Release Notes
Should I update?
We highly recommend regularly updating to the latest SAP Cloud SDK for AI version. It will help you:
- Ensure access to the latest SAP Cloud SDK for AI features
- Keep up with the latest changes in SAP ecosystem
- Protect yourself from bugs and breaking changes in the future
1.5.0 - March 13, 2025
✨ New Functionality
- [Orchestration] Add Spring AI Chat Memory support
- [Orchestration] Prompt templates can be consumed from registry.
- [Orchestration] Masking is now available on grounding.
- [Orchestration] Grounding via help.sap.com is enabled.
- [OpenAI] Spring AI integration for embedding calls.
1.4.0 - February 28, 2025
🔧 Compatibility Notes
- [Orchestration] The constructors
UserMessage(MessageContent)
andSystemMessage(MessageContent)
are removed. UseMessage.user(String)
,Message.user(ImageItem)
, orMessage.system(String)
instead. - Deprecate
getCustomField(String)
in favor oftoMap()
on generated model classes.com.sap.ai.sdk.core.model.*
com.sap.ai.sdk.orchestration.model.*
✨ New Functionality
- [Orchestration] Add Spring AI tool calling.
- [Orchestration] Add new convenient methods to set the response format for Orchestration.
- [Document Grounding] Add Document Grounding Client
com.sap.ai.sdk:document-grounding:1.4.0
- [OpenAI] New generated model classes introduced for AzureOpenAI specification dated 2024-10-21.
- [OpenAI] Introducing new user interface for chat completion wrapping the generated model classes.
OpenAiChatCompletionRequest
andOpenAiChatCompletionResponse
' for high level request and response handling.OpenAiUserMessage
,OpenAiSystemMessage
,OpenAiAssistantMessage
andOpenAiToolMessage
for message creation for different content types.OpenAiToolChoice
for configuring chat completion requests with tool selection strategy.
- [OpenAI] Introducing new user interface for embedding calls using
OpenAiEmbeddingRequest
andOpenAiEmbeddingResponse
.
1.3.0 - February 13, 2025
🔧 Compatibility Notes
Message.content()
returns aContentItem
now instead of aString
. Use((TextItem) Message.content().items().get(0)).text()
if the correspondingContentItem
is aTextItem
and the string representation is needed.
✨ New Functionality
- Upgrade to release 2502a of AI Core.
- Orchestration:
- [Add
LlamaGuardFilter
](guides/orchestration-chat-completion#filtering. - Convenient methods to create messages containing images and multiple text inputs
- Enable setting the response format
- [Add
1.2.0 - January 30, 2025
🔧 Compatibility Notes
SingleChatMessage
, as well as newMultiChatMessage
, are now subtypes of new interfaceChatMessage
. Most variables or methods previously typed asChatMessage
inmodel
package are now typed asSingleChatMessage
.- Add missing
@Beta
annotations to allcom.sap.ai.sdk.core.client
andcom.sap.ai.sdk.core.model
classes.
✨ New Functionality
- New Orchestration features:
- Spring AI integration
- Add Grounding configuration convenience
- Images are now supported as input in newly introduced
MultiChatMessage
. MultiChatMessage
also allows for multiple content items (text or image) in one object.- Grounding input can be masked with
DPIConfig
. - LLama Guard can now be used for content filtering.
- Support for tool calling and response format
- Updated the list for supported models (e.g., added amazon nova models).
📈 Improvements
- Update Orchestration client to version 0.48.2 (2501a)
1.1.0 - January 07, 2025
🔧 Compatibility Notes
- Changed return type of
List<Double> getEmbedding()
from experimental APIOpenAiEmbeddingData
tofloat[]
to match recent Spring AI change.
✨ New Functionality
- Added
streamChatCompletion()
andstreamChatCompletionDeltas()
to theOrchestrationClient
.
📈 Improvements
- Update AI Core client to 2.37.0
1.0.0 - December 03, 2024
✨ New Functionality
- Introduce AI Core client to consume the AI Core Rest APIs.
Here are a few features:
- Artifact management: register and organize datasets and model artifacts.
- Configuration management: set up configurations for various models and use cases.
- Deployment management: deploy AI models and manage their lifecycle within SAP AI Core.
- Introduce Orchestration client for consuming the following features of the orchestration service:
- Harmonized LLM access via orchestration
- Prompt templates
- Content filtering
- Masking
- Introduce the OpenAI client to consume the following features:
- Chat completion and streaming chat completion
- Text
- Images
- Tools
- Generate embeddings for input text.
- Chat completion and streaming chat completion
warning
All classes under any of the ...model
packages are generated from an OpenAPI specification and marked as @Beta
.
This means that these model classes are not guaranteed to be stable and may change with future releases.
They are safe to use, but may require updates even in minor releases.