ingress is fully functional once you see the above page. -![Ingress Final](../imgs/gcp/ingress_final.png) + +

+ +

+ diff --git a/docs/dev-guides/timeline.md b/docs/dev-guides/timeline.md index 966e659b90991..829aef1d3eefa 100644 --- a/docs/dev-guides/timeline.md +++ b/docs/dev-guides/timeline.md @@ -14,7 +14,11 @@ The Timeline API is available in server versions `0.8.28` and higher. The `cli` ## Entity Timeline Conceptually For the visually inclined, here is a conceptual diagram that illustrates how to think about the entity timeline with categorical changes overlaid on it. -![../imgs/timeline/timeline-conceptually.png](../imgs/timeline/timeline-conceptually.png) + +

+ +

+ ## Change Event Each modification is modeled as a @@ -228,8 +232,16 @@ http://localhost:8080/openapi/timeline/v1/urn%3Ali%3Adataset%3A%28urn%3Ali%3Adat The API is browse-able via the UI through through the dropdown. Here are a few screenshots showing how to navigate to it. You can try out the API and send example requests. -![../imgs/timeline/dropdown-apis.png](../imgs/timeline/dropdown-apis.png) -![../imgs/timeline/swagger-ui.png](../imgs/timeline/swagger-ui.png) + +

+ +

+ + +

+ +

+ # Future Work diff --git a/docs/docker/development.md b/docs/docker/development.md index 2153aa9dc613f..91a303744a03b 100644 --- a/docs/docker/development.md +++ b/docs/docker/development.md @@ -92,7 +92,11 @@ Environment variables control the debugging ports for GMS and the frontend. The screenshot shows an example configuration for IntelliJ using the default GMS debugging port of 5001. -![](../imgs/development/intellij-remote-debug.png) + +

+ +

+ ## Tips for People New To Docker diff --git a/docs/glossary/business-glossary.md b/docs/glossary/business-glossary.md index faab6f12fc55e..e10cbed30b913 100644 --- a/docs/glossary/business-glossary.md +++ b/docs/glossary/business-glossary.md @@ -31,59 +31,103 @@ In order to view a Business Glossary, users must have the Platform Privilege cal Once granted this privilege, you can access your Glossary by clicking the dropdown at the top of the page called **Govern** and then click **Glossary**: -![](../imgs/glossary/glossary-button.png) + +

+ +

+ You are now at the root of your Glossary and should see all Terms and Term Groups with no parents assigned to them. You should also notice a hierarchy navigator on the left where you can easily check out the structure of your Glossary! -![](../imgs/glossary/root-glossary.png) + +

+ +

+ ## Creating a Term or Term Group There are two ways to create Terms and Term Groups through the UI. First, you can create directly from the Glossary home page by clicking the menu dots on the top right and selecting your desired option: -![](../imgs/glossary/root-glossary-create.png) + +

+ +

+ You can also create Terms or Term Groups directly from a Term Group's page. In order to do that you need to click the menu dots on the top right and select what you want: -![](../imgs/glossary/create-from-node.png) + +

+ +

+ Note that the modal that pops up will automatically set the current Term Group you are in as the **Parent**. You can easily change this by selecting the input and navigating through your Glossary to find your desired Term Group. In addition, you could start typing the name of a Term Group to see it appear by searching. You can also leave this input blank in order to create a Term or Term Group with no parent. -![](../imgs/glossary/create-modal.png) + +

+ +

+ ## Editing a Term or Term Group In order to edit a Term or Term Group, you first need to go the page of the Term or Term group you want to edit. Then simply click the edit icon right next to the name to open up an inline editor. Change the text and it will save when you click outside or hit Enter. -![](../imgs/glossary/edit-term.png) + +

+ +

+ ## Moving a Term or Term Group Once a Term or Term Group has been created, you can always move it to be under a different Term Group parent. In order to do this, click the menu dots on the top right of either entity and select **Move**. -![](../imgs/glossary/move-term-button.png) + +

+ +

+ This will open a modal where you can navigate through your Glossary to find your desired Term Group. -![](../imgs/glossary/move-term-modal.png) + +

+ +

+ ## Deleting a Term or Term Group In order to delete a Term or Term Group, you need to go to the entity page of what you want to delete then click the menu dots on the top right. From here you can select **Delete** followed by confirming through a separate modal. **Note**: at the moment we only support deleting Term Groups that do not have any children. Until cascade deleting is supported, you will have to delete all children first, then delete the Term Group. -![](../imgs/glossary/delete-button.png) + +

+ +

+ ## Adding a Term to an Entity Once you've defined your Glossary, you can begin attaching terms to data assets. To add a Glossary Term to an asset, go to the entity page of your asset and find the **Add Terms** button on the right sidebar. -![](../imgs/glossary/add-term-to-entity.png) + +

+ +

+ In the modal that pops up you can select the Term you care about in one of two ways: - Search for the Term by name in the input - Navigate through the Glossary dropdown that appears after clicking into the input -![](../imgs/glossary/add-term-modal.png) + +

+ +

+ ## Privileges diff --git a/docs/how/configuring-authorization-with-apache-ranger.md b/docs/how/configuring-authorization-with-apache-ranger.md index 26d3be6d358b2..46f9432e6c18a 100644 --- a/docs/how/configuring-authorization-with-apache-ranger.md +++ b/docs/how/configuring-authorization-with-apache-ranger.md @@ -67,7 +67,11 @@ Now, you should have the DataHub plugin registered with Apache Ranger. Next, we' **DATAHUB** plugin and **ranger_datahub** service is shown in below screenshot:
- ![Privacera Portal DATAHUB screenshot](../imgs/apache-ranger/datahub-plugin.png) + +

+ +

+ 4. Create a new policy under service **ranger_datahub** - this will be used to control DataHub authorization. 5. Create a test user & assign them to a policy. We'll use the `datahub` user, which is the default root user inside DataHub. @@ -80,7 +84,11 @@ Now, you should have the DataHub plugin registered with Apache Ranger. Next, we' DataHub platform access policy screenshot:
- ![Privacera Portal DATAHUB screenshot](../imgs/apache-ranger/datahub-platform-access-policy.png) + +

+ +

+ Once we've created our first policy, we can set up DataHub to start authorizing requests using Ranger policies. @@ -178,7 +186,11 @@ then follow the below sections to undo the configuration steps you have performe **ranger_datahub** service is shown in below screenshot:
- ![Privacera Portal DATAHUB screenshot](../imgs/apache-ranger/datahub-plugin.png) + +

