Adding RDF ingestion capabilities

datahub-web-react/src/app/ingest/source/builder/sources.json

@@ -371,5 +371,13 @@
         "description": "Import Charts and Dashboards from Preset",
         "docsUrl": "https://docs.datahub.com/docs/generated/ingestion/sources/preset/",
         "recipe": "source:\n  type: preset\n  config:\n    # Coordinates\n    connect_uri: Preset workspace URL\n    manager_uri: https://api.app.preset.io\n\n    # Credentials\n    api_key: Preset API Key\n    api_secret: Preset API Secret"
+    },
+    {
+        "urn": "urn:li:dataPlatform:rdf",
+        "name": "rdf",
+        "displayName": "RDF",
+        "description": "Import glossary terms, term groups, and relationships from RDF/OWL ontologies (SKOS, Turtle, RDF/XML).",
+        "docsUrl": "https://docs.datahub.com/docs/generated/ingestion/sources/rdf",
+        "recipe": "source:\n  type: rdf\n  config:\n    source: path/to/glossary.ttl\n    environment: PROD\n    export_only:\n      - glossary"
     }
 ]

datahub-web-react/src/app/ingestV2/source/builder/RecipeForm/constants.ts

@@ -167,6 +167,14 @@ import {
     PRESTO_PASSWORD,
     PRESTO_USERNAME,
 } from '@app/ingestV2/source/builder/RecipeForm/presto';
+import {
+    RDF_DIALECT,
+    RDF_ENVIRONMENT,
+    RDF_EXTENSIONS,
+    RDF_FORMAT,
+    RDF_RECURSIVE,
+    RDF_SOURCE,
+} from '@app/ingestV2/source/builder/RecipeForm/rdf';
 import {
     REDSHIFT_DATABASE,
     REDSHIFT_HOST_PORT,
@@ -239,6 +247,7 @@ import {
     MYSQL,
     OKTA,
     POWER_BI,
+    RDF,
     SAC,
     VERTICA,
 } from '@app/ingestV2/source/builder/constants';
@@ -586,6 +595,13 @@ export const RECIPE_FIELDS: RecipeFields = {
         ],
         advancedFields: [STATEFUL_INGESTION_ENABLED],
     },
+    [RDF]: {
+        fields: [RDF_SOURCE],
+        filterFields: [],
+        advancedFields: [RDF_FORMAT, RDF_EXTENSIONS, RDF_RECURSIVE, RDF_ENVIRONMENT, RDF_DIALECT],
+        connectionSectionTooltip: 'Configure the RDF source location and basic settings.',
+        advancedSectionTooltip: 'Advanced options for RDF format, file processing, and dialect selection.',
+    },
 };
 
 export const CONNECTORS_WITH_FORM = new Set(Object.keys(RECIPE_FIELDS));

datahub-web-react/src/app/ingestV2/source/builder/RecipeForm/rdf.ts

@@ -0,0 +1,83 @@
+import { FieldType, RecipeField } from '@app/ingestV2/source/builder/RecipeForm/common';
+
+export const RDF_SOURCE: RecipeField = {
+    name: 'source',
+    label: 'Source',
+    tooltip:
+        'Source to process: file path, folder path, server URL, or comma-separated files. Examples: /path/to/file.ttl, /path/to/folder, https://example.com/data.ttl, file1.ttl,file2.ttl',
+    type: FieldType.TEXT,
+    fieldPath: 'source.config.source',
+    placeholder: '/path/to/file.ttl or /path/to/folder or https://example.com/data.ttl',
+    required: true,
+    rules: null,
+};
+
+export const RDF_FORMAT: RecipeField = {
+    name: 'format',
+    label: 'RDF Format',
+    tooltip: 'RDF format (auto-detected if not specified). Examples: turtle, xml, n3, nt, json-ld',
+    type: FieldType.SELECT,
+    fieldPath: 'source.config.format',
+    placeholder: 'Auto-detect',
+    options: [
+        { label: 'Auto-detect', value: '' },
+        { label: 'Turtle', value: 'turtle' },
+        { label: 'RDF/XML', value: 'xml' },
+        { label: 'N3', value: 'n3' },
+        { label: 'N-Triples', value: 'nt' },
+        { label: 'JSON-LD', value: 'json-ld' },
+    ],
+    rules: null,
+};
+
+export const RDF_EXTENSIONS: RecipeField = {
+    name: 'extensions',
+    label: 'File Extensions',
+    tooltip: 'File extensions to process when source is a folder. Default: .ttl, .rdf, .owl, .n3, .nt',
+    type: FieldType.LIST,
+    fieldPath: 'source.config.extensions',
+    placeholder: '.ttl',
+    buttonLabel: 'Add extension',
+    rules: null,
+};
+
+export const RDF_RECURSIVE: RecipeField = {
+    name: 'recursive',
+    label: 'Recursive Folder Processing',
+    tooltip: 'Enable recursive folder processing when source is a folder (default: true)',
+    type: FieldType.BOOLEAN,
+    fieldPath: 'source.config.recursive',
+    rules: null,
+};
+
+export const RDF_ENVIRONMENT: RecipeField = {
+    name: 'environment',
+    label: 'DataHub Environment',
+    tooltip: 'DataHub environment (PROD, DEV, TEST, etc.)',
+    type: FieldType.SELECT,
+    fieldPath: 'source.config.environment',
+    placeholder: 'PROD',
+    options: [
+        { label: 'PROD', value: 'PROD' },
+        { label: 'DEV', value: 'DEV' },
+        { label: 'TEST', value: 'TEST' },
+        { label: 'UAT', value: 'UAT' },
+    ],
+    rules: null,
+};
+
+export const RDF_DIALECT: RecipeField = {
+    name: 'dialect',
+    label: 'RDF Dialect',
+    tooltip: 'Force a specific RDF dialect (default: auto-detect). Options: default, fibo, generic',
+    type: FieldType.SELECT,
+    fieldPath: 'source.config.dialect',
+    placeholder: 'Auto-detect',
+    options: [
+        { label: 'Auto-detect', value: '' },
+        { label: 'Default', value: 'default' },
+        { label: 'FIBO', value: 'fibo' },
+        { label: 'Generic', value: 'generic' },
+    ],
+    rules: null,
+};

