Reference documentation and code samples for the Google Cloud Discovery Engine V1 Client class GcsTrainingInput.
Cloud Storage training data input.
Generated from protobuf message google.cloud.discoveryengine.v1.TrainCustomModelRequest.GcsTrainingInput
Namespace
Google \ Cloud \ DiscoveryEngine \ V1 \ TrainCustomModelRequestMethods
__construct
Constructor.
Parameters | |
---|---|
Name | Description |
data |
array
Optional. Data for populating the Message object. |
↳ corpus_data_path |
string
The Cloud Storage corpus data which could be associated in train data. The data path format is |
↳ query_data_path |
string
The gcs query data which could be associated in train data. The data path format is |
↳ train_data_path |
string
Cloud Storage training data path whose format should be |
↳ test_data_path |
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. |
getCorpusDataPath
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"}
Returns | |
---|---|
Type | Description |
string |
setCorpusDataPath
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"}
Parameter | |
---|---|
Name | Description |
var |
string
|
Returns | |
---|---|
Type | Description |
$this |
getQueryDataPath
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"}
Returns | |
---|---|
Type | Description |
string |
setQueryDataPath
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"}
Parameter | |
---|---|
Name | Description |
var |
string
|
Returns | |
---|---|
Type | Description |
$this |
getTrainDataPath
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
Returns | |
---|---|
Type | Description |
string |
setTrainDataPath
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
Parameter | |
---|---|
Name | Description |
var |
string
|
Returns | |
---|---|
Type | Description |
$this |
getTestDataPath
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.
Returns | |
---|---|
Type | Description |
string |
setTestDataPath
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.
Parameter | |
---|---|
Name | Description |
var |
string
|
Returns | |
---|---|
Type | Description |
$this |