Class QualityMetrics.Builder (0.49.0)

public static final class QualityMetrics.Builder extends GeneratedMessageV3.Builder<QualityMetrics.Builder> implements QualityMetricsOrBuilder

Describes the metrics produced by the evaluation.

Protobuf type google.cloud.discoveryengine.v1alpha.QualityMetrics

Static Methods

getDescriptor()

public static final Descriptors.Descriptor getDescriptor()
Returns
Type Description
Descriptor

Methods

addRepeatedField(Descriptors.FieldDescriptor field, Object value)

public QualityMetrics.Builder addRepeatedField(Descriptors.FieldDescriptor field, Object value)
Parameters
Name Description
field FieldDescriptor
value Object
Returns
Type Description
QualityMetrics.Builder
Overrides

build()

public QualityMetrics build()
Returns
Type Description
QualityMetrics

buildPartial()

public QualityMetrics buildPartial()
Returns
Type Description
QualityMetrics

clear()

public QualityMetrics.Builder clear()
Returns
Type Description
QualityMetrics.Builder
Overrides

clearDocNdcg()

public QualityMetrics.Builder clearDocNdcg()

Normalized discounted cumulative gain (NDCG) per document, at various top-k cutoff levels.

NDCG measures the ranking quality, giving higher relevance to top results.

Example (top-3): Suppose SampleQuery with three retrieved documents (D1, D2, D3) and binary relevance judgements (1 for relevant, 0 for not relevant):

Retrieved: [D3 (0), D1 (1), D2 (1)] Ideal: [D1 (1), D2 (1), D3 (0)]

Calculate NDCG@3 for each SampleQuery:

  • DCG@3: 0/log2(1+1) + 1/log2(2+1) + 1/log2(3+1) = 1.13
  • Ideal DCG@3: 1/log2(1+1) + 1/log2(2+1) + 0/log2(3+1) = 1.63
  • NDCG@3: 1.13/1.63 = 0.693

.google.cloud.discoveryengine.v1alpha.QualityMetrics.TopkMetrics doc_ndcg = 3;

Returns
Type Description
QualityMetrics.Builder

clearDocPrecision()

public QualityMetrics.Builder clearDocPrecision()

Precision per document, at various top-k cutoff levels.

Precision is the fraction of retrieved documents that are relevant.

Example (top-5):

  • For a single SampleQuery, If 4 out of 5 retrieved documents in the top-5 are relevant, precision@5 = 4/5 = 0.8

.google.cloud.discoveryengine.v1alpha.QualityMetrics.TopkMetrics doc_precision = 2;

Returns
Type Description
QualityMetrics.Builder

clearDocRecall()

public QualityMetrics.Builder clearDocRecall()

Recall per document, at various top-k cutoff levels.

Recall is the fraction of relevant documents retrieved out of all relevant documents.

Example (top-5):

  • For a single SampleQuery, If 3 out of 5 relevant documents are retrieved in the top-5, recall@5 = 3/5 = 0.6

.google.cloud.discoveryengine.v1alpha.QualityMetrics.TopkMetrics doc_recall = 1;

Returns
Type Description
QualityMetrics.Builder

clearField(Descriptors.FieldDescriptor field)

public QualityMetrics.Builder clearField(Descriptors.FieldDescriptor field)
Parameter
Name Description
field FieldDescriptor
Returns
Type Description
QualityMetrics.Builder
Overrides

clearOneof(Descriptors.OneofDescriptor oneof)

public QualityMetrics.Builder clearOneof(Descriptors.OneofDescriptor oneof)
Parameter
Name Description
oneof OneofDescriptor
Returns
Type Description
QualityMetrics.Builder
Overrides

clearPageNdcg()

public QualityMetrics.Builder clearPageNdcg()

Normalized discounted cumulative gain (NDCG) per page, at various top-k cutoff levels.

NDCG measures the ranking quality, giving higher relevance to top results.

Example (top-3): Suppose SampleQuery with three retrieved pages (P1, P2, P3) and binary relevance judgements (1 for relevant, 0 for not relevant):

Retrieved: [P3 (0), P1 (1), P2 (1)] Ideal: [P1 (1), P2 (1), P3 (0)]

Calculate NDCG@3 for SampleQuery:

  • DCG@3: 0/log2(1+1) + 1/log2(2+1) + 1/log2(3+1) = 1.13
  • Ideal DCG@3: 1/log2(1+1) + 1/log2(2+1) + 0/log2(3+1) = 1.63
  • NDCG@3: 1.13/1.63 = 0.693

.google.cloud.discoveryengine.v1alpha.QualityMetrics.TopkMetrics page_ndcg = 5;

Returns
Type Description
QualityMetrics.Builder

clearPageRecall()

public QualityMetrics.Builder clearPageRecall()

Recall per page, at various top-k cutoff levels.

Recall is the fraction of relevant pages retrieved out of all relevant pages.

Example (top-5):

  • For a single SampleQuery, if 3 out of 5 relevant pages are retrieved in the top-5, recall@5 = 3/5 = 0.6

.google.cloud.discoveryengine.v1alpha.QualityMetrics.TopkMetrics page_recall = 4;

Returns
Type Description
QualityMetrics.Builder

clone()

public QualityMetrics.Builder clone()
Returns
Type Description
QualityMetrics.Builder
Overrides

getDefaultInstanceForType()

public QualityMetrics getDefaultInstanceForType()
Returns
Type Description
QualityMetrics

getDescriptorForType()

public Descriptors.Descriptor getDescriptorForType()
Returns
Type Description
Descriptor
Overrides

getDocNdcg()

public QualityMetrics.TopkMetrics getDocNdcg()

Normalized discounted cumulative gain (NDCG) per document, at various top-k cutoff levels.

NDCG measures the ranking quality, giving higher relevance to top results.

Example (top-3): Suppose SampleQuery with three retrieved documents (D1, D2, D3) and binary relevance judgements (1 for relevant, 0 for not relevant):

Retrieved: [D3 (0), D1 (1), D2 (1)] Ideal: [D1 (1), D2 (1), D3 (0)]

Calculate NDCG@3 for each SampleQuery:

  • DCG@3: 0/log2(1+1) + 1/log2(2+1) + 1/log2(3+1) = 1.13
  • Ideal DCG@3: 1/log2(1+1) + 1/log2(2+1) + 0/log2(3+1) = 1.63
  • NDCG@3: 1.13/1.63 = 0.693

.google.cloud.discoveryengine.v1alpha.QualityMetrics.TopkMetrics doc_ndcg = 3;

Returns
Type Description
QualityMetrics.TopkMetrics

The docNdcg.

getDocNdcgBuilder()

public QualityMetrics.TopkMetrics.Builder getDocNdcgBuilder()

Normalized discounted cumulative gain (NDCG) per document, at various top-k cutoff levels.

NDCG measures the ranking quality, giving higher relevance to top results.

Example (top-3): Suppose SampleQuery with three retrieved documents (D1, D2, D3) and binary relevance judgements (1 for relevant, 0 for not relevant):

Retrieved: [D3 (0), D1 (1), D2 (1)] Ideal: [D1 (1), D2 (1), D3 (0)]

Calculate NDCG@3 for each SampleQuery:

  • DCG@3: 0/log2(1+1) + 1/log2(2+1) + 1/log2(3+1) = 1.13
  • Ideal DCG@3: 1/log2(1+1) + 1/log2(2+1) + 0/log2(3+1) = 1.63
  • NDCG@3: 1.13/1.63 = 0.693

.google.cloud.discoveryengine.v1alpha.QualityMetrics.TopkMetrics doc_ndcg = 3;

Returns
Type Description
QualityMetrics.TopkMetrics.Builder

getDocNdcgOrBuilder()

public QualityMetrics.TopkMetricsOrBuilder getDocNdcgOrBuilder()

Normalized discounted cumulative gain (NDCG) per document, at various top-k cutoff levels.

NDCG measures the ranking quality, giving higher relevance to top results.

Example (top-3): Suppose SampleQuery with three retrieved documents (D1, D2, D3) and binary relevance judgements (1 for relevant, 0 for not relevant):

Retrieved: [D3 (0), D1 (1), D2 (1)] Ideal: [D1 (1), D2 (1), D3 (0)]

Calculate NDCG@3 for each SampleQuery:

  • DCG@3: 0/log2(1+1) + 1/log2(2+1) + 1/log2(3+1) = 1.13
  • Ideal DCG@3: 1/log2(1+1) + 1/log2(2+1) + 0/log2(3+1) = 1.63
  • NDCG@3: 1.13/1.63 = 0.693

.google.cloud.discoveryengine.v1alpha.QualityMetrics.TopkMetrics doc_ndcg = 3;

Returns
Type Description
QualityMetrics.TopkMetricsOrBuilder

getDocPrecision()

public QualityMetrics.TopkMetrics getDocPrecision()

Precision per document, at various top-k cutoff levels.

Precision is the fraction of retrieved documents that are relevant.

