Spaces:
Sleeping
Sleeping
File size: 10,809 Bytes
70a2533 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 |
from flask import Flask, request, jsonify
import threading
import requests
import json
app = Flask(__name__)
def create_databricks_job(data):
mode = data.get('mode')
databricks_instance = data.get('databricks_instance')
databricks_api_key = data.get('databricks_api_key')
new_dataset = data.get('new_dataset')
dataset_id = data.get('dataset_id')
table_path = data.get('table_path')
labelbox_api_key = data.get('labelbox_api_key')
frequency = data.get('frequency')
new_cluster = data.get('new_cluster')
cluster_id = data.get('cluster_id')
schema_map = data.get('schema_map')
# Define the authentication headers
headers = {
"Authorization": f"Bearer {databricks_api_key}",
"Content-Type": "application/json",
}
# ----- CLUSTER CREATION LOGIC -----
def create_all_purpose_cluster(databricks_instance):
url = f"https://{databricks_instance}/api/2.0/clusters/create"
cluster_payload = {
"autoscale": {
"min_workers": 1,
"max_workers": 10
},
"cluster_name": "Labelbox Worker",
"spark_version": "11.3.x-scala2.12",
"gcp_attributes": {
"use_preemptible_executors": False,
"availability": "PREEMPTIBLE_WITH_FALLBACK_GCP",
"zone_id": "HA"
},
"node_type_id": "n2-highmem-4",
"driver_node_type_id": "n2-highmem-4",
"ssh_public_keys": [],
"custom_tags": {},
"cluster_log_conf": {
"dbfs": {
"destination": "dbfs:/cluster-logs"
}
},
"spark_env_vars": {},
"autotermination_minutes": 60,
"enable_elastic_disk": False,
"init_scripts": [],
"enable_local_disk_encryption": False,
"runtime_engine": "STANDARD"
}
response = requests.post(url, data=json.dumps(cluster_payload), headers=headers)
if response.status_code == 200:
return response.json()['cluster_id']
else:
raise Exception(f"Failed to create all-purpose cluster. Error: {response.text}")
# ----- PREVIEW MODE LOGIC -----
def create_preview(dataset_id, table_path, labelbox_api_key, frequency, cluster_id):
# ----- JOB SCHEDULING LOGIC -----
if frequency == "continuous":
schedule_block = {
"continuous": {
"pause_status": "UNPAUSED"
}
}
else:
schedule_block = {
"schedule": {
"quartz_cron_expression": frequency,
"timezone_id": "UTC",
"pause_status": "UNPAUSED"
}
}
# ----- JOB DEFINITION -----
# Define the parameters and structure of the job to be created in Databricks
payload = {
"name": "PREVIEW_upload_to_labelbox",
"email_notifications": {"no_alert_for_skipped_runs": False},
"webhook_notifications": {},
"timeout_seconds": 0,
"max_concurrent_runs": 1,
"tasks": [
{
"existing_cluster_id": cluster_id, # Move this inside the task
"task_key": "PREVIEW_upload_to_labelbox",
"run_if": "ALL_SUCCESS",
"notebook_task": {
"notebook_path": "notebooks/databricks_pipeline_creator/preview_upload_to_labelbox",
"base_parameters": {
"dataset_id": dataset_id,
"table_path": table_path,
"labelbox_api_key": labelbox_api_key,
"schema_map": schema_map
},
"source": "GIT"
},
"libraries": [
{"pypi": {"package": "labelspark"}},
{"pypi": {"package": "labelbox==3.49.1"}},
{"pypi": {"package": "numpy==1.25"}},
{"pypi": {"package": "opencv-python==4.8.0.74"}}
],
"timeout_seconds": 0,
"email_notifications": {},
"notification_settings": {
"no_alert_for_skipped_runs": False,
"no_alert_for_canceled_runs": False,
"alert_on_last_attempt": False
}
}
],
"git_source": {
"git_url": "https://github.com/Labelbox/labelspark.git",
"git_provider": "gitHub",
"git_branch": "master"
},
"format": "MULTI_TASK"
}
