Discovery Engine v1beta API - Class TrainCustomModelRequest.Types.GcsTrainingInput (1.0.0-beta12)

public sealed class TrainCustomModelRequest.Types.GcsTrainingInput : IMessage<TrainCustomModelRequest.Types.GcsTrainingInput>, IEquatable<TrainCustomModelRequest.Types.GcsTrainingInput>, IDeepCloneable<TrainCustomModelRequest.Types.GcsTrainingInput>, IBufferMessage, IMessage

Reference documentation and code samples for the Discovery Engine v1beta API class TrainCustomModelRequest.Types.GcsTrainingInput.

Cloud Storage training data input.

Inheritance

object > TrainCustomModelRequest.Types.GcsTrainingInput

Namespace

Google.Cloud.DiscoveryEngine.V1Beta

Assembly

Google.Cloud.DiscoveryEngine.V1Beta.dll

Constructors

GcsTrainingInput()

public GcsTrainingInput()

GcsTrainingInput(GcsTrainingInput)

public GcsTrainingInput(TrainCustomModelRequest.Types.GcsTrainingInput other)
Parameter
NameDescription
otherTrainCustomModelRequestTypesGcsTrainingInput

Properties

CorpusDataPath

public string CorpusDataPath { get; set; }

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"}

Property Value
TypeDescription
string

QueryDataPath

public string QueryDataPath { get; set; }

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"}

Property Value
TypeDescription
string

TestDataPath

public string TestDataPath { get; set; }

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.

Property Value
TypeDescription
string

TrainDataPath

public string TrainDataPath { get; set; }

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
Property Value
TypeDescription
string