Skip to content
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.

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

Blogpost #190

Draft
wants to merge 23 commits into
base: main
Choose a base branch
from
Draft
Changes from 17 commits
Commits
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
46 changes: 46 additions & 0 deletions BLOGPOST.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,46 @@
# Introducing the SAP Cloud SDK for AI (JavaScript/TypeScript) 🎉

Check warning on line 1 in BLOGPOST.md

View workflow job for this annotation

GitHub Actions / grammar-check

[vale] reported by reviewdog 🐶 [SAP.Readability] The text is very complex! It has a grade score of >14. Raw Output: {"message": "[SAP.Readability] The text is very complex! It has a grade score of \u003e14.", "location": {"path": "BLOGPOST.md", "range": {"start": {"line": 1, "column": 1}}}, "severity": "WARNING"}
marikaner marked this conversation as resolved.
Show resolved Hide resolved

We are excited to announce the initial release of the [SAP Cloud SDK for AI](https://github.com/SAP/ai-sdk-js#readme)!
It simplifies the integration of generative AI capabilities into your SAP Business Technology Platform (BTP) applications.

Check failure on line 4 in BLOGPOST.md

View workflow job for this annotation

GitHub Actions / grammar-check

[vale] reported by reviewdog 🐶 [SAP.Products] Use 'SAP BTP' instead of 'BTP'. Raw Output: {"message": "[SAP.Products] Use 'SAP BTP' instead of 'BTP'.", "location": {"path": "BLOGPOST.md", "range": {"start": {"line": 4, "column": 105}}}, "severity": "ERROR"}

The SDK allows you to leverage [SAP AI Core](https://help.sap.com/docs/sap-ai-core/sap-ai-core-service-guide/what-is-sap-ai-core) and [SAP AI Launchpad](https://help.sap.com/docs/ai-launchpad/sap-ai-launchpad-user-guide/using-sap-ai-launchpad?locale=en-US), enabling capabilities like templating, grounding, data masking, and more.
In this blog post, we'll introduce you to the key packages and their features.

## Key Packages
### AI Orchestration with `@sap-ai-sdk/orchestration`
The [@sap-ai-sdk/orchestration](https://github.com/SAP/ai-sdk-js/tree/main/packages/orchestration#readme) package enables generative AI orchestration, allowing you to configure templating, content filtering, and data masking for your applications.
With the orchestration service, you can streamline AI interactions and ensure compliance with content safety guidelines.

- **[Templating](https://github.com/SAP/ai-sdk-js/blob/main/packages/orchestration/README.md#templating)**: Create dynamic prompts with placeholders to customize AI interactions based on user inputs.
- **[Content Filtering](https://github.com/SAP/ai-sdk-js/blob/main/packages/orchestration/README.md#content-filtering)**: Apply filters to ensure input and output adhere to content safety guidelines.
- **[Data Masking](https://github.com/SAP/ai-sdk-js/blob/main/packages/orchestration/README.md#data-masking)**: Anonymize sensitive information with data masking features.

Choose a reason for hiding this comment

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

Anonymise or pseudonymize

marikaner marked this conversation as resolved.
Show resolved Hide resolved

### AI Management with `@sap-ai-sdk/ai-api`
The [@sap-ai-sdk/ai-api](https://github.com/SAP/ai-sdk-js/tree/main/packages/ai-api#readme) package provides comprehensive tools for managing scenarios and workflows in SAP AI Core.
You can automate processes such as creating artifacts, configurations, and deployments; executing batch inference jobs; and managing Docker registries and object storage for training data.
marikaner marked this conversation as resolved.
Show resolved Hide resolved

- **[Artifact Management](https://github.com/SAP/ai-sdk-js/tree/main/packages/ai-api#create-an-artifact)**: Register and manage datasets and other model artifacts.
- **[Configuration Management](https://github.com/SAP/ai-sdk-js/tree/main/packages/ai-api#create-a-configuration)**: Set up configurations for different models and use cases.
- **[Deployment Management](https://github.com/SAP/ai-sdk-js/tree/main/packages/ai-api#create-a-deployment)**: Deploy AI models and manage their lifecycle within SAP AI Core.

### LangChain Integration with `@sap-ai-sdk/langchain`
The [@sap-ai-sdk/langchain](https://github.com/SAP/ai-sdk-js/tree/main/packages/langchain#readme) package provides LangChain-compatible clients for Azure OpenAI models deployed in SAP AI Core, enabling sophisticated AI pipelines within your SAP BTP applications.

- **Seamless Integration**: Built on SAP Cloud SDK for AI's foundation model clients, ensuring compatibility with SAP AI Core and LangChain's ecosystem.
- **Flexible Clients**: Easily initialize chat and embedding clients with support for advanced features like templating and output parsing.

Check warning on line 30 in BLOGPOST.md

View workflow job for this annotation

GitHub Actions / grammar-check

[vale] reported by reviewdog 🐶 [SAP.Weasel] 'Easily' is a weasel word! Raw Output: {"message": "[SAP.Weasel] 'Easily' is a weasel word!", "location": {"path": "BLOGPOST.md", "range": {"start": {"line": 30, "column": 25}}}, "severity": "WARNING"}
- **RAG Support**: Implement [Retrieval-Augmented Generation workflows](https://github.com/SAP/ai-sdk-js/blob/main/sample-code/src/langchain-azure-openai.ts#L65) by combining embedding capabilities with LangChain's text splitters and vector stores.

### Generative AI with `@sap-ai-sdk/foundation-models`
The [@sap-ai-sdk/foundation-models](https://github.com/SAP/ai-sdk-js/tree/main/packages/foundation-models#readme) package offers streamlined access to specific generative AI models deployed in SAP AI Core and SAP AI Launchpad.
It provides a more focused interface compared to the full orchestration capabilities, concentrating on direct model interactions.

tomfrenken marked this conversation as resolved.
Show resolved Hide resolved
This package is ideal for developers who need direct access to foundation models for inference and embedding requests without the additional layers of templating, content filtering, or data masking provided by the orchestration service.

## Getting Started
To use the packages, you will need Node v20 or higher, as well as an ESM (ECMAScript Modules) compatible application.

To explore these packages further, check out our [sample project](https://github.com/SAP/ai-sdk-js/tree/main/sample-code#readme) demonstrating the usage of various SDK packages.

## Support and Feedback
We value your feedback on this initial release!
If you need support or want to share your thoughts and ideas, please do so with [GitHub issues](https://github.com/SAP/ai-sdk-js/issues).
Loading