{"type":"doc","content":[{"type":"paragraph","content":[{"text":"The following are steps to run a Batch Scoring Job on a Batch Deployed Model.","type":"text"}]},{"type":"paragraph","content":[{"text":"Table of Contents","type":"text","marks":[{"type":"strong"}]}]},{"type":"extension","attrs":{"layout":"default","extensionType":"com.atlassian.confluence.macro.core","extensionKey":"toc","parameters":{"macroParams":{"minLevel":{"value":"1"},"maxLevel":{"value":"7"}},"macroMetadata":{"macroId":{"value":"7a6ed7fb7216a6c2f90f38220fddc731"},"schemaVersion":{"value":"1"},"title":"Table of Contents"}},"localId":"5e0ff779-4d09-498a-bd75-0249133cceb8"}},{"type":"heading","attrs":{"level":1},"content":[{"text":"Pre-requisites:","type":"text"}]},{"type":"heading","attrs":{"level":2},"content":[{"text":"Deploy a Model as Batch","type":"text"}]},{"type":"paragraph","content":[{"text":"Prior to running a Batch Scoring job, you should have a Model Deployed as Batch. To do so, please refer to the section ","type":"text"},{"type":"inlineCard","attrs":{"url":"https://modelopdocs.atlassian.net/wiki/spaces/dv25/pages/1655341915/Operationalizing+Models%3A+Batch#Operationalize-a-Model---Batch-Deployment-in-a-ModelOp-Runtime"}},{"text":".","type":"text"}]},{"type":"heading","attrs":{"level":2},"content":[{"text":"Pepare Runtimes","type":"text"}]},{"type":"paragraph","content":[{"text":"Identify the target Runtimes across the requisite Environments. ","type":"text"}]},{"type":"panel","attrs":{"panelType":"info"},"content":[{"type":"paragraph","content":[{"text":"Please note, it is possible this step has already been done given the pre-requisites, but it’s worth noting that the Runtime matching also happens at Job scheduling so the engine still has to match at Job creation, not only at deployment time. ","type":"text"}]}]},{"type":"paragraph","content":[{"text":"For each target Runtime, complete the following:","type":"text"}]},{"type":"orderedList","attrs":{"order":1},"content":[{"type":"listItem","content":[{"type":"paragraph","content":[{"text":"Add “Environment/Stage Tags”","type":"text","marks":[{"type":"strong"}]},{"text":". Based on the environments/stages required (see pre-requisites), add the necessary “environment/stage tag” to the runtime.","type":"text"}]},{"type":"orderedList","attrs":{"order":1},"content":[{"type":"listItem","content":[{"type":"paragraph","content":[{"text":"Example","type":"text","marks":[{"type":"strong"}]},{"text":": add a “DEV” tag to the Runtime in their development environment, an “SIT” tag to the Runtime in their SIT environment, a “UAT” tag to the Runtime in their UAT environment, and ultimately a “PROD” tag to the Runtime in their Prod environment","type":"text"}]}]}]}]},{"type":"listItem","content":[{"type":"paragraph","content":[{"text":"Add “Model Service Tags”","type":"text","marks":[{"type":"strong"}]},{"text":". The Model “Service” tag will be used to identify that this specific runtime is designed to be a target runtime for that particular model. Add the appropriate “Model Service Tag” to the runtime.","type":"text"}]},{"type":"orderedList","attrs":{"order":1},"content":[{"type":"listItem","content":[{"type":"paragraph","content":[{"text":"Example","type":"text","marks":[{"type":"strong"}]},{"text":": add a “cc-fraud” Model Service Tag to the runtime for a 3rd party credit card model to the “Dev”, “SIT”, “UAT”, and “Prod” runtimes.","type":"text"}]}]}]}]}]},{"type":"heading","attrs":{"level":1},"content":[{"text":"Running batch Job with MLC","type":"text"}]},{"type":"heading","attrs":{"level":2},"content":[{"text":"Trigger Job Creation:","type":"text"}]},{"type":"heading","attrs":{"level":3},"content":[{"text":"Launch MLC via REST API","type":"text"}]},{"type":"bulletList","content":[{"type":"listItem","content":[{"type":"paragraph","content":[{"text":"Make sure the ","type":"text"},{"text":"RunBatchJob.bpmn","type":"text","marks":[{"type":"link","attrs":{"href":"https://github.com/modelop/mlc-building-blocks/blob/master/eval-bpmns/default/RunBatchJob.bpmn"}}]},{"text":" MLC is deployed in the MOC environment.","type":"text"}]},{"type":"bulletList","content":[{"type":"listItem","content":[{"type":"paragraph","content":[{"text":"More info about the MLC found on the ","type":"text"},{"text":"Run Batch Job MLC","type":"text","marks":[{"type":"link","attrs":{"href":"https://modelopdocs.atlassian.net/wiki/spaces/dv25/pages/1655341684/Model+Lifecycle+Management%3A+Overview#Run-Batch-Model-Job-MLC-Process"}}]},{"text":".","type":"text"}]}]}]}]},{"type":"listItem","content":[{"type":"paragraph","content":[{"text":"Send a request to run a batch job with the endpoint signalResponsive as below:","type":"text"},{"type":"hardBreak"},{"text":"http://gateway/mlc-service/rest/signalResponsive","type":"text","marks":[{"type":"link","attrs":{"href":"http://gateway/mlc-service/rest/signalResponsive"}},{"type":"strong"}]},{"text":" ","type":"text","marks":[{"type":"strong"}]}]},{"type":"bulletList","content":[{"type":"listItem","content":[{"type":"paragraph","content":[{"text":"More info about Camunda Signal endpoint found on the ","type":"text"},{"text":"Trigger Execution Camunda docs","type":"text","marks":[{"type":"link","attrs":{"href":"https://docs.camunda.org/manual/7.15/reference/rest/execution/post-signal/"}}]},{"text":". Note the endpoint used above is called signalResponsive as opposed to the documentation linked.","type":"text"}]}]},{"type":"listItem","content":[{"type":"paragraph","content":[{"text":"More info about customizing the variables on the request found ","type":"text"},{"text":"Variables in the REST API Camunda docs","type":"text","marks":[{"type":"link","attrs":{"href":"https://docs.camunda.org/manual/latest/reference/rest/overview/variables/"}}]},{"text":".","type":"text"}]}]}]}]}]},{"type":"paragraph","content":[{"text":"Example request:","type":"text","marks":[{"type":"em"}]}]},{"type":"codeBlock","attrs":{"language":"shell"},"content":[{"text":"curl --request POST 'http://gateway/mlc-service/rest/signalResponsive' \\\n--header 'Content-Type: application/json' \\\n--header 'Authorization: Bearer {{token}}' \\\n--data-raw '{\n \"name\": \"com.modelop.mlc.definitions.Signals_DEPLOYED_BATCH_JOB\",\n \"variables\": {\n \"TAG\": {\n \"value\": \"model-service-tag\"\n },\n \"MODEL_STAGE\": {\n \"value\": \"PROD\"\n }\n }\n}'","type":"text"}]},{"type":"paragraph"},{"type":"expand","attrs":{"title":"Additional example including custom input asset"},"content":[{"type":"codeBlock","attrs":{"language":"json"},"content":[{"text":"{\n \"name\": \"com.modelop.mlc.definitions.Signals_DEPLOYED_BATCH_JOB\",\n \"variables\": {\n \"TAG\": {\n \"value\": \"model-service-tag\"\n },\n \"MODEL_STAGE\": {\n \"value\": \"PROD\"\n },\n \"INPUT_ASSETS\": {\n \"value\": \"[{\\\"name\\\": \\\"input_data.json\\\",\\\"assetType\\\": \\\"EXTERNAL_FILE\\\",\\\"repositoryInfo\\\": {\\\"repositoryType\\\": \\\"S3_REPOSITORY\\\",\\\"secure\\\": false,\\\"host\\\": \\\"modelop\\\",\\\"port\\\": 9000,\\\"region\\\": \\\"default-region\\\"},\\\"fileUrl\\\": \\\"http://modelop:9000/modelop/input_data.json\\\",\\\"filename\\\": \\\"input_data.json\\\",\\\"fileFormat\\\":\\\"JSON\\\"}]\",\n \"type\": \"Object\",\n \"valueInfo\": {\n \"objectTypeName\": \"java.util.ArrayList\",\n \"serializationDataFormat\": \"application/json\"\n }\n }\n }\n}","type":"text"}]},{"type":"panel","attrs":{"panelType":"info"},"content":[{"type":"paragraph","content":[{"text":"Notice the escaped value with the serialized asset list and the valueInfo with serialization info. ","type":"text"},{"type":"hardBreak"},{"text":"More info here (","type":"text"},{"text":"Variables in the REST API Camunda