This may or may not be considered a bug, but I do wonder what the expected behavior should be.Put simply, when using Saf...

Add customizable failure response instead of empty resultAdd order parameter for advisor prioritizationImplement default...

Prevent potential resource leaksWrap OnnxTensor creation in try-with-resources blockExplicitly close inputIds, attention...

Hello,Bug descriptionWe discovered a memory leak after a few days we've put our application into production.Native memor...

the PR content:add observability to QianFan chat modeladd related unit testsrelated issue: https://github.com/spring-pro...

the PR content:add observability to ZhiPu chat modeladd related unit testsrelated issue: https://github.com/spring-proje...

I want to exclude ElasticsearchVectorStoreAutoConfiguration from my spring boot application to define a custom configura...

Please do a quick search on GitHub issues first, there might be already a duplicate issue for the one you are about to c...

Fixes grammar in (Ollama) Function Calling.Fixes grammar in ETL Pipeline.Fixes grammar in Vector Databases.Closes #1494C...

Integrate ObservationRegistry and EmbeddingModelObservationConventionUpdate TransformersEmbeddingModel to use observatio...

Removed the duplicate entry of the 'spring.ai.vectorstore.elasticsearch.initialize-schema' property from the Elasticsea...

The reason is that there is a problem with the batching logic in the TokenCountBatchingStrategy:public List> batch(List ...

I'am trying to use AzureOpenAiChatClient.When I'am using the stream() method, I can not get info about input and output ...

the PR content:add observability to moonshot chat modeladd related unit testsrelated issue: https://github.com/spring-pr...

Adding observability for Vertex Gemini chat model streaming callUpdating auto-configuration for gemini chat model with t...

Implement observation instrumentation for AzureOpenAiEmbeddingModelCreate AzureOpenAiEmbeddingModelObservationIT for int...

…chat modelIntegrate ObservationRegistry for instrumentation in VertexAiGeminiChatModel's non-streaming callAdd ChatMode...

I find that the results improve when I add ", without any introduction." to the prompt.Example:List 10 unique unicorn na...

Please do a quick search on GitHub issues first, there might be already a duplicate issue for the one you are about to c...

I want get Usage stats for ChatResponseI want get Usage stats for streaming"stream_options": { "include_usage":...