Interface ModelServerConfigOuterClass.ModelConfigOrBuilder

All Superinterfaces:
com.google.protobuf.MessageLiteOrBuilder, com.google.protobuf.MessageOrBuilder
All Known Implementing Classes:
ModelServerConfigOuterClass.ModelConfig, ModelServerConfigOuterClass.ModelConfig.Builder
Enclosing class:
ModelServerConfigOuterClass

public static interface ModelServerConfigOuterClass.ModelConfigOrBuilder extends com.google.protobuf.MessageOrBuilder
  • Method Details

    • getName

      String getName()
       Name of the model.
       
      string name = 1;
      Returns:
      The name.
    • getNameBytes

      com.google.protobuf.ByteString getNameBytes()
       Name of the model.
       
      string name = 1;
      Returns:
      The bytes for name.
    • getBasePath

      String getBasePath()
       Base path to the model, excluding the version directory.
       E.g> for a model at /foo/bar/my_model/123, where 123 is the version, the
       base path is /foo/bar/my_model.
      
       (This can be changed once a model is in serving, *if* the underlying data
       remains the same. Otherwise there are no guarantees about whether the old
       or new data will be used for model versions currently loaded.)
       
      string base_path = 2;
      Returns:
      The basePath.
    • getBasePathBytes

      com.google.protobuf.ByteString getBasePathBytes()
       Base path to the model, excluding the version directory.
       E.g> for a model at /foo/bar/my_model/123, where 123 is the version, the
       base path is /foo/bar/my_model.
      
       (This can be changed once a model is in serving, *if* the underlying data
       remains the same. Otherwise there are no guarantees about whether the old
       or new data will be used for model versions currently loaded.)
       
      string base_path = 2;
      Returns:
      The bytes for basePath.
    • getModelTypeValue

      @Deprecated int getModelTypeValue()
      Deprecated.
      tensorflow.serving.ModelConfig.model_type is deprecated. See tensorflow_serving/config/model_server_config.proto;l=50
       Type of model.
       TODO(b/31336131): DEPRECATED. Please use 'model_platform' instead.
       
      .tensorflow.serving.ModelType model_type = 3 [deprecated = true];
      Returns:
      The enum numeric value on the wire for modelType.
    • getModelType

      Deprecated.
      tensorflow.serving.ModelConfig.model_type is deprecated. See tensorflow_serving/config/model_server_config.proto;l=50
       Type of model.
       TODO(b/31336131): DEPRECATED. Please use 'model_platform' instead.
       
      .tensorflow.serving.ModelType model_type = 3 [deprecated = true];
      Returns:
      The modelType.
    • getModelPlatform

      String getModelPlatform()
       Type of model (e.g. "tensorflow").
      
       (This cannot be changed once a model is in serving.)
       
      string model_platform = 4;
      Returns:
      The modelPlatform.
    • getModelPlatformBytes

      com.google.protobuf.ByteString getModelPlatformBytes()
       Type of model (e.g. "tensorflow").
      
       (This cannot be changed once a model is in serving.)
       
      string model_platform = 4;
      Returns:
      The bytes for modelPlatform.
    • hasModelVersionPolicy

      boolean hasModelVersionPolicy()
       Version policy for the model indicating which version(s) of the model to
       load and make available for serving simultaneously.
       The default option is to serve only the latest version of the model.
      
       (This can be changed once a model is in serving.)
       
      .tensorflow.serving.FileSystemStoragePathSourceConfig.ServableVersionPolicy model_version_policy = 7;
      Returns:
      Whether the modelVersionPolicy field is set.
    • getModelVersionPolicy

       Version policy for the model indicating which version(s) of the model to
       load and make available for serving simultaneously.
       The default option is to serve only the latest version of the model.
      
       (This can be changed once a model is in serving.)
       
      .tensorflow.serving.FileSystemStoragePathSourceConfig.ServableVersionPolicy model_version_policy = 7;
      Returns:
      The modelVersionPolicy.
    • getModelVersionPolicyOrBuilder

       Version policy for the model indicating which version(s) of the model to
       load and make available for serving simultaneously.
       The default option is to serve only the latest version of the model.
      
       (This can be changed once a model is in serving.)
       
      .tensorflow.serving.FileSystemStoragePathSourceConfig.ServableVersionPolicy model_version_policy = 7;
    • getVersionLabelsCount

      int getVersionLabelsCount()
       String labels to associate with versions of the model, allowing inference
       queries to refer to versions by label instead of number. Multiple labels
       can map to the same version, but not vice-versa.
      