+ +

+ 2. Delete **datahub** plugin: Execute below curl command to delete **datahub** plugin Replace variables with corresponding values in curl command diff --git a/docs/imgs/add-schema-tag.png b/docs/imgs/add-schema-tag.png deleted file mode 100644 index b6fd273389c90..0000000000000 Binary files a/docs/imgs/add-schema-tag.png and /dev/null differ diff --git a/docs/imgs/add-tag-search.png b/docs/imgs/add-tag-search.png deleted file mode 100644 index a129f5eba4271..0000000000000 Binary files a/docs/imgs/add-tag-search.png and /dev/null differ diff --git a/docs/imgs/add-tag.png b/docs/imgs/add-tag.png deleted file mode 100644 index 386b4cdcd9911..0000000000000 Binary files a/docs/imgs/add-tag.png and /dev/null differ diff --git a/docs/imgs/added-tag.png b/docs/imgs/added-tag.png deleted file mode 100644 index 96ae48318a35a..0000000000000 Binary files a/docs/imgs/added-tag.png and /dev/null differ diff --git a/docs/imgs/airflow/connection_error.png b/docs/imgs/airflow/connection_error.png deleted file mode 100644 index c2f3344b8cc45..0000000000000 Binary files a/docs/imgs/airflow/connection_error.png and /dev/null differ diff --git a/docs/imgs/airflow/datahub_lineage_view.png b/docs/imgs/airflow/datahub_lineage_view.png deleted file mode 100644 index c7c774c203d2f..0000000000000 Binary files a/docs/imgs/airflow/datahub_lineage_view.png and /dev/null differ diff --git a/docs/imgs/airflow/datahub_pipeline_entity.png b/docs/imgs/airflow/datahub_pipeline_entity.png deleted file mode 100644 index 715baefd784ca..0000000000000 Binary files a/docs/imgs/airflow/datahub_pipeline_entity.png and /dev/null differ diff --git a/docs/imgs/airflow/datahub_pipeline_view.png b/docs/imgs/airflow/datahub_pipeline_view.png deleted file mode 100644 index 5b3afd13c4ce6..0000000000000 Binary files a/docs/imgs/airflow/datahub_pipeline_view.png and /dev/null differ diff --git a/docs/imgs/airflow/datahub_task_view.png b/docs/imgs/airflow/datahub_task_view.png deleted file mode 100644 index 66b3487d87319..0000000000000 Binary files a/docs/imgs/airflow/datahub_task_view.png and /dev/null differ diff --git a/docs/imgs/airflow/entity_page_screenshot.png b/docs/imgs/airflow/entity_page_screenshot.png deleted file mode 100644 index a782969a1f17b..0000000000000 Binary files a/docs/imgs/airflow/entity_page_screenshot.png and /dev/null differ diff --git a/docs/imgs/airflow/find_the_dag.png b/docs/imgs/airflow/find_the_dag.png deleted file mode 100644 index 37cda041e4b75..0000000000000 Binary files a/docs/imgs/airflow/find_the_dag.png and /dev/null differ diff --git a/docs/imgs/airflow/finding_failed_log.png b/docs/imgs/airflow/finding_failed_log.png deleted file mode 100644 index 96552ba1e1983..0000000000000 Binary files a/docs/imgs/airflow/finding_failed_log.png and /dev/null differ diff --git a/docs/imgs/airflow/paused_dag.png b/docs/imgs/airflow/paused_dag.png deleted file mode 100644 index c314de5d38d75..0000000000000 Binary files a/docs/imgs/airflow/paused_dag.png and /dev/null differ diff --git a/docs/imgs/airflow/successful_run.png b/docs/imgs/airflow/successful_run.png deleted file mode 100644 index b997cc7210ff6..0000000000000 Binary files a/docs/imgs/airflow/successful_run.png and /dev/null differ diff --git a/docs/imgs/airflow/trigger_dag.png b/docs/imgs/airflow/trigger_dag.png deleted file mode 100644 index a44999c929d4e..0000000000000 Binary files a/docs/imgs/airflow/trigger_dag.png and /dev/null differ diff --git a/docs/imgs/airflow/unpaused_dag.png b/docs/imgs/airflow/unpaused_dag.png deleted file mode 100644 index 8462562f31d97..0000000000000 Binary files a/docs/imgs/airflow/unpaused_dag.png and /dev/null differ diff --git a/docs/imgs/apache-ranger/datahub-platform-access-policy.png b/docs/imgs/apache-ranger/datahub-platform-access-policy.png deleted file mode 100644 index 7e3ff6fd372a9..0000000000000 Binary files a/docs/imgs/apache-ranger/datahub-platform-access-policy.png and /dev/null differ diff --git a/docs/imgs/apache-ranger/datahub-plugin.png b/docs/imgs/apache-ranger/datahub-plugin.png deleted file mode 100644 index 5dd044c014657..0000000000000 Binary files a/docs/imgs/apache-ranger/datahub-plugin.png and /dev/null differ diff --git a/docs/imgs/apis/postman-graphql.png b/docs/imgs/apis/postman-graphql.png deleted file mode 100644 index 1cffd226fdf77..0000000000000 Binary files a/docs/imgs/apis/postman-graphql.png and /dev/null differ diff --git a/docs/imgs/apis/tutorials/column-description-added.png b/docs/imgs/apis/tutorials/column-description-added.png deleted file mode 100644 index ed8cbd3bf5622..0000000000000 Binary files a/docs/imgs/apis/tutorials/column-description-added.png and /dev/null differ diff --git a/docs/imgs/apis/tutorials/column-level-lineage-added.png b/docs/imgs/apis/tutorials/column-level-lineage-added.png deleted file mode 100644 index 6092436e0a6a8..0000000000000 Binary files a/docs/imgs/apis/tutorials/column-level-lineage-added.png and /dev/null differ diff --git a/docs/imgs/apis/tutorials/custom-properties-added.png b/docs/imgs/apis/tutorials/custom-properties-added.png deleted file mode 100644 index a7e85d875045c..0000000000000 Binary files a/docs/imgs/apis/tutorials/custom-properties-added.png and /dev/null differ diff --git a/docs/imgs/apis/tutorials/datahub-main-ui.png b/docs/imgs/apis/tutorials/datahub-main-ui.png deleted file mode 100644 index b058e2683a851..0000000000000 Binary files a/docs/imgs/apis/tutorials/datahub-main-ui.png and /dev/null differ diff --git a/docs/imgs/apis/tutorials/dataset-created.png b/docs/imgs/apis/tutorials/dataset-created.png deleted file mode 100644 index 086dd8b7c9b16..0000000000000 Binary files a/docs/imgs/apis/tutorials/dataset-created.png and /dev/null differ diff --git a/docs/imgs/apis/tutorials/dataset-deleted.png b/docs/imgs/apis/tutorials/dataset-deleted.png deleted file mode 100644 index d94ad7e85195f..0000000000000 Binary files a/docs/imgs/apis/tutorials/dataset-deleted.png and /dev/null differ diff --git a/docs/imgs/apis/tutorials/dataset-description-added.png b/docs/imgs/apis/tutorials/dataset-description-added.png deleted file mode 100644 index 41aa9f109115b..0000000000000 Binary files a/docs/imgs/apis/tutorials/dataset-description-added.png and /dev/null differ diff --git a/docs/imgs/apis/tutorials/dataset-properties-added-removed.png b/docs/imgs/apis/tutorials/dataset-properties-added-removed.png deleted file mode 100644 index 9eb0284776f13..0000000000000 Binary files a/docs/imgs/apis/tutorials/dataset-properties-added-removed.png and /dev/null differ diff --git a/docs/imgs/apis/tutorials/dataset-properties-added.png b/docs/imgs/apis/tutorials/dataset-properties-added.png deleted file mode 100644 index e0d2acbb66eb5..0000000000000 Binary files a/docs/imgs/apis/tutorials/dataset-properties-added.png and /dev/null differ diff --git a/docs/imgs/apis/tutorials/dataset-properties-before.png b/docs/imgs/apis/tutorials/dataset-properties-before.png deleted file mode 100644 index b4915121a8c65..0000000000000 Binary files a/docs/imgs/apis/tutorials/dataset-properties-before.png and /dev/null differ diff --git a/docs/imgs/apis/tutorials/dataset-properties-replaced.png b/docs/imgs/apis/tutorials/dataset-properties-replaced.png deleted file mode 100644 index 8624689c20ada..0000000000000 Binary files a/docs/imgs/apis/tutorials/dataset-properties-replaced.png and /dev/null differ diff --git a/docs/imgs/apis/tutorials/deprecation-updated.png b/docs/imgs/apis/tutorials/deprecation-updated.png deleted file mode 100644 index 06fedf746f694..0000000000000 Binary files a/docs/imgs/apis/tutorials/deprecation-updated.png and /dev/null differ diff --git a/docs/imgs/apis/tutorials/domain-added.png b/docs/imgs/apis/tutorials/domain-added.png deleted file mode 100644 index cb2002ec9ab4d..0000000000000 Binary files a/docs/imgs/apis/tutorials/domain-added.png and /dev/null differ diff --git a/docs/imgs/apis/tutorials/domain-created.png b/docs/imgs/apis/tutorials/domain-created.png deleted file mode 100644 index cafab2a5e8d5c..0000000000000 Binary files a/docs/imgs/apis/tutorials/domain-created.png and /dev/null differ diff --git a/docs/imgs/apis/tutorials/domain-removed.png b/docs/imgs/apis/tutorials/domain-removed.png deleted file mode 100644 index 1b21172be11d2..0000000000000 Binary files a/docs/imgs/apis/tutorials/domain-removed.png and /dev/null differ diff --git a/docs/imgs/apis/tutorials/feature-added-to-model.png b/docs/imgs/apis/tutorials/feature-added-to-model.png deleted file mode 100644 index 311506e4b2783..0000000000000 Binary files a/docs/imgs/apis/tutorials/feature-added-to-model.png and /dev/null differ diff --git a/docs/imgs/apis/tutorials/feature-table-created.png b/docs/imgs/apis/tutorials/feature-table-created.png deleted file mode 100644 index 0541cbe572435..0000000000000 Binary files a/docs/imgs/apis/tutorials/feature-table-created.png and /dev/null differ diff --git a/docs/imgs/apis/tutorials/group-upserted.png b/docs/imgs/apis/tutorials/group-upserted.png deleted file mode 100644 index 5283f6273f02a..0000000000000 Binary files a/docs/imgs/apis/tutorials/group-upserted.png and /dev/null differ diff --git a/docs/imgs/apis/tutorials/lineage-added.png b/docs/imgs/apis/tutorials/lineage-added.png deleted file mode 100644 index b381498bad5ac..0000000000000 Binary files a/docs/imgs/apis/tutorials/lineage-added.png and /dev/null differ diff --git a/docs/imgs/apis/tutorials/model-group-added-to-model.png b/docs/imgs/apis/tutorials/model-group-added-to-model.png deleted file mode 100644 index 360b7fbb2d922..0000000000000 Binary files a/docs/imgs/apis/tutorials/model-group-added-to-model.png and /dev/null differ diff --git a/docs/imgs/apis/tutorials/model-group-created.png b/docs/imgs/apis/tutorials/model-group-created.png deleted file mode 100644 index 2e0fdcea4803f..0000000000000 Binary files a/docs/imgs/apis/tutorials/model-group-created.png and /dev/null differ diff --git a/docs/imgs/apis/tutorials/owner-added.png b/docs/imgs/apis/tutorials/owner-added.png deleted file mode 100644 index 6508c231cfb4b..0000000000000 Binary files a/docs/imgs/apis/tutorials/owner-added.png and /dev/null differ diff --git a/docs/imgs/apis/tutorials/owner-removed.png b/docs/imgs/apis/tutorials/owner-removed.png deleted file mode 100644 index a7b6567888caf..0000000000000 Binary files a/docs/imgs/apis/tutorials/owner-removed.png and /dev/null differ diff --git a/docs/imgs/apis/tutorials/sample-ingestion.png b/docs/imgs/apis/tutorials/sample-ingestion.png deleted file mode 100644 index 40aa046904841..0000000000000 Binary files a/docs/imgs/apis/tutorials/sample-ingestion.png and /dev/null differ diff --git a/docs/imgs/apis/tutorials/tag-added.png b/docs/imgs/apis/tutorials/tag-added.png deleted file mode 100644 index fd99a04f6cceb..0000000000000 Binary files a/docs/imgs/apis/tutorials/tag-added.png and /dev/null differ diff --git a/docs/imgs/apis/tutorials/tag-created.png b/docs/imgs/apis/tutorials/tag-created.png deleted file mode 100644 index 99e3fea8a14e1..0000000000000 Binary files a/docs/imgs/apis/tutorials/tag-created.png and /dev/null differ diff --git a/docs/imgs/apis/tutorials/tag-removed.png b/docs/imgs/apis/tutorials/tag-removed.png deleted file mode 100644 index 31a267549843e..0000000000000 Binary files a/docs/imgs/apis/tutorials/tag-removed.png and /dev/null differ diff --git a/docs/imgs/apis/tutorials/term-added.png b/docs/imgs/apis/tutorials/term-added.png deleted file mode 100644 index 62e285a92e7af..0000000000000 Binary files a/docs/imgs/apis/tutorials/term-added.png and /dev/null differ diff --git a/docs/imgs/apis/tutorials/term-created.png b/docs/imgs/apis/tutorials/term-created.png deleted file mode 100644 index deff0179b155e..0000000000000 Binary files a/docs/imgs/apis/tutorials/term-created.png and /dev/null differ diff --git a/docs/imgs/apis/tutorials/term-removed.png b/docs/imgs/apis/tutorials/term-removed.png deleted file mode 100644 index dbf9f35f09339..0000000000000 Binary files a/docs/imgs/apis/tutorials/term-removed.png and /dev/null differ diff --git a/docs/imgs/apis/tutorials/user-upserted.png b/docs/imgs/apis/tutorials/user-upserted.png deleted file mode 100644 index 38c5bbb9ad828..0000000000000 Binary files a/docs/imgs/apis/tutorials/user-upserted.png and /dev/null differ diff --git a/docs/imgs/aws/aws-elasticsearch.png b/docs/imgs/aws/aws-elasticsearch.png deleted file mode 100644 index e16d5eee26fd8..0000000000000 Binary files a/docs/imgs/aws/aws-elasticsearch.png and /dev/null differ diff --git a/docs/imgs/aws/aws-msk.png b/docs/imgs/aws/aws-msk.png deleted file mode 100644 index 96a3173747007..0000000000000 Binary files a/docs/imgs/aws/aws-msk.png and /dev/null differ diff --git a/docs/imgs/aws/aws-rds.png b/docs/imgs/aws/aws-rds.png deleted file mode 100644 index ab329952c7756..0000000000000 Binary files a/docs/imgs/aws/aws-rds.png and /dev/null differ diff --git a/docs/imgs/browse-domains.png b/docs/imgs/browse-domains.png deleted file mode 100644 index 41444470517d2..0000000000000 Binary files a/docs/imgs/browse-domains.png and /dev/null differ diff --git a/docs/imgs/cancelled-ingestion.png b/docs/imgs/cancelled-ingestion.png deleted file mode 100644 index 0c4af7b66a8ff..0000000000000 Binary files a/docs/imgs/cancelled-ingestion.png and /dev/null differ diff --git a/docs/imgs/confluent-cloud-config-2.png b/docs/imgs/confluent-cloud-config-2.png deleted file mode 100644 index 543101154f42c..0000000000000 Binary files a/docs/imgs/confluent-cloud-config-2.png and /dev/null differ diff --git a/docs/imgs/confluent-cloud-config.png b/docs/imgs/confluent-cloud-config.png deleted file mode 100644 index a2490eab5c6a7..0000000000000 Binary files a/docs/imgs/confluent-cloud-config.png and /dev/null differ diff --git a/docs/imgs/confluent-create-topic.png b/docs/imgs/confluent-create-topic.png deleted file mode 100644 index 1972bb3770388..0000000000000 Binary files a/docs/imgs/confluent-create-topic.png and /dev/null differ diff --git a/docs/imgs/create-domain.png b/docs/imgs/create-domain.png deleted file mode 100644 index 1db2090fca6b8..0000000000000 Binary files a/docs/imgs/create-domain.png and /dev/null differ diff --git a/docs/imgs/create-new-ingestion-source-button.png b/docs/imgs/create-new-ingestion-source-button.png deleted file mode 100644 index c425f0837c51d..0000000000000 Binary files a/docs/imgs/create-new-ingestion-source-button.png and /dev/null differ diff --git a/docs/imgs/create-secret.png b/docs/imgs/create-secret.png deleted file mode 100644 index a0cc63e3b4892..0000000000000 Binary files a/docs/imgs/create-secret.png and /dev/null differ diff --git a/docs/imgs/custom-ingestion-cli-version.png b/docs/imgs/custom-ingestion-cli-version.png deleted file mode 100644 index 43d4736684abb..0000000000000 Binary files a/docs/imgs/custom-ingestion-cli-version.png and /dev/null differ diff --git a/docs/imgs/datahub-architecture.png b/docs/imgs/datahub-architecture.png deleted file mode 100644 index 236f939f74198..0000000000000 Binary files a/docs/imgs/datahub-architecture.png and /dev/null differ diff --git a/docs/imgs/datahub-architecture.svg b/docs/imgs/datahub-architecture.svg deleted file mode 100644 index 842194a5e377c..0000000000000 --- a/docs/imgs/datahub-architecture.svg +++ /dev/null @@ -1 +0,0 @@ - \ No newline at end of file diff --git a/docs/imgs/datahub-components.png b/docs/imgs/datahub-components.png deleted file mode 100644 index 8b7d0e5330275..0000000000000 Binary files a/docs/imgs/datahub-components.png and /dev/null differ diff --git a/docs/imgs/datahub-logo-color-mark.svg b/docs/imgs/datahub-logo-color-mark.svg deleted file mode 100644 index a984092952bae..0000000000000 --- a/docs/imgs/datahub-logo-color-mark.svg +++ /dev/null @@ -1 +0,0 @@ - \ No newline at end of file diff --git a/docs/imgs/datahub-metadata-ingestion-framework.png b/docs/imgs/datahub-metadata-ingestion-framework.png deleted file mode 100644 index 1319329710906..0000000000000 Binary files a/docs/imgs/datahub-metadata-ingestion-framework.png and /dev/null differ diff --git a/docs/imgs/datahub-metadata-model.png b/docs/imgs/datahub-metadata-model.png deleted file mode 100644 index 59449cd0d4ef5..0000000000000 Binary files a/docs/imgs/datahub-metadata-model.png and /dev/null differ diff --git a/docs/imgs/datahub-sequence-diagram.png b/docs/imgs/datahub-sequence-diagram.png deleted file mode 100644 index b5a8f8a9c25ce..0000000000000 Binary files a/docs/imgs/datahub-sequence-diagram.png and /dev/null differ diff --git a/docs/imgs/datahub-serving.png b/docs/imgs/datahub-serving.png deleted file mode 100644 index 67a2f8eb3f085..0000000000000 Binary files a/docs/imgs/datahub-serving.png and /dev/null differ diff --git a/docs/imgs/development/intellij-remote-debug.png b/docs/imgs/development/intellij-remote-debug.png deleted file mode 100644 index 32a41a75d1dc3..0000000000000 Binary files a/docs/imgs/development/intellij-remote-debug.png and /dev/null differ diff --git a/docs/imgs/domain-entities.png b/docs/imgs/domain-entities.png deleted file mode 100644 index 5766d051fa209..0000000000000 Binary files a/docs/imgs/domain-entities.png and /dev/null differ diff --git a/docs/imgs/domains-tab.png b/docs/imgs/domains-tab.png deleted file mode 100644 index 20be5b103fdca..0000000000000 Binary files a/docs/imgs/domains-tab.png and /dev/null differ diff --git a/docs/imgs/entity-registry-diagram.png b/docs/imgs/entity-registry-diagram.png deleted file mode 100644 index 08cb5edd8e13f..0000000000000 Binary files a/docs/imgs/entity-registry-diagram.png and /dev/null differ diff --git a/docs/imgs/entity.png b/docs/imgs/entity.png deleted file mode 100644 index cfe9eb38b2921..0000000000000 Binary files a/docs/imgs/entity.png and /dev/null differ diff --git a/docs/imgs/example-mysql-recipe.png b/docs/imgs/example-mysql-recipe.png deleted file mode 100644 index 9cb2cbb169a56..0000000000000 Binary files a/docs/imgs/example-mysql-recipe.png and /dev/null differ diff --git a/docs/imgs/failed-ingestion.png b/docs/imgs/failed-ingestion.png deleted file mode 100644 index 4f9de8eb002d2..0000000000000 Binary files a/docs/imgs/failed-ingestion.png and /dev/null differ diff --git a/docs/imgs/feature-create-new-tag.gif b/docs/imgs/feature-create-new-tag.gif deleted file mode 100644 index 57b8ad852dd5b..0000000000000 Binary files a/docs/imgs/feature-create-new-tag.gif and /dev/null differ diff --git a/docs/imgs/feature-datahub-analytics.png b/docs/imgs/feature-datahub-analytics.png deleted file mode 100644 index 7fe66b84682f9..0000000000000 Binary files a/docs/imgs/feature-datahub-analytics.png and /dev/null differ diff --git a/docs/imgs/feature-rich-documentation.gif b/docs/imgs/feature-rich-documentation.gif deleted file mode 100644 index 48ad795670022..0000000000000 Binary files a/docs/imgs/feature-rich-documentation.gif and /dev/null differ diff --git a/docs/imgs/feature-tag-browse.gif b/docs/imgs/feature-tag-browse.gif deleted file mode 100644 index e70a30db7d3ba..0000000000000 Binary files a/docs/imgs/feature-tag-browse.gif and /dev/null differ diff --git a/docs/imgs/feature-validation-timeseries.png b/docs/imgs/feature-validation-timeseries.png deleted file mode 100644 index 28ce1daec5f32..0000000000000 Binary files a/docs/imgs/feature-validation-timeseries.png and /dev/null differ diff --git a/docs/imgs/feature-view-entitiy-details-via-lineage-vis.gif b/docs/imgs/feature-view-entitiy-details-via-lineage-vis.gif deleted file mode 100644 index aad77df373574..0000000000000 Binary files a/docs/imgs/feature-view-entitiy-details-via-lineage-vis.gif and /dev/null differ diff --git a/docs/imgs/gcp/ingress1.png b/docs/imgs/gcp/ingress1.png deleted file mode 100644 index 4cb49834af5b6..0000000000000 Binary files a/docs/imgs/gcp/ingress1.png and /dev/null differ diff --git a/docs/imgs/gcp/ingress2.png b/docs/imgs/gcp/ingress2.png deleted file mode 100644 index cdf2446b0e923..0000000000000 Binary files a/docs/imgs/gcp/ingress2.png and /dev/null differ diff --git a/docs/imgs/gcp/ingress3.png b/docs/imgs/gcp/ingress3.png deleted file mode 100644 index cc3745ad97f5b..0000000000000 Binary files a/docs/imgs/gcp/ingress3.png and /dev/null differ diff --git a/docs/imgs/gcp/ingress_final.png b/docs/imgs/gcp/ingress_final.png deleted file mode 100644 index a30ca744c49f7..0000000000000 Binary files a/docs/imgs/gcp/ingress_final.png and /dev/null differ diff --git a/docs/imgs/gcp/ingress_ready.png b/docs/imgs/gcp/ingress_ready.png deleted file mode 100644 index d14016e420fd3..0000000000000 Binary files a/docs/imgs/gcp/ingress_ready.png and /dev/null differ diff --git a/docs/imgs/gcp/services_ingress.png b/docs/imgs/gcp/services_ingress.png deleted file mode 100644 index 1d9ff2b313715..0000000000000 Binary files a/docs/imgs/gcp/services_ingress.png and /dev/null differ diff --git a/docs/imgs/glossary/add-term-modal.png b/docs/imgs/glossary/add-term-modal.png deleted file mode 100644 index e32a9cb8d648c..0000000000000 Binary files a/docs/imgs/glossary/add-term-modal.png and /dev/null differ diff --git a/docs/imgs/glossary/add-term-to-entity.png b/docs/imgs/glossary/add-term-to-entity.png deleted file mode 100644 index 7487a68c0d755..0000000000000 Binary files a/docs/imgs/glossary/add-term-to-entity.png and /dev/null differ diff --git a/docs/imgs/glossary/create-from-node.png b/docs/imgs/glossary/create-from-node.png deleted file mode 100644 index 70638d083343c..0000000000000 Binary files a/docs/imgs/glossary/create-from-node.png and /dev/null differ diff --git a/docs/imgs/glossary/create-modal.png b/docs/imgs/glossary/create-modal.png deleted file mode 100644 index e84fb5a36e2d4..0000000000000 Binary files a/docs/imgs/glossary/create-modal.png and /dev/null differ diff --git a/docs/imgs/glossary/delete-button.png b/docs/imgs/glossary/delete-button.png deleted file mode 100644 index 3e0cc2a5b0a54..0000000000000 Binary files a/docs/imgs/glossary/delete-button.png and /dev/null differ diff --git a/docs/imgs/glossary/edit-term.png b/docs/imgs/glossary/edit-term.png deleted file mode 100644 index 62b0e425c8c4f..0000000000000 Binary files a/docs/imgs/glossary/edit-term.png and /dev/null differ diff --git a/docs/imgs/glossary/glossary-button.png b/docs/imgs/glossary/glossary-button.png deleted file mode 100644 index e4b8fd2393587..0000000000000 Binary files a/docs/imgs/glossary/glossary-button.png and /dev/null differ diff --git a/docs/imgs/glossary/move-term-button.png b/docs/imgs/glossary/move-term-button.png deleted file mode 100644 index df03c820340ef..0000000000000 Binary files a/docs/imgs/glossary/move-term-button.png and /dev/null differ diff --git a/docs/imgs/glossary/move-term-modal.png b/docs/imgs/glossary/move-term-modal.png deleted file mode 100644 index 0fda501911b2b..0000000000000 Binary files a/docs/imgs/glossary/move-term-modal.png and /dev/null differ diff --git a/docs/imgs/glossary/root-glossary-create.png b/docs/imgs/glossary/root-glossary-create.png deleted file mode 100644 index c91f397eb6213..0000000000000 Binary files a/docs/imgs/glossary/root-glossary-create.png and /dev/null differ diff --git a/docs/imgs/glossary/root-glossary.png b/docs/imgs/glossary/root-glossary.png deleted file mode 100644 index 1296c16b0dc3d..0000000000000 Binary files a/docs/imgs/glossary/root-glossary.png and /dev/null differ diff --git a/docs/imgs/ingestion-architecture.png b/docs/imgs/ingestion-architecture.png deleted file mode 100644 index fc7bc74acacfa..0000000000000 Binary files a/docs/imgs/ingestion-architecture.png and /dev/null differ diff --git a/docs/imgs/ingestion-logs.png b/docs/imgs/ingestion-logs.png deleted file mode 100644 index 42211be7379d6..0000000000000 Binary files a/docs/imgs/ingestion-logs.png and /dev/null differ diff --git a/docs/imgs/ingestion-privileges.png b/docs/imgs/ingestion-privileges.png deleted file mode 100644 index 8e23868309676..0000000000000 Binary files a/docs/imgs/ingestion-privileges.png and /dev/null differ diff --git a/docs/imgs/ingestion-tab.png b/docs/imgs/ingestion-tab.png deleted file mode 100644 index 046068c63bdb7..0000000000000 Binary files a/docs/imgs/ingestion-tab.png and /dev/null differ diff --git a/docs/imgs/ingestion-with-token.png b/docs/imgs/ingestion-with-token.png deleted file mode 100644 index 5e1a2cce036f7..0000000000000 Binary files a/docs/imgs/ingestion-with-token.png and /dev/null differ diff --git a/docs/imgs/invite-users-button.png b/docs/imgs/invite-users-button.png deleted file mode 100644 index a5d07a1c1e7e7..0000000000000 Binary files a/docs/imgs/invite-users-button.png and /dev/null differ diff --git a/docs/imgs/invite-users-popup.png b/docs/imgs/invite-users-popup.png deleted file mode 100644 index 621b1521eae75..0000000000000 Binary files a/docs/imgs/invite-users-popup.png and /dev/null differ diff --git a/docs/imgs/lineage.png b/docs/imgs/lineage.png deleted file mode 100644 index 7488c1e04c31b..0000000000000 Binary files a/docs/imgs/lineage.png and /dev/null differ diff --git a/docs/imgs/list-domains.png b/docs/imgs/list-domains.png deleted file mode 100644 index 98a28130f8c99..0000000000000 Binary files a/docs/imgs/list-domains.png and /dev/null differ diff --git a/docs/imgs/locust-example.png b/docs/imgs/locust-example.png deleted file mode 100644 index bbae3e0ca19d0..0000000000000 Binary files a/docs/imgs/locust-example.png and /dev/null differ diff --git a/docs/imgs/metadata-model-chart.png b/docs/imgs/metadata-model-chart.png deleted file mode 100644 index 2fb7483654906..0000000000000 Binary files a/docs/imgs/metadata-model-chart.png and /dev/null differ diff --git a/docs/imgs/metadata-model-to-fork-or-not-to.png b/docs/imgs/metadata-model-to-fork-or-not-to.png deleted file mode 100644 index f9d89d555196d..0000000000000 Binary files a/docs/imgs/metadata-model-to-fork-or-not-to.png and /dev/null differ diff --git a/docs/imgs/metadata-modeling.png b/docs/imgs/metadata-modeling.png deleted file mode 100644 index cbad7613e04e4..0000000000000 Binary files a/docs/imgs/metadata-modeling.png and /dev/null differ diff --git a/docs/imgs/metadata-service-auth.png b/docs/imgs/metadata-service-auth.png deleted file mode 100644 index 15a3ac51876c2..0000000000000 Binary files a/docs/imgs/metadata-service-auth.png and /dev/null differ diff --git a/docs/imgs/metadata-serving.png b/docs/imgs/metadata-serving.png deleted file mode 100644 index 54b928a0cff52..0000000000000 Binary files a/docs/imgs/metadata-serving.png and /dev/null differ diff --git a/docs/imgs/metadata.png b/docs/imgs/metadata.png deleted file mode 100644 index 45bb0cdce12e9..0000000000000 Binary files a/docs/imgs/metadata.png and /dev/null differ diff --git a/docs/imgs/name-ingestion-source.png b/docs/imgs/name-ingestion-source.png deleted file mode 100644 index bde1208248473..0000000000000 Binary files a/docs/imgs/name-ingestion-source.png and /dev/null differ diff --git a/docs/imgs/no-code-after.png b/docs/imgs/no-code-after.png deleted file mode 100644 index c0eee88625ace..0000000000000 Binary files a/docs/imgs/no-code-after.png and /dev/null differ diff --git a/docs/imgs/no-code-before.png b/docs/imgs/no-code-before.png deleted file mode 100644 index 50315578b1804..0000000000000 Binary files a/docs/imgs/no-code-before.png and /dev/null differ diff --git a/docs/imgs/platform-instances-for-ingestion.png b/docs/imgs/platform-instances-for-ingestion.png deleted file mode 100644 index 740249a805fb8..0000000000000 Binary files a/docs/imgs/platform-instances-for-ingestion.png and /dev/null differ diff --git a/docs/imgs/quickstart-ingestion-config.png b/docs/imgs/quickstart-ingestion-config.png deleted file mode 100644 index de51777ccddc3..0000000000000 Binary files a/docs/imgs/quickstart-ingestion-config.png and /dev/null differ diff --git a/docs/imgs/reset-credentials-screen.png b/docs/imgs/reset-credentials-screen.png deleted file mode 100644 index 4b680837b77ab..0000000000000 Binary files a/docs/imgs/reset-credentials-screen.png and /dev/null differ diff --git a/docs/imgs/reset-user-password-button.png b/docs/imgs/reset-user-password-button.png deleted file mode 100644 index 5b1f3ee153d07..0000000000000 Binary files a/docs/imgs/reset-user-password-button.png and /dev/null differ diff --git a/docs/imgs/reset-user-password-popup.png b/docs/imgs/reset-user-password-popup.png deleted file mode 100644 index ac2456dde4d4d..0000000000000 Binary files a/docs/imgs/reset-user-password-popup.png and /dev/null differ diff --git a/docs/imgs/running-ingestion.png b/docs/imgs/running-ingestion.png deleted file mode 100644 index a03fb444a029e..0000000000000 Binary files a/docs/imgs/running-ingestion.png and /dev/null differ diff --git a/docs/imgs/s3-ingestion/10_outputs.png b/docs/imgs/s3-ingestion/10_outputs.png deleted file mode 100644 index e0d1ed3376ade..0000000000000 Binary files a/docs/imgs/s3-ingestion/10_outputs.png and /dev/null differ diff --git a/docs/imgs/s3-ingestion/1_crawler-info.png b/docs/imgs/s3-ingestion/1_crawler-info.png deleted file mode 100644 index 1288247392047..0000000000000 Binary files a/docs/imgs/s3-ingestion/1_crawler-info.png and /dev/null differ diff --git a/docs/imgs/s3-ingestion/2_crawler-type.png b/docs/imgs/s3-ingestion/2_crawler-type.png deleted file mode 100644 index 4898438417913..0000000000000 Binary files a/docs/imgs/s3-ingestion/2_crawler-type.png and /dev/null differ diff --git a/docs/imgs/s3-ingestion/3_data-store.png b/docs/imgs/s3-ingestion/3_data-store.png deleted file mode 100644 index d29e4b1be05d6..0000000000000 Binary files a/docs/imgs/s3-ingestion/3_data-store.png and /dev/null differ diff --git a/docs/imgs/s3-ingestion/4_data-store-2.png b/docs/imgs/s3-ingestion/4_data-store-2.png deleted file mode 100644 index c0a6f140bedb2..0000000000000 Binary files a/docs/imgs/s3-ingestion/4_data-store-2.png and /dev/null differ diff --git a/docs/imgs/s3-ingestion/5_iam.png b/docs/imgs/s3-ingestion/5_iam.png deleted file mode 100644 index 73a631cb74f56..0000000000000 Binary files a/docs/imgs/s3-ingestion/5_iam.png and /dev/null differ diff --git a/docs/imgs/s3-ingestion/6_schedule.png b/docs/imgs/s3-ingestion/6_schedule.png deleted file mode 100644 index c5df59348fbc6..0000000000000 Binary files a/docs/imgs/s3-ingestion/6_schedule.png and /dev/null differ diff --git a/docs/imgs/s3-ingestion/7_output.png b/docs/imgs/s3-ingestion/7_output.png deleted file mode 100644 index 6201fa40bcfb3..0000000000000 Binary files a/docs/imgs/s3-ingestion/7_output.png and /dev/null differ diff --git a/docs/imgs/s3-ingestion/8_review.png b/docs/imgs/s3-ingestion/8_review.png deleted file mode 100644 index 2d27e79c2128b..0000000000000 Binary files a/docs/imgs/s3-ingestion/8_review.png and /dev/null differ diff --git a/docs/imgs/s3-ingestion/9_run.png b/docs/imgs/s3-ingestion/9_run.png deleted file mode 100644 index 2b0644f6ad038..0000000000000 Binary files a/docs/imgs/s3-ingestion/9_run.png and /dev/null differ diff --git a/docs/imgs/schedule-ingestion.png b/docs/imgs/schedule-ingestion.png deleted file mode 100644 index 0e6ec8e268c32..0000000000000 Binary files a/docs/imgs/schedule-ingestion.png and /dev/null differ diff --git a/docs/imgs/schema-blame-blame-activated.png b/docs/imgs/schema-blame-blame-activated.png deleted file mode 100644 index 363466c39aedf..0000000000000 Binary files a/docs/imgs/schema-blame-blame-activated.png and /dev/null differ diff --git a/docs/imgs/schema-history-audit-activated.png b/docs/imgs/schema-history-audit-activated.png deleted file mode 100644 index f59676b9b8a8f..0000000000000 Binary files a/docs/imgs/schema-history-audit-activated.png and /dev/null differ diff --git a/docs/imgs/schema-history-latest-version.png b/docs/imgs/schema-history-latest-version.png deleted file mode 100644 index 0a54df4d520d5..0000000000000 Binary files a/docs/imgs/schema-history-latest-version.png and /dev/null differ diff --git a/docs/imgs/schema-history-older-version.png b/docs/imgs/schema-history-older-version.png deleted file mode 100644 index 8d295f176104f..0000000000000 Binary files a/docs/imgs/schema-history-older-version.png and /dev/null differ diff --git a/docs/imgs/search-by-domain.png b/docs/imgs/search-by-domain.png deleted file mode 100644 index 4b92e58959187..0000000000000 Binary files a/docs/imgs/search-by-domain.png and /dev/null differ diff --git a/docs/imgs/search-domain.png b/docs/imgs/search-domain.png deleted file mode 100644 index b1359e07d5fc2..0000000000000 Binary files a/docs/imgs/search-domain.png and /dev/null differ diff --git a/docs/imgs/search-tag.png b/docs/imgs/search-tag.png deleted file mode 100644 index cf4b6b629d1e2..0000000000000 Binary files a/docs/imgs/search-tag.png and /dev/null differ diff --git a/docs/imgs/select-platform-template.png b/docs/imgs/select-platform-template.png deleted file mode 100644 index 4f78e2b7309ed..0000000000000 Binary files a/docs/imgs/select-platform-template.png and /dev/null differ diff --git a/docs/imgs/set-domain-id.png b/docs/imgs/set-domain-id.png deleted file mode 100644 index 3e1dde4ae51ee..0000000000000 Binary files a/docs/imgs/set-domain-id.png and /dev/null differ diff --git a/docs/imgs/set-domain.png b/docs/imgs/set-domain.png deleted file mode 100644 index 1c4460e747835..0000000000000 Binary files a/docs/imgs/set-domain.png and /dev/null differ diff --git a/docs/imgs/successful-ingestion.png b/docs/imgs/successful-ingestion.png deleted file mode 100644 index fa8dbdff7501e..0000000000000 Binary files a/docs/imgs/successful-ingestion.png and /dev/null differ diff --git a/docs/imgs/timeline/dropdown-apis.png b/docs/imgs/timeline/dropdown-apis.png deleted file mode 100644 index f7aba08bbc061..0000000000000 Binary files a/docs/imgs/timeline/dropdown-apis.png and /dev/null differ diff --git a/docs/imgs/timeline/swagger-ui.png b/docs/imgs/timeline/swagger-ui.png deleted file mode 100644 index e52a57e8ca670..0000000000000 Binary files a/docs/imgs/timeline/swagger-ui.png and /dev/null differ diff --git a/docs/imgs/timeline/timeline-conceptually.png b/docs/imgs/timeline/timeline-conceptually.png deleted file mode 100644 index 70bd843bf8aed..0000000000000 Binary files a/docs/imgs/timeline/timeline-conceptually.png and /dev/null differ diff --git a/docs/imgs/user-sign-up-screen.png b/docs/imgs/user-sign-up-screen.png deleted file mode 100644 index 88c2589203bd1..0000000000000 Binary files a/docs/imgs/user-sign-up-screen.png and /dev/null differ diff --git a/docs/links.md b/docs/links.md index f175262b9b5d9..45ba391e557cd 100644 --- a/docs/links.md +++ b/docs/links.md @@ -39,7 +39,7 @@ * [Creating Notebook-based Dynamic Dashboards](https://towardsdatascience.com/creating-notebook-based-dynamic-dashboards-91f936adc6f3) ## Talks & Presentations -* [DataHub: Powering LinkedIn's Metadata](demo/DataHub_-_Powering_LinkedIn_Metadata.pdf) @ [Budapest Data Forum 2020](https://budapestdata.hu/2020/en/) +* [DataHub: Powering LinkedIn's Metadata](https://github.com/acryldata/static-assets-test/raw/master/imgs/demo/DataHub_-_Powering_LinkedIn_Metadata.pdf) @ [Budapest Data Forum 2020](https://budapestdata.hu/2020/en/) * [Taming the Data Beast Using DataHub](https://www.youtube.com/watch?v=bo4OhiPro7Y) @ [Data Engineering Melbourne Meetup November 2020](https://www.meetup.com/Data-Engineering-Melbourne/events/kgnvlrybcpbjc/) * [Metadata Management And Integration At LinkedIn With DataHub](https://www.dataengineeringpodcast.com/datahub-metadata-management-episode-147/) @ [Data Engineering Podcast](https://www.dataengineeringpodcast.com) * [The evolution of metadata: LinkedIn’s story](https://speakerdeck.com/shirshanka/the-evolution-of-metadata-linkedins-journey-strata-nyc-2019) @ [Strata Data Conference 2019](https://conferences.oreilly.com/strata/strata-ny-2019.html) diff --git a/docs/managed-datahub/chrome-extension.md b/docs/managed-datahub/chrome-extension.md index a614327c7fd29..c6840f4e8e221 100644 --- a/docs/managed-datahub/chrome-extension.md +++ b/docs/managed-datahub/chrome-extension.md @@ -10,7 +10,11 @@ import FeatureAvailability from '@site/src/components/FeatureAvailability'; In order to use the Acryl DataHub Chrome extension, you need to download it onto your browser from the Chrome web store [here](https://chrome.google.com/webstore/detail/datahub-chrome-extension/aoenebhmfokhglijmoacfjcnebdpchfj). -![](imgs/saas/chrome-store-extension-screenshot.png) + +

