skilld
All skills
secondsky avatar

/sap-ai-core

@620a19a
by Eddiesecondsky/sap-skills456 stars
120

Guides development with SAP AI Core and SAP AI Launchpad for enterprise AI/ML workloads on SAP BTP. Use when: deploying generative AI models, building orchestration workflows with templating/filtering/grounding, implementing RAG with vector databases, managing ML training pipelines with Argo Workflows, configuring content filtering and data masking for PII protection, using the Generative AI Hub for prompt experimentation, managing prompt templates via the Prompt Registry, or integrating AI capabilities into SAP applications. Covers service plans (Free/Standard/Extended), model providers (Azure OpenAI, AWS Bedrock, GCP Vertex AI, Mistral, IBM, Perplexity), orchestration modules, embeddings, tool calling, and structured outputs.

Ask your Agent

Use this Skill: https://skilld.dev/gh/secondsky/sap-skills/sap-ai-core

This session only. Nothing lands on disk.

referencesmodel-providers.md

≈3k tokens on demand. Your agent reads this file only when SKILL.md points to it.

Model Providers Reference

Complete reference for SAP AI Core model providers and available models.

Documentation Source: SAP Help Portal - SAP AI Core

Latest Models: SAP Note 3437766

Overview

SAP AI Core provides access to models from multiple providers via the Generative AI Hub. All models are accessed through a unified API, allowing easy switching between providers.

Catalog rule: This reference describes provider families and common configuration shapes. Exact model IDs, versions, context windows, pricing, regions, and deprecation dates must be verified in the target tenant through SAP AI Launchpad Model Library, GET /v2/lm/scenarios/foundation-models/models, and SAP Note 3437766 before implementation.

Provider Summary

Provider Executable ID Access Type Model Categories
Azure OpenAI azure-openai Remote Chat, Embeddings, Vision, Reasoning, Realtime
SAP Open Source aicore-opensource Local Chat, Embeddings, Vision
Google Vertex AI gcp-vertexai Remote Chat, Embeddings, Vision, Code, Image Gen
AWS Bedrock aws-bedrock Remote Chat, Embeddings
Mistral AI aicore-mistralai Local Chat, Code
IBM aicore-ibm Local Chat, Code
Perplexity aicore-perplexity Remote Chat with Citations, Deep Research

1. Azure OpenAI

Executable ID: azure-openai Access Type: Remote (Azure-hosted)

Example Model Families

Family Typical Capabilities Selection Guidance
GPT chat/multimodal Chat, vision, structured output Verify exact model ID, context window, and region in tenant catalog.
Reasoning models Complex reasoning chains Use when quality justifies added latency/cost; verify quota.
Realtime models Low-latency conversational API Verify endpoint support and streaming/realtime quotas.
Embedding models Vector embeddings Match dimensions and language coverage to the target vector store.

Deprecated/retiring patterns: older GPT-4, GPT-4 Turbo, GPT-4-32k, and GPT-3.5-era deployments should be checked against SAP Note 3437766 and migrated before retirement dates shown in the tenant catalog.

Configuration Example

{
  "name": "azure-gpt4o-config",
  "executableId": "azure-openai",
  "scenarioId": "foundation-models",
  "parameterBindings": [
    {"key": "modelName", "value": "gpt-4o"},
    {"key": "modelVersion", "value": "2024-05-13"}
  ]
}

2. SAP-Hosted Open Source

Executable ID: aicore-opensource Access Type: Local (SAP-hosted)

Example Model Families

Family Typical Capabilities Selection Guidance
Llama-family Chat, reasoning, select vision variants Verify enabled model IDs and context windows in tenant catalog.
Mistral/Mixtral-family Instruction following, code, low-latency chat Check tenant catalog before using exact IDs.
Falcon-family General text generation Use only where explicitly enabled.