Example (top-5):

  • For a single SampleQuery, If 4 out of 5 retrieved documents in the top-5 are relevant, precision@5 = 4/5 = 0.8

.google.cloud.discoveryengine.v1alpha.QualityMetrics.TopkMetrics doc_precision = 2;

Returns
Type Description
QualityMetrics.TopkMetrics

The docPrecision.

getDocPrecisionBuilder()

public QualityMetrics.TopkMetrics.Builder getDocPrecisionBuilder()

Precision per document, at various top-k cutoff levels.

Precision is the fraction of retrieved documents that are relevant.

Example (top-5):

  • For a single SampleQuery, If 4 out of 5 retrieved documents in the top-5 are relevant, precision@5 = 4/5 = 0.8

.google.cloud.discoveryengine.v1alpha.QualityMetrics.TopkMetrics doc_precision = 2;

Returns
Type Description
QualityMetrics.TopkMetrics.Builder

getDocPrecisionOrBuilder()

public QualityMetrics.TopkMetricsOrBuilder getDocPrecisionOrBuilder()

Precision per document, at various top-k cutoff levels.

Precision is the fraction of retrieved documents that are relevant.

Example (top-5):

  • For a single SampleQuery, If 4 out of 5 retrieved documents in the top-5 are relevant, precision@5 = 4/5 = 0.8

.google.cloud.discoveryengine.v1alpha.QualityMetrics.TopkMetrics doc_precision = 2;

Returns
Type Description
QualityMetrics.TopkMetricsOrBuilder

getDocRecall()

public QualityMetrics.TopkMetrics getDocRecall()

Recall per document, at various top-k cutoff levels.

Recall is the fraction of relevant documents retrieved out of all relevant documents.

Example (top-5):

  • For a single SampleQuery, If 3 out of 5 relevant documents are retrieved in the top-5, recall@5 = 3/5 = 0.6

.google.cloud.discoveryengine.v1alpha.QualityMetrics.TopkMetrics doc_recall = 1;

Returns
Type Description
QualityMetrics.TopkMetrics

The docRecall.

getDocRecallBuilder()

public QualityMetrics.TopkMetrics.Builder getDocRecallBuilder()

Recall per document, at various top-k cutoff levels.

Recall is the fraction of relevant documents retrieved out of all relevant documents.

Example (top-5):

  • For a single SampleQuery, If 3 out of 5 relevant documents are retrieved in the top-5, recall@5 = 3/5 = 0.6

.google.cloud.discoveryengine.v1alpha.QualityMetrics.TopkMetrics doc_recall = 1;

Returns
Type Description
QualityMetrics.TopkMetrics.Builder

getDocRecallOrBuilder()

public QualityMetrics.TopkMetricsOrBuilder getDocRecallOrBuilder()

Recall per document, at various top-k cutoff levels.

Recall is the fraction of relevant documents retrieved out of all relevant documents.

Example (top-5):

  • For a single SampleQuery, If 3 out of 5 relevant documents are retrieved in the top-5, recall@5 = 3/5 = 0.6

.google.cloud.discoveryengine.v1alpha.QualityMetrics.TopkMetrics doc_recall = 1;

Returns
Type Description
QualityMetrics.TopkMetricsOrBuilder

getPageNdcg()

public QualityMetrics.TopkMetrics getPageNdcg()

Normalized discounted cumulative gain (NDCG) per page, at various top-k cutoff levels.

NDCG measures the ranking quality, giving higher relevance to top results.

Example (top-3): Suppose SampleQuery with three retrieved pages (P1, P2, P3) and binary relevance judgements (1 for relevant, 0 for not relevant):

Retrieved: [P3 (0), P1 (1), P2 (1)] Ideal: [P1 (1), P2 (1), P3 (0)]

Calculate NDCG@3 for SampleQuery:

  • DCG@3: 0/log2(1+1) + 1/log2(2+1) + 1/log2(3+1) = 1.13
  • Ideal DCG@3: 1/log2(1+1) + 1/log2(2+1) + 0/log2(3+1) = 1.63
  • NDCG@3: 1.13/1.63 = 0.693

.google.cloud.discoveryengine.v1alpha.QualityMetrics.TopkMetrics page_ndcg = 5;

Returns
Type Description
QualityMetrics.TopkMetrics

The pageNdcg.

getPageNdcgBuilder()

public QualityMetrics.TopkMetrics.Builder getPageNdcgBuilder()

Normalized discounted cumulative gain (NDCG) per page, at various top-k cutoff levels.

NDCG measures the ranking quality, giving higher relevance to top results.