+ +

+ Simply click "Add to Chrome" then "Add extension" on the ensuing popup. @@ -20,11 +24,19 @@ Once you have your extension installed, you'll need to configure it to work with 1. Click the extension button on the right of your browser's address bar to view all of your installed extensions. Click on the newly installed DataHub extension. -![](imgs/saas/extension_open_popup.png) + +

+ +

+ 2. Fill in your DataHub domain and click "Continue" in the extension popup that appears. -![](imgs/saas/extension_enter_domain.png) + +

+ +

+ If your organization uses standard SaaS domains for Looker, you should be ready to go! @@ -34,11 +46,19 @@ Some organizations have custom SaaS domains for Looker and some Acryl DataHub de 1. Click on the extension button and select your DataHub extension to open the popup again. Now click the settings icon in order to open the configurations page. -![](imgs/saas/extension_open_options_page.png) + +

+ +

+ 2. Fill out any and save custom configurations you have in the **TOOL CONFIGURATIONS** section. Here you can configure a custom domain, a Platform Instance associated with that domain, and the Environment set on your DataHub assets. If you don't have a custom domain but do have a custom Platform Instance or Environment, feel free to leave the field domain empty. -![](imgs/saas/extension_custom_configs.png) + +

+ +

+ ## Using the Extension @@ -52,7 +72,11 @@ Once you have everything configured on your extension, it's time to use it! 4. Click the Acryl DataHub extension button on the bottom right of your page to open a drawer where you can now see additional information about this asset right from your DataHub instance. -![](imgs/saas/extension_view_in_looker.png) + +

+ +

+ ## Advanced: Self-Hosted DataHub diff --git a/docs/managed-datahub/datahub-api/graphql-api/getting-started.md b/docs/managed-datahub/datahub-api/graphql-api/getting-started.md index 3c57b0a21d96e..57d46f05c4e0c 100644 --- a/docs/managed-datahub/datahub-api/graphql-api/getting-started.md +++ b/docs/managed-datahub/datahub-api/graphql-api/getting-started.md @@ -10,7 +10,11 @@ For a full reference to the Queries & Mutations available for consumption, check ### Connecting to the API -![](../../imgs/saas/image-(3).png) + +

+ +

+ When you generate the token you will see an example of `curl` command which you can use to connect to the GraphQL API. diff --git a/docs/managed-datahub/datahub-api/graphql-api/incidents-api-beta.md b/docs/managed-datahub/datahub-api/graphql-api/incidents-api-beta.md index 89bacb2009e49..bfd8e8f2dae1b 100644 --- a/docs/managed-datahub/datahub-api/graphql-api/incidents-api-beta.md +++ b/docs/managed-datahub/datahub-api/graphql-api/incidents-api-beta.md @@ -404,7 +404,11 @@ You can configure Acryl to send slack notifications to a specific channel when i These notifications are also able to tag the immediate asset's owners, along with the owners of downstream assets consuming it. -![](../../imgs/saas/Screen-Shot-2022-03-22-at-6.46.41-PM.png) + +