       An envisioned use-case for these labels is canarying tentative versions.
       For example, one can assign labels "stable" and "canary" to two specific
       versions. Perhaps initially "stable" is assigned to version 0 and "canary"
       to version 1. Once version 1 passes canary, one can shift the "stable"
       label to refer to version 1 (at that point both labels map to the same
       version -- version 1 -- which is fine). Later once version 2 is ready to
       canary one can move the "canary" label to version 2. And so on.
       
      map<string, int64> version_labels = 8;
    • containsVersionLabels

      boolean containsVersionLabels(String key)
       String labels to associate with versions of the model, allowing inference
       queries to refer to versions by label instead of number. Multiple labels
       can map to the same version, but not vice-versa.
      
       An envisioned use-case for these labels is canarying tentative versions.
       For example, one can assign labels "stable" and "canary" to two specific
       versions. Perhaps initially "stable" is assigned to version 0 and "canary"
       to version 1. Once version 1 passes canary, one can shift the "stable"
       label to refer to version 1 (at that point both labels map to the same
       version -- version 1 -- which is fine). Later once version 2 is ready to
       canary one can move the "canary" label to version 2. And so on.
       
      map<string, int64> version_labels = 8;
    • getVersionLabels

      @Deprecated Map<String,Long> getVersionLabels()
      Deprecated.
    • getVersionLabelsMap

      Map<String,Long> getVersionLabelsMap()
       String labels to associate with versions of the model, allowing inference
       queries to refer to versions by label instead of number. Multiple labels
       can map to the same version, but not vice-versa.
      
       An envisioned use-case for these labels is canarying tentative versions.
       For example, one can assign labels "stable" and "canary" to two specific
       versions. Perhaps initially "stable" is assigned to version 0 and "canary"
       to version 1. Once version 1 passes canary, one can shift the "stable"
       label to refer to version 1 (at that point both labels map to the same
       version -- version 1 -- which is fine). Later once version 2 is ready to
       canary one can move the "canary" label to version 2. And so on.
       
      map<string, int64> version_labels = 8;
    • getVersionLabelsOrDefault

      long getVersionLabelsOrDefault(String key, long defaultValue)
       String labels to associate with versions of the model, allowing inference
       queries to refer to versions by label instead of number. Multiple labels
       can map to the same version, but not vice-versa.
      
       An envisioned use-case for these labels is canarying tentative versions.
       For example, one can assign labels "stable" and "canary" to two specific
       versions. Perhaps initially "stable" is assigned to version 0 and "canary"
       to version 1. Once version 1 passes canary, one can shift the "stable"
       label to refer to version 1 (at that point both labels map to the same
       version -- version 1 -- which is fine). Later once version 2 is ready to
       canary one can move the "canary" label to version 2. And so on.
       
      map<string, int64> version_labels = 8;
    • getVersionLabelsOrThrow

      long getVersionLabelsOrThrow(String key)
       String labels to associate with versions of the model, allowing inference
       queries to refer to versions by label instead of number. Multiple labels
       can map to the same version, but not vice-versa.
      
       An envisioned use-case for these labels is canarying tentative versions.
       For example, one can assign labels "stable" and "canary" to two specific
       versions. Perhaps initially "stable" is assigned to version 0 and "canary"
       to version 1. Once version 1 passes canary, one can shift the "stable"
       label to refer to version 1 (at that point both labels map to the same
       version -- version 1 -- which is fine). Later once version 2 is ready to
       canary one can move the "canary" label to version 2. And so on.
       
      map<string, int64> version_labels = 8;
    • hasLoggingConfig

      boolean hasLoggingConfig()
       Configures logging requests and responses, to the model.
      
       (This can be changed once a model is in serving.)
       
      .tensorflow.serving.LoggingConfig logging_config = 6;
      Returns:
      Whether the loggingConfig field is set.
    • getLoggingConfig

       Configures logging requests and responses, to the model.
      
       (This can be changed once a model is in serving.)
       
      .tensorflow.serving.LoggingConfig logging_config = 6;
      Returns:
      The loggingConfig.
    • getLoggingConfigOrBuilder

       Configures logging requests and responses, to the model.
      
       (This can be changed once a model is in serving.)
       
      .tensorflow.serving.LoggingConfig logging_config = 6;