Example (top-3): Suppose SampleQuery with three retrieved pages (P1, P2, P3) and binary relevance judgements (1 for relevant, 0 for not relevant):

Retrieved: [P3 (0), P1 (1), P2 (1)] Ideal: [P1 (1), P2 (1), P3 (0)]

Calculate NDCG@3 for SampleQuery:

  • DCG@3: 0/log2(1+1) + 1/log2(2+1) + 1/log2(3+1) = 1.13
  • Ideal DCG@3: 1/log2(1+1) + 1/log2(2+1) + 0/log2(3+1) = 1.63
  • NDCG@3: 1.13/1.63 = 0.693

.google.cloud.discoveryengine.v1alpha.QualityMetrics.TopkMetrics page_ndcg = 5;

Returns
Type Description
QualityMetrics.TopkMetrics.Builder

getPageNdcgOrBuilder()

public QualityMetrics.TopkMetricsOrBuilder getPageNdcgOrBuilder()

Normalized discounted cumulative gain (NDCG) per page, at various top-k cutoff levels.

NDCG measures the ranking quality, giving higher relevance to top results.

Example (top-3): Suppose SampleQuery with three retrieved pages (P1, P2, P3) and binary relevance judgements (1 for relevant, 0 for not relevant):

Retrieved: [P3 (0), P1 (1), P2 (1)] Ideal: [P1 (1), P2 (1), P3 (0)]

Calculate NDCG@3 for SampleQuery:

  • DCG@3: 0/log2(1+1) + 1/log2(2+1) + 1/log2(3+1) = 1.13
  • Ideal DCG@3: 1/log2(1+1) + 1/log2(2+1) + 0/log2(3+1) = 1.63
  • NDCG@3: 1.13/1.63 = 0.693

.google.cloud.discoveryengine.v1alpha.QualityMetrics.TopkMetrics page_ndcg = 5;

Returns
Type Description
QualityMetrics.TopkMetricsOrBuilder

getPageRecall()

public QualityMetrics.TopkMetrics getPageRecall()

Recall per page, at various top-k cutoff levels.

Recall is the fraction of relevant pages retrieved out of all relevant pages.

Example (top-5):

  • For a single SampleQuery, if 3 out of 5 relevant pages are retrieved in the top-5, recall@5 = 3/5 = 0.6

.google.cloud.discoveryengine.v1alpha.QualityMetrics.TopkMetrics page_recall = 4;

Returns
Type Description
QualityMetrics.TopkMetrics

The pageRecall.

getPageRecallBuilder()

public QualityMetrics.TopkMetrics.Builder getPageRecallBuilder()

Recall per page, at various top-k cutoff levels.

Recall is the fraction of relevant pages retrieved out of all relevant pages.

Example (top-5):

  • For a single SampleQuery, if 3 out of 5 relevant pages are retrieved in the top-5, recall@5 = 3/5 = 0.6

.google.cloud.discoveryengine.v1alpha.QualityMetrics.TopkMetrics page_recall = 4;

Returns
Type Description
QualityMetrics.TopkMetrics.Builder

getPageRecallOrBuilder()

public QualityMetrics.TopkMetricsOrBuilder getPageRecallOrBuilder()

Recall per page, at various top-k cutoff levels.

Recall is the fraction of relevant pages retrieved out of all relevant pages.

Example (top-5):

  • For a single SampleQuery, if 3 out of 5 relevant pages are retrieved in the top-5, recall@5 = 3/5 = 0.6

.google.cloud.discoveryengine.v1alpha.QualityMetrics.TopkMetrics page_recall = 4;

Returns
Type Description
QualityMetrics.TopkMetricsOrBuilder

hasDocNdcg()

public boolean hasDocNdcg()

Normalized discounted cumulative gain (NDCG) per document, at various top-k cutoff levels.

NDCG measures the ranking quality, giving higher relevance to top results.

Example (top-3): Suppose SampleQuery with three retrieved documents (D1, D2, D3) and binary relevance judgements (1 for relevant, 0 for not relevant):

Retrieved: [D3 (0), D1 (1), D2 (1)] Ideal: [D1 (1), D2 (1), D3 (0)]

Calculate NDCG@3 for each SampleQuery:

  • DCG@3: 0/log2(1+1) + 1/log2(2+1) + 1/log2(3+1) = 1.13
  • Ideal DCG@3: 1/log2(1+1) + 1/log2(2+1) + 0/log2(3+1) = 1.63
  • NDCG@3: 1.13/1.63 = 0.693

.google.cloud.discoveryengine.v1alpha.QualityMetrics.TopkMetrics doc_ndcg = 3;

Returns
Type Description
boolean

Whether the docNdcg field is set.

hasDocPrecision()

public boolean hasDocPrecision()

Precision per document, at various top-k cutoff levels.

