implement batch document optimization for text embedding processor #1217

will-hwang · 2025-03-07T22:42:52Z

Description

This PR includes changes for:

refactor of InferenceFilter to simplify logic for copying embeddings
implementation for batch document update optimization by overriding InferenceProcessor's subBatchExecute to include filter when skip_existing flag is on

Proposed State [Batch Document Update]

Steps:

Process Maps are generated for each IngestDocument based on the Field Map defined.
If skip_existing feature is set to true, filter the process map for each IngestDocument.
1. Existing documents are fetched via OpenSearch client’s Multi-Get Action to compare each of the existing inference text against its corresponding IngestDocument
  1. if documents do not exist, or any exception is thrown, fallback to calling model inference
2. Locate the embedding fields in each existing document
  1. Recursively traverse the process map to find embedding fields. Keeping track of the traversal path is required for look up in existing document.
  2. Once embedding fields are found, attempt to copy embeddings from existing document to its corresponding ingest document.
3. If eligible, copy over the vector embeddings from existing document to its corresponding ingest document
  1. It is eligible for copy if inference text in ingest document and its corresponding existing document is the same, and embeddings for the inference text exist in its existing document.
  2. Note, if in case of values in list, the fields in the same index are compared to determine text equality
4. If eligible fields have been copied, remove the entry in process map
Inference List is generated based on entries in Filtered Process Map.
ML Commons InferenceSentence API is invoked with filtered inference list.
Embeddings for filtered inference list are generated in ML Commons.
Embeddings for filtered inference list are mapped to target fields via entries defined in process map.
Embeddings for filtered inference list are populated to target fields in IngestDocument.

Related Issues

HLD: #1138

Check List

New functionality includes testing.
New functionality has been documented.
API changes companion pull request created.
Commits are signed per the DCO using --signoff.
Public documentation issue/PR created.

By submitting this pull request, I confirm that my contribution is made under the terms of the Apache 2.0 license.
For more information on following Developer Certificate of Origin and signing off your commits, please check here.

codecov · 2025-03-08T04:53:38Z

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 81.97%. Comparing base (1a6e58e) to head (3bb0a19).

Additional details and impacted files

@@                    Coverage Diff                    @@
##             optimized-processor    #1217      +/-   ##
=========================================================
+ Coverage                  81.94%   81.97%   +0.02%     
+ Complexity                  2604     1315    -1289     
=========================================================
  Files                        194       97      -97     
  Lines                       8858     4487    -4371     
  Branches                    1498      760     -738     
=========================================================
- Hits                        7259     3678    -3581     
+ Misses                      1016      513     -503     
+ Partials                     583      296     -287

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

❄ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.

heemin32 · 2025-03-11T16:22:58Z

src/main/java/org/opensearch/neuralsearch/processor/InferenceProcessor.java

+
+    protected List<List<IngestDocumentWrapper>> cutBatches(List<IngestDocumentWrapper> ingestDocumentWrappers) {
+        List<List<IngestDocumentWrapper>> batches = new ArrayList();
+        for (int i = 0; i < ingestDocumentWrappers.size(); i += this.batchSize) {


This document mention that batch_size parameter is deprecated. Should we keep supporting it for 3.0?

wanted to keep the changes minimal to the existing implementation of batchExecute in core here: https://github.com/opensearch-project/OpenSearch/blob/main/server/src/main/java/org/opensearch/ingest/AbstractBatchingProcessor.java#L48-L74

Do you think we should completely rewrite the function?

since there are conflicting explanation for batch_size, i think it's safe to leave it for now

heemin32 · 2025-03-11T16:27:27Z

src/main/java/org/opensearch/neuralsearch/processor/InferenceProcessor.java

+    protected List<List<IngestDocumentWrapper>> cutBatches(List<IngestDocumentWrapper> ingestDocumentWrappers) {
+        List<List<IngestDocumentWrapper>> batches = new ArrayList();
+        for (int i = 0; i < ingestDocumentWrappers.size(); i += this.batchSize) {
+            batches.add(ingestDocumentWrappers.subList(i, Math.min(i + this.batchSize, ingestDocumentWrappers.size())));


Using subList may not be efficient for certain data structures. For instance, with a LinkedList, if batchSize is 1, making n calls to subList would result in an O(n²) time complexity.

this is used as a default behavior for batchExecute (https://github.com/opensearch-project/OpenSearch/blob/main/server/src/main/java/org/opensearch/ingest/AbstractBatchingProcessor.java#L48-L74), which we extend in our inferenceProcessor.
I think it's better to leave the existing logic as is, and make changes to what is needed only. let me know your thoughts.

