Merge pull request #75 from databricks-industry-solutions/bugfix/runme

New RUNME! 100% Serverless + OHIF in lakehouse APP deploy

00-README.py

@@ -14,7 +14,7 @@
 # MAGIC   - Uses proven `gdcm`, `python-gdcm` & `pydicom` python packages & C++ libraries
 # MAGIC   - Simple composing and extension into De-Identification and Deep Learing
 # MAGIC <!-- -->
-# MAGIC 
+# MAGIC
 # MAGIC The `dbx.pixels` solution accelerator turns DICOM images into SQL data
 
 # COMMAND ----------
@@ -28,17 +28,20 @@
 # COMMAND ----------
 
 # MAGIC %md ## Licensing
-# MAGIC 
-# MAGIC &copy; 2022 Databricks, Inc. All rights reserved. The source in this notebook is provided subject to the Databricks License [https://databricks.com/db-license-source].  All included or referenced third party libraries are subject to the licenses set forth below.
-# MAGIC 
+# MAGIC
+# MAGIC &copy; 2024 Databricks, Inc. All rights reserved. The source in this notebook is provided subject to the Databricks License [https://databricks.com/db-license-source].  All included or referenced third party libraries are subject to the licenses set forth below.
+# MAGIC
 # MAGIC | library              | purpose                             | license                       | source                                                  |
 # MAGIC |----------------------|-------------------------------------|-------------------------------|---------------------------------------------------------|
 # MAGIC | dbx.pixels    | Scale out image processong Spark    | Databricks                    | https://github.com/databricks-industry-solutions/pixels |
 # MAGIC | pydicom              | Reading Dicom file wrapper          | MIT                           | https://github.com/pydicom/pydicom                      |
 # MAGIC | python-gdcm          | Install gdcm C++ libraries          | Apache Software License (BSD) | https://github.com/tfmoraes/python-gdcm                 |
-# MAGIC | gdcm                 | Parse Dicom files.                  | BSD                           | https://gdcm.sourceforge.net/wiki/index.php/Main_Page   |
+# MAGIC | gdcm                 | Parse Dicom files                   | BSD                           | https://gdcm.sourceforge.net/wiki/index.php/Main_Page   |
 # MAGIC | s3fs                 | Resolve s3:// paths                 | BSD 3-Clause                  | https://github.com/fsspec/s3fs                          |
 # MAGIC | pandas               | Pandas UDFs                         | BSD License (BSD-3-Clause)    | https://github.com/pandas-dev/pandas                    |
+# MAGIC | OHIF Viewer          | Medical image viewer                | MIT                           | https://github.com/OHIF/Viewers                         |
+# MAGIC | MONAILabel           | Intelligent open source image labeling and learning tool | Apache-2.0 license  | https://github.com/Project-MONAI/MONAILabel |
+# MAGIC
 
 # COMMAND ----------
 

07-OHIF-Lakehouse-App.py

@@ -6,7 +6,7 @@
 
 # COMMAND ----------
 
-# MAGIC %pip install --upgrade databricks-sdk -q
+# MAGIC %pip install --upgrade databricks-sdk==0.36.0 -q
 # MAGIC dbutils.library.restartPython()
 
 # COMMAND ----------
@@ -26,7 +26,7 @@
 init_env()
 
 app_name = "pixels-ohif-viewer"
-serving_endpoint = "pixels-monai-uc"
+serving_endpoint_name = "pixels-monai-uc"
 
 w = WorkspaceClient()
 
@@ -70,25 +70,31 @@
                 .replace("{PIXELS_TABLE}", table)
             )
 
+resources = []
+
 sql_resource = AppResource(
   name="sql_warehouse",
   sql_warehouse=AppResourceSqlWarehouse(
     id=sql_warehouse_id,
     permission=AppResourceSqlWarehouseSqlWarehousePermission.CAN_USE
   )
 )
-
-serving_endpoint = AppResource(
-  name="serving_endpoint",
-  serving_endpoint=AppResourceServingEndpoint(
-    name=serving_endpoint,
-    permission=AppResourceServingEndpointServingEndpointPermission.CAN_QUERY
+resources.append(sql_resource)
+
+if serving_endpoint_name in [endpoint.name for endpoint in w.serving_endpoints.list()]:
+  serving_endpoint = AppResource(
+    name="serving_endpoint",
+    serving_endpoint=AppResourceServingEndpoint(
+      name=serving_endpoint_name,
+      permission=AppResourceServingEndpointServingEndpointPermission.CAN_QUERY
+    )
   )
-)
+  resources.append(serving_endpoint)
+
 
 print(f"Creating Lakehouse App with name {app_name}, this step will require few minutes to complete")
 