Precision is the fraction of retrieved documents that are relevant.

Example (top-5):

  • For a single SampleQuery, If 4 out of 5 retrieved documents in the top-5 are relevant, precision@5 = 4/5 = 0.8

.google.cloud.discoveryengine.v1alpha.QualityMetrics.TopkMetrics doc_precision = 2;

Returns
Type Description
boolean

Whether the docPrecision field is set.

hasDocRecall()

public boolean hasDocRecall()

Recall per document, at various top-k cutoff levels.

Recall is the fraction of relevant documents retrieved out of all relevant documents.

Example (top-5):

  • For a single SampleQuery, If 3 out of 5 relevant documents are retrieved in the top-5, recall@5 = 3/5 = 0.6

.google.cloud.discoveryengine.v1alpha.QualityMetrics.TopkMetrics doc_recall = 1;

Returns
Type Description
boolean

Whether the docRecall field is set.

hasPageNdcg()

public boolean hasPageNdcg()

Normalized discounted cumulative gain (NDCG) per page, at various top-k cutoff levels.

NDCG measures the ranking quality, giving higher relevance to top results.

Example (top-3): Suppose SampleQuery with three retrieved pages (P1, P2, P3) and binary relevance judgements (1 for relevant, 0 for not relevant):

Retrieved: [P3 (0), P1 (1), P2 (1)] Ideal: [P1 (1), P2 (1), P3 (0)]

Calculate NDCG@3 for SampleQuery:

  • DCG@3: 0/log2(1+1) + 1/log2(2+1) + 1/log2(3+1) = 1.13
  • Ideal DCG@3: 1/log2(1+1) + 1/log2(2+1) + 0/log2(3+1) = 1.63
  • NDCG@3: 1.13/1.63 = 0.693

.google.cloud.discoveryengine.v1alpha.QualityMetrics.TopkMetrics page_ndcg = 5;

Returns
Type Description
boolean

Whether the pageNdcg field is set.

hasPageRecall()

public boolean hasPageRecall()

Recall per page, at various top-k cutoff levels.

Recall is the fraction of relevant pages retrieved out of all relevant pages.

Example (top-5):

  • For a single SampleQuery, if 3 out of 5 relevant pages are retrieved in the top-5, recall@5 = 3/5 = 0.6

.google.cloud.discoveryengine.v1alpha.QualityMetrics.TopkMetrics page_recall = 4;

Returns
Type Description
boolean

Whether the pageRecall field is set.

internalGetFieldAccessorTable()

protected GeneratedMessageV3.FieldAccessorTable internalGetFieldAccessorTable()
Returns
Type Description
FieldAccessorTable
Overrides

isInitialized()

public final boolean isInitialized()
Returns
Type Description
boolean
Overrides

mergeDocNdcg(QualityMetrics.TopkMetrics value)

public QualityMetrics.Builder mergeDocNdcg(QualityMetrics.TopkMetrics value)

Normalized discounted cumulative gain (NDCG) per document, at various top-k cutoff levels.

NDCG measures the ranking quality, giving higher relevance to top results.

Example (top-3): Suppose SampleQuery with three retrieved documents (D1, D2, D3) and binary relevance judgements (1 for relevant, 0 for not relevant):

Retrieved: [D3 (0), D1 (1), D2 (1)] Ideal: [D1 (1), D2 (1), D3 (0)]

Calculate NDCG@3 for each SampleQuery:

  • DCG@3: 0/log2(1+1) + 1/log2(2+1) + 1/log2(3+1) = 1.13
  • Ideal DCG@3: 1/log2(1+1) + 1/log2(2+1) + 0/log2(3+1) = 1.63
  • NDCG@3: 1.13/1.63 = 0.693

.google.cloud.discoveryengine.v1alpha.QualityMetrics.TopkMetrics doc_ndcg = 3;

Parameter
Name Description
value QualityMetrics.TopkMetrics
Returns
Type Description
QualityMetrics.Builder

mergeDocPrecision(QualityMetrics.TopkMetrics value)

public QualityMetrics.Builder mergeDocPrecision(QualityMetrics.TopkMetrics value)

Precision per document, at various top-k cutoff levels.

Precision is the fraction of retrieved documents that are relevant.