datahub-web-react/src/app/ingestV2/source/builder/constants.ts

@@ -151,6 +151,8 @@ export const VERTEX_AI = 'vertexai';
 export const VERTEXAI_URN = `urn:li:dataPlatform:${VERTEX_AI}`;
 export const SNAPLOGIC = 'snaplogic';
 export const SNAPLOGIC_URN = `urn:li:dataPlatform:${SNAPLOGIC}`;
+export const RDF = 'rdf';
+export const RDF_URN = `urn:li:dataPlatform:${RDF}`;
 
 export const PLATFORM_URN_TO_LOGO = {
     [ATHENA_URN]: athenaLogo,

datahub-web-react/src/app/ingestV2/source/builder/sources.json

@@ -371,5 +371,13 @@
         "description": "Import Charts and Dashboards from Preset",
         "docsUrl": "https://docs.datahub.com/docs/generated/ingestion/sources/preset/",
         "recipe": "source:\n  type: preset\n  config:\n    # Coordinates\n    connect_uri: Preset workspace URL\n    manager_uri: https://api.app.preset.io\n\n    # Credentials\n    api_key: Preset API Key\n    api_secret: Preset API Secret"
+    },
+    {
+        "urn": "urn:li:dataPlatform:rdf",
+        "name": "rdf",
+        "displayName": "RDF",
+        "description": "Import glossary terms, term groups, and relationships from RDF/OWL ontologies (SKOS, Turtle, RDF/XML).",
+        "docsUrl": "https://docs.datahub.com/docs/generated/ingestion/sources/rdf",
+        "recipe": "source:\n  type: rdf\n  config:\n    source: path/to/glossary.ttl\n    environment: PROD\n    export_only:\n      - glossary"
     }
 ]

datahub-web-react/src/app/ingestV2/source/multiStepBuilder/steps/step1SelectSource/sources.json

@@ -446,5 +446,15 @@
         "recipe": "source:\n  type: hex\n  config:\n    workspace_name: # Your Hex Workspace name\n     token: # Your PAT or Workspace token",
         "category": "Other",
         "isPopular": false
+    },
+    {
+        "urn": "urn:li:dataPlatform:rdf",
+        "name": "rdf",
+        "displayName": "RDF",
+        "description": "Import glossary terms, term groups, and relationships from RDF/OWL ontologies (SKOS, Turtle, RDF/XML).",
+        "docsUrl": "https://docs.datahub.com/docs/generated/ingestion/sources/rdf",
+        "recipe": "source:\n  type: rdf\n  config:\n    source: path/to/glossary.ttl\n    environment: PROD\n    export_only:\n      - glossary",
+        "category": "Other",
+        "isPopular": false
     }
 ]

docker/datahub-actions/Dockerfile

@@ -301,7 +301,7 @@ RUN --mount=type=bind,source=./python-build/version_updater.py,target=/version_u
 
 # Install metadata-ingestion with base extras (network enabled, can install more at runtime)
 RUN --mount=type=cache,target=$HOME/.cache/uv,uid=1000,gid=1000,id=datahub-actions \
-  uv pip install -e '/metadata-ingestion/[base,s3,gcs,abs]'
+  uv pip install -e '/metadata-ingestion/[base,s3,gcs,abs,rdf]'
 
 # Install datahub-actions with all extras
 RUN --mount=type=cache,target=$HOME/.cache/uv,uid=1000,gid=1000,id=datahub-actions \
@@ -355,7 +355,7 @@ RUN --mount=type=bind,source=./python-build/version_updater.py,target=/version_u
 
 # Install metadata-ingestion with SLIM extras (no PySpark, network enabled for flexibility)
 RUN --mount=type=cache,target=$HOME/.cache/uv,uid=1000,gid=1000,id=datahub-actions \
-  uv pip install -e '/metadata-ingestion/[base,s3-slim,gcs-slim,abs-slim]'
+  uv pip install -e '/metadata-ingestion/[base,s3-slim,gcs-slim,abs-slim,rdf]'
 
 # Install datahub-actions with all extras
 RUN --mount=type=cache,target=$HOME/.cache/uv,uid=1000,gid=1000,id=datahub-actions \

docker/datahub-ingestion/Dockerfile

@@ -142,7 +142,7 @@ RUN --mount=type=bind,source=./python-build/version_updater.py,target=/version_u
 FROM add-code AS install-slim
 
 RUN --mount=type=cache,target=$HOME/.cache/uv,uid=1000,gid=1000 \
-    UV_LINK_MODE=copy uv pip install -e "/metadata-ingestion/[base,datahub-rest,datahub-kafka,snowflake,bigquery,redshift,mysql,postgres,s3-slim,gcs-slim,abs-slim,clickhouse,glue,dbt,looker,lookml,tableau,powerbi,superset,datahub-business-glossary]" && \
+    UV_LINK_MODE=copy uv pip install -e "/metadata-ingestion/[base,datahub-rest,datahub-kafka,snowflake,bigquery,redshift,mysql,postgres,s3-slim,gcs-slim,abs-slim,clickhouse,glue,dbt,looker,lookml,tableau,powerbi,superset,datahub-business-glossary,rdf]" && \
     datahub --version
 
 FROM add-code AS install-full