Interface QualityMetricsOrBuilder (0.45.0)

public interface QualityMetricsOrBuilder extends MessageOrBuilder

Implements

MessageOrBuilder

Methods

getDocNdcg()

public abstract 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.v1beta.QualityMetrics.TopkMetrics doc_ndcg = 3;

Returns
Type	Description
`QualityMetrics.TopkMetrics`	The docNdcg.

getDocNdcgOrBuilder()

public abstract 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.v1beta.QualityMetrics.TopkMetrics doc_ndcg = 3;

Returns
Type	Description
`QualityMetrics.TopkMetricsOrBuilder`

getDocPrecision()

public abstract 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.v1beta.QualityMetrics.TopkMetrics doc_precision = 2;

Returns
Type	Description
`QualityMetrics.TopkMetrics`	The docPrecision.

getDocPrecisionOrBuilder()

public abstract 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.v1beta.QualityMetrics.TopkMetrics doc_precision = 2;

Returns
Type	Description
`QualityMetrics.TopkMetricsOrBuilder`

getDocRecall()

public abstract 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.v1beta.QualityMetrics.TopkMetrics doc_recall = 1;

Returns
Type	Description
`QualityMetrics.TopkMetrics`	The docRecall.

getDocRecallOrBuilder()

public abstract 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.v1beta.QualityMetrics.TopkMetrics doc_recall = 1;

Returns
Type	Description
`QualityMetrics.TopkMetricsOrBuilder`

getPageNdcg()

public abstract 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.v1beta.QualityMetrics.TopkMetrics page_ndcg = 5;

Returns
Type	Description
`QualityMetrics.TopkMetrics`	The pageNdcg.

getPageNdcgOrBuilder()

public abstract 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.v1beta.QualityMetrics.TopkMetrics page_ndcg = 5;

Returns
Type	Description
`QualityMetrics.TopkMetricsOrBuilder`

getPageRecall()

public abstract 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.v1beta.QualityMetrics.TopkMetrics page_recall = 4;

Returns
Type	Description
`QualityMetrics.TopkMetrics`	The pageRecall.

getPageRecallOrBuilder()

public abstract 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.v1beta.QualityMetrics.TopkMetrics page_recall = 4;

Returns
Type	Description
`QualityMetrics.TopkMetricsOrBuilder`

hasDocNdcg()

public abstract 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.v1beta.QualityMetrics.TopkMetrics doc_ndcg = 3;

Returns
Type	Description
`boolean`	Whether the docNdcg field is set.

hasDocPrecision()

public abstract 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.v1beta.QualityMetrics.TopkMetrics doc_precision = 2;

Returns
Type	Description
`boolean`	Whether the docPrecision field is set.

hasDocRecall()

public abstract 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.v1beta.QualityMetrics.TopkMetrics doc_recall = 1;

Returns
Type	Description
`boolean`	Whether the docRecall field is set.

hasPageNdcg()

public abstract 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.v1beta.QualityMetrics.TopkMetrics page_ndcg = 5;

Returns
Type	Description
`boolean`	Whether the pageNdcg field is set.

hasPageRecall()

public abstract 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.v1beta.QualityMetrics.TopkMetrics page_recall = 4;

Returns
Type	Description
`boolean`	Whether the pageRecall field is set.