Example (top-5):

  • For a single SampleQuery, If 4 out of 5 retrieved documents in the top-5 are relevant, precision@5 = 4/5 = 0.8

.google.cloud.discoveryengine.v1alpha.QualityMetrics.TopkMetrics doc_precision = 2;

Parameter
Name Description
value QualityMetrics.TopkMetrics
Returns
Type Description
QualityMetrics.Builder

mergeDocRecall(QualityMetrics.TopkMetrics value)

public QualityMetrics.Builder mergeDocRecall(QualityMetrics.TopkMetrics value)

Recall per document, at various top-k cutoff levels.

Recall is the fraction of relevant documents retrieved out of all relevant documents.

Example (top-5):

  • For a single SampleQuery, If 3 out of 5 relevant documents are retrieved in the top-5, recall@5 = 3/5 = 0.6

.google.cloud.discoveryengine.v1alpha.QualityMetrics.TopkMetrics doc_recall = 1;

Parameter
Name Description
value QualityMetrics.TopkMetrics
Returns
Type Description
QualityMetrics.Builder

mergeFrom(QualityMetrics other)

public QualityMetrics.Builder mergeFrom(QualityMetrics other)
Parameter
Name Description
other QualityMetrics
Returns
Type Description
QualityMetrics.Builder

mergeFrom(CodedInputStream input, ExtensionRegistryLite extensionRegistry)

public QualityMetrics.Builder mergeFrom(CodedInputStream input, ExtensionRegistryLite extensionRegistry)
Parameters
Name Description
input CodedInputStream
extensionRegistry ExtensionRegistryLite
Returns
Type Description
QualityMetrics.Builder
Overrides
Exceptions
Type Description
IOException

mergeFrom(Message other)

public QualityMetrics.Builder mergeFrom(Message other)
Parameter
Name Description
other Message
Returns
Type Description
QualityMetrics.Builder
Overrides

mergePageNdcg(QualityMetrics.TopkMetrics value)

public QualityMetrics.Builder mergePageNdcg(QualityMetrics.TopkMetrics value)

Normalized discounted cumulative gain (NDCG) per page, at various top-k cutoff levels.

NDCG measures the ranking quality, giving higher relevance to top results.

Example (top-3): Suppose SampleQuery with three retrieved pages (P1, P2, P3) and binary relevance judgements (1 for relevant, 0 for not relevant):

Retrieved: [P3 (0), P1 (1), P2 (1)] Ideal: [P1 (1), P2 (1), P3 (0)]

Calculate NDCG@3 for SampleQuery:

  • DCG@3: 0/log2(1+1) + 1/log2(2+1) + 1/log2(3+1) = 1.13
  • Ideal DCG@3: 1/log2(1+1) + 1/log2(2+1) + 0/log2(3+1) = 1.63
  • NDCG@3: 1.13/1.63 = 0.693

.google.cloud.discoveryengine.v1alpha.QualityMetrics.TopkMetrics page_ndcg = 5;

Parameter
Name Description
value QualityMetrics.TopkMetrics
Returns
Type Description
QualityMetrics.Builder

mergePageRecall(QualityMetrics.TopkMetrics value)

public QualityMetrics.Builder mergePageRecall(QualityMetrics.TopkMetrics value)

Recall per page, at various top-k cutoff levels.

Recall is the fraction of relevant pages retrieved out of all relevant pages.

Example (top-5):

  • For a single SampleQuery, if 3 out of 5 relevant pages are retrieved in the top-5, recall@5 = 3/5 = 0.6

.google.cloud.discoveryengine.v1alpha.QualityMetrics.TopkMetrics page_recall = 4;

Parameter
Name Description
value QualityMetrics.TopkMetrics
Returns
Type Description
QualityMetrics.Builder

mergeUnknownFields(UnknownFieldSet unknownFields)

public final QualityMetrics.Builder mergeUnknownFields(UnknownFieldSet unknownFields)
Parameter
Name Description
unknownFields UnknownFieldSet
Returns
Type Description
QualityMetrics.Builder
Overrides

setDocNdcg(QualityMetrics.TopkMetrics value)

public QualityMetrics.Builder setDocNdcg(QualityMetrics.TopkMetrics value)

Normalized discounted cumulative gain (NDCG) per document, at various top-k cutoff levels.

NDCG measures the ranking quality, giving higher relevance to top results.

