View Source GoogleApi.DiscoveryEngine.V1beta.Model.GoogleCloudDiscoveryengineV1betaTrainCustomModelRequestGcsTrainingInput (google_api_discovery_engine v0.15.0)
Cloud Storage training data input.
Attributes
-
corpusDataPath
(type:String.t
, default:nil
) - The Cloud Storage corpus data which could be associated in train data. The data path format isgs:///
. 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"}
-
queryDataPath
(type:String.t
, default:nil
) - The gcs query data which could be associated in train data. The data path format isgs:///
. A newline delimited jsonl/ndjson file. For search-tuning model, each line should have the _id and text. Example: {"_id": "query1", "text": "example query"} -
testDataPath
(type:String.t
, default:nil
) - 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. -
trainDataPath
(type:String.t
, default:nil
) - Cloud Storage training data path whose format should begs:///
. 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
Summary
Functions
Unwrap a decoded JSON object into its complex fields.
Types
Functions
Unwrap a decoded JSON object into its complex fields.