+ +

+ To do so, simply follow the [Slack Integration Guide](docs/managed-datahub/saas-slack-setup.md) and contact your Acryl customer success team to enable the feature! diff --git a/docs/managed-datahub/imgs/saas/DataHub-Architecture.png b/docs/managed-datahub/imgs/saas/DataHub-Architecture.png deleted file mode 100644 index 95b3ab0b06ad6..0000000000000 Binary files a/docs/managed-datahub/imgs/saas/DataHub-Architecture.png and /dev/null differ diff --git a/docs/managed-datahub/imgs/saas/Screen-Shot-2022-01-13-at-7.45.56-PM.png b/docs/managed-datahub/imgs/saas/Screen-Shot-2022-01-13-at-7.45.56-PM.png deleted file mode 100644 index 721989a6c37e1..0000000000000 Binary files a/docs/managed-datahub/imgs/saas/Screen-Shot-2022-01-13-at-7.45.56-PM.png and /dev/null differ diff --git a/docs/managed-datahub/imgs/saas/Screen-Shot-2022-01-24-at-4.35.17-PM.png b/docs/managed-datahub/imgs/saas/Screen-Shot-2022-01-24-at-4.35.17-PM.png deleted file mode 100644 index dffac92f257c7..0000000000000 Binary files a/docs/managed-datahub/imgs/saas/Screen-Shot-2022-01-24-at-4.35.17-PM.png and /dev/null differ diff --git a/docs/managed-datahub/imgs/saas/Screen-Shot-2022-01-24-at-4.37.22-PM.png b/docs/managed-datahub/imgs/saas/Screen-Shot-2022-01-24-at-4.37.22-PM.png deleted file mode 100644 index ff0c29de1fbad..0000000000000 Binary files a/docs/managed-datahub/imgs/saas/Screen-Shot-2022-01-24-at-4.37.22-PM.png and /dev/null differ diff --git a/docs/managed-datahub/imgs/saas/Screen-Shot-2022-03-07-at-10.23.31-AM.png b/docs/managed-datahub/imgs/saas/Screen-Shot-2022-03-07-at-10.23.31-AM.png deleted file mode 100644 index 070bfd9f6b897..0000000000000 Binary files a/docs/managed-datahub/imgs/saas/Screen-Shot-2022-03-07-at-10.23.31-AM.png and /dev/null differ diff --git a/docs/managed-datahub/imgs/saas/Screen-Shot-2022-03-22-at-6.43.25-PM.png b/docs/managed-datahub/imgs/saas/Screen-Shot-2022-03-22-at-6.43.25-PM.png deleted file mode 100644 index b4bb4e2ba60ed..0000000000000 Binary files a/docs/managed-datahub/imgs/saas/Screen-Shot-2022-03-22-at-6.43.25-PM.png and /dev/null differ diff --git a/docs/managed-datahub/imgs/saas/Screen-Shot-2022-03-22-at-6.44.15-PM.png b/docs/managed-datahub/imgs/saas/Screen-Shot-2022-03-22-at-6.44.15-PM.png deleted file mode 100644 index b0397afd1b3a4..0000000000000 Binary files a/docs/managed-datahub/imgs/saas/Screen-Shot-2022-03-22-at-6.44.15-PM.png and /dev/null differ diff --git a/docs/managed-datahub/imgs/saas/Screen-Shot-2022-03-22-at-6.46.41-PM.png b/docs/managed-datahub/imgs/saas/Screen-Shot-2022-03-22-at-6.46.41-PM.png deleted file mode 100644 index 9258badb6f088..0000000000000 Binary files a/docs/managed-datahub/imgs/saas/Screen-Shot-2022-03-22-at-6.46.41-PM.png and /dev/null differ diff --git a/docs/managed-datahub/imgs/saas/Screen-Shot-2022-04-05-at-4.52.55-PM.png b/docs/managed-datahub/imgs/saas/Screen-Shot-2022-04-05-at-4.52.55-PM.png deleted file mode 100644 index 386b4cdcd9911..0000000000000 Binary files a/docs/managed-datahub/imgs/saas/Screen-Shot-2022-04-05-at-4.52.55-PM.png and /dev/null differ diff --git a/docs/managed-datahub/imgs/saas/Screen-Shot-2022-04-05-at-4.56.50-PM.png b/docs/managed-datahub/imgs/saas/Screen-Shot-2022-04-05-at-4.56.50-PM.png deleted file mode 100644 index a129f5eba4271..0000000000000 Binary files a/docs/managed-datahub/imgs/saas/Screen-Shot-2022-04-05-at-4.56.50-PM.png and /dev/null differ diff --git a/docs/managed-datahub/imgs/saas/Screen-Shot-2022-04-05-at-4.58.46-PM.png b/docs/managed-datahub/imgs/saas/Screen-Shot-2022-04-05-at-4.58.46-PM.png deleted file mode 100644 index 96ae48318a35a..0000000000000 Binary files a/docs/managed-datahub/imgs/saas/Screen-Shot-2022-04-05-at-4.58.46-PM.png and /dev/null differ diff --git a/docs/managed-datahub/imgs/saas/Screen-Shot-2022-04-05-at-5.01.16-PM.png b/docs/managed-datahub/imgs/saas/Screen-Shot-2022-04-05-at-5.01.16-PM.png deleted file mode 100644 index b6fd273389c90..0000000000000 Binary files a/docs/managed-datahub/imgs/saas/Screen-Shot-2022-04-05-at-5.01.16-PM.png and /dev/null differ diff --git a/docs/managed-datahub/imgs/saas/Screen-Shot-2022-04-05-at-5.03.36-PM.png b/docs/managed-datahub/imgs/saas/Screen-Shot-2022-04-05-at-5.03.36-PM.png deleted file mode 100644 index 0acd4e75bc6d2..0000000000000 Binary files a/docs/managed-datahub/imgs/saas/Screen-Shot-2022-04-05-at-5.03.36-PM.png and /dev/null differ diff --git a/docs/managed-datahub/imgs/saas/Screen-Shot-2022-04-13-at-2.34.24-PM.png b/docs/managed-datahub/imgs/saas/Screen-Shot-2022-04-13-at-2.34.24-PM.png deleted file mode 100644 index 364b9292cfaab..0000000000000 Binary files a/docs/managed-datahub/imgs/saas/Screen-Shot-2022-04-13-at-2.34.24-PM.png and /dev/null differ diff --git a/docs/managed-datahub/imgs/saas/Screen-Shot-2022-06-13-at-7.56.16-AM-(1).png b/docs/managed-datahub/imgs/saas/Screen-Shot-2022-06-13-at-7.56.16-AM-(1).png deleted file mode 100644 index 6a12dc545ec62..0000000000000 Binary files a/docs/managed-datahub/imgs/saas/Screen-Shot-2022-06-13-at-7.56.16-AM-(1).png and /dev/null differ diff --git a/docs/managed-datahub/imgs/saas/Screen-Shot-2022-06-13-at-7.56.16-AM.png b/docs/managed-datahub/imgs/saas/Screen-Shot-2022-06-13-at-7.56.16-AM.png deleted file mode 100644 index 6a12dc545ec62..0000000000000 Binary files a/docs/managed-datahub/imgs/saas/Screen-Shot-2022-06-13-at-7.56.16-AM.png and /dev/null differ diff --git a/docs/managed-datahub/imgs/saas/Screen-Shot-2022-06-13-at-8.02.55-AM.png b/docs/managed-datahub/imgs/saas/Screen-Shot-2022-06-13-at-8.02.55-AM.png deleted file mode 100644 index 83645e00d724a..0000000000000 Binary files a/docs/managed-datahub/imgs/saas/Screen-Shot-2022-06-13-at-8.02.55-AM.png and /dev/null differ diff --git a/docs/managed-datahub/imgs/saas/Screen-Shot-2022-06-24-at-11.02.47-AM.png b/docs/managed-datahub/imgs/saas/Screen-Shot-2022-06-24-at-11.02.47-AM.png deleted file mode 100644 index a2f239ce847e0..0000000000000 Binary files a/docs/managed-datahub/imgs/saas/Screen-Shot-2022-06-24-at-11.02.47-AM.png and /dev/null differ diff --git a/docs/managed-datahub/imgs/saas/Screen-Shot-2022-06-24-at-12.59.38-PM.png b/docs/managed-datahub/imgs/saas/Screen-Shot-2022-06-24-at-12.59.38-PM.png deleted file mode 100644 index e31d4b089d929..0000000000000 Binary files a/docs/managed-datahub/imgs/saas/Screen-Shot-2022-06-24-at-12.59.38-PM.png and /dev/null differ diff --git a/docs/managed-datahub/imgs/saas/Screen-Shot-2022-08-22-at-11.21.42-AM.png b/docs/managed-datahub/imgs/saas/Screen-Shot-2022-08-22-at-11.21.42-AM.png deleted file mode 100644 index c003581c9d1b6..0000000000000 Binary files a/docs/managed-datahub/imgs/saas/Screen-Shot-2022-08-22-at-11.21.42-AM.png and /dev/null differ diff --git a/docs/managed-datahub/imgs/saas/Screen-Shot-2022-08-22-at-11.22.23-AM.png b/docs/managed-datahub/imgs/saas/Screen-Shot-2022-08-22-at-11.22.23-AM.png deleted file mode 100644 index 660dd121dd0a4..0000000000000 Binary files a/docs/managed-datahub/imgs/saas/Screen-Shot-2022-08-22-at-11.22.23-AM.png and /dev/null differ diff --git a/docs/managed-datahub/imgs/saas/Screen-Shot-2022-08-22-at-11.23.08-AM.png b/docs/managed-datahub/imgs/saas/Screen-Shot-2022-08-22-at-11.23.08-AM.png deleted file mode 100644 index 07e3c71dba262..0000000000000 Binary files a/docs/managed-datahub/imgs/saas/Screen-Shot-2022-08-22-at-11.23.08-AM.png and /dev/null differ diff --git a/docs/managed-datahub/imgs/saas/Screen-Shot-2022-08-22-at-11.47.57-AM.png b/docs/managed-datahub/imgs/saas/Screen-Shot-2022-08-22-at-11.47.57-AM.png deleted file mode 100644 index 579e7f62af708..0000000000000 Binary files a/docs/managed-datahub/imgs/saas/Screen-Shot-2022-08-22-at-11.47.57-AM.png and /dev/null differ diff --git a/docs/managed-datahub/imgs/saas/Screen-Shot-2022-08-29-at-6.07.25-PM-(1).png b/docs/managed-datahub/imgs/saas/Screen-Shot-2022-08-29-at-6.07.25-PM-(1).png deleted file mode 100644 index f85f4d5c79bfb..0000000000000 Binary files a/docs/managed-datahub/imgs/saas/Screen-Shot-2022-08-29-at-6.07.25-PM-(1).png and /dev/null differ diff --git a/docs/managed-datahub/imgs/saas/Screen-Shot-2022-08-29-at-6.07.25-PM.png b/docs/managed-datahub/imgs/saas/Screen-Shot-2022-08-29-at-6.07.25-PM.png deleted file mode 100644 index f85f4d5c79bfb..0000000000000 Binary files a/docs/managed-datahub/imgs/saas/Screen-Shot-2022-08-29-at-6.07.25-PM.png and /dev/null differ diff --git a/docs/managed-datahub/imgs/saas/Screen-Shot-2023-01-19-at-4.16.52-PM.png b/docs/managed-datahub/imgs/saas/Screen-Shot-2023-01-19-at-4.16.52-PM.png deleted file mode 100644 index cb8b7470cd957..0000000000000 Binary files a/docs/managed-datahub/imgs/saas/Screen-Shot-2023-01-19-at-4.16.52-PM.png and /dev/null differ diff --git a/docs/managed-datahub/imgs/saas/Screen-Shot-2023-01-19-at-4.23.32-PM.png b/docs/managed-datahub/imgs/saas/Screen-Shot-2023-01-19-at-4.23.32-PM.png deleted file mode 100644 index 1de51e33d87c2..0000000000000 Binary files a/docs/managed-datahub/imgs/saas/Screen-Shot-2023-01-19-at-4.23.32-PM.png and /dev/null differ diff --git a/docs/managed-datahub/imgs/saas/Screen-Shot-2023-01-19-at-5.12.47-PM.png b/docs/managed-datahub/imgs/saas/Screen-Shot-2023-01-19-at-5.12.47-PM.png deleted file mode 100644 index df687dabe345c..0000000000000 Binary files a/docs/managed-datahub/imgs/saas/Screen-Shot-2023-01-19-at-5.12.47-PM.png and /dev/null differ diff --git a/docs/managed-datahub/imgs/saas/Screen-Shot-2023-01-19-at-5.12.56-PM-(1).png b/docs/managed-datahub/imgs/saas/Screen-Shot-2023-01-19-at-5.12.56-PM-(1).png deleted file mode 100644 index a8d9ee37c7a55..0000000000000 Binary files a/docs/managed-datahub/imgs/saas/Screen-Shot-2023-01-19-at-5.12.56-PM-(1).png and /dev/null differ diff --git a/docs/managed-datahub/imgs/saas/Screen-Shot-2023-01-19-at-5.12.56-PM.png b/docs/managed-datahub/imgs/saas/Screen-Shot-2023-01-19-at-5.12.56-PM.png deleted file mode 100644 index a8d9ee37c7a55..0000000000000 Binary files a/docs/managed-datahub/imgs/saas/Screen-Shot-2023-01-19-at-5.12.56-PM.png and /dev/null differ diff --git a/docs/managed-datahub/imgs/saas/Untitled(1).png b/docs/managed-datahub/imgs/saas/Untitled(1).png deleted file mode 100644 index 87846e7897f6e..0000000000000 Binary files a/docs/managed-datahub/imgs/saas/Untitled(1).png and /dev/null differ diff --git a/docs/managed-datahub/imgs/saas/Untitled-(2)-(1).png b/docs/managed-datahub/imgs/saas/Untitled-(2)-(1).png deleted file mode 100644 index 7715bf4a51fbe..0000000000000 Binary files a/docs/managed-datahub/imgs/saas/Untitled-(2)-(1).png and /dev/null differ diff --git a/docs/managed-datahub/imgs/saas/Untitled-(2).png b/docs/managed-datahub/imgs/saas/Untitled-(2).png deleted file mode 100644 index a01a1af370442..0000000000000 Binary files a/docs/managed-datahub/imgs/saas/Untitled-(2).png and /dev/null differ diff --git a/docs/managed-datahub/imgs/saas/Untitled-(3).png b/docs/managed-datahub/imgs/saas/Untitled-(3).png deleted file mode 100644 index 02d84b326896c..0000000000000 Binary files a/docs/managed-datahub/imgs/saas/Untitled-(3).png and /dev/null differ diff --git a/docs/managed-datahub/imgs/saas/Untitled-(4).png b/docs/managed-datahub/imgs/saas/Untitled-(4).png deleted file mode 100644 index a01a1af370442..0000000000000 Binary files a/docs/managed-datahub/imgs/saas/Untitled-(4).png and /dev/null differ diff --git a/docs/managed-datahub/imgs/saas/Untitled.png b/docs/managed-datahub/imgs/saas/Untitled.png deleted file mode 100644 index a01a1af370442..0000000000000 Binary files a/docs/managed-datahub/imgs/saas/Untitled.png and /dev/null differ diff --git a/docs/managed-datahub/imgs/saas/chrome-store-extension-screenshot.png b/docs/managed-datahub/imgs/saas/chrome-store-extension-screenshot.png deleted file mode 100644 index e00a4d57f32dd..0000000000000 Binary files a/docs/managed-datahub/imgs/saas/chrome-store-extension-screenshot.png and /dev/null differ diff --git a/docs/managed-datahub/imgs/saas/extension_custom_configs.png b/docs/managed-datahub/imgs/saas/extension_custom_configs.png deleted file mode 100644 index b3d70dfac00ff..0000000000000 Binary files a/docs/managed-datahub/imgs/saas/extension_custom_configs.png and /dev/null differ diff --git a/docs/managed-datahub/imgs/saas/extension_developer_mode.png b/docs/managed-datahub/imgs/saas/extension_developer_mode.png deleted file mode 100644 index e740d15912e17..0000000000000 Binary files a/docs/managed-datahub/imgs/saas/extension_developer_mode.png and /dev/null differ diff --git a/docs/managed-datahub/imgs/saas/extension_enter_domain.png b/docs/managed-datahub/imgs/saas/extension_enter_domain.png deleted file mode 100644 index 3304fa168beaf..0000000000000 Binary files a/docs/managed-datahub/imgs/saas/extension_enter_domain.png and /dev/null differ diff --git a/docs/managed-datahub/imgs/saas/extension_load_unpacked.png b/docs/managed-datahub/imgs/saas/extension_load_unpacked.png deleted file mode 100644 index 8f56705cd9176..0000000000000 Binary files a/docs/managed-datahub/imgs/saas/extension_load_unpacked.png and /dev/null differ diff --git a/docs/managed-datahub/imgs/saas/extension_open_options_page.png b/docs/managed-datahub/imgs/saas/extension_open_options_page.png deleted file mode 100644 index c1366d5673b59..0000000000000 Binary files a/docs/managed-datahub/imgs/saas/extension_open_options_page.png and /dev/null differ diff --git a/docs/managed-datahub/imgs/saas/extension_open_popup.png b/docs/managed-datahub/imgs/saas/extension_open_popup.png deleted file mode 100644 index 216056b847fb5..0000000000000 Binary files a/docs/managed-datahub/imgs/saas/extension_open_popup.png and /dev/null differ diff --git a/docs/managed-datahub/imgs/saas/extension_view_in_looker.png b/docs/managed-datahub/imgs/saas/extension_view_in_looker.png deleted file mode 100644 index bf854b3e840f7..0000000000000 Binary files a/docs/managed-datahub/imgs/saas/extension_view_in_looker.png and /dev/null differ diff --git a/docs/managed-datahub/imgs/saas/home-(1).png b/docs/managed-datahub/imgs/saas/home-(1).png deleted file mode 100644 index 88cf2017dd7e7..0000000000000 Binary files a/docs/managed-datahub/imgs/saas/home-(1).png and /dev/null differ diff --git a/docs/managed-datahub/imgs/saas/home.png b/docs/managed-datahub/imgs/saas/home.png deleted file mode 100644 index 8ad63deec75c9..0000000000000 Binary files a/docs/managed-datahub/imgs/saas/home.png and /dev/null differ diff --git a/docs/managed-datahub/imgs/saas/image-(1).png b/docs/managed-datahub/imgs/saas/image-(1).png deleted file mode 100644 index c1a249125fcf7..0000000000000 Binary files a/docs/managed-datahub/imgs/saas/image-(1).png and /dev/null differ diff --git a/docs/managed-datahub/imgs/saas/image-(10).png b/docs/managed-datahub/imgs/saas/image-(10).png deleted file mode 100644 index a580fdc3d6730..0000000000000 Binary files a/docs/managed-datahub/imgs/saas/image-(10).png and /dev/null differ diff --git a/docs/managed-datahub/imgs/saas/image-(11).png b/docs/managed-datahub/imgs/saas/image-(11).png deleted file mode 100644 index ee95eb4384272..0000000000000 Binary files a/docs/managed-datahub/imgs/saas/image-(11).png and /dev/null differ diff --git a/docs/managed-datahub/imgs/saas/image-(12).png b/docs/managed-datahub/imgs/saas/image-(12).png deleted file mode 100644 index bbd8e6a66cf85..0000000000000 Binary files a/docs/managed-datahub/imgs/saas/image-(12).png and /dev/null differ diff --git a/docs/managed-datahub/imgs/saas/image-(13).png b/docs/managed-datahub/imgs/saas/image-(13).png deleted file mode 100644 index bbd8e6a66cf85..0000000000000 Binary files a/docs/managed-datahub/imgs/saas/image-(13).png and /dev/null differ diff --git a/docs/managed-datahub/imgs/saas/image-(14).png b/docs/managed-datahub/imgs/saas/image-(14).png deleted file mode 100644 index a580fdc3d6730..0000000000000 Binary files a/docs/managed-datahub/imgs/saas/image-(14).png and /dev/null differ diff --git a/docs/managed-datahub/imgs/saas/image-(15).png b/docs/managed-datahub/imgs/saas/image-(15).png deleted file mode 100644 index f282e2d92c1a1..0000000000000 Binary files a/docs/managed-datahub/imgs/saas/image-(15).png and /dev/null differ diff --git a/docs/managed-datahub/imgs/saas/image-(16).png b/docs/managed-datahub/imgs/saas/image-(16).png deleted file mode 100644 index 1340c77bd648c..0000000000000 Binary files a/docs/managed-datahub/imgs/saas/image-(16).png and /dev/null differ diff --git a/docs/managed-datahub/imgs/saas/image-(17).png b/docs/managed-datahub/imgs/saas/image-(17).png deleted file mode 100644 index 6eee2fb2d821f..0000000000000 Binary files a/docs/managed-datahub/imgs/saas/image-(17).png and /dev/null differ diff --git a/docs/managed-datahub/imgs/saas/image-(2).png b/docs/managed-datahub/imgs/saas/image-(2).png deleted file mode 100644 index cf475edd7b95d..0000000000000 Binary files a/docs/managed-datahub/imgs/saas/image-(2).png and /dev/null differ diff --git a/docs/managed-datahub/imgs/saas/image-(3).png b/docs/managed-datahub/imgs/saas/image-(3).png deleted file mode 100644 index b08818ff3e97c..0000000000000 Binary files a/docs/managed-datahub/imgs/saas/image-(3).png and /dev/null differ diff --git a/docs/managed-datahub/imgs/saas/image-(4).png b/docs/managed-datahub/imgs/saas/image-(4).png deleted file mode 100644 index a580fdc3d6730..0000000000000 Binary files a/docs/managed-datahub/imgs/saas/image-(4).png and /dev/null differ diff --git a/docs/managed-datahub/imgs/saas/image-(5).png b/docs/managed-datahub/imgs/saas/image-(5).png deleted file mode 100644 index 48438c6001e4f..0000000000000 Binary files a/docs/managed-datahub/imgs/saas/image-(5).png and /dev/null differ diff --git a/docs/managed-datahub/imgs/saas/image-(6).png b/docs/managed-datahub/imgs/saas/image-(6).png deleted file mode 100644 index 54e569e853f24..0000000000000 Binary files a/docs/managed-datahub/imgs/saas/image-(6).png and /dev/null differ diff --git a/docs/managed-datahub/imgs/saas/image-(7).png b/docs/managed-datahub/imgs/saas/image-(7).png deleted file mode 100644 index 6e89e5881cfa7..0000000000000 Binary files a/docs/managed-datahub/imgs/saas/image-(7).png and /dev/null differ diff --git a/docs/managed-datahub/imgs/saas/image-(8).png b/docs/managed-datahub/imgs/saas/image-(8).png deleted file mode 100644 index ee0a3c89d58fa..0000000000000 Binary files a/docs/managed-datahub/imgs/saas/image-(8).png and /dev/null differ diff --git a/docs/managed-datahub/imgs/saas/image-(9).png b/docs/managed-datahub/imgs/saas/image-(9).png deleted file mode 100644 index 301ca98593ef9..0000000000000 Binary files a/docs/managed-datahub/imgs/saas/image-(9).png and /dev/null differ diff --git a/docs/managed-datahub/imgs/saas/image.png b/docs/managed-datahub/imgs/saas/image.png deleted file mode 100644 index a1cfc3e74c5dd..0000000000000 Binary files a/docs/managed-datahub/imgs/saas/image.png and /dev/null differ diff --git a/docs/managed-datahub/imgs/saas/settings.png b/docs/managed-datahub/imgs/saas/settings.png deleted file mode 100644 index ca99984abbbc9..0000000000000 Binary files a/docs/managed-datahub/imgs/saas/settings.png and /dev/null differ diff --git a/docs/managed-datahub/integrations/oidc-sso-integration.md b/docs/managed-datahub/integrations/oidc-sso-integration.md index 6a9e085186b44..c0f5069d849fa 100644 --- a/docs/managed-datahub/integrations/oidc-sso-integration.md +++ b/docs/managed-datahub/integrations/oidc-sso-integration.md @@ -42,4 +42,8 @@ To enable the OIDC integration, start by navigating to **Settings > Platform > S 4. If there are any advanced settings you would like to configure, click on the **Advanced** button. These come with defaults, so only input settings here if there is something you need changed from the default configuration. 5. Click **Update** to save your settings. -![](../imgs/saas/image-(10).png) + +