Example (top-3): Suppose SampleQuery with three retrieved documents (D1, D2, D3) and binary relevance judgements (1 for relevant, 0 for not relevant):

Retrieved: [D3 (0), D1 (1), D2 (1)] Ideal: [D1 (1), D2 (1), D3 (0)]

Calculate NDCG@3 for each SampleQuery:

  • DCG@3: 0/log2(1+1) + 1/log2(2+1) + 1/log2(3+1) = 1.13
  • Ideal DCG@3: 1/log2(1+1) + 1/log2(2+1) + 0/log2(3+1) = 1.63
  • NDCG@3: 1.13/1.63 = 0.693

.google.cloud.discoveryengine.v1alpha.QualityMetrics.TopkMetrics doc_ndcg = 3;

Parameter
Name Description
value QualityMetrics.TopkMetrics
Returns
Type Description
QualityMetrics.Builder

setDocNdcg(QualityMetrics.TopkMetrics.Builder builderForValue)

public QualityMetrics.Builder setDocNdcg(QualityMetrics.TopkMetrics.Builder builderForValue)

Normalized discounted cumulative gain (NDCG) per document, at various top-k cutoff levels.

NDCG measures the ranking quality, giving higher relevance to top results.

Example (top-3): Suppose SampleQuery with three retrieved documents (D1, D2, D3) and binary relevance judgements (1 for relevant, 0 for not relevant):

Retrieved: [D3 (0), D1 (1), D2 (1)] Ideal: [D1 (1), D2 (1), D3 (0)]

Calculate NDCG@3 for each SampleQuery:

  • DCG@3: 0/log2(1+1) + 1/log2(2+1) + 1/log2(3+1) = 1.13
  • Ideal DCG@3: 1/log2(1+1) + 1/log2(2+1) + 0/log2(3+1) = 1.63
  • NDCG@3: 1.13/1.63 = 0.693

.google.cloud.discoveryengine.v1alpha.QualityMetrics.TopkMetrics doc_ndcg = 3;

Parameter
Name Description
builderForValue QualityMetrics.TopkMetrics.Builder
Returns
Type Description
QualityMetrics.Builder

setDocPrecision(QualityMetrics.TopkMetrics value)

public QualityMetrics.Builder setDocPrecision(QualityMetrics.TopkMetrics value)

Precision per document, at various top-k cutoff levels.

Precision is the fraction of retrieved documents that are relevant.

Example (top-5):

  • For a single SampleQuery, If 4 out of 5 retrieved documents in the top-5 are relevant, precision@5 = 4/5 = 0.8

.google.cloud.discoveryengine.v1alpha.QualityMetrics.TopkMetrics doc_precision = 2;

Parameter
Name Description
value QualityMetrics.TopkMetrics
Returns
Type Description
QualityMetrics.Builder

setDocPrecision(QualityMetrics.TopkMetrics.Builder builderForValue)

public QualityMetrics.Builder setDocPrecision(QualityMetrics.TopkMetrics.Builder builderForValue)

Precision per document, at various top-k cutoff levels.

Precision is the fraction of retrieved documents that are relevant.

Example (top-5):

  • For a single SampleQuery, If 4 out of 5 retrieved documents in the top-5 are relevant, precision@5 = 4/5 = 0.8

.google.cloud.discoveryengine.v1alpha.QualityMetrics.TopkMetrics doc_precision = 2;

Parameter
Name Description
builderForValue QualityMetrics.TopkMetrics.Builder
Returns
Type Description
QualityMetrics.Builder

setDocRecall(QualityMetrics.TopkMetrics value)

public QualityMetrics.Builder setDocRecall(QualityMetrics.TopkMetrics value)

Recall per document, at various top-k cutoff levels.

Recall is the fraction of relevant documents retrieved out of all relevant documents.

Example (top-5):

  • For a single SampleQuery, If 3 out of 5 relevant documents are retrieved in the top-5, recall@5 = 3/5 = 0.6

.google.cloud.discoveryengine.v1alpha.QualityMetrics.TopkMetrics doc_recall = 1;

Parameter
Name Description
value QualityMetrics.TopkMetrics
Returns
Type Description
QualityMetrics.Builder

setDocRecall(QualityMetrics.TopkMetrics.Builder builderForValue)

public QualityMetrics.Builder setDocRecall(QualityMetrics.TopkMetrics.Builder builderForValue)

Recall per document, at various top-k cutoff levels.

Recall is the fraction of relevant documents retrieved out of all relevant documents.

Example (top-5):

  • For a single SampleQuery, If 3 out of 5 relevant documents are retrieved in the top-5, recall@5 = 3/5 = 0.6

.google.cloud.discoveryengine.v1alpha.QualityMetrics.TopkMetrics doc_recall = 1;

Parameter
Name Description
builderForValue QualityMetrics.TopkMetrics.Builder
Returns
Type Description
QualityMetrics.Builder

setField(Descriptors.FieldDescriptor field, Object value)

public QualityMetrics.Builder setField(Descriptors.FieldDescriptor field, Object value)
Parameters
Name Description
field FieldDescriptor
value Object
Returns
Type Description
QualityMetrics.Builder
Overrides

setPageNdcg(QualityMetrics.TopkMetrics value)

public QualityMetrics.Builder setPageNdcg(QualityMetrics.TopkMetrics value)

Normalized discounted cumulative gain (NDCG) per page, at various top-k cutoff levels.