-app_created = w.apps.create_and_wait(name=app_name, resources=[sql_resource, serving_endpoint])
+app_created = w.apps.create_and_wait(name=app_name, resources=resources)
 app_deploy = w.apps.deploy_and_wait(app_name=app_name, source_code_path=lha_path)
 
 print(app_deploy.status.message)

RUNME.py

@@ -1,30 +1,30 @@
 # Databricks notebook source
 # MAGIC %md This notebook sets up the companion cluster(s) to run the solution accelerator. It also creates the Workflow to illustrate the order of execution. Happy exploring! 
 # MAGIC 🎉
-# MAGIC 
+# MAGIC
 # MAGIC **Steps**
 # MAGIC 1. Simply attach this notebook to a cluster and hit `Run all` for this notebook. A multi-step job and the clusters used in the job will be created for you and hyperlinks are printed on the last block of the notebook. 
-# MAGIC 
+# MAGIC
 # MAGIC 2. Run the accelerator notebooks: Feel free to explore the multi-step job page and **run the Workflow**, or **run the notebooks interactively** with the cluster to see how this solution accelerator executes. 
-# MAGIC 
+# MAGIC
 # MAGIC     2a. **Run the Workflow**: Navigate to the Workflow link and hit the `Run Now` 💥. 
 # MAGIC   
 # MAGIC     2b. **Run the notebooks interactively**: Attach the notebook with the cluster(s) created and execute as described in the `job_json['tasks']` below.
-# MAGIC 
+# MAGIC
 # MAGIC **Prerequisites** 
 # MAGIC 1. You need to have cluster creation permissions in this workspace.
-# MAGIC 
+# MAGIC
 # MAGIC 2. In case the environment has cluster-policies that interfere with automated deployment, you may need to manually create the cluster in accordance with the workspace cluster policy. The `job_json` definition below still provides valuable information about the configuration these series of notebooks should run with. 
-# MAGIC 
+# MAGIC
 # MAGIC **Notes**
 # MAGIC 1. The pipelines, workflows and clusters created in this script are not user-specific. Keep in mind that rerunning this script again after modification resets them for other users too.
-# MAGIC 
+# MAGIC
 # MAGIC 2. If the job execution fails, please confirm that you have set up other environment dependencies as specified in the accelerator notebooks. Accelerators may require the user to set up additional cloud infra or secrets to manage credentials. 
 
 # COMMAND ----------
 
 # DBTITLE 0,Install util packages
-# MAGIC %pip install git+https://github.com/databricks-academy/[email protected] git+https://github.com/databricks-industry-solutions/notebook-solution-companion@safe-print-html --quiet
+# MAGIC %pip install git+https://github.com/databricks-academy/[email protected] git+https://github.com/databricks-industry-solutions/notebook-solution-companion@serverless --quiet
 