docs","type":"text","marks":[{"type":"link","attrs":{"href":"https://docs.camunda.org/manual/latest/reference/rest/overview/variables/"}}]},{"text":").","type":"text"}]}]}]},{"type":"heading","attrs":{"level":3},"content":[{"text":"Launch MLC via MOC CLI","type":"text"}]},{"type":"bulletList","content":[{"type":"listItem","content":[{"type":"paragraph","content":[{"text":"Make sure to have the ","type":"text"},{"text":"MOC CLI","type":"text","marks":[{"type":"link","attrs":{"__confluenceMetadata":{"isRenamedTitle":true,"linkType":"page","contentTitle":"ModelOp CLI Reference","versionAtSave":"1"},"href":"/wiki/spaces/dv25/pages/1655343681"}}]},{"text":" installed.","type":"text"}]}]},{"type":"listItem","content":[{"type":"paragraph","content":[{"text":"Create a json file a similar structure as the one described in the body of the request above.","type":"text"}]}]},{"type":"listItem","content":[{"type":"paragraph","content":[{"text":"Trigger signal with the following command:","type":"text"},{"type":"hardBreak"},{"text":"moc mlc trigger --file ","type":"text","marks":[{"type":"code"}]}]}]}]},{"type":"paragraph","content":[{"text":"Additional details","type":"text"}]},{"type":"expand","attrs":{"title":"Additional options about the MLC trigger through the CLI (file vs body)"},"content":[{"type":"paragraph","content":[{"text":"moc mlc trigger -h","type":"text","marks":[{"type":"code"}]}]},{"type":"codeBlock","attrs":{"language":"none"},"content":[{"text":"Trigger/launch an MLC process by providing signal object json body using --file or --body flag.\n\nUsage:\n moc mlc trigger [flags]\n\nExamples:\n\n# Trigger mlc using signal object from a file\nmoc mlc trigger --file ./path/to/file/signal.json\n\n# Trigger mlc using raw json\nmoc mlc trigger --body {\"name\":\"com.modelop.mlc.definitions.Signals_start_data_drift\",\"variables\":{\"TAG\":{\"value\":\"model_a\",\"type\":\"Object\",\"valueInfo\":{\"objectTypeName\":\"java.lang.String\",\"serializationDataFormat\":\"application/json\"}}}}\n\nFlags:\n --body string Provide JSON body for launching the MLC\n -f, --file string Use json from the file for launching the MLC\n -h, --help help for trigger","type":"text"}]}]},{"type":"heading","attrs":{"level":2},"content":[{"text":"Follow up:","type":"text"}]},{"type":"paragraph","content":[{"text":"To follow up the process triggered via MLC there are several points of validation. Please look at the following diagram to identify them as explained below.","type":"text"}]},{"type":"mediaSingle","attrs":{"layout":"center"},"content":[{"type":"media","attrs":{"width":701,"id":"405abf21-58e7-467b-bd0e-47e12c983c04","collection":"contentId-1655342067","type":"file","height":418}}]},{"type":"paragraph"},{"type":"orderedList","attrs":{"order":1},"content":[{"type":"listItem","content":[{"type":"paragraph","content":[{"text":"Use the ‘processInstanceId' returned by the signalResponsive endpoint mentioned above, to call the following endpoint and retrieve the “jobId\" from the JSON response.","type":"text"},{"type":"hardBreak"},{"text":"http://gateway/model-manage/api/jobHistories/search/findAllByJobMLCS_ProcessInstanceRootProcessInstanceId?processInstanceId={processInstanceId}","type":"text","marks":[{"type":"link","attrs":{"href":"https://gateway/model-manage/api/jobHistories/search/findAllByJobMLCS_ProcessInstanceRootProcessInstanceId?processInstanceId={processInstanceId}"}}]},{"text":" ","type":"text"}]}]},{"type":"listItem","content":[{"type":"paragraph","content":[{"text":"Use the ‘jobId’ returned by the previous call, to check the status of the job in the following endpoint. ","type":"text"},{"type":"hardBreak"},{"text":"http://gateway/model-manage/api/jobs/{jobId}","type":"text","marks":[{"type":"link","attrs":{"href":"http://gateway/model-manage/api/jobs/{jobId}"}}]},{"type":"hardBreak"},{"text":"If the job finished successfully or