+ +

+ diff --git a/docs/managed-datahub/metadata-ingestion-with-acryl/ingestion.md b/docs/managed-datahub/metadata-ingestion-with-acryl/ingestion.md index 95ca6e5e33e16..e225fd8b014c8 100644 --- a/docs/managed-datahub/metadata-ingestion-with-acryl/ingestion.md +++ b/docs/managed-datahub/metadata-ingestion-with-acryl/ingestion.md @@ -56,9 +56,17 @@ In Acryl DataHub deployments, you _must_ use a sink of type `datahub-rest`, whic 2. **token**: a unique API key used to authenticate requests to your instance's REST API The token can be retrieved by logging in as admin. You can go to Settings page and generate a Personal Access Token with your desired expiration date. -![](../imgs/saas/home-(1).png) -![](../imgs/saas/settings.png) +

+ +

+ + + +

+ +

+ To configure your instance of DataHub as the destination for ingestion, set the "server" field of your recipe to point to your Acryl instance's domain suffixed by the path `/gms`, as shown below. A complete example of a DataHub recipe file, which reads from MySQL and writes into a DataHub instance: diff --git a/docs/managed-datahub/operator-guide/setting-up-remote-ingestion-executor-on-aws.md b/docs/managed-datahub/operator-guide/setting-up-remote-ingestion-executor-on-aws.md index d389ec97d0550..6c6cce51ea098 100644 --- a/docs/managed-datahub/operator-guide/setting-up-remote-ingestion-executor-on-aws.md +++ b/docs/managed-datahub/operator-guide/setting-up-remote-ingestion-executor-on-aws.md @@ -17,11 +17,19 @@ Acryl DataHub comes packaged with an Acryl-managed ingestion executor, which is For example, if an ingestion source is not publicly accessible via the internet, e.g. hosted privately within a specific AWS account, then the Acryl executor will be unable to extract metadata from it. -![Option 1: Acryl-hosted ingestion runner](../imgs/saas/image-(12).png) + +

+ +

+ To accommodate these cases, Acryl supports configuring a remote ingestion executor which can be deployed inside of your AWS account. This setup allows you to continue leveraging the Acryl DataHub console to create, schedule, and run metadata ingestion, all while retaining network and credential isolation. -![Option 2: Customer-hosted ingestion runner](../imgs/saas/image-(6).png) + +

+ +

+ ## Deploying a Remote Ingestion Executor 1. **Provide AWS Account Id**: Provide Acryl Team with the id of the AWS in which the remote executor will be hosted. This will be used to grant access to private Acryl containers and create a unique SQS queue which your remote agent will subscribe to. The account id can be provided to your Acryl representative via Email or [One Time Secret](https://onetimesecret.com/). @@ -40,23 +48,39 @@ To accommodate these cases, Acryl supports configuring a remote ingestion execut Note that the only external secret provider that is currently supported is AWS Secrets Manager. -![](../imgs/saas/Screen-Shot-2023-01-19-at-5.12.47-PM.png) -![](../imgs/saas/Screen-Shot-2023-01-19-at-5.12.56-PM.png) +

+ +

+ + + +

+ +

+ 3. **Test the Executor:** To test your remote executor: 1. Create a new Ingestion Source by clicking '**Create new Source**' the '**Ingestion**' tab of the DataHub console. Configure your Ingestion Recipe as though you were running it from inside of your environment. 2. When working with "secret" fields (passwords, keys, etc), you can refer to any "self-managed" secrets by name: `${SECRET_NAME}:` - ![Using a secret called BQ_DEPLOY_KEY which is managed in AWS secrets manager](../imgs/saas/Screen-Shot-2023-01-19-at-4.16.52-PM.png) + +

+ +

+ 3. In the 'Finish Up' step, click '**Advanced'**. 4. Update the '**Executor Id**' form field to be '**remote**'. This indicates that you'd like to use the remote executor. 5. Click '**Done**'. Now, simple click '**Execute**' to test out the remote executor. If your remote executor is configured properly, you should promptly see the ingestion task state change to 'Running'. -![](../imgs/saas/Screen-Shot-2022-03-07-at-10.23.31-AM.png) + +