# Merge the scheduling configuration into the main job payload
payload.update(schedule_block)
return payload
# ----- PRODUCTION MODE LOGIC -----
def create_production(dataset_id, table_path, labelbox_api_key, frequency):
# ----- JOB SCHEDULING LOGIC -----
# If the job needs to run continuously, use the "continuous" block
# Else, use the "schedule" block with the specified cron frequency
if frequency == "continuous":
schedule_block = {
"continuous": {
"pause_status": "UNPAUSED"
}
}
else:
schedule_block = {
"schedule": {
"quartz_cron_expression": frequency,
"timezone_id": "UTC",
"pause_status": "UNPAUSED"
}
}
# ----- JOB DEFINITION -----
# Define the parameters and structure of the job to be created in Databricks
payload = {
"name": "upload_to_labelbox",
"email_notifications": {"no_alert_for_skipped_runs": False},
"webhook_notifications": {},
"timeout_seconds": 0,
"max_concurrent_runs": 1,
"tasks": [
{
"task_key": "upload_to_labelbox",
"run_if": "ALL_SUCCESS",
"notebook_task": {
"notebook_path": "notebooks/databricks_pipeline_creator/upload_to_labelbox",
"base_parameters": {
"dataset_id": dataset_id,
"table_path": table_path,
"labelbox_api_key": labelbox_api_key,
"schema_map": schema_map
},
"source": "GIT"
},
"job_cluster_key": "Job_cluster",
"libraries": [
{"pypi": {"package": "labelspark"}},
{"pypi": {"package": "labelbox==3.49.1"}},
{"pypi": {"package": "numpy==1.25"}},
{"pypi": {"package": "opencv-python==4.8.0.74"}}
],
"timeout_seconds": 0,
"email_notifications": {},
"notification_settings": {
"no_alert_for_skipped_runs": False,
"no_alert_for_canceled_runs": False,
"alert_on_last_attempt": False
}
}
],
"job_clusters": [
{
"job_cluster_key": "Job_cluster",
"new_cluster": {
"cluster_name": "",
"spark_version": "13.3.x-scala2.12",
"gcp_attributes": {
"use_preemptible_executors": False,
"availability": "ON_DEMAND_GCP",
"zone_id": "HA"
},
"node_type_id": "n2-highmem-4",
"enable_elastic_disk": True,
"data_security_mode": "SINGLE_USER",
"runtime_engine": "STANDARD",
"autoscale": {
"min_workers": 1,
"max_workers": 10
}
}
}
],
"git_source": {
"git_url": "https://github.com/Labelbox/labelspark.git",
"git_provider": "gitHub",
"git_branch": "master"
},
"format": "MULTI_TASK"
}
# Merge the scheduling configuration into the main job payload
payload.update(schedule_block)
return payload
# if cluster_id blank or null:
if new_cluster == True:
cluster_id = create_all_purpose_cluster(databricks_instance)
print(f"Created all-purpose cluster with ID: {cluster_id}")
else:
print(f"Using existing cluster with ID: {cluster_id}")
if mode == "preview":
payload = create_preview(dataset_id, table_path, labelbox_api_key, frequency, cluster_id)
elif mode == "production":
payload = create_production(dataset_id, table_path, labelbox_api_key, frequency)
else:
return f"Invalid mode: {mode}"
# ----- JOB CREATION -----
# Formulate the endpoint URL for the Databricks REST API job creation
url = f"https://{databricks_instance}/api/2.0/jobs/create"
# Send the POST request to Databricks to create the job
response = requests.post(url, data=json.dumps(payload), headers=headers)
# ----- RESPONSE HANDLING -----
if response.status_code == 200:
return f"Job created successfully. {response.text}"
else:
return f"Failed to create job. Error: {response.text}"
@app.route('/create-databricks-job', methods=['POST'])
def api_create_databricks_job():
data = request.get_json()
result = create_databricks_job(data)
return jsonify({"message": result})
def run():
app.run(port=5000)
threading.Thread(target=run).start() |