Got it. Can't we just override subBatchExecute instead of repeating the core code here?

if we just override subBatchExecute, we won't be able to use multiGet operation to fetch all documents at once, since subBatchExecute only contains a subset (mostly just one) of the documents.

That is what we want. We should not get all documents at once. It might fail if the number of document is too big. Customer can increase batch_size if they want.

okay, with this change we would be calling multiple multiGet operation, since we are calling it at subBatch level.

For example, If user ingests 6 documents, with a batch size of 2,

there will be 3 multiGet calls with each batch size of 2.

src/main/java/org/opensearch/neuralsearch/processor/InferenceProcessor.java

src/main/java/org/opensearch/neuralsearch/processor/TextEmbeddingProcessor.java

heemin32 · 2025-03-11T16:47:40Z

src/main/java/org/opensearch/neuralsearch/processor/TextEmbeddingProcessor.java

+                    assert counter.get() >= 0 : "counter is negative";
+                });
+            }
+        }, e -> { handler.accept(null); }));


If we call handler.accept(null), will the cx see the error?

no, will update the PR to include exception in each document

with the latest change, when mget throws an exception, handler will still accept the ingested document, with exception message populated in each document

src/main/java/org/opensearch/neuralsearch/processor/TextEmbeddingProcessor.java

vibrantvarun · 2025-03-12T16:12:55Z

src/main/java/org/opensearch/neuralsearch/processor/TextEmbeddingProcessor.java

@@ -106,4 +112,60 @@ public void doBatchExecute(List<String> inferenceList, Consumer<List<?>> handler
            ActionListener.wrap(handler::accept, onException)
        );
    }
+
+    @Override
+    public void subBatchExecute(List<IngestDocumentWrapper> ingestDocumentWrappers, Consumer<List<IngestDocumentWrapper>> handler) {


Could you divide this method into three parts?

Validations

MGet call

Checking for embeddings

i refactored the method and added comments to make it more readable. Left the validations at the beginning of the method for cleaner implementation

src/main/java/org/opensearch/neuralsearch/processor/InferenceProcessor.java

src/main/java/org/opensearch/neuralsearch/processor/TextEmbeddingProcessor.java

vibrantvarun · 2025-03-12T16:15:01Z

...in/java/org/opensearch/neuralsearch/processor/optimization/TextEmbeddingInferenceFilter.java

@@ -47,7 +45,7 @@ public Object filterInferenceValue(
        Optional<Object> existingValueOptional = ProcessorUtils.getValueFromSource(existingSourceAndMetadataMap, textPath);
        Optional<Object> embeddingValueOptional = ProcessorUtils.getValueFromSource(existingSourceAndMetadataMap, embeddingKey);
        if (existingValueOptional.isPresent() && embeddingValueOptional.isPresent()) {
-            return copyEmbeddingForSingleValue(


QQ: why we change this method here?

this was a change from previous PR. Since we're comparing single value and list values as object values, we can have just one method for comparison and copying embeddings

src/main/java/org/opensearch/neuralsearch/processor/InferenceProcessor.java

heemin32 · 2025-03-13T23:19:18Z

src/main/java/org/opensearch/neuralsearch/processor/TextEmbeddingProcessor.java

+            handler.accept(Collections.emptyList());
+            return;
+        }
+        List<DataForInference> dataForInferences = getDataForInference(ingestDocumentWrappers);


What happen if this line throw exception? Shouldn't we catch it and set it in handler or will it be handled already?

it is already handled in the method: here

That's the issue—you need to check every method to ensure exceptions are handled properly, which isn't a future-proof approach. It would be better to handle the exception here as well, ensuring that any exceptions thrown by underlying methods are caught.

heemin32 · 2025-03-13T23:19:38Z

src/main/java/org/opensearch/neuralsearch/processor/TextEmbeddingProcessor.java

+            // create a map of documents with key: doc_id and value: doc
+            Map<String, Map<String, Object>> existingDocuments = createDocumentMap(multiGetItemResponses);
+            List<DataForInference> filteredDataForInference = filterDataForInference(dataForInferences, existingDocuments);
+            List<String> filteredInferenceList = constructInferenceTexts(filteredDataForInference);