Configuration Example

{
  "name": "llama-config",
  "executableId": "aicore-opensource",
  "scenarioId": "foundation-models",
  "parameterBindings": [
    {"key": "modelName", "value": "meta--llama-3.1-70b-instruct"},
    {"key": "modelVersion", "value": "latest"}
  ]
}

3. Google Vertex AI

Executable ID: gcp-vertexai Access Type: Remote (Google Cloud)

Example Model Families

Family Typical Capabilities Selection Guidance
Gemini Pro-family Chat, vision, code, long context Verify catalog entry, preview/stable status, and token limits.
Gemini Flash-family Fast multimodal responses Use for lower-latency use cases when enabled.
Google embedding models Vector embeddings Match dimensions and language coverage to the target vector store.

Deprecated/retiring patterns: older Gemini and PaLM-era deployments should be checked against SAP Note 3437766 and migrated before retirement dates shown in the tenant catalog.

Configuration Example

{
  "name": "gemini-config",
  "executableId": "gcp-vertexai",
  "scenarioId": "foundation-models",
  "parameterBindings": [
    {"key": "modelName", "value": "gemini-1.5-pro"},
    {"key": "modelVersion", "value": "latest"}
  ]
}

4. AWS Bedrock

Executable ID: aws-bedrock Access Type: Remote (AWS)

Example Model Families

Family Typical Capabilities Selection Guidance
Anthropic Claude-family Chat, reasoning, coding, summarization Verify exact model ID and Bedrock regional availability in SAP AI Core catalog.
Amazon Nova-family General chat and multimodal tasks Use only where enabled in the tenant catalog.
Amazon Titan-family Text and embeddings Verify dimensions and cost before vector workloads.

Configuration Example

{
  "name": "claude-config",
  "executableId": "aws-bedrock",
  "scenarioId": "foundation-models",
  "parameterBindings": [
    {"key": "modelName", "value": "anthropic--claude-3-5-sonnet"},
    {"key": "modelVersion", "value": "latest"}
  ]
}

5. Mistral AI

Executable ID: aicore-mistralai Access Type: Local (SAP-hosted)

Models

Model Parameters Context Use Case
mistral-large - 32K Advanced reasoning
mistral-medium - 32K Balanced
mistral-small - 32K Cost-efficient
codestral - 32K Code generation

Configuration Example

{
  "name": "mistral-config",
  "executableId": "aicore-mistralai",
  "scenarioId": "foundation-models",
  "parameterBindings": [
    {"key": "modelName", "value": "mistralai--mistral-large"},
    {"key": "modelVersion", "value": "latest"}
  ]
}

6. IBM

Executable ID: aicore-ibm Access Type: Local (SAP-hosted)

Granite Models

Model Parameters Use Case
granite-family entries Various Verify exact model ID and generation in the tenant catalog
granite-13b-chat 13B Conversational
granite-13b-instruct 13B Task completion
granite-code - Code generation

Configuration Example

{
  "name": "granite-config",
  "executableId": "aicore-ibm",
  "scenarioId": "foundation-models",
  "parameterBindings": [
    {"key": "modelName", "value": "ibm--granite-13b-chat"},
    {"key": "modelVersion", "value": "latest"}
  ]
}

7. Perplexity

Executable ID: aicore-perplexity Access Type: Remote (Perplexity-hosted) Availability: tenant-dependent; verify in SAP AI Core catalog.

Example Model Families

Family Use Case
Sonar-family Web-grounded chat with citations
Deep-research family Longer research flows with citations where enabled

Unique Features:

  • Returns citation URLs alongside responses
  • Web-grounded responses for up-to-date information
  • Supports output-with-citations in orchestration workflows

Configuration Example

{
  "name": "perplexity-config",
  "executableId": "aicore-perplexity",
  "scenarioId": "foundation-models",
  "parameterBindings": [
    {"key": "modelName", "value": "perplexity--sonar"},
    {"key": "modelVersion", "value": "latest"}
  ]
}