finished in error will be (or is still running), will be visible on this state.","type":"text"}]}]},{"type":"listItem","content":[{"type":"paragraph","content":[{"text":"But if the job never ran due to an error during the MLC, we can follow up on the runningInstance incidents through this endpoint.","type":"text"},{"type":"hardBreak"},{"text":"http://gateway/mlc-service/rest/incident?processInstanceId={processInstanceId}","type":"text","marks":[{"type":"link","attrs":{"href":"https://gateway/mlc-service/rest/incident?processInstanceId={processInstanceId}"}}]}]}]}]},{"type":"paragraph"},{"type":"heading","attrs":{"level":1},"content":[{"text":"Running batch job with CLI","type":"text"}]},{"type":"heading","attrs":{"level":2},"content":[{"text":"Trigger Job Creation:","type":"text"}]},{"type":"heading","attrs":{"level":3},"content":[{"text":"Launch MLC via REST API","type":"text"}]},{"type":"bulletList","content":[{"type":"listItem","content":[{"type":"paragraph","content":[{"text":"Make sure to have the ","type":"text"},{"text":"MOC CLI","type":"text","marks":[{"type":"link","attrs":{"__confluenceMetadata":{"isRenamedTitle":true,"linkType":"page","contentTitle":"ModelOp CLI Reference","versionAtSave":"1"},"href":"/wiki/spaces/dv25/pages/1655343681"}}]},{"text":" installed.","type":"text"}]}]},{"type":"listItem","content":[{"type":"paragraph","content":[{"text":"Create a json file a similar structure as the one described in the body of the request above.","type":"text"}]}]},{"type":"listItem","content":[{"type":"paragraph","content":[{"text":"Retrieve the deployment id","type":"text"},{"type":"hardBreak"},{"text":"moc deployment ls --state deployed --tag ","type":"text","marks":[{"type":"code"}]}]}]},{"type":"listItem","content":[{"type":"paragraph","content":[{"text":"Trigger signal with the following command:","type":"text"},{"type":"hardBreak"},{"text":"moc job create deployedbatch [flags]","type":"text","marks":[{"type":"code"}]}]}]}]},{"type":"paragraph","content":[{"text":"Additional details","type":"text"}]},{"type":"expand","attrs":{"title":"Additional options about the CLI job scoring batch job creation for a deployed model as batch."},"content":[{"type":"paragraph","content":[{"text":"moc job create deployedbatch -h","type":"text","marks":[{"type":"code"}]}]},{"type":"codeBlock","attrs":{"language":"none"},"content":[{"text":"Create and run a deployed batch job in ModelOp Center using a deployment ID, an input file, and an output file name.\n\nInput can be provided by the following methods:\n • Provide the path to a local file that will be embedded in the database for input. There is a size limit of 10MB for embedding files. If unsure of the file size, use the --force flag; this will not fail the command, and will push the file to the S3 bucket configured with ModelOp Center.\n • Provide the path to a local file and use the --upload-input flag to push the file to the S3 bucket configured with ModelOp Center.\n • Provide a URL to an existing file in the S3 bucket in the format [http/s3/S3n/S3a]://Domain/PATH/file.txt. The credentials should be configured with the ModelOp Center. When using a URL of a file in S3, use the --input-region flag to provide the S3 region. If the URL is not using one of the schemes - \"http\", \"s3\", \"s3n\", \"s3a\", use the --external-input flag to enforce the URL to be an external asset URL.\n • Provide a SQL asset as input. Use the connection URL as the input URL, e.g., mysql://username:password@host:3306/db_name. The query can be provided using the --input-query flag, and additional parameters can be provided using the --input-param flag. The --input-param flag can be used multiple times and the query parameters will be stored in the order the flags are provided. If the connection URL is not using one of the schemes - \"mysql\", \"sqlserver\", \"snowflakedsiidriver\", \"db2\", use the --sql-input flag to enforce the URL to be used as a SQL connection URL.