+ +

+ ## Updating a Remote Ingestion Executor In order to update the executor, ie. to deploy a new container version, you'll need to update the CloudFormation Stack to re-deploy the CloudFormation template with a new set of parameters. ### Steps - AWS Console @@ -66,7 +90,11 @@ In order to update the executor, ie. to deploy a new container version, you'll n 4. Select **Replace Current Template** 5. Select **Upload a template file** 6. Upload a copy of the Acryl Remote Executor [CloudFormation Template](https://raw.githubusercontent.com/acryldata/datahub-cloudformation/master/Ingestion/templates/python.ecs.template.yaml) -![](../imgs/saas/Screen-Shot-2023-01-19-at-4.23.32-PM.png) + +

+ +

+ 7. Click **Next** 8. Change parameters based on your modifications (e.g. ImageTag, etc) 9. Click **Next** diff --git a/docs/modeling/extending-the-metadata-model.md b/docs/modeling/extending-the-metadata-model.md index f47630f44e772..98f70f6d933e4 100644 --- a/docs/modeling/extending-the-metadata-model.md +++ b/docs/modeling/extending-the-metadata-model.md @@ -11,7 +11,11 @@ these two concepts prior to making changes. ## To fork or not to fork? An important question that will arise once you've decided to extend the metadata model is whether you need to fork the main repo or not. Use the diagram below to understand how to make this decision. -![Metadata Model To Fork or Not](../imgs/metadata-model-to-fork-or-not-to.png) + +

+ +

+ The green lines represent pathways that will lead to lesser friction for you to maintain your code long term. The red lines represent higher risk of conflicts in the future. We are working hard to move the majority of model extension use-cases to no-code / low-code pathways to ensure that you can extend the core metadata model without having to maintain a custom fork of DataHub. diff --git a/docs/modeling/metadata-model.md b/docs/modeling/metadata-model.md index 704fce1412329..037c9c7108a6e 100644 --- a/docs/modeling/metadata-model.md +++ b/docs/modeling/metadata-model.md @@ -30,7 +30,11 @@ Conceptually, metadata is modeled using the following abstractions Here is an example graph consisting of 3 types of entity (CorpUser, Chart, Dashboard), 2 types of relationship (OwnedBy, Contains), and 3 types of metadata aspect (Ownership, ChartInfo, and DashboardInfo). -![metadata-modeling](../imgs/metadata-model-chart.png) + +

+ +

+ ## The Core Entities @@ -73,7 +77,11 @@ to the YAML configuration, instead of creating new Snapshot / Aspect files. ## Exploring DataHub's Metadata Model To explore the current DataHub metadata model, you can inspect this high-level picture that shows the different entities and edges between them showing the relationships between them. -![Metadata Model Graph](../imgs/datahub-metadata-model.png) + +

+ +

+ To navigate the aspect model for specific entities and explore relationships using the `foreign-key` concept, you can view them in our demo environment or navigate the auto-generated docs in the **Metadata Modeling/Entities** section on the left. diff --git a/docs/platform-instances.md b/docs/platform-instances.md index c6bfe3315de98..0f4515aedae54 100644 --- a/docs/platform-instances.md +++ b/docs/platform-instances.md @@ -1,44 +1,48 @@ -# Working With Platform Instances - -DataHub's metadata model for Datasets supports a three-part key currently: -- Data Platform (e.g. urn:li:dataPlatform:mysql) -- Name (e.g. db.schema.name) -- Env or Fabric (e.g. DEV, PROD, etc.) - -This naming scheme unfortunately does not allow for easy representation of the multiplicity of platforms (or technologies) that might be deployed at an organization within the same environment or fabric. For example, an organization might have multiple Redshift instances in Production and would want to see all the data assets located in those instances inside the DataHub metadata repository. - -As part of the `v0.8.24+` releases, we are unlocking the first phase of supporting Platform Instances in the metadata model. This is done via two main additions: -- The `dataPlatformInstance` aspect that has been added to Datasets which allows datasets to be associated to an instance of a platform -- Enhancements to all ingestion sources that allow them to attach a platform instance to the recipe that changes the generated urns to go from `urn:li:dataset:(urn:li:dataPlatform:,,ENV)` format to `urn:li:dataset:(urn:li:dataPlatform:,,ENV)` format. Sources that produce lineage to datasets in other platforms (e.g. Looker, Superset etc) also have specific configuration additions that allow the recipe author to specify the mapping between a platform and the instance name that it should be mapped to. - -![./imgs/platform-instances-for-ingestion.png](./imgs/platform-instances-for-ingestion.png) - -## Naming Platform Instances - -When configuring a platform instance, choose an instance name that is understandable and will be stable for the foreseeable future. e.g. `core_warehouse` or `finance_redshift` are allowed names, as are pure guids like `a37dc708-c512-4fe4-9829-401cd60ed789`. Remember that whatever instance name you choose, you will need to specify it in more than one recipe to ensure that the identifiers produced by different sources will line up. - -## Enabling Platform Instances - -Read the Ingestion source specific guides for how to enable platform instances in each of them. -The general pattern is to add an additional optional configuration parameter called `platform_instance`. - -e.g. here is how you would configure a recipe to ingest a mysql instance that you want to call `core_finance` -```yaml -source: - type: mysql - config: - # Coordinates - host_port: localhost:3306 - platform_instance: core_finance - database: dbname - - # Credentials - username: root - password: example - -sink: - # sink configs -``` - - -## +# Working With Platform Instances + +DataHub's metadata model for Datasets supports a three-part key currently: +- Data Platform (e.g. urn:li:dataPlatform:mysql) +- Name (e.g. db.schema.name) +- Env or Fabric (e.g. DEV, PROD, etc.) + +This naming scheme unfortunately does not allow for easy representation of the multiplicity of platforms (or technologies) that might be deployed at an organization within the same environment or fabric. For example, an organization might have multiple Redshift instances in Production and would want to see all the data assets located in those instances inside the DataHub metadata repository. + +As part of the `v0.8.24+` releases, we are unlocking the first phase of supporting Platform Instances in the metadata model. This is done via two main additions: +- The `dataPlatformInstance` aspect that has been added to Datasets which allows datasets to be associated to an instance of a platform +- Enhancements to all ingestion sources that allow them to attach a platform instance to the recipe that changes the generated urns to go from `urn:li:dataset:(urn:li:dataPlatform:,,ENV)` format to `urn:li:dataset:(urn:li:dataPlatform:,,ENV)` format. Sources that produce lineage to datasets in other platforms (e.g. Looker, Superset etc) also have specific configuration additions that allow the recipe author to specify the mapping between a platform and the instance name that it should be mapped to. + + +

+ +

+ + +## Naming Platform Instances + +When configuring a platform instance, choose an instance name that is understandable and will be stable for the foreseeable future. e.g. `core_warehouse` or `finance_redshift` are allowed names, as are pure guids like `a37dc708-c512-4fe4-9829-401cd60ed789`. Remember that whatever instance name you choose, you will need to specify it in more than one recipe to ensure that the identifiers produced by different sources will line up. + +## Enabling Platform Instances + +Read the Ingestion source specific guides for how to enable platform instances in each of them. +The general pattern is to add an additional optional configuration parameter called `platform_instance`. + +e.g. here is how you would configure a recipe to ingest a mysql instance that you want to call `core_finance` +```yaml +source: + type: mysql + config: + # Coordinates + host_port: localhost:3306 + platform_instance: core_finance + database: dbname + + # Credentials + username: root + password: example + +sink: + # sink configs +``` + + +## diff --git a/docs/schema-history.md b/docs/schema-history.md index 9fc9ec1af52bb..120d041960186 100644 --- a/docs/schema-history.md +++ b/docs/schema-history.md @@ -23,20 +23,32 @@ must have the **View Entity Page** privilege, or be assigned to **any** DataHub You can view the Schema History for a Dataset by navigating to that Dataset's Schema Tab. As long as that Dataset has more than one version, you can view what a Dataset looked like at any given version by using the version selector. Here's an example from DataHub's official Demo environment with the -[Snowflake pets dataset](https://demo.datahubproject.io/dataset/urn:li:dataset:(urn:li:dataPlatform:snowflake,long_tail_companions.adoption.pets,PROD)/Schema?is_lineage_mode=false). +Snowflake pets dataset. + + +

+ +

-![](./imgs/schema-history-latest-version.png) If you click on an older version in the selector, you'll be able to see what the schema looked like back then. Notice the changes here to the glossary terms for the `status` field, and to the descriptions for the `created_at` and `updated_at` fields. -![](./imgs/schema-history-older-version.png) + +

+ +

+ In addition to this, you can also toggle the Audit view that shows you when the most recent changes were made to each field. You can active this by clicking on the Audit icon you see above the top right of the table. -![](./imgs/schema-history-audit-activated.png) + +

+ +

+ You can see here that some of these fields were added at the oldest dataset version, while some were added only at this latest version. Some fields were even modified and had a type change at the latest version! diff --git a/docs/townhall-history.md b/docs/townhall-history.md index 1da490ca6fa69..e235a70c5d7b9 100644 --- a/docs/townhall-history.md +++ b/docs/townhall-history.md @@ -343,8 +343,7 @@ Agenda - Announcements - 2 mins - Community Updates ([video](https://youtu.be/r862MZTLAJ0?t=99)) - 10 mins -- Use-Case: DataHub at Viasat ([slides](demo/ViasatMetadataJourney.pdf),[video](https://youtu.be/2SrDAJnzkjE)) by [Anna Kepler](https://www.linkedin.com/in/akepler) - 15 mins -- Tech Deep Dive: GraphQL + React RFCs readout and discussion ([slides](https://docs.google.com/presentation/d/e/2PACX-1vRtnINnpi6PvFw7-5iW8PSQoT9Kdf1O_0YW7QAr1_mSdJMNftYFTVCjKL-e3fpe8t6IGkha8UpdmoOI/pub?start=false&loop=false&delayms=3000) ,[video](https://www.youtube.com/watch?v=PrBaFrb7pqA)) by [John Joyce](https://www.linkedin.com/in/john-joyce-759883aa) and [Arun Vasudevan](https://www.linkedin.com/in/arun-vasudevan-55117368/) - 15 mins +- Use-Case: DataHub at Viasat ([slides](https://github.com/acryldata/static-assets-test/raw/master/imgs/demo/ViasatMetadataJourney.pdf),[video](https://youtu.be/2SrDAJnzkjE)) by [Anna Kepler](https://www.linkedin.com/in/akepler) - 15 mins- Tech Deep Dive: GraphQL + React RFCs readout and discussion ([slides](https://docs.google.com/presentation/d/e/2PACX-1vRtnINnpi6PvFw7-5iW8PSQoT9Kdf1O_0YW7QAr1_mSdJMNftYFTVCjKL-e3fpe8t6IGkha8UpdmoOI/pub?start=false&loop=false&delayms=3000) ,[video](https://www.youtube.com/watch?v=PrBaFrb7pqA)) by [John Joyce](https://www.linkedin.com/in/john-joyce-759883aa) and [Arun Vasudevan](https://www.linkedin.com/in/arun-vasudevan-55117368/) - 15 mins - General Q&A from sign up sheet, slack, and participants - 15 mins - Closing remarks - 3 mins - General Q&A from sign up sheet, slack, and participants - 15 mins @@ -356,8 +355,8 @@ Agenda Agenda - Quick intro - 5 mins -- [Why did Grofers choose DataHub for their data catalog?](demo/Datahub_at_Grofers.pdf) by [Shubham Gupta](https://www.linkedin.com/in/shubhamg931/) - 15 minutes -- [DataHub UI development - Part 2](demo/Town_Hall_Presentation_-_12-2020_-_UI_Development_Part_2.pdf) by [Charlie Tran](https://www.linkedin.com/in/charlie-tran/) (LinkedIn) - 20 minutes +- [Why did Grofers choose DataHub for their data catalog?](https://github.com/acryldata/static-assets-test/raw/master/imgs/demo/Datahub_at_Grofers.pdf) by [Shubham Gupta](https://www.linkedin.com/in/shubhamg931/) - 15 minutes +- [DataHub UI development - Part 2](https://github.com/acryldata/static-assets-test/raw/master/imgs/demo/Town_Hall_Presentation_-_12-2020_-_UI_Development_Part_2.pdf) by [Charlie Tran](https://www.linkedin.com/in/charlie-tran/) (LinkedIn) - 20 minutes - General Q&A from sign up sheet, slack, and participants - 15 mins - Closing remarks - 5 minutes @@ -368,9 +367,9 @@ Agenda Agenda - Quick intro - 5 mins -- [Lightning talk on Metadata use-cases at LinkedIn](demo/Metadata_Use-Cases_at_LinkedIn_-_Lightning_Talk.pdf) by [Shirshanka Das](https://www.linkedin.com/in/shirshankadas/) (LinkedIn) - 5 mins -- [Strongly Consistent Secondary Index (SCSI) in GMA](demo/Datahub_-_Strongly_Consistent_Secondary_Indexing.pdf), an upcoming feature by [Jyoti Wadhwani](https://www.linkedin.com/in/jyotiwadhwani/) (LinkedIn) - 15 minutes -- [DataHub UI overview](demo/DataHub-UIOverview.pdf) by [Ignacio Bona](https://www.linkedin.com/in/ignaciobona) (LinkedIn) - 20 minutes +- [Lightning talk on Metadata use-cases at LinkedIn](https://github.com/acryldata/static-assets-test/raw/master/imgs/demo/Metadata_Use-Cases_at_LinkedIn_-_Lightning_Talk.pdf) by [Shirshanka Das](https://www.linkedin.com/in/shirshankadas/) (LinkedIn) - 5 mins +- [Strongly Consistent Secondary Index (SCSI) in GMA](https://github.com/acryldata/static-assets-test/raw/master/imgs/demo/Datahub_-_Strongly_Consistent_Secondary_Indexing.pdf), an upcoming feature by [Jyoti Wadhwani](https://www.linkedin.com/in/jyotiwadhwani/) (LinkedIn) - 15 minutes +- [DataHub UI overview](https://github.com/acryldata/static-assets-test/raw/master/imgs/demo/DataHub-UIOverview.pdf) by [Ignacio Bona](https://www.linkedin.com/in/ignaciobona) (LinkedIn) - 20 minutes - General Q&A from sign up sheet, slack, and participants - 10 mins - Closing remarks - 5 minutes @@ -382,8 +381,8 @@ Agenda Agenda - Quick intro - 5 mins -- [Data Discoverability at SpotHero](demo/Data_Discoverability_at_SpotHero.pdf) by [Maggie Hays](https://www.linkedin.com/in/maggie-hays/) (SpotHero) - 20 mins -- [Designing the next generation of metadata events for scale](demo/Designing_the_next_generation_of_metadata_events_for_scale.pdf) by [Chris Lee](https://www.linkedin.com/in/chrisleecmu/) (LinkedIn) - 15 mins +- [Data Discoverability at SpotHero](https://github.com/acryldata/static-assets-test/raw/master/imgs/demo/Data_Discoverability_at_SpotHero.pdf) by [Maggie Hays](https://www.linkedin.com/in/maggie-hays/) (SpotHero) - 20 mins +- [Designing the next generation of metadata events for scale](https://github.com/acryldata/static-assets-test/raw/master/imgs/demo/Designing_the_next_generation_of_metadata_events_for_scale.pdf) by [Chris Lee](https://www.linkedin.com/in/chrisleecmu/) (LinkedIn) - 15 mins - General Q&A from sign up sheet, slack, and participants - 15 mins - Closing remarks - 5 mins diff --git a/docs/ui-ingestion.md b/docs/ui-ingestion.md index 4435f66e514f3..2ecb1e634c79f 100644 --- a/docs/ui-ingestion.md +++ b/docs/ui-ingestion.md @@ -14,11 +14,19 @@ This document will describe the steps required to configure, schedule, and execu To view & manage UI-based metadata ingestion, you must have the `Manage Metadata Ingestion` & `Manage Secrets` privileges assigned to your account. These can be granted by a [Platform Policy](authorization/policies.md). -![](./imgs/ingestion-privileges.png) + +

