Class: Google::Cloud::DiscoveryEngine::V1::TrainCustomModelRequest

Inherits:
Object
  • Object
show all
Extended by:
Protobuf::MessageExts::ClassMethods
Includes:
Protobuf::MessageExts
Defined in:
proto_docs/google/cloud/discoveryengine/v1/search_tuning_service.rb

Overview

Request message for SearchTuningService.TrainCustomModel method.

Defined Under Namespace

Classes: GcsTrainingInput

Instance Attribute Summary collapse

Instance Attribute Details

#data_store ⇒ ::String

Returns Required. The resource name of the Data Store, such as projects/*/locations/global/collections/default_collection/dataStores/default_data_store. This field is used to identify the data store where to train the models.

Returns:

  • (::String) —

    Required. The resource name of the Data Store, such as projects/*/locations/global/collections/default_collection/dataStores/default_data_store. This field is used to identify the data store where to train the models.



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
 
# File 'proto_docs/google/cloud/discoveryengine/v1/search_tuning_service.rb', line 72

class TrainCustomModelRequest
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods

  # Cloud Storage training data input.
  # @!attribute [rw] corpus_data_path
  #   @return [::String]
  #     The Cloud Storage corpus data which could be associated in train data.
  #     The data path format is `gs://<bucket_to_data>/<jsonl_file_name>`.
  #     A newline delimited jsonl/ndjson file.
  #
  #     For search-tuning model, each line should have the _id, title
  #     and text. Example:
  #     `{"_id": "doc1", title: "relevant doc", "text": "relevant text"}`
  # @!attribute [rw] query_data_path
  #   @return [::String]
  #     The gcs query data which could be associated in train data.
  #     The data path format is `gs://<bucket_to_data>/<jsonl_file_name>`.
  #     A newline delimited jsonl/ndjson file.
  #
  #     For search-tuning model, each line should have the _id
  #     and text. Example: \\{"_id": "query1",  "text": "example query"}
  # @!attribute [rw] train_data_path
  #   @return [::String]
  #     Cloud Storage training data path whose format should be
  #     `gs://<bucket_to_data>/<tsv_file_name>`. The file should be in tsv
  #     format. Each line should have the doc_id and query_id and score (number).
  #
  #     For search-tuning model, it should have the query-id corpus-id
  #     score as tsv file header. The score should be a number in `[0, inf+)`.
  #     The larger the number is, the more relevant the pair is. Example:
  #
  #     * `query-id\tcorpus-id\tscore`
  #     * `query1\tdoc1\t1`
  # @!attribute [rw] test_data_path
  #   @return [::String]
  #     Cloud Storage test data. Same format as train_data_path. If not provided,
  #     a random 80/20 train/test split will be performed on train_data_path.
  class GcsTrainingInput
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end
end

#error_config ⇒ ::Google::Cloud::DiscoveryEngine::V1::ImportErrorConfig

Returns The desired location of errors incurred during the data ingestion and training.

Returns:



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
 
# File 'proto_docs/google/cloud/discoveryengine/v1/search_tuning_service.rb', line 72

class TrainCustomModelRequest
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods

  # Cloud Storage training data input.
  # @!attribute [rw] corpus_data_path
  #   @return [::String]
  #     The Cloud Storage corpus data which could be associated in train data.
  #     The data path format is `gs://<bucket_to_data>/<jsonl_file_name>`.
  #     A newline delimited jsonl/ndjson file.
  #
  #     For search-tuning model, each line should have the _id, title
  #     and text. Example:
  #     `{"_id": "doc1", title: "relevant doc", "text": "relevant text"}`
  # @!attribute [rw] query_data_path
  #   @return [::String]
  #     The gcs query data which could be associated in train data.
  #     The data path format is `gs://<bucket_to_data>/<jsonl_file_name>`.
  #     A newline delimited jsonl/ndjson file.
  #
  #     For search-tuning model, each line should have the _id
  #     and text. Example: \\{"_id": "query1",  "text": "example query"}
  # @!attribute [rw] train_data_path
  #   @return [::String]
  #     Cloud Storage training data path whose format should be
  #     `gs://<bucket_to_data>/<tsv_file_name>`. The file should be in tsv
  #     format. Each line should have the doc_id and query_id and score (number).
  #
  #     For search-tuning model, it should have the query-id corpus-id
  #     score as tsv file header. The score should be a number in `[0, inf+)`.
  #     The larger the number is, the more relevant the pair is. Example:
  #
  #     * `query-id\tcorpus-id\tscore`
  #     * `query1\tdoc1\t1`
  # @!attribute [rw] test_data_path
  #   @return [::String]
  #     Cloud Storage test data. Same format as train_data_path. If not provided,
  #     a random 80/20 train/test split will be performed on train_data_path.
  class GcsTrainingInput
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end
end

#gcs_training_input ⇒ ::Google::Cloud::DiscoveryEngine::V1::TrainCustomModelRequest::GcsTrainingInput

Returns Cloud Storage training input.

