Blogpost #190
Draft
Blogpost #190
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
KavithaSiva
reviewed
Oct 4, 2024
|
|
||
| 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. | ||
|
|
||
| The SDK allows you to leverage the SAP AI Core and SAP AI Launchpad, enabling capabilities like templating, grounding, data masking, and more. In this blog post, we’ll introduce you to the key packages and their features. |
There was a problem hiding this comment.
Please link to help documents for SAP AI Core & Launchpad.
AI core -> https://help.sap.com/docs/sap-ai-core/sap-ai-core-service-guide/what-is-sap-ai-core
|
|
||
| ## Key Features | ||
| ### 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 its orchestration service, you can streamline workflows and manage AI models within SAP AI Core. |
There was a problem hiding this comment.
Suggested change
| 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 its orchestration service, you can streamline workflows and manage AI models within SAP AI Core. | |
| 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 workflows and manage AI models within SAP AI Core. |
[question] It's unclear what kind of workflows are we talking about.
Also, we don't really manage models with the orchestration service right?
Comment on lines
+11
to
+13
| - **Templating**: Create dynamic prompts with placeholders to customize AI interactions based on user inputs. | ||
| - **Content Filtering**: Apply filters to ensure input and output adhere to content safety guidelines. | ||
| - **Data Masking**: Anonymize sensitive information with data masking features. |
There was a problem hiding this comment.
[pp] It would be nice to see some code examples. Consider adding a very minimal usage and linking to readme of the orchestration client for specific code samples related to each module.
Comment on lines
+18
to
+20
| - **Artifact Management**: Register and manage datasets and other model artifacts. | ||
| - **Configuration Management**: Set up configurations for different models and use cases. | ||
| - **Deployment Management**: Deploy AI models and manage their lifecycle within SAP AI Core. |
There was a problem hiding this comment.
[pp] Consider linking to readme of the ai core client for specific code samples related to each section.
| - **Data Masking**: Anonymize sensitive information with data masking features. | ||
|
|
||
| ### 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. |
There was a problem hiding this comment.
[question] Should we mention that this client is generated and will be updated regularly based on spec?
| ### 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. | ||
|
|
||
| This package is ideal for developers who need direct access to foundation models without the additional layers of orchestration, content filtering, or data masking provided by the orchestration service. |
There was a problem hiding this comment.
Suggested change
| This package is ideal for developers who need direct access to foundation models without the additional layers of orchestration, content filtering, or data masking provided by the orchestration service. | |
| 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. |
|
|
||
| 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. | ||
|
|
||
| The SDK allows you to leverage the SAP AI Core and SAP AI Launchpad, enabling capabilities like templating, grounding, data masking, and more. In this blog post, we’ll introduce you to the key packages and their features. |
There was a problem hiding this comment.
[question] Is it important to mention somewhere that we use ESM instead of CJS?
What about minimum node version required?
|
|
||
| ### 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. | ||
|
|
There was a problem hiding this comment.
[pp] Minimal code samples for at least orchestration and the OpenAI client would be a nice to have.
|
|
||
| - **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. | ||
| - **RAG Support**: Implement Retrieval-Augmented Generation workflows by combining embedding capabilities with LangChain's text splitters and vector stores. |
There was a problem hiding this comment.
[question] Do we have an example for RAG in our sample code?
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Context
AI/gen-ai-hub-sdk-js-backlog#ISSUENUMBER.
Please provide a description of what your change does and why it is needed.
Definition of Done