Skip to content

[GH-2609] Fix resource leak issue in VertexAiTextEmbeddingModel #2611

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 1 commit into from
Closed

[GH-2609] Fix resource leak issue in VertexAiTextEmbeddingModel #2611

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
45 changes: 23 additions & 22 deletions .../main/java/org/springframework/ai/vertexai/embedding/text/VertexAiTextEmbeddingModel.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -128,37 +128,38 @@ public EmbeddingResponse call(EmbeddingRequest request) {
.observation(this.observationConvention, DEFAULT_OBSERVATION_CONVENTION, () -> observationContext,
this.observationRegistry)
.observe(() -> {
PredictionServiceClient client = createPredictionServiceClient();
try (PredictionServiceClient client = createPredictionServiceClient()) {
Copy link
Contributor Author

@rodrigomalara rodrigomalara Mar 31, 2025 •
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

the proposed fix


EndpointName endpointName = this.connectionDetails.getEndpointName(finalOptions.getModel());
EndpointName endpointName = this.connectionDetails.getEndpointName(finalOptions.getModel());

PredictRequest.Builder predictRequestBuilder = getPredictRequestBuilder(request, endpointName,
finalOptions);
PredictRequest.Builder predictRequestBuilder = getPredictRequestBuilder(request, endpointName,
finalOptions);

PredictResponse embeddingResponse = this.retryTemplate
.execute(context -> getPredictResponse(client, predictRequestBuilder));
PredictResponse embeddingResponse = this.retryTemplate
.execute(context -> getPredictResponse(client, predictRequestBuilder));

int index = 0;
int totalTokenCount = 0;
List<Embedding> embeddingList = new ArrayList<>();
for (Value prediction : embeddingResponse.getPredictionsList()) {
Value embeddings = prediction.getStructValue().getFieldsOrThrow("embeddings");
Value statistics = embeddings.getStructValue().getFieldsOrThrow("statistics");
Value tokenCount = statistics.getStructValue().getFieldsOrThrow("token_count");
totalTokenCount = totalTokenCount + (int) tokenCount.getNumberValue();
int index = 0;
int totalTokenCount = 0;
List<Embedding> embeddingList = new ArrayList<>();
for (Value prediction : embeddingResponse.getPredictionsList()) {
Value embeddings = prediction.getStructValue().getFieldsOrThrow("embeddings");
Value statistics = embeddings.getStructValue().getFieldsOrThrow("statistics");
Value tokenCount = statistics.getStructValue().getFieldsOrThrow("token_count");
totalTokenCount = totalTokenCount + (int) tokenCount.getNumberValue();

Value values = embeddings.getStructValue().getFieldsOrThrow("values");
Value values = embeddings.getStructValue().getFieldsOrThrow("values");

float[] vectorValues = VertexAiEmbeddingUtils.toVector(values);
float[] vectorValues = VertexAiEmbeddingUtils.toVector(values);

embeddingList.add(new Embedding(vectorValues, index++));
}
EmbeddingResponse response = new EmbeddingResponse(embeddingList,
generateResponseMetadata(finalOptions.getModel(), totalTokenCount));
embeddingList.add(new Embedding(vectorValues, index++));
}
EmbeddingResponse response = new EmbeddingResponse(embeddingList,
generateResponseMetadata(finalOptions.getModel(), totalTokenCount));

observationContext.setResponse(response);
observationContext.setResponse(response);

return response;
return response;
}
});
}

Expand Down