What happen if exception is thrown here. Will that be handled gracefully?

it checks for whether exception was thrown and only create inference text for valid data inferences here

Same as above comment.

heemin32 · 2025-03-13T23:24:15Z

src/main/java/org/opensearch/neuralsearch/processor/optimization/InferenceFilter.java

+                existingListValue.getFirst(),
+                embeddingListOptional.get(),
+                sourceAndMetadataMap,
+                -1


This is a bit unclear—I’m not sure when to pass -1 versus another value. It would be helpful to have a separate method for clarity and include a detailed Javadoc explaining when to use each method.

// Use when xys public Object copyEmbeddingXYZ( String embeddingKey, Object processValue, Object existingValue, Object embeddingValue, Map<String, Object> sourceAndMetadataMap ) { return copyEmbedding(embeddingKey, processValue, existingValue, embeddingValue, sourceAndMetadataMap, -1); }

okay, will create a separate method

vibrantvarun

@will-hwang could you add tests in failure cases of this feature? Like when will the functionality fail and user will not see 200 status from api

vibrantvarun · 2025-03-14T17:29:07Z

Overall I have similar comments like @heemin32 so will wait for once it gets addressed before doing final round of review

will-hwang · 2025-03-14T22:43:49Z

@will-hwang could you add tests in failure cases of this feature? Like when will the functionality fail and user will not see 200 status from api

i've added a failure test case here where mget fails with runtime exception. In summary, the error handling is the same as our existing implementation, where if dependent service (opensearch client or mlcommonclient) fails with exception, ingestDocument is updated with exception, instead of failing ingestion.

heemin32 · 2025-03-17T23:16:51Z

src/main/java/org/opensearch/neuralsearch/processor/InferenceProcessor.java

+            inferenceList = sortedResult.v1();
+            Map<Integer, Integer> originalOrder = sortedResult.v2();
+            doBatchExecute(inferenceList, results -> {
+                int startIndex = 0;


Missing try catch here.

heemin32 · 2025-03-17T23:17:19Z

src/main/java/org/opensearch/neuralsearch/processor/TextEmbeddingProcessor.java

+                MultiGetAction.INSTANCE,
+                buildMultiGetRequest(ingestDocumentWrappers),
+                ActionListener.wrap(response -> {
+                    MultiGetItemResponse[] multiGetItemResponses = response.getResponses();


missing try catch here.

Signed-off-by: Will Hwang <[email protected]>

heemin32

LGTM

junqiu-lei

LGTM, thanks.

heemin32 · 2025-03-18T21:13:28Z

Build failures are coming from changes in knn and it is resolved by #1233

…pensearch-project#1217) Signed-off-by: Will Hwang <[email protected]>

…pensearch-project#1217) Signed-off-by: will-hwang <[email protected]>

…opensearch-project#1217) Signed-off-by: Will Hwang <[email protected]>

…1238) * implement single document update scenario for text embedding processor (#1191) Signed-off-by: Will Hwang <[email protected]> * implement batch document update scenario for text embedding processor (#1217) Signed-off-by: Will Hwang <[email protected]> --------- Signed-off-by: Will Hwang <[email protected]>

…pensearch-project#1238) * implement single document update scenario for text embedding processor (opensearch-project#1191) Signed-off-by: Will Hwang <[email protected]> * implement batch document update scenario for text embedding processor (opensearch-project#1217) Signed-off-by: Will Hwang <[email protected]> --------- Signed-off-by: Will Hwang <[email protected]>

…pensearch-project#1238) * implement single document update scenario for text embedding processor (opensearch-project#1191) Signed-off-by: Will Hwang <[email protected]> * implement batch document update scenario for text embedding processor (opensearch-project#1217) Signed-off-by: Will Hwang <[email protected]> --------- Signed-off-by: Will Hwang <[email protected]> Signed-off-by: yeonghyeonKo <[email protected]>

