{"payload":{"pageCount":2,"repositories":[{"type":"Public","name":"lsql","owner":"databrickslabs","isFork":false,"description":"Lightweight SQL execution wrapper only on top of Databricks SDK","topicNames":["databricks","databricks-sql","databricks-sdk"],"topicsNotShown":0,"allTopics":["databricks","databricks-sql","databricks-sdk"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":4,"issueCount":17,"starsCount":2,"forksCount":1,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-17T02:41:03.442Z"}},{"type":"Public","name":"remorph","owner":"databrickslabs","isFork":false,"description":"Cross-compiler into Databricks Lakehouse","topicNames":["transpiler","databricks"],"topicsNotShown":0,"allTopics":["transpiler","databricks"],"primaryLanguage":{"name":"ANTLR","color":"#9DC3FF"},"pullRequestCount":13,"issueCount":102,"starsCount":12,"forksCount":10,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-17T01:34:40.139Z"}},{"type":"Public","name":"dbldatagen","owner":"databrickslabs","isFork":false,"description":"Generate relevant synthetic data quickly for your projects. The Databricks Labs synthetic data generator (aka `dbldatagen`) may be used to generate large simulated / synthetic data sets for test, POCs, and other uses in Databricks environments including in Delta Live Tables pipelines","topicNames":["spark","faker","pyspark","spark-streaming","data-generation","databricks","synthetic-data","datagen","datagenerator","deltalake"],"topicsNotShown":3,"allTopics":["spark","faker","pyspark","spark-streaming","data-generation","databricks","synthetic-data","datagen","datagenerator","deltalake","datageneration","delta-live-tables","python"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":16,"issueCount":15,"starsCount":268,"forksCount":52,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-16T23:49:36.794Z"}},{"type":"Public","name":"ucx","owner":"databrickslabs","isFork":false,"description":"Your best companion for upgrading to Unity Catalog. UCX will guide you, the Databricks customer, through the process of upgrading your account, groups, workspaces, jobs etc. to Unity Catalog.","topicNames":["databricks","unity-catalog","databricks-cli-installable"],"topicsNotShown":0,"allTopics":["databricks","unity-catalog","databricks-cli-installable"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":16,"issueCount":106,"starsCount":162,"forksCount":61,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-16T22:54:10.781Z"}},{"type":"Public","name":"mosaic","owner":"databrickslabs","isFork":false,"description":"An extension to the Apache Spark framework that allows easy and fast processing of very large geospatial datasets.","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Jupyter Notebook","color":"#DA5B0B"},"pullRequestCount":10,"issueCount":57,"starsCount":255,"forksCount":61,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-16T21:32:10.300Z"}},{"type":"Public","name":"overwatch","owner":"databrickslabs","isFork":false,"description":"Capture deep metrics on one or all assets within a Databricks workspace","topicNames":["monitoring","databricks"],"topicsNotShown":0,"allTopics":["monitoring","databricks"],"primaryLanguage":{"name":"Scala","color":"#c22d40"},"pullRequestCount":12,"issueCount":136,"starsCount":217,"forksCount":59,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-16T21:03:07.013Z"}},{"type":"Public","name":"blueprint","owner":"databrickslabs","isFork":false,"description":"Baseline for Databricks Labs projects written in Python ","topicNames":["python","cli","databricks","databricks-cli-installable"],"topicsNotShown":0,"allTopics":["python","cli","databricks","databricks-cli-installable"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":2,"issueCount":3,"starsCount":10,"forksCount":6,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-16T19:47:30.907Z"}},{"type":"Public","name":"sandbox","owner":"databrickslabs","isFork":false,"description":"Experimental or low-maturity things","topicNames":["databricks","databricks-api","databricks-sdk"],"topicsNotShown":0,"allTopics":["databricks","databricks-api","databricks-sdk"],"primaryLanguage":{"name":"Go","color":"#00ADD8"},"pullRequestCount":13,"issueCount":6,"starsCount":16,"forksCount":4,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-16T16:04:23.385Z"}},{"type":"Public","name":"tempo","owner":"databrickslabs","isFork":false,"description":"API for manipulating time series on top of Apache Spark: lagged time values, rolling statistics (mean, avg, sum, count, etc), AS OF joins, downsampling, and interpolation","topicNames":["python","scala","timeseries-data","timeseries-analysis","data-science","timeseries","time-series","pandas","data-analysis"],"topicsNotShown":0,"allTopics":["python","scala","timeseries-data","timeseries-analysis","data-science","timeseries","time-series","pandas","data-analysis"],"primaryLanguage":{"name":"Jupyter