add hybrid search with rescore IT #1066
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,117 @@ | ||
| /* | ||
| * Copyright OpenSearch Contributors | ||
| * SPDX-License-Identifier: Apache-2.0 | ||
| */ | ||
| package org.opensearch.neuralsearch.bwc; | ||
|
|
||
| import java.nio.file.Files; | ||
| import java.nio.file.Path; | ||
| import java.util.Arrays; | ||
| import java.util.List; | ||
| import java.util.Map; | ||
| import java.util.Objects; | ||
|
|
||
| import static org.opensearch.neuralsearch.util.TestUtils.DEFAULT_COMBINATION_METHOD; | ||
| import static org.opensearch.neuralsearch.util.TestUtils.DEFAULT_NORMALIZATION_METHOD; | ||
| import static org.opensearch.neuralsearch.util.TestUtils.NODES_BWC_CLUSTER; | ||
| import static org.opensearch.neuralsearch.util.TestUtils.PARAM_NAME_WEIGHTS; | ||
| import static org.opensearch.neuralsearch.util.TestUtils.TEXT_EMBEDDING_PROCESSOR; | ||
| import static org.opensearch.neuralsearch.util.TestUtils.getModelId; | ||
|
|
||
| import org.opensearch.index.query.MatchQueryBuilder; | ||
| import org.opensearch.index.query.QueryBuilder; | ||
| import org.opensearch.index.query.QueryBuilders; | ||
| import org.opensearch.knn.index.query.rescore.RescoreContext; | ||
| import org.opensearch.neuralsearch.query.HybridQueryBuilder; | ||
| import org.opensearch.neuralsearch.query.NeuralQueryBuilder; | ||
|
|
||
| public class HybridSearchWithRescoreIT extends AbstractRestartUpgradeRestTestCase { | ||
| private static final String PIPELINE_NAME = "nlp-hybrid-with-rescore-pipeline"; | ||
| private static final String SEARCH_PIPELINE_NAME = "nlp-search-with_rescore-pipeline"; | ||
| private static final String TEST_FIELD = "passage_text"; | ||
| private static final String TEXT = "Hello world"; | ||
| private static final String TEXT_UPGRADED = "Hi earth"; | ||
| private static final String QUERY = "Hi world"; | ||
| private static final int NUM_DOCS_PER_ROUND = 1; | ||
| private static final String VECTOR_EMBEDDING_FIELD = "passage_embedding"; | ||
| protected static final String RESCORE_QUERY = "hi"; | ||
|
|
||
| /** | ||
| * Test normalization with hybrid query and rescore. This test is required as rescore will not be compatible with version lower than 2.15 | ||
| */ | ||
| public void testHybridQueryWithRescore_whenIndexWithMultipleShards_E2EFlow() throws Exception { | ||
| waitForClusterHealthGreen(NODES_BWC_CLUSTER); | ||
|
|
||
| if (isRunningAgainstOldCluster()) { | ||
| String modelId = uploadTextEmbeddingModel(); | ||
| loadModel(modelId); | ||
| createPipelineProcessor(modelId, PIPELINE_NAME); | ||
| createIndexWithConfiguration( | ||
| getIndexNameForTest(), | ||
| Files.readString(Path.of(classLoader.getResource("processor/IndexMappingMultipleShard.json").toURI())), | ||
| PIPELINE_NAME | ||
| ); | ||
| addDocument(getIndexNameForTest(), "0", TEST_FIELD, TEXT, null, null); | ||
| createSearchPipeline( | ||
| SEARCH_PIPELINE_NAME, | ||
| DEFAULT_NORMALIZATION_METHOD, | ||
| DEFAULT_COMBINATION_METHOD, | ||
| Map.of(PARAM_NAME_WEIGHTS, Arrays.toString(new float[] { 0.3f, 0.7f })) | ||
| ); | ||
| } else { | ||
| String modelId = null; | ||
| try { | ||
| modelId = getModelId(getIngestionPipeline(PIPELINE_NAME), TEXT_EMBEDDING_PROCESSOR); | ||
| loadModel(modelId); | ||
| addDocument(getIndexNameForTest(), "1", TEST_FIELD, TEXT_UPGRADED, null, null); | ||
| HybridQueryBuilder hybridQueryBuilder = getQueryBuilder(modelId, null, null); | ||
| QueryBuilder rescorer = QueryBuilders.matchQuery(TEST_FIELD, RESCORE_QUERY).boost(0.3f); | ||
| validateTestIndex(getIndexNameForTest(), hybridQueryBuilder, rescorer); | ||
| hybridQueryBuilder = getQueryBuilder(modelId, Map.of("ef_search", 100), RescoreContext.getDefault()); | ||
| validateTestIndex(getIndexNameForTest(), hybridQueryBuilder, rescorer); | ||
| } finally { | ||
| wipeOfTestResources(getIndexNameForTest(), PIPELINE_NAME, modelId, null); | ||
| } | ||
| } | ||
| } | ||
|
|
||
| private void validateTestIndex(final String index, HybridQueryBuilder queryBuilder, QueryBuilder rescorer) { | ||
| int docCount = getDocCount(index); | ||
| assertEquals(2, docCount); | ||
| Map<String, Object> searchResponseAsMap = search(index, queryBuilder, rescorer, 1, Map.of("search_pipeline", SEARCH_PIPELINE_NAME)); | ||
| assertNotNull(searchResponseAsMap); | ||
| int hits = getHitCount(searchResponseAsMap); | ||
| assertEquals(1, hits); | ||
| List<Double> scoresList = getNormalizationScoreList(searchResponseAsMap); | ||
| for (Double score : scoresList) { | ||
| assertTrue(0 <= score && score <= 2); | ||
| } | ||
| } | ||
|
|
||
| private HybridQueryBuilder getQueryBuilder( | ||
| final String modelId, | ||
| final Map<String, ?> methodParameters, | ||
| final RescoreContext rescoreContextForNeuralQuery | ||
| ) { | ||
| NeuralQueryBuilder neuralQueryBuilder = NeuralQueryBuilder.builder() | ||
| .fieldName(VECTOR_EMBEDDING_FIELD) | ||
| .modelId(modelId) | ||
| .queryText(QUERY) | ||
| .k(5) | ||
| .build(); | ||
| if (methodParameters != null) { | ||
| neuralQueryBuilder.methodParameters(methodParameters); | ||
| } | ||
| if (Objects.nonNull(rescoreContextForNeuralQuery)) { | ||
| neuralQueryBuilder.rescoreContext(rescoreContextForNeuralQuery); | ||
| } | ||
|
|
||
| MatchQueryBuilder matchQueryBuilder = new MatchQueryBuilder("text", QUERY); | ||
|
|
||
| HybridQueryBuilder hybridQueryBuilder = new HybridQueryBuilder(); | ||
| hybridQueryBuilder.add(matchQueryBuilder); | ||
| hybridQueryBuilder.add(neuralQueryBuilder); | ||
|
|
||
| return hybridQueryBuilder; | ||
| } | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
this check is not needed in main, latest 2.x which is 2.18 already supports rescore.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I prefer to keep it so that the code looks same between
mainand2.x