#1342) * Implement Optimized embedding generation in text embedding processor (#1238) * implement single document update scenario for text embedding processor (#1191) Signed-off-by: Will Hwang <[email protected]> * implement batch document update scenario for text embedding processor (#1217) Signed-off-by: Will Hwang <[email protected]> --------- Signed-off-by: Will Hwang <[email protected]> Signed-off-by: yeonghyeonKo <[email protected]> * Going from alpha1 to beta1 for 3.0 release (#1245) Signed-off-by: yeonghyeonKo <[email protected]> * Implement Optimized embedding generation in sparse encoding processor (#1246) Signed-off-by: Will Hwang <[email protected]> Signed-off-by: yeonghyeonKo <[email protected]> * Implement Optimized embedding generation in text and image embedding processor (#1249) Signed-off-by: will-hwang <[email protected]> Signed-off-by: yeonghyeonKo <[email protected]> * Inner hits support with hybrid query (#1253) * Inner Hits in Hybrid query Signed-off-by: Varun Jain <[email protected]> * Inner hits support with hybrid query Signed-off-by: Varun Jain <[email protected]> * Add changelog Signed-off-by: Varun Jain <[email protected]> * fix integ tests Signed-off-by: Varun Jain <[email protected]> * Modify comment Signed-off-by: Varun Jain <[email protected]> * Explain test case Signed-off-by: Varun Jain <[email protected]> * Optimize inner hits count calculation method Signed-off-by: Varun Jain <[email protected]> --------- Signed-off-by: Varun Jain <[email protected]> Signed-off-by: yeonghyeonKo <[email protected]> * Support custom tags in semantic highlighter (#1254) Signed-off-by: yeonghyeonKo <[email protected]> * Add neural stats API (#1256) * Add neural stats API Signed-off-by: Andy Qin <[email protected]> Signed-off-by: yeonghyeonKo <[email protected]> * Added release notes for 3.0 beta1 (#1252) * Added release notes for 3.0 beta1 Signed-off-by: Martin Gaievski <[email protected]> Signed-off-by: yeonghyeonKo <[email protected]> * Update semantic highlighter test model (#1259) Signed-off-by: Junqiu Lei <[email protected]> Signed-off-by: yeonghyeonKo <[email protected]> * Fix the edge case when the value of a fieldMap key in ingestDocument is empty string (#1257) Signed-off-by: Chloe Gao <[email protected]> Signed-off-by: yeonghyeonKo <[email protected]> * Hybrid query should call rewrite before creating weight (#1268) * Hybrid query should call rewrite before creating weight Signed-off-by: Harsha Vamsi Kalluri <[email protected]> * Awaits fix Signed-off-by: Harsha Vamsi Kalluri <[email protected]> * Rewrite with searcher Signed-off-by: Harsha Vamsi Kalluri <[email protected]> * Feature flag issue Signed-off-by: Harsha Vamsi Kalluri <[email protected]> --------- Signed-off-by: Harsha Vamsi Kalluri <[email protected]> Signed-off-by: yeonghyeonKo <[email protected]> * Support phasing off SecurityManager usage in favor of Java Agent (#1265) Signed-off-by: Gulshan <[email protected]> Signed-off-by: yeonghyeonKo <[email protected]> * Fix multi node transport issue on NeuralKNNQueryBuilder originalQueryText (#1272) Signed-off-by: Junqiu Lei <[email protected]> Signed-off-by: yeonghyeonKo <[email protected]> * Add semantic field mapper. (#1225) Signed-off-by: Bo Zhang <[email protected]> Signed-off-by: yeonghyeonKo <[email protected]> * Increment version to 3.0.0-SNAPSHOT (#1286) Signed-off-by: opensearch-ci-bot <[email protected]> Co-authored-by: opensearch-ci-bot <[email protected]> Signed-off-by: yeonghyeonKo <[email protected]> * Remove beta1 qualifier (#1292) Signed-off-by: Peter Zhu <[email protected]> Signed-off-by: yeonghyeonKo <[email protected]> * Fix for