 # COMMAND ----------
 
@@ -42,14 +42,12 @@
         },
         "tasks": [
            {
-                "job_cluster_key": "pixels_cluster",
                 "notebook_task": {
                     "notebook_path": f"00-README"
                 },
                 "task_key": "00-README"
             },
             {
-                "job_cluster_key": "pixels_cluster",
                 "notebook_task": {
                     "notebook_path": f"01-dcm-demo"
                 },
@@ -61,36 +59,27 @@
                   ]
             },
             {
-                "job_cluster_key": "pixels_cluster",
                 "notebook_task": {
-                    "notebook_path": f"02-dcm-browser"
+                    "notebook_path": f"07-OHIF-Lakehouse-App"
                 },
-                "task_key": "02-dcm-browser",
+                "task_key": "07-OHIF-Lakehouse-App",
                 "depends_on": [
                     {
                         "task_key": "01-dcm-demo"
                     }
                 ]
             }
         ],
-        "job_clusters": [
+        "parameters": [
             {
-                "job_cluster_key": "pixels_cluster",
-                "new_cluster": {
-                    "spark_version": "14.3.x-scala2.12",
-                "spark_conf": {
-                    "spark.databricks.delta.formatCheck.enabled": "false"
-                    },
-                    "num_workers": 8,
-                    "node_type_id": {"AWS": "c5d.2xlarge", "MSA": "Standard_DS4_v2", "GCP": "n1-highmem-4"},
-                    "custom_tags": {
-                      "usage": "solacc_testing",
-                      "group": "HLS",
-                      "accelerator": "pixels"
-                  },
-                }
+                "name": "table",
+                "default": "main.pixel_solacc.object_catalog"
+            },
+            {
+                "name": "volume",
+                "default": "main.pixel_solacc.pixels_volume"
             }
-        ]
+            ]
     }
 
 # COMMAND ----------

config/proxy_prep.py

@@ -16,6 +16,12 @@ def init_widgets(show_volume=False):
   dbutils.widgets.text("sqlWarehouseID", "", label="2.0 SQL Warehouse")
   sql_warehouse_id = dbutils.widgets.get("sqlWarehouseID")
 
+  if sql_warehouse_id == "":
+    sql_warehouse = w.warehouses.list()[0]
+    sql_warehouse_id = sql_warehouse.id
+    dbutils.widgets.text("sqlWarehouseID", sql_warehouse_id, label="2.0 SQL Warehouse")
+    print(f"SQL Warehouse is mandatory, taking the first available: '{sql_warehouse.name}'")
+
   if show_volume:
     dbutils.widgets.text("volume", "main.pixels_solacc.pixels_volume", label="3.0 Catalog Schema Volume where pixel volumes are stored into")
     volume = dbutils.widgets.get("volume")
@@ -47,10 +53,10 @@ def init_env():
   else:
       wh = w.warehouses.get(id=sql_warehouse_id)
       print(f"Using '{wh.as_dict()['name']}' as SQL Warehouse")
-        
+
   os.environ["DATABRICKS_TOKEN"] = ctx.apiToken
   os.environ["DATABRICKS_WAREHOUSE_ID"] = sql_warehouse_id
-  os.environ["DATABRICKS_HOST"] = f"https://{ctx.browserHostName}"
+  os.environ["DATABRICKS_HOST"] = ctx.apiUrl
   os.environ["DATABRICKS_PIXELS_TABLE"] = table
 
 # COMMAND ----------

config/setup.py

@@ -17,7 +17,7 @@
 
 # DBTITLE 1,Collect Input Parameters
 def init_widgets():
-  dbutils.widgets.text("path", "s3://hls-eng-data-public/dicom/ddsm/benigns_2*.zip", label="1.0 Path to directory tree containing files. /dbfs , /Volumes/ or s3:// supported")
+  dbutils.widgets.text("path", "s3://hls-eng-data-public/dicom/ddsm/benigns_21*.zip", label="1.0 Path to directory tree containing files. /dbfs , /Volumes/ or s3:// supported")
   dbutils.widgets.text("table", "main.pixels_solacc.object_catalog", label="2.0 Catalog Schema Table to store object metadata into")
   dbutils.widgets.text("volume", "main.pixels_solacc.pixels_volume", label="3.0 Catalog Schema Volume to store checkpoints and unzipped files")
   dbutils.widgets.dropdown("mode",defaultValue="append",choices=["overwrite","append"], label="4.0 Update mode on object metadata table")

dbx/pixels/resources/lakehouse_app/app.py

@@ -30,7 +30,11 @@
 
 table = os.environ["DATABRICKS_PIXELS_TABLE"]
 warehouse_id = os.environ["DATABRICKS_WAREHOUSE_ID"]
-serving_endpoint = os.environ["MONAI_SERVING_ENDPOINT"]
+
+if "MONAI_SERVING_ENDPOINT" in os.environ:
+    serving_endpoint = os.environ["MONAI_SERVING_ENDPOINT"]
+else:
+    serving_endpoint = ""
 
 path = Path(dbx.pixels.__file__).parent
 ohif_path = f"{path}/resources/ohif"