Thank you for taking time to contribute this pull request!You might have already read the [contributor guide][1], but as...

Thank you for taking time to contribute this pull request!You might have already read the [contributor guide][1], but as...

Some model providers use short-lived api keys which must be renewed at regular intervals using another credential. For e...

Polishing: Extract repeated code into a method to make the code more concise.Comment From: markpollackI would chain the ...

Provide sensible defaults for overloaded methods in PromptUserSpec, PromptSystemSpec, AdvisorSpec, CallResponseSpec, Cha...

Additionally:Throw IllegalArgumentException instead of NullPointerException from constructor for null EmbeddingModel.Del...

Many of the AI provider ChatModels prematurely construct an Observation.Context when ChatModel Observations may not even...

See title.Comment From: ThomasVitaleGeneral comment about the added @Nullable annotations in the observation classes. Th...

this PR is Support for Embedding-3 Model and Update Related Tests.the PR content:- Add Embedding_3 Model in ZhiPuAiApi- ...

An option to use a generic JdbcChatMemory with a starter for users that want to use SQL as chat memory.Comment From: ogb...

Consolidate SpeechModel APIs into the spring-ai-core module, make it null-safe and covered by unit tests.Refactor OpenAi...

Pinecone Java Client released 2.1.0, and currently spring-ai still uses 0.8.0 version.Comment From: markpollackThanks! ...

Created TranscriptionModel interface that extends ModelImplemented call(AudioTranscriptionPrompt) method for better comp...

Thank you for taking time to contribute this pull request!You might have already read the [contributor guide][1], but as...

Improving the content methods of the DefaultChatClientThis pull request contains a proposal for updating the content met...

Hello, this PR implements StabilityAi Image Edit - Remove Background API's client.[The result of the execution]BeforeAft...

MotivationFor the Azure AudioTranscription, we need to obtain a structured response in the verbose_json response format....

In the current implementation of QuestionAnswerAdvisor, the user text is always used as the query sent to VectorStore's...

This PR aims to achieve two objectives through the proposed changes:Separate the common embedding logic present in the V...

Updated the core vector store's classes to support vector search (enabled by default as today), full-text search, and re...