merging scoreDocs when totalHits are greater than 1 and fieldDocs are 0 (#1295) (#1296) (cherry picked from commit 6f3aabb) Co-authored-by: Varun Jain <[email protected]> Signed-off-by: yeonghyeonKo <[email protected]> * add release notes for 3.0 (#1287) Signed-off-by: will-hwang <[email protected]> Signed-off-by: yeonghyeonKo <[email protected]> * Allow maven to publish to all versions (#1300) (#1301) Signed-off-by: Peter Zhu <[email protected]> (cherry picked from commit c5625db) Co-authored-by: Peter Zhu <[email protected]> Signed-off-by: yeonghyeonKo <[email protected]> * [FEAT] introduce new FixedStringLengthChunker Signed-off-by: yeonghyeonKo <[email protected]> * [TEST] initial test cases for FixedStringLengthChunker Signed-off-by: yeonghyeonKo <[email protected]> * [FIX] gradlew spotlessApply Signed-off-by: yeonghyeonKo <[email protected]> * [REFACTOR] remove unnecessary comments Signed-off-by: yeonghyeonKo <[email protected]> * [Performance Improvement] Add custom bulk scorer for hybrid query (2-3x faster) (#1289) Signed-off-by: Martin Gaievski <[email protected]> Signed-off-by: yeonghyeonKo <[email protected]> * Add TextChunkingProcessor stats (#1308) * Add TextChunkingProcessor stats Signed-off-by: Andy Qin <[email protected]> # Conflicts: # CHANGELOG.md * Update unit and integ tests Signed-off-by: Andy Qin <[email protected]> --------- Signed-off-by: Andy Qin <[email protected]> Signed-off-by: yeonghyeonKo <[email protected]> * Update Lucene dependencies (#1336) * Update Lucene dependencies Signed-off-by: Ryan Bogan <[email protected]> * Add changelog entry Signed-off-by: Ryan Bogan <[email protected]> * Update model request body for bwc and integ tests Signed-off-by: Ryan Bogan <[email protected]> --------- Signed-off-by: Ryan Bogan <[email protected]> Signed-off-by: yeonghyeonKo <[email protected]> * [REFACTOR] modify algorithm name and related parts Signed-off-by: yeonghyeonKo <[email protected]> * [REFACTOR] update test codes along with the change in CharacterLengthChunker Signed-off-by: yeonghyeonKo <[email protected]> * [REFACTOR] remove defensive check to prevent adding redundant code lines Signed-off-by: yeonghyeonKo <[email protected]> * Update CharacterLengthChunker to FixedCharLengthChunker Signed-off-by: Marcel Yeonghyeon Ko <[email protected]> Signed-off-by: yeonghyeonKo <[email protected]> * Update ChunkerFactory Signed-off-by: Marcel Yeonghyeon Ko <[email protected]> Signed-off-by: yeonghyeonKo <[email protected]> * Update CharacterLengthChunkerTests to FixedCharLengthChunkerTests Signed-off-by: Marcel Yeonghyeon Ko <[email protected]> Signed-off-by: yeonghyeonKo <[email protected]> * [FIX] handle a corner case where the content is shorter than charLimit Signed-off-by: yeonghyeonKo <[email protected]> * [TEST] Add integration test codes for fixed_char_length chunking algorithm Signed-off-by: yeonghyeonKo <[email protected]> * [TEST] integration test code for cascaded pipeline Signed-off-by: yeonghyeonKo <[email protected]> * Support analyzer-based neural sparse query (#1088) * merge main; add analyzer impl Signed-off-by: zhichao-aws <[email protected]> * two phase adaption Signed-off-by: zhichao-aws <[email protected]> * two phase adaption Signed-off-by: zhichao-aws <[email protected]> * remove analysis Signed-off-by: zhichao-aws <[email protected]> * lint Signed-off-by: zhichao-aws <[email protected]> * update Signed-off-by: zhichao-aws <[email protected]> * address comments Signed-off-by: zhichao-aws <[email protected]> * tests Signed-off-by: zhichao-aws <[email protected]> * modify plugin security policy Signed-off-by: zhichao-aws <[email protected]> * change