Notebook","color":"#DA5B0B"},"pullRequestCount":11,"issueCount":32,"starsCount":294,"forksCount":50,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-15T18:33:43.781Z"}},{"type":"Public","name":"dlt-meta","owner":"databrickslabs","isFork":false,"description":"This is metadata driven DLT based framework for bronze/silver pipelines","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":3,"issueCount":15,"starsCount":122,"forksCount":51,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-09T23:29:32.612Z"}},{"type":"Public","name":"dbignite","owner":"databrickslabs","isFork":false,"description":"","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":22,"forksCount":10,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-08T23:38:59.965Z"}},{"type":"Public","name":"dataframe-rules-engine","owner":"databrickslabs","isFork":false,"description":"Extensible Rules Engine for custom Dataframe / Dataset validation","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Scala","color":"#c22d40"},"pullRequestCount":4,"issueCount":8,"starsCount":133,"forksCount":30,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-07T21:04:37.881Z"}},{"type":"Public","name":"splunk-integration","owner":"databrickslabs","isFork":false,"description":"Databricks Add-on for Splunk","topicNames":["cybersecurity","databricks","databricks-notebooks","splunk-addon"],"topicsNotShown":0,"allTopics":["cybersecurity","databricks","databricks-notebooks","splunk-addon"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":3,"issueCount":14,"starsCount":26,"forksCount":17,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-07T10:27:01.996Z"}},{"type":"Public","name":"pylint-plugin","owner":"databrickslabs","isFork":false,"description":"Databricks Plugin for PyLint","topicNames":["python","databricks","pylint-plugin"],"topicsNotShown":0,"allTopics":["python","databricks","pylint-plugin"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":11,"starsCount":7,"forksCount":2,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-04-26T12:01:18.287Z"}},{"type":"Public","name":"databricks-sdk-r","owner":"databrickslabs","isFork":false,"description":"Databricks SDK for R (Experimental)","topicNames":["data-science","r","sdk","databricks"],"topicsNotShown":0,"allTopics":["data-science","r","sdk","databricks"],"primaryLanguage":{"name":"R","color":"#198CE7"},"pullRequestCount":1,"issueCount":6,"starsCount":20,"forksCount":4,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-04-08T10:28:16.311Z"}},{"type":"Public","name":"tika-ocr","owner":"databrickslabs","isFork":false,"description":"","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Rich Text Format","color":"#ccc"},"pullRequestCount":4,"issueCount":0,"starsCount":17,"forksCount":2,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-04-03T20:25:20.972Z"}},{"type":"Public","name":"discoverx","owner":"databrickslabs","isFork":false,"description":"A Swiss-Army-knife for your Data Intelligence platform administration.","topicNames":["scanning","data-retrieval","pii-detection","semantic-classification","multi-table-operations"],"topicsNotShown":0,"allTopics":["scanning","data-retrieval","pii-detection","semantic-classification","multi-table-operations"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":10,"issueCount":7,"starsCount":98,"forksCount":9,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-03-27T11:23:04.648Z"}},{"type":"Public","name":"delta-sharing-java-connector","owner":"databrickslabs","isFork":false,"description":"A Java connector for delta.io/sharing/ that allows you to easily ingest data on any JVM.","topicNames":["java","delta-sharing"],"topicsNotShown":0,"allTopics":["java","delta-sharing"],"primaryLanguage":{"name":"Java","color":"#b07219"},"pullRequestCount":2,"issueCount":2,"starsCount":12,"forksCount":5,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-03-25T18:59:46.547Z"}},{"type":"Public","name":"transpiler","owner":"databrickslabs","isFork":false,"description":"SIEM-to-Spark Transpiler","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Scala","color":"#c22d40"},"pullRequestCount":5,"issueCount":13,"starsCount":39,"forksCount":5,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-03-18T20:31:06.843Z"}},{"type":"Public","name":"smolder","owner":"databrickslabs","isFork":false,"description":"HL7 Apache Spark Datasource","topicNames":["spark","hl7","datasource","hl7v2"],"topicsNotShown":0,"allTopics":["spark","hl7","datasource","hl7v2"],"primaryLanguage":{"name":"Scala","color":"#c22d40"},"pullRequestCount":0,"issueCount":1,"starsCount":56,"forksCount":19,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-03-15T17:53:23.893Z"}},{"type":"Public","name":"dbx","owner":"databrickslabs","isFork":false,"description":"🧱 Databricks CLI eXtensions - aka dbx is a CLI tool for development