+ +

+ Once you have these privileges, you can begin to manage ingestion by navigating to the 'Ingestion' tab in DataHub. -![](./imgs/ingestion-tab.png) + +

+ +

+ On this page, you'll see a list of active **Ingestion Sources**. An Ingestion Sources is a unique source of metadata ingested into DataHub from an external source like Snowflake, Redshift, or BigQuery. @@ -33,7 +41,11 @@ your first **Ingestion Source**. Before ingesting any metadata, you need to create a new Ingestion Source. Start by clicking **+ Create new source**. -![](./imgs/create-new-ingestion-source-button.png) + +

+ +

+ #### Step 1: Select a Platform Template @@ -41,7 +53,11 @@ In the first step, select a **Recipe Template** corresponding to the source type a variety of natively supported integrations, from Snowflake to Postgres to Kafka. Select `Custom` to construct an ingestion recipe from scratch. -![](./imgs/select-platform-template.png) + +

+ +

+ Next, you'll configure an ingestion **Recipe**, which defines _how_ and _what_ to extract from the source system. @@ -68,7 +84,11 @@ used by DataHub to extract metadata from a 3rd party system. It most often consi A sample of a full recipe configured to ingest metadata from MySQL can be found in the image below. -![](./imgs/example-mysql-recipe.png) + +

+ +

+ Detailed configuration examples & documentation for each source type can be found on the [DataHub Docs](https://datahubproject.io/docs/metadata-ingestion/) website. @@ -80,7 +100,11 @@ that are encrypted and stored within DataHub's storage layer. To create a secret, first navigate to the 'Secrets' tab. Then click `+ Create new secret`. -![](./imgs/create-secret.png) + +

+ +

+ _Creating a Secret to store the username for a MySQL database_ @@ -123,7 +147,11 @@ Secret values are not persisted to disk beyond execution time, and are never tra Next, you can optionally configure a schedule on which to execute your new Ingestion Source. This enables to schedule metadata extraction on a monthly, weekly, daily, or hourly cadence depending on the needs of your organization. Schedules are defined using CRON format. -![](./imgs/schedule-ingestion.png) + +

+ +

+ _An Ingestion Source that is executed at 9:15am every day, Los Angeles time_ @@ -136,7 +164,11 @@ you can always come back and change this. Finally, give your Ingestion Source a name. -![](./imgs/name-ingestion-source.png) + +

+ +

+ Once you're happy with your configurations, click 'Done' to save your changes. @@ -149,7 +181,11 @@ with the server. However, you can override the default package version using the To do so, simply click 'Advanced', then change the 'CLI Version' text box to contain the exact version of the DataHub CLI you'd like to use. -![](./imgs/custom-ingestion-cli-version.png) + +

+ +

+ _Pinning the CLI version to version `0.8.23.2`_ Once you're happy with your changes, simply click 'Done' to save. @@ -200,11 +236,19 @@ Once you've created your Ingestion Source, you can run it by clicking 'Execute'. you should see the 'Last Status' column of the ingestion source change from `N/A` to `Running`. This means that the request to execute ingestion has been successfully picked up by the DataHub ingestion executor. -![](./imgs/running-ingestion.png) + +

+ +

+ If ingestion has executed successfully, you should see it's state shown in green as `Succeeded`. -![](./imgs/successful-ingestion.png) + +

+ +

+ ### Cancelling an Ingestion Run @@ -212,14 +256,22 @@ If ingestion has executed successfully, you should see it's state shown in green If your ingestion run is hanging, there may a bug in the ingestion source, or another persistent issue like exponential timeouts. If these situations, you can cancel ingestion by clicking **Cancel** on the problematic run. -![](./imgs/cancelled-ingestion.png) + +

+ +

+ Once cancelled, you can view the output of the ingestion run by clicking **Details**. ### Debugging a Failed Ingestion Run -![](./imgs/failed-ingestion.png) + +

+ +

+ A variety of things can cause an ingestion run to fail. Common reasons for failure include: @@ -235,12 +287,20 @@ A variety of things can cause an ingestion run to fail. Common reasons for failu 4. **Authentication**: If you've enabled [Metadata Service Authentication](authentication/introducing-metadata-service-authentication.md), you'll need to provide a Personal Access Token in your Recipe Configuration. To so this, set the 'token' field of the sink configuration to contain a Personal Access Token: - ![](./imgs/ingestion-with-token.png) + +

+ +

+ The output of each run is captured and available to view in the UI for easier debugging. To view output logs, click **DETAILS** on the corresponding ingestion run. -![](./imgs/ingestion-logs.png) + +

+ +

+ ## FAQ @@ -250,7 +310,11 @@ If not due to one of the reasons outlined above, this may be because the executo to reach DataHub's backend using the default configurations. Try changing your ingestion recipe to make the `sink.config.server` variable point to the Docker DNS name for the `datahub-gms` pod: -![](./imgs/quickstart-ingestion-config.png) + +

+ +

+ ### I see 'N/A' when I try to run ingestion. What do I do? diff --git a/docs/what/relationship.md b/docs/what/relationship.md index 1908bbd6ce75f..dcfe093a1b124 100644 --- a/docs/what/relationship.md +++ b/docs/what/relationship.md @@ -2,7 +2,11 @@ A relationship is a named associate between exactly two [entities](entity.md), a source and a destination. -![metadata-modeling](../imgs/metadata-modeling.png) + +

+ +

+ From the above graph, a `Group` entity can be linked to a `User` entity via a `HasMember` relationship. Note that the name of the relationship reflects the direction, i.e. pointing from `Group` to `User`. diff --git a/metadata-ingestion/adding-source.md b/metadata-ingestion/adding-source.md index 50e6a1cd5fcc6..e4fc950a7cdbd 100644 --- a/metadata-ingestion/adding-source.md +++ b/metadata-ingestion/adding-source.md @@ -44,7 +44,11 @@ class LookerAPIConfig(ConfigModel): ``` generates the following documentation: -![Generated Config Documentation](./docs/images/generated_config_docs.png) + +

+ +

+ :::note Inline markdown or code snippets are not yet supported for field level documentation. diff --git a/metadata-ingestion/developing.md b/metadata-ingestion/developing.md index 67041d23a21b1..5d49b9a866a3d 100644 --- a/metadata-ingestion/developing.md +++ b/metadata-ingestion/developing.md @@ -74,7 +74,9 @@ The syntax for installing plugins is slightly different in development. For exam ## Architecture -![metadata ingestion framework layout](../docs/imgs/datahub-metadata-ingestion-framework.png) +

+ +

The architecture of this metadata ingestion framework is heavily inspired by [Apache Gobblin](https://gobblin.apache.org/) (also originally a LinkedIn project!). We have a standardized format - the MetadataChangeEvent - and sources and sinks which respectively produce and consume these objects. The sources pull metadata from a variety of data systems, while the sinks are primarily for moving this metadata into DataHub. diff --git a/metadata-ingestion/docs/dev_guides/stateful.md b/metadata-ingestion/docs/dev_guides/stateful.md index eccacbb416714..b3a409e965c62 100644 --- a/metadata-ingestion/docs/dev_guides/stateful.md +++ b/metadata-ingestion/docs/dev_guides/stateful.md @@ -38,7 +38,9 @@ Following is the list of current use-cases powered by stateful ingestion in data Stateful ingestion can be used to automatically soft-delete the tables and views that are seen in a previous run but absent in the current run (they are either deleted or no longer desired). -![Stale Metadata Deletion](./stale_metadata_deletion.png) +

+ +

#### Supported sources * All sql based sources. diff --git a/metadata-ingestion/docs/sources/azure-ad/azure-ad.md b/metadata-ingestion/docs/sources/azure-ad/azure-ad.md index 8b375fbee4f33..d2677d7e4fc7a 100644 --- a/metadata-ingestion/docs/sources/azure-ad/azure-ad.md +++ b/metadata-ingestion/docs/sources/azure-ad/azure-ad.md @@ -5,6 +5,15 @@ to read your organization's Users and Groups. The following permissions are requ - `GroupMember.Read.All` - `User.Read.All` -You can add a permission by navigating to the permissions tab in your DataHub application on the Azure AD portal. ![Azure AD API Permissions](./azure_ad_api_permissions.png) +You can add a permission by navigating to the permissions tab in your DataHub application on the Azure AD portal. +

+ +

-You can view the necessary endpoints to configure by clicking on the Endpoints button in the Overview tab. ![Azure AD Endpoints](./azure_ad_endpoints.png) + +You can view the necessary endpoints to configure by clicking on the Endpoints button in the Overview tab. + + +

+ +

diff --git a/metadata-ingestion/docs/sources/databricks/README.md b/metadata-ingestion/docs/sources/databricks/README.md index 01aee3236e01c..b380a892c22b9 100644 --- a/metadata-ingestion/docs/sources/databricks/README.md +++ b/metadata-ingestion/docs/sources/databricks/README.md @@ -15,8 +15,11 @@ To complete the picture, we recommend adding push-based ingestion from your Spar ## Watch the DataHub Talk at the Data and AI Summit 2022 For a deeper look at how to think about DataHub within and across your Databricks ecosystem, watch the recording of our talk at the Data and AI Summit 2022. - -[![IMAGE_ALT](../../images/databricks/data_and_ai_summit_2022.png)](https://www.youtube.com/watch?v=SCP0PR3t7dc) +

+ + + +

diff --git a/metadata-ingestion/docs/sources/looker/looker_datahub_permission_set.png b/metadata-ingestion/docs/sources/looker/looker_datahub_permission_set.png deleted file mode 100644 index 7227dc04fb8a0..0000000000000 Binary files a/metadata-ingestion/docs/sources/looker/looker_datahub_permission_set.png and /dev/null differ diff --git a/metadata-ingestion/docs/sources/looker/looker_pre.md b/metadata-ingestion/docs/sources/looker/looker_pre.md index ad7fff9c0daaf..6798103d66e99 100644 --- a/metadata-ingestion/docs/sources/looker/looker_pre.md +++ b/metadata-ingestion/docs/sources/looker/looker_pre.md @@ -19,7 +19,10 @@ see_user_dashboards see_users ``` Here is an example permission set after configuration. -![Looker DataHub Permission Set](./looker_datahub_permission_set.png) + +

+ +

#### Get an API key diff --git a/perf-test/README.md b/perf-test/README.md index 24fb064d3e28a..191833361eae9 100644 --- a/perf-test/README.md +++ b/perf-test/README.md @@ -58,7 +58,9 @@ locust -f perf-test/locustfiles/ingest.py This will set up the web interface in http://localhost:8089 (unless the port is already taken). Once you click into it, you should see the following -![Locust Example](../docs/imgs/locust-example.png) +

+ +

Input the number of users you would like to spawn and the spawn rate. Point the host to the deployed DataHub GMS ( locally, it should be http://localhost:8080). Click on the "Start swarming" button to start the load test.