LogoLogo
HomeCommunity
EN master
EN master
  • Introduction
  • Components
  • Quickstart
    • Using Docker
    • Using Java SDK
    • Using Python SDK
    • Using CLI
  • Building from source
  • Installing Binaries
  • Configurations
    • JSON
    • YAML
  • GitHub
  • Examples
    • Java
      • Server
        • Pipeline Steps
          • Image To NDArray Step
          • Python Step
          • DL4J Step
          • Keras Step
          • ONNX Step
          • Tensorflow Step
        • Sequence Pipeline
        • Graph Pipeline
      • Client
        • Running Predictions
        • Inspecting a Server
    • Python
      • Server
        • Pipeline Steps
          • Image To NDArray Step
          • Python Step
          • DL4J Step
        • Sequence Pipeline
        • Graph Pipeline
      • Client
        • Running Predictions
        • Inspecting a Server
    • IPython Notebook
      • Basic
      • ONNX
        • Pytorch (IRIS)
        • Pytorch (MNIST)
      • Keras
      • Tensorflow
      • DL4J
    • CLI
      • Use-Cases
        • Creating a Sequence Pipeline
        • Creating a Graph Pipeline
        • Create Server URL with Inspection Queries
        • Adding Extra Classpaths
        • Multiple Instances of a Server
      • Commands
        • Serve Command
        • Logs Command
        • Inspect Command
        • Profile Command
  • How-To Guides
    • Serving a BMI Model
      • With HTML Content
    • Performing Object Detection
    • RPA Use-Case
    • Showing Metrics
      • Prometheus
      • Grafana
  • References
    • Pipeline Steps
      • IMAGE_TO_NDARRAY
      • IMAGE_CROP
      • IMAGE_RESIZE
      • DEEPLEARNINGL4J
      • KERAS
      • ND4JTENSORFLOW
      • ONNX
      • TENSORFLOW
      • SAMEDIFF
      • CLASSIFIER_OUTPUT
      • REGRESSION_OUTPUT
      • LOGGING
      • BOUNDING_BOX_FILTER
      • BOUNDING_BOX_TO_POINT
      • CROP_GRID
      • CROP_FIXED_GRID
      • DRAW_BOUNDING_BOX
      • DRAW_FACE_KEY_POINT
      • DRAW_GRID
      • DRAW_FIXED_GRID
      • DRAW_HEATMAP
      • DRAW_POINTS
      • DRAW_SEGMENTATION
      • EXTRACT_BOUNDING_BOX
      • SSD_TO_BBOX
      • YOLO_BBOX
      • RELATIVE_TO_ABSOLUTE
      • SHOW_IMAGE
      • FRAME_CAPTURE
      • VIDEO_CAPTURE
      • PERSPECTIVE_TRANSFORM
    • Inference Configuration
      • MQTT Configuration
      • KAFKA Configuration
    • CLI Commands
      • Serve Command
      • Logs Command
      • Inspect Command
      • Pythonpaths Command
      • Build Command
      • Config Command
      • Predict Command
      • Profile Command
  • Change Logs
    • Version 0.1.0
  • Contribution Guidelines
Powered by GitBook
On this page

Was this helpful?

  1. Configurations

JSON

In JSON format

Below is the example of a default configuration file in JSON format that needs to serve the model in Konduit-Serving. This configuration file may need simple editing to set up your setup, especially in Pipeline Steps.

Example default Inference Configuration with Sequence Pipeline Steps:

{
  "host" : "localhost",
  "port" : 0,
  "useSsl" : false,
  "protocol" : "HTTP",
  "staticContentRoot" : "static-content",
  "staticContentUrl" : "/static-content",
  "staticContentIndexPage" : "/index.html",
  "kafkaConfiguration" : {
    "startHttpServerForKafka" : true,
    "httpKafkaHost" : "localhost",
    "httpKafkaPort" : 0,
    "consumerTopicName" : "inference-in",
    "consumerKeyDeserializerClass" : "io.vertx.kafka.client.serialization.JsonObjectDeserializer",
    "consumerValueDeserializerClass" : "io.vertx.kafka.client.serialization.JsonObjectDeserializer",
    "consumerGroupId" : "konduit-serving-consumer-group",
    "consumerAutoOffsetReset" : "earliest",
    "consumerAutoCommit" : "true",
    "producerTopicName" : "inference-out",
    "producerKeySerializerClass" : "io.vertx.kafka.client.serialization.JsonObjectSerializer",
    "producerValueSerializerClass" : "io.vertx.kafka.client.serialization.JsonObjectSerializer",
    "producerAcks" : "1"
  },
  "mqttConfiguration" : { },
  "customEndpoints" : [ ],
  "pipeline" : {
    "steps" : [ {
      "@type" : "DEEPLEARNING4J",
      "modelUri" : "<path_to_model>",
      "inputNames" : [ "1", "2" ],
      "outputNames" : [ "11", "22" ]
    }, {
      "@type" : "LOGGING",
      "logLevel" : "INFO",
      "log" : "KEYS_AND_VALUES"
    } ]
  }
}

Example default Inference Configuration with Graph Pipeline Steps:

{
  "host" : "localhost",
  "port" : 0,
  "useSsl" : false,
  "protocol" : "HTTP",
  "staticContentRoot" : "static-content",
  "staticContentUrl" : "/static-content",
  "staticContentIndexPage" : "/index.html",
  "kafkaConfiguration" : {
    "startHttpServerForKafka" : true,
    "httpKafkaHost" : "localhost",
    "httpKafkaPort" : 0,
    "consumerTopicName" : "inference-in",
    "consumerKeyDeserializerClass" : "io.vertx.kafka.client.serialization.JsonObjectDeserializer",
    "consumerValueDeserializerClass" : "io.vertx.kafka.client.serialization.JsonObjectDeserializer",
    "consumerGroupId" : "konduit-serving-consumer-group",
    "consumerAutoOffsetReset" : "earliest",
    "consumerAutoCommit" : "true",
    "producerTopicName" : "inference-out",
    "producerKeySerializerClass" : "io.vertx.kafka.client.serialization.JsonObjectSerializer",
    "producerValueSerializerClass" : "io.vertx.kafka.client.serialization.JsonObjectSerializer",
    "producerAcks" : "1"
  },
  "mqttConfiguration" : { },
  "customEndpoints" : [ ],
  "pipeline" : {
    "outputStep" : "4",
    "steps" : {
      "1" : {
        "@type" : "LOGGING",
        "@input" : "input",
        "logLevel" : "INFO",
        "log" : "KEYS_AND_VALUES"
      },
      "2" : {
        "@type" : "TENSORFLOW",
        "@input" : "1",
        "inputNames" : [ "1", "2" ],
        "outputNames" : [ "11", "22" ],
        "modelUri" : "<path_to_model>"
      },
      "3" : {
        "@type" : "DEEPLEARNING4J",
        "@input" : "1",
        "modelUri" : "<path_to_model>",
        "inputNames" : [ "1", "2" ],
        "outputNames" : [ "11", "22" ]
      },
      "4" : {
        "@type" : "MERGE",
        "@input" : [ "2", "3" ]
      }
    }
  }
}

For more details on how to create the configuration file, please refer to the examples:

PreviousConfigurationsNextYAML

Last updated 4 years ago

Was this helpful?

Creating a Sequence Pipeline
Creating a Graph Pipeline