NDCG measures the ranking quality, giving higher relevance to top results.

Example (top-3): Suppose SampleQuery with three retrieved pages (P1, P2, P3) and binary relevance judgements (1 for relevant, 0 for not relevant):

Retrieved: [P3 (0), P1 (1), P2 (1)] Ideal: [P1 (1), P2 (1), P3 (0)]

Calculate NDCG@3 for SampleQuery:

  • DCG@3: 0/log2(1+1) + 1/log2(2+1) + 1/log2(3+1) = 1.13
  • Ideal DCG@3: 1/log2(1+1) + 1/log2(2+1) + 0/log2(3+1) = 1.63
  • NDCG@3: 1.13/1.63 = 0.693

.google.cloud.discoveryengine.v1alpha.QualityMetrics.TopkMetrics page_ndcg = 5;

Parameter
Name Description
value QualityMetrics.TopkMetrics
Returns
Type Description
QualityMetrics.Builder

setPageNdcg(QualityMetrics.TopkMetrics.Builder builderForValue)

public QualityMetrics.Builder setPageNdcg(QualityMetrics.TopkMetrics.Builder builderForValue)

Normalized discounted cumulative gain (NDCG) per page, at various top-k cutoff levels.

NDCG measures the ranking quality, giving higher relevance to top results.

Example (top-3): Suppose SampleQuery with three retrieved pages (P1, P2, P3) and binary relevance judgements (1 for relevant, 0 for not relevant):

Retrieved: [P3 (0), P1 (1), P2 (1)] Ideal: [P1 (1), P2 (1), P3 (0)]

Calculate NDCG@3 for SampleQuery:

  • DCG@3: 0/log2(1+1) + 1/log2(2+1) + 1/log2(3+1) = 1.13
  • Ideal DCG@3: 1/log2(1+1) + 1/log2(2+1) + 0/log2(3+1) = 1.63
  • NDCG@3: 1.13/1.63 = 0.693

.google.cloud.discoveryengine.v1alpha.QualityMetrics.TopkMetrics page_ndcg = 5;

Parameter
Name Description
builderForValue QualityMetrics.TopkMetrics.Builder
Returns
Type Description
QualityMetrics.Builder

setPageRecall(QualityMetrics.TopkMetrics value)

public QualityMetrics.Builder setPageRecall(QualityMetrics.TopkMetrics value)

Recall per page, at various top-k cutoff levels.

Recall is the fraction of relevant pages retrieved out of all relevant pages.

Example (top-5):

  • For a single SampleQuery, if 3 out of 5 relevant pages are retrieved in the top-5, recall@5 = 3/5 = 0.6

.google.cloud.discoveryengine.v1alpha.QualityMetrics.TopkMetrics page_recall = 4;

Parameter
Name Description
value QualityMetrics.TopkMetrics
Returns
Type Description
QualityMetrics.Builder

setPageRecall(QualityMetrics.TopkMetrics.Builder builderForValue)

public QualityMetrics.Builder setPageRecall(QualityMetrics.TopkMetrics.Builder builderForValue)

Recall per page, at various top-k cutoff levels.

Recall is the fraction of relevant pages retrieved out of all relevant pages.

Example (top-5):

  • For a single SampleQuery, if 3 out of 5 relevant pages are retrieved in the top-5, recall@5 = 3/5 = 0.6

.google.cloud.discoveryengine.v1alpha.QualityMetrics.TopkMetrics page_recall = 4;

Parameter
Name Description
builderForValue QualityMetrics.TopkMetrics.Builder
Returns
Type Description
QualityMetrics.Builder

setRepeatedField(Descriptors.FieldDescriptor field, int index, Object value)

public QualityMetrics.Builder setRepeatedField(Descriptors.FieldDescriptor field, int index, Object value)
Parameters
Name Description
field FieldDescriptor
index int
value Object
Returns
Type Description
QualityMetrics.Builder
Overrides

setUnknownFields(UnknownFieldSet unknownFields)

public final QualityMetrics.Builder setUnknownFields(UnknownFieldSet unknownFields)
Parameter
Name Description
unknownFields UnknownFieldSet
Returns
Type Description
QualityMetrics.Builder
Overrides