and advanced Databricks workflows management.","topicNames":["ci","cicd","databricks","mlops","databricks-cli","databricks-api"],"topicsNotShown":0,"allTopics":["ci","cicd","databricks","mlops","databricks-cli","databricks-api"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":12,"issueCount":91,"starsCount":434,"forksCount":119,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-02-26T13:26:25.713Z"}},{"type":"Public","name":"doc-qa","owner":"databrickslabs","isFork":false,"description":"","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":4,"issueCount":0,"starsCount":41,"forksCount":5,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-02-23T06:55:32.059Z"}},{"type":"Public","name":"databricks-sync","owner":"databrickslabs","isFork":false,"description":"An experimental tool to synchronize source Databricks deployment with a target Databricks deployment.","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":7,"issueCount":16,"starsCount":45,"forksCount":12,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-01-21T19:34:04.619Z"}},{"type":"Public","name":"arcuate","owner":"databrickslabs","isFork":false,"description":"Delta Sharing + MLflow for ML model &amp; experiment exchange (arcuate delta - a fan shaped river delta)","topicNames":["big-data","spark","data-sharing","mlflow","delta-sharing"],"topicsNotShown":0,"allTopics":["big-data","spark","data-sharing","mlflow","delta-sharing"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":9,"issueCount":0,"starsCount":21,"forksCount":1,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-12-27T15:16:04.250Z"}},{"type":"Public","name":"feature-factory","owner":"databrickslabs","isFork":false,"description":"Accelerator to rapidly deploy customized features for your business","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":4,"issueCount":1,"starsCount":54,"forksCount":25,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-12-10T20:34:04.112Z"}},{"type":"Public","name":"delta-oms","owner":"databrickslabs","isFork":false,"description":"DeltaOMS is a solution that help build a centralized repository of Delta Transaction logs and associated operational metrics/statistics for your Delta Lakehouse. Unity Catalog supported in the v0.7.0-rc1 release.Documentation here - <a href=\"https://databrickslabs.github.io/delta-oms/v0.7.0-rc1/\" rel=\"nofollow\">https://databrickslabs.github.io/delta-oms/v0.7.0-rc1/</a>","topicNames":["monitoring","metrics","delta","centralized","databricks","delta-lake","lakehouse"],"topicsNotShown":0,"allTopics":["monitoring","metrics","delta","centralized","databricks","delta-lake","lakehouse"],"primaryLanguage":{"name":"Scala","color":"#c22d40"},"pullRequestCount":1,"issueCount":6,"starsCount":36,"forksCount":3,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-11-27T22:06:31.489Z"}},{"type":"Public","name":"partner-connect-api","owner":"databrickslabs","isFork":false,"description":"","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Scala","color":"#c22d40"},"pullRequestCount":11,"issueCount":1,"starsCount":12,"forksCount":3,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-11-27T22:05:07.253Z"}},{"type":"Public","name":"migrate","owner":"databrickslabs","isFork":false,"description":"Old scripts for one-off ST-to-E2 migrations. Use \"terraform exporter\" linked in the readme.","topicNames":["databricks-migration"],"topicsNotShown":0,"allTopics":["databricks-migration"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":7,"issueCount":42,"starsCount":170,"forksCount":122,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-11-27T22:01:42.597Z"}},{"type":"Public","name":"dolly","owner":"databrickslabs","isFork":false,"description":"Databricks’ Dolly, a large language model trained on the Databricks Machine Learning Platform","topicNames":["chatbot","gpt","databricks","dolly"],"topicsNotShown":0,"allTopics":["chatbot","gpt","databricks","dolly"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":5,"starsCount":10791,"forksCount":1162,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-06-30T18:36:16.616Z"}},{"type":"Public","name":"geoscan","owner":"databrickslabs","isFork":false,"description":"Geospatial clustering at massive scale","topicNames":["library","spark-ml","clustering"],"topicsNotShown":0,"allTopics":["library","spark-ml","clustering"],"primaryLanguage":{"name":"Scala","color":"#c22d40"},"pullRequestCount":5,"issueCount":2,"starsCount":92,"forksCount":19,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-05-22T01:58:31.628Z"}}],"repositoryCount":34,"userInfo":null,"searchable":true,"definitions":[],"typeFilters":[{"id":"all","text":"All"},{"id":"public","text":"Public"},{"id":"source","text":"Sources"},{"id":"fork","text":"Forks"},{"id":"archived","text":"Archived"},{"id":"template","text":"Templates"}],"compactMode":false},"title":"Repositories"}