log Signed-off-by: zhichao-aws <[email protected]> * address comments Signed-off-by: zhichao-aws <[email protected]> * modify to package-private Signed-off-by: zhichao-aws <[email protected]> --------- Signed-off-by: zhichao-aws <[email protected]> Signed-off-by: yeonghyeonKo <[email protected]> * Fixed score value as null for single shard for sorting (#1277) * Fixed score value as null for single shard for sorting Signed-off-by: Owais <[email protected]> * Addressed comment Signed-off-by: Owais <[email protected]> * Addressed more comments Signed-off-by: Owais <[email protected]> * Added UT Signed-off-by: Owais <[email protected]> --------- Signed-off-by: Owais <[email protected]> Signed-off-by: yeonghyeonKo <[email protected]> * Add IT for neural sparse query + bert-uncased mbert-uncased analyzer (#1279) * add it Signed-off-by: zhichao-aws <[email protected]> * change log Signed-off-by: zhichao-aws <[email protected]> --------- Signed-off-by: zhichao-aws <[email protected]> Signed-off-by: yeonghyeonKo <[email protected]> * Add WithFieldName implementation to QueryBuilders (#1285) Signed-off-by: Owais <[email protected]> Signed-off-by: yeonghyeonKo <[email protected]> * [AUTO] Increment version to 3.1.0-SNAPSHOT (#1288) * Increment version to 3.1.0-SNAPSHOT Signed-off-by: opensearch-ci-bot <[email protected]> * Update build.gradle Signed-off-by: Peter Zhu <[email protected]> --------- Signed-off-by: opensearch-ci-bot <[email protected]> Signed-off-by: Peter Zhu <[email protected]> Co-authored-by: opensearch-ci-bot <[email protected]> Co-authored-by: Peter Zhu <[email protected]> Signed-off-by: yeonghyeonKo <[email protected]> * add release notes for 3.0 (#1298) Signed-off-by: will-hwang <[email protected]> Signed-off-by: yeonghyeonKo <[email protected]> * Return bad request for invalid stat parameters in stats API (#1291) Signed-off-by: Andy Qin <[email protected]> Signed-off-by: yeonghyeonKo <[email protected]> * Add semantic mapping transformer. (#1276) Signed-off-by: Bo Zhang <[email protected]> Signed-off-by: yeonghyeonKo <[email protected]> * Add semantic ingest processor. (#1309) Signed-off-by: Bo Zhang <[email protected]> Signed-off-by: yeonghyeonKo <[email protected]> * [Performance Improvement] Add custom bulk scorer for hybrid query (2-3x faster) (#1289) Signed-off-by: Martin Gaievski <[email protected]> Signed-off-by: yeonghyeonKo <[email protected]> * Implement the query logic for the semantic field. (#1315) Signed-off-by: Bo Zhang <[email protected]> Signed-off-by: yeonghyeonKo <[email protected]> * Support custom weights params in RRF (#1322) * Support Weights params in RRF Signed-off-by: Varun Jain <[email protected]> Signed-off-by: yeonghyeonKo <[email protected]> * add validation for invalid nested hybrid query (#1305) * add validation for nested hybrid query Signed-off-by: will-hwang <[email protected]> Signed-off-by: yeonghyeonKo <[email protected]> * Add stats tracking for semantic highlighting (#1327) * Add stats tracking for semantic highlighting Signed-off-by: Junqiu Lei <[email protected]> Signed-off-by: yeonghyeonKo <[email protected]> * Update Lucene dependencies (#1336) * Update Lucene dependencies Signed-off-by: Ryan Bogan <[email protected]> * Add changelog entry Signed-off-by: Ryan Bogan <[email protected]> * Update model request body for bwc and integ tests Signed-off-by: Ryan Bogan <[email protected]> --------- Signed-off-by: Ryan Bogan <[email protected]> Signed-off-by: yeonghyeonKo <[email protected]> * Enhance semantic field to allow to enable/disable chunking. (#1337) * Implement the query logic for the semantic field. Signed-off-by: Bo Zhang <[email protected]> * Enhance semantic field to allow to enable/disable chunking. Signed-off-by: Bo Zhang <[email protected]> --------- Signed-off-by: Bo Zhang <[email protected]> Signed-off-by: yeonghyeonKo <[email protected]> * [REFACTOR] modify algorithm name and related parts Signed-off-by: yeonghyeonKo <[email protected]> * Update CHANGELOG.md Signed-off-by: Marcel Yeonghyeon Ko <[email protected]> Signed-off-by: yeonghyeonKo <[email protected]> * [FEAT] Add fixed_char_length chunking algorithm to STAT manager Signed-off-by: yeonghyeonKo <[email protected]> * [TEST] Add integration test codes for fixed_char_length chunking algorithm Signed-off-by: yeonghyeonKo <[email protected]> * [TEST] integration test code for cascaded pipeline Signed-off-by: yeonghyeonKo <[email protected]> * Going from alpha1 to beta1 for 3.0 release (#1245) Signed-off-by: yeonghyeonKo <[email protected]> * Fix multi node transport issue on NeuralKNNQueryBuilder originalQueryText (#1272) Signed-off-by: Junqiu Lei <[email protected]> Signed-off-by: yeonghyeonKo <[email protected]> * Add semantic field mapper. (#1225) Signed-off-by: Bo Zhang <[email protected]> Signed-off-by: yeonghyeonKo <[email protected]> * Add semantic mapping transformer. (#1276) Signed-off-by: Bo Zhang <[email protected]> Signed-off-by: yeonghyeonKo <[email protected]> * Fix multi node transport issue on NeuralKNNQueryBuilder originalQueryText (#1272) Signed-off-by: Junqiu Lei <[email protected]> * Add semantic field mapper. (#1225) Signed-off-by: Bo Zhang <[email protected]> * Add semantic mapping transformer. (#1276) Signed-off-by: Bo Zhang <[email protected]> * [FIX] minor typo Signed-off-by: yeonghyeonKo <[email protected]> * [REFACTOR] adopt FixedTokenLengthChunker's loop strategy for robust final chunking Signed-off-by: yeonghyeonKo <[email protected]> * [TEST] sum the number of processors and their executions correctly in TextChunkingProcessorIT Signed-off-by: yeonghyeonKo <[email protected]> * [REFACTOR] gradlew spotlessApply Signed-off-by: yeonghyeonKo <[email protected]> --------- Signed-off-by: Will Hwang <[email protected]> Signed-off-by: yeonghyeonKo <[email protected]> Signed-off-by: will-hwang <[email protected]> Signed-off-by: Varun Jain <[email protected]> Signed-off-by: Andy Qin <[email protected]> Signed-off-by: Martin Gaievski <[email protected]> Signed-off-by: Junqiu Lei <[email protected]> Signed-off-by: Chloe Gao <[email protected]> Signed-off-by: Harsha Vamsi Kalluri <[email protected]> Signed-off-by: Gulshan <[email protected]> Signed-off-by: Bo Zhang <[email protected]> Signed-off-by: opensearch-ci-bot <[email protected]> Signed-off-by: Peter Zhu <[email protected]> Signed-off-by: Ryan Bogan <[email protected]> Signed-off-by: Marcel Yeonghyeon Ko <[email protected]> Signed-off-by: zhichao-aws <[email protected]> Signed-off-by: Owais <[email protected]> Co-authored-by: Will Hwang <[email protected]> Co-authored-by: Martin Gaievski <[email protected]> Co-authored-by: Varun Jain <[email protected]> Co-authored-by: Junqiu Lei <[email protected]> Co-authored-by: Andy <[email protected]> Co-authored-by: Chloe Gao <[email protected]> Co-authored-by: Harsha Vamsi Kalluri <[email protected]> Co-authored-by: Gulshan <[email protected]> Co-authored-by: Bo Zhang <[email protected]> Co-authored-by: opensearch-trigger-bot[bot] <98922864+opensearch-trigger-bot[bot]@users.noreply.github.com> Co-authored-by: opensearch-ci-bot <[email protected]> Co-authored-by: Peter Zhu <[email protected]> Co-authored-by: Ryan Bogan <[email protected]> Co-authored-by: zhichao-aws <[email protected]> Co-authored-by: Owais Kazi <[email protected]>