\n • Provide a HDFS asset using a URL, e.g., hdfs:///hadoop/demo/test_model/sample_data.csv. If the URL is not using the \"hdfs\" scheme, use the --hdfs-input flag to enforce the URL to be a HDFS asset URL.\n\t• Use existing asset from the storedModel by providing asset name, e.g ref:asset_tes.json\n\nOutput can be provided in a similar way to the input, but uses output-related flags:\n • Provide a name for the output file that will be embedded in the database.\n • Provide a name of the file, and use the --upload-output flag to push the file to the S3 bucket configured with ModelOp Center.\n • Provide a URL to an existing file in the S3 bucket in a similar format as the input file. When using a URL of a file in S3, use the --output-region flag to provide the S3 region. If the URL is not using one of the schemes - \"http\", \"s3\", \"s3n\", \"s3a\", use the --external-output flag to enforce the URL to be external asset URL.\n • Provide a SQL asset as output. Use connection URL as the output URL, e.g., mysql://username:password@host:3306/db_name. The query can be provided using the --output-query flag, and additional parameters can be provided using the --output-param flag. The --output-param flag can be used multiple times and the query parameters will be stored in the order the flags are provided. If the connection URL is not using one of the schemes - \"mysql\", \"sqlserver\", \"snowflakedsiidriver\", \"db2\", use the --sql-output flag to enforce the URL to be used as a SQL connection URL.\n • Provide a HDFS asset using URL, e.g., hdfs:///hadoop/demo/test_model/sample_data.csv. If the URL is not using the \"hdfs\" scheme, use the --hdfs-output flag to enforce the URL to be a HDFS asset URL.\n\t• Use existing asset from the storedModel by providing asset name, e.g ref:output.json\n\nOnce the job is created, an engine is assigned to the job based on the MLC used for engine-to-job assignments. To specify the target engine, use the --engine flag and provide the engine name where the job should run.\n\nBy default, schema checking is disabled for all jobs. To enable input and/or output schema checking, use the --input-schema-check, --output-schema-check or --schema-check flags.\n\nThe deployment provided as a command argument should be a batch deployment and not a persistent deployment (endpoint deployment). To make sure that the batch model is in the DEPLOYED state, use --enforce-deployed flag.\n\nBy default, the command creates a job of type MODEL_BATCH_JOB using the deployed model provided. To create a job of type MODEL_BATCH_TRAINING_JOB and MODEL_BATCH_TEST_JOB, use --training-job and --test-job flag respectively.\n\nUsage:\n moc job create deployedbatch [flags]\n\nExamples:\n\n# Input: local file (embed) - Output: Empty embedded file\nmoc job create deployedbatch 4e4a19c7-2acb-4337-83c6-d0cc82db5a96 input.json output.json\n\n# Input: local file (embed) - Output: Create empty S3 file\nmoc job create deployedbatch 4e4a19c7-2acb-4337-83c6-d0cc82db5a96 input.json output.json --upload-output\n\n# Input: Upload local file to S3 - Output: Create empty S3 file\nmoc job create deployedbatch 4e4a19c7-2acb-4337-83c6-d0cc82db5a96 input.json --upload-input output.json --upload-output\n\n# Input: URL to file in S3 bucket configured with ModelOp Center - Output: Create empty S3 file\nmoc job create deployedbatch 4e4a19c7-2acb-4337-83c6-d0cc82db5a96 https://modelop.s3.us-east-2.amazonaws.com/test_model_data/input.json --input-region us-east-2 output.json --upload-output\n\n# Input: SQL asset - Output: SQL asset\nmoc job create deployedbatch 4e4a19c7-2acb-4337-83c6-d0cc82db5a96 mysql://username:password@host:3306/db_name --input-query 'SELECT symbol,price FROM xyz_table' mysql://username:password@host:3306/db_name --output-query 'INSERT INTO test_output (value) VALUES (?)' --output-param total\n\n# Input: URL to file in S3 bucket configured with ModelOp Center - Output: SQL asset\nmoc job create deployedbatch 4e4a19c7-2acb-4337-83c6-d0cc82db5a96 https://modelop.s3.us-east-2.amazonaws.com/test_model_data/input.json --input-region us-east-2 mysql://username:password@host:3306/db_name --output-query 'INSERT INTO test_output (value) VALUES (?)' --output-param total\n\n# Input: HDFS asset - Output: HDFS asset\nmoc job create deployedbatch 4e4a19c7-2acb-4337-83c6-d0cc82db5a96 hdfs:///hadoop/demo/test_model/sample_data.csv hdfs:///hadoop/demo/test_model/sample_output.csv\n\n# Input: Referenced asset from storedModel - Output: Referenced asset from storedModel\nmoc job create deployedbatch 4e4a19c7-2acb-4337-83c6-d0cc82db5a96 ref:input.sql ref:output.sql\n\n# Input - Upload local file to S3 and Output - Create empty S3 file, create deployed batch test job\nmoc job create deployedbatch 4e4a19c7-2acb-4337-83c6-d0cc82db5a96 input.json --upload-input output.json --upload-output --test-job\n\n# Input - SQL asset and Output - Create empty S3 file, create deployed batch training job\nmoc job create deployedbatch 4e4a19c7-2acb-4337-83c6-d0cc82db5a96 mysql://username:password@host:3306/db_name --input-query 'SELECT symbol,price FROM xyz_table' output.json --upload-output --training-job\n\nFlags:\n --enforce-deployed Enforce the state to be DEPLOYED on the model provided\n --engine string Specify target engine name where the job should run\n --external-input Force the URL provided for input to be an external S3 file URL\n --external-output Force the URL provided for output to be an external S3 file URL\n -f, --force In case file is too large to be stored as a local asset, store it as an external asset\n --hdfs-input Force the URL provided for input to be a HDFS URL\n --hdfs-output Force the URL provided for output to be a HDFS URL\n -h, --help help for deployedbatch\n --input-param stringArray Provide parameters for the input SQL query\n --input-query string Provide a query string for the input SQL asset\n --input-region string Provide the region for the input S3 URL\n --input-schema-check Enable schema checking on input\n --output-param stringArray Provide parameters for the output SQL query\n --output-query string Provide a query string for the output SQL asset\n --output-region string Provide the region for the output S3 URL\n --output-schema-check Enable schema checking on output\n --schema-check Enable schema checking on both input and output\n --sql-input Force the URL provided for input to be a SQL connection string\n --sql-output Force the URL provided for output to be a SQL connection string\n --test-job Create MODEL_BATCH_TEST_JOB with the model provided\n --training-job Create MODEL_BATCH_TRAINING_JOB with the model provided\n --upload-input Upload the input file provided to the S3 bucket configured with ModelOp Center\n --upload-output Create an output file with the provided name in the S3 bucket configured with ModelOp Center","type":"text"}]},{"type":"paragraph","content":[{"text":"More info about the CLI command on the (","type":"text"},{"text":"moc job docs","type":"text","marks":[{"type":"link","attrs":{"href":"https://modelop.atlassian.net/wiki/spaces/DV21/pages/1118896163/v2.1+ModelOp+CLI+Reference#job"}}]},{"text":").","type":"text"}]}]},{"type":"heading","attrs":{"level":2},"content":[{"text":"Follow up:","type":"text"}]},{"type":"paragraph","content":[{"text":"The above command returns the jobId which can be used in the following REST API endpoint to query the status:","type":"text"},{"type":"hardBreak"},{"text":"http://gateway/model-manage/api/jobs/{jobId}","type":"text","marks":[{"type":"link","attrs":{"href":"http://gateway/model-manage/api/jobs/{jobId}"}}]}]}],"version":1}

Browser not supported