Introduces retry functionality to VertexAI embedding and chat models, enhancing their resilience against transient failu...

Long content will have read timeout.2024-03-27T17:33:17.498+08:00 ERROR 11752 --- [nio-8083-exec-4] o.a.c.c.C.[.[.[/].[d...

When I make vectorization embedding requests using Ollama, it takes a long time due to the performance issues of the ser...

All output parser functionality has already been migrated to the converter package since milestone M1.Changes: - Replace...

ObjectMapper instantiation is costly, so unless its usage is one-shot, it is better to create a reusable instance for up...

The reason is that the OpenAiImageResponseMetadata class does not have standard getter methods.Comment From: izeyehttps:...

The OpenAI Moderation is a tool you can use to check whether text is potentially harmful.This PR content :Moderation API...

This change enhances safety in multi-threaded environments by returning unmodifiable objects from getters.getter returns...

This change aims to conceal the implementation and facilitate handling option objects through the interface.And enforcin...

Prevent external modification of internal state by returning unmodifiable collections and adding defensive copies in set...

Please do a quick search on GitHub issues first, the feature you are about to request might have already been requested....

Ensure that Generation and AssistantMessage has Id, index, isCompleted attributes. Also the ChatResponse should have an...

Relevant versions:Spring AI version 1.0.0-SNAPSHOTorg.springframework.cloud:spring-cloud-function-context 4.1.3org.sprin...

Adds special handling for BiFunction class typesAdds test cases to verify BiFunction class type resolutionRemoves deprec...

Bug descriptionCould not transfer artifact io.springboot.ai:spring-ai-bom:pom:1.0.3 from/to central (https://repo.maven....

does spring ai support the vllm +qwen?which starter can i use? and how to use spring ai connect the vllm ?tks.Comment F...

Reefer issue #652 For some use case after local function is called no need to pass the results to LLMs. (eg: data extrac...

Now huggingface text-generation-inference only support Llama, Falcon, StarCoder, BLOOM, GPT-NeoX, and T5. If you select ...

This PR contains an enhancement to the splitter, adding the ability to compose the various parameters and make them immu...

The current set delimiters { and } do not follow the stringtemplate default and need escaping if you want to build a pro...