Returns:



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
 
# File 'proto_docs/google/cloud/discoveryengine/v1/search_tuning_service.rb', line 72

class TrainCustomModelRequest
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods

  # Cloud Storage training data input.
  # @!attribute [rw] corpus_data_path
  #   @return [::String]
  #     The Cloud Storage corpus data which could be associated in train data.
  #     The data path format is `gs://<bucket_to_data>/<jsonl_file_name>`.
  #     A newline delimited jsonl/ndjson file.
  #
  #     For search-tuning model, each line should have the _id, title
  #     and text. Example:
  #     `{"_id": "doc1", title: "relevant doc", "text": "relevant text"}`
  # @!attribute [rw] query_data_path
  #   @return [::String]
  #     The gcs query data which could be associated in train data.
  #     The data path format is `gs://<bucket_to_data>/<jsonl_file_name>`.
  #     A newline delimited jsonl/ndjson file.
  #
  #     For search-tuning model, each line should have the _id
  #     and text. Example: \\{"_id": "query1",  "text": "example query"}
  # @!attribute [rw] train_data_path
  #   @return [::String]
  #     Cloud Storage training data path whose format should be
  #     `gs://<bucket_to_data>/<tsv_file_name>`. The file should be in tsv
  #     format. Each line should have the doc_id and query_id and score (number).
  #
  #     For search-tuning model, it should have the query-id corpus-id
  #     score as tsv file header. The score should be a number in `[0, inf+)`.
  #     The larger the number is, the more relevant the pair is. Example:
  #
  #     * `query-id\tcorpus-id\tscore`
  #     * `query1\tdoc1\t1`
  # @!attribute [rw] test_data_path
  #   @return [::String]
  #     Cloud Storage test data. Same format as train_data_path. If not provided,
  #     a random 80/20 train/test split will be performed on train_data_path.
  class GcsTrainingInput
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end
end

#model_id ⇒ ::String

Returns If not provided, a UUID will be generated.

Returns:

  • (::String) —

    If not provided, a UUID will be generated.



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
 
# File 'proto_docs/google/cloud/discoveryengine/v1/search_tuning_service.rb', line 72

class TrainCustomModelRequest
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods

  # Cloud Storage training data input.
  # @!attribute [rw] corpus_data_path
  #   @return [::String]
  #     The Cloud Storage corpus data which could be associated in train data.
  #     The data path format is `gs://<bucket_to_data>/<jsonl_file_name>`.
  #     A newline delimited jsonl/ndjson file.
  #
  #     For search-tuning model, each line should have the _id, title
  #     and text. Example:
  #     `{"_id": "doc1", title: "relevant doc", "text": "relevant text"}`
  # @!attribute [rw] query_data_path
  #   @return [::String]
  #     The gcs query data which could be associated in train data.
  #     The data path format is `gs://<bucket_to_data>/<jsonl_file_name>`.
  #     A newline delimited jsonl/ndjson file.
  #
  #     For search-tuning model, each line should have the _id
  #     and text. Example: \\{"_id": "query1",  "text": "example query"}
  # @!attribute [rw] train_data_path
  #   @return [::String]
  #     Cloud Storage training data path whose format should be
  #     `gs://<bucket_to_data>/<tsv_file_name>`. The file should be in tsv
  #     format. Each line should have the doc_id and query_id and score (number).
  #
  #     For search-tuning model, it should have the query-id corpus-id
  #     score as tsv file header. The score should be a number in `[0, inf+)`.
  #     The larger the number is, the more relevant the pair is. Example:
  #
  #     * `query-id\tcorpus-id\tscore`
  #     * `query1\tdoc1\t1`
  # @!attribute [rw] test_data_path
  #   @return [::String]
  #     Cloud Storage test data. Same format as train_data_path. If not provided,
  #     a random 80/20 train/test split will be performed on train_data_path.
  class GcsTrainingInput
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end
end

#model_type ⇒ ::String

Returns Model to be trained. Supported values are:

  • search-tuning: Fine tuning the search system based on data provided.

Returns:

  • (::String) —

    Model to be trained. Supported values are:

    • search-tuning: Fine tuning the search system based on data provided.


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
 
# File 'proto_docs/google/cloud/discoveryengine/v1/search_tuning_service.rb', line 72

class TrainCustomModelRequest
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods

  # Cloud Storage training data input.
  # @!attribute [rw] corpus_data_path
  #   @return [::String]
  #     The Cloud Storage corpus data which could be associated in train data.
  #     The data path format is `gs://<bucket_to_data>/<jsonl_file_name>`.
  #     A newline delimited jsonl/ndjson file.
  #
  #     For search-tuning model, each line should have the _id, title
  #     and text. Example:
  #     `{"_id": "doc1", title: "relevant doc", "text": "relevant text"}`
  # @!attribute [rw] query_data_path
  #   @return [::String]
  #     The gcs query data which could be associated in train data.
  #     The data path format is `gs://<bucket_to_data>/<jsonl_file_name>`.
  #     A newline delimited jsonl/ndjson file.
  #
  #     For search-tuning model, each line should have the _id
  #     and text. Example: \\{"_id": "query1",  "text": "example query"}
  # @!attribute [rw] train_data_path
  #   @return [::String]
  #     Cloud Storage training data path whose format should be
  #     `gs://<bucket_to_data>/<tsv_file_name>`. The file should be in tsv
  #     format. Each line should have the doc_id and query_id and score (number).
  #
  #     For search-tuning model, it should have the query-id corpus-id
  #     score as tsv file header. The score should be a number in `[0, inf+)`.
  #     The larger the number is, the more relevant the pair is. Example:
  #
  #     * `query-id\tcorpus-id\tscore`
  #     * `query1\tdoc1\t1`
  # @!attribute [rw] test_data_path
  #   @return [::String]
  #     Cloud Storage test data. Same format as train_data_path. If not provided,
  #     a random 80/20 train/test split will be performed on train_data_path.
  class GcsTrainingInput
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods
  end
end