will-hwang force-pushed the optimized-text-embedding-processor-batch branch from c04d826 to 516c43a Compare March 8, 2025 04:41

will-hwang marked this pull request as ready for review March 8, 2025 04:58

will-hwang requested review from heemin32, navneet1v, VijayanB, vamshin, jmazanec15, naveentatikonda, junqiu-lei, martin-gaievski, sean-zheng-amazon, model-collapse, zane-neo, vibrantvarun, zhichao-aws, yuye-aws and minalsha as code owners March 8, 2025 04:58

heemin32 reviewed Mar 11, 2025

View reviewed changes

src/main/java/org/opensearch/neuralsearch/processor/TextEmbeddingProcessor.java Outdated Show resolved Hide resolved

will-hwang force-pushed the optimized-text-embedding-processor-batch branch 2 times, most recently from ddc33f8 to a257a0c Compare March 11, 2025 22:15

vibrantvarun reviewed Mar 12, 2025

View reviewed changes

will-hwang force-pushed the optimized-text-embedding-processor-batch branch from a257a0c to 3bb0a19 Compare March 12, 2025 21:56

heemin32 reviewed Mar 13, 2025

View reviewed changes

vibrantvarun reviewed Mar 14, 2025

View reviewed changes

will-hwang force-pushed the optimized-text-embedding-processor-batch branch from 3bb0a19 to d69a219 Compare March 14, 2025 22:30

will-hwang force-pushed the optimized-text-embedding-processor-batch branch from d69a219 to 4400154 Compare March 17, 2025 23:13

heemin32 reviewed Mar 17, 2025

View reviewed changes

implement batch document update scenario in text embedding processor

ac037de

Signed-off-by: Will Hwang <[email protected]>

will-hwang force-pushed the optimized-text-embedding-processor-batch branch from 4400154 to ac037de Compare March 17, 2025 23:58

heemin32 approved these changes Mar 18, 2025

View reviewed changes

junqiu-lei approved these changes Mar 18, 2025

View reviewed changes

heemin32 merged commit bef96ab into opensearch-project:optimized-processor Mar 18, 2025
39 of 48 checks passed

will-hwang added a commit to will-hwang/neural-search that referenced this pull request Mar 20, 2025

implement batch document update scenario in text embedding processor (o…

fd5dfad

…pensearch-project#1217) Signed-off-by: Will Hwang <[email protected]>

will-hwang mentioned this pull request Mar 20, 2025

Implement Optimized embedding generation in text embedding processor #1238

Merged

5 tasks

will-hwang added a commit to will-hwang/neural-search that referenced this pull request Mar 20, 2025

implement batch document update scenario in text embedding processor (o…

fc5936c

…pensearch-project#1217) Signed-off-by: Will Hwang <[email protected]>

will-hwang added a commit to will-hwang/neural-search that referenced this pull request Mar 20, 2025

implement batch document update scenario in text embedding processor (o…

48d242a

…pensearch-project#1217) Signed-off-by: will-hwang <[email protected]>

will-hwang added a commit to will-hwang/neural-search that referenced this pull request Mar 24, 2025

implement batch document update scenario for text embedding processor (…

8c6e6a9

…opensearch-project#1217) Signed-off-by: Will Hwang <[email protected]>

will-hwang added a commit to will-hwang/neural-search that referenced this pull request Mar 24, 2025

implement batch document update scenario for text embedding processor (…

5db22b0

…opensearch-project#1217) Signed-off-by: Will Hwang <[email protected]>

will-hwang added a commit to will-hwang/neural-search that referenced this pull request Mar 24, 2025

implement batch document update scenario for text embedding processor (…

fccccf4

…opensearch-project#1217) Signed-off-by: Will Hwang <[email protected]>

will-hwang added a commit to will-hwang/neural-search that referenced this pull request Mar 24, 2025

implement batch document update scenario for text embedding processor (…

e77f881

…opensearch-project#1217) Signed-off-by: Will Hwang <[email protected]>

will-hwang added a commit to will-hwang/neural-search that referenced this pull request Mar 24, 2025

implement batch document update scenario for text embedding processor (…

fca9a4f

…opensearch-project#1217) Signed-off-by: Will Hwang <[email protected]>

will-hwang added a commit to will-hwang/neural-search that referenced this pull request Mar 24, 2025

implement batch document update scenario for text embedding processor (…

3dc9d7c

…opensearch-project#1217) Signed-off-by: Will Hwang <[email protected]>

implement batch document optimization for text embedding processor #1217

implement batch document optimization for text embedding processor #1217

Uh oh!

Conversation

will-hwang commented Mar 7, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Description

Proposed State [Batch Document Update]

Related Issues

Check List

Uh oh!

codecov bot commented Mar 8, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Codecov Report

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

will-hwang Mar 11, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Uh oh!

heemin32 Mar 11, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

vibrantvarun left a comment

Choose a reason for hiding this comment

will-hwang commented Mar 7, 2025 •

edited

Loading

codecov bot commented Mar 8, 2025 •

edited

Loading

will-hwang Mar 11, 2025 •

edited

Loading

heemin32 Mar 11, 2025 •

edited

Loading

heemin32 commented Mar 18, 2025 •

edited

Loading