Model Selection Guide

By Use Case

Use Case Selection Guidance
General chat Use the highest-quality tenant-approved chat model that meets cost and data-residency constraints.
Code generation Use a code-capable catalog entry and validate output with project tests.
Long documents Select catalog entries with sufficient context and explicit long-context support.
Vision/images Choose multimodal catalog entries and verify image-input support.
Embeddings Match embedding dimensions, language coverage, and vector-store requirements.
Cost-sensitive Prefer smaller or mini/nano variants shown in the tenant catalog.
High throughput Prefer lower-latency catalog entries and confirm quota.
Reasoning Use reasoning-capable catalog entries when latency/cost tradeoffs are acceptable.
Web-grounded / citations Use citation-capable entries and preserve returned source URLs.
Deep research Use only where deep-research entries are enabled and validate citation quality.
Realtime Verify realtime endpoint and quota support before implementation.

By Budget

Budget Tier Guidance
Low Economy Use smaller variants and strict token limits.
Medium Standard Use balanced chat models with predictable latency.
High Premium Use top-tier catalog entries after confirming quota and cost.

By Capability

Capability Selection Guidance
Reasoning Choose reasoning-capable entries and measure latency/cost.
Speed Choose smaller, low-latency variants with sufficient quality.
Context length Verify the context window reported by the tenant catalog.
Multimodal Verify input media types and output modality support.
Code Use code-capable entries and validate against project tests.
Citations Use citation-capable entries and preserve returned source URLs.

Model Version Management

Version Strategies

Strategy Configuration Use Case
Latest "modelVersion": "latest" Development, auto-upgrade
Pinned "modelVersion": "2024-05-13" Production stability

Checking Available Versions

curl -X GET "$AI_API_URL/v2/lm/scenarios/foundation-models/models" \
  -H "Authorization: Bearer $AUTH_TOKEN" \
  -H "AI-Resource-Group: default" | \
  jq '.resources[] | select(.model == "gpt-4o") | .versions'

Handling Deprecation

  1. Monitor deprecationDate in model metadata
  2. Plan migration before retirementDate
  3. Test new version in staging
  4. Update configuration with new version
  5. Patch existing deployments

Pricing Considerations

Pricing varies by:

  • Model complexity (larger = more expensive)
  • Input vs output tokens (output often 2-3x input cost)
  • Provider region
  • Access type (Remote vs Local)

Reference: SAP Note 3437766 for current token rates.

Cost Optimization

  1. Right-size models: Use smaller models for simple tasks
  2. Batch requests: Combine multiple queries when possible
  3. Cache responses: Store and reuse common query results
  4. Limit tokens: Set appropriate max_tokens limits
  5. Use streaming: No additional cost, better UX

Rate Limits

Rate limits vary by:

  • Service plan tier
  • Model provider
  • Specific model

Default limits (vary by configuration):

  • Requests per minute: 60-600
  • Tokens per minute: 40K-400K

Handling Rate Limits

import time
from requests.exceptions import HTTPError

def call_with_retry(func, max_retries=3):
    for attempt in range(max_retries):
        try:
            return func()
        except HTTPError as e:
            if e.response.status_code == 429:
                wait_time = 2 ** attempt
                time.sleep(wait_time)
            else:
                raise
    raise Exception("Max retries exceeded")

Documentation Links

Source: SKILL.md on GitHub

Third-party checks

1 alert16d5 checks · Risk SAFE
  • Gen Agent Trust Hub16d

    This skill provides a comprehensive documentation suite and template library for developing with SAP AI Core and SAP AI Launchpad on the SAP Business Technology Platform (BTP). It includes detailed guidance on model orchestration, RAG (Retrieval-Augmented Generation), and ML training pipelines. The skill emphasizes security best practices, including content filtering and data masking, and no malicious patterns were identified.

  • Socket16d

    No alerts

  • Snyk16d

    Risk: LOW · No issues

  • Runlayer6mo

    9/14 files flagged

  • ZeroLeaks5mo

    Score: 93/100 · 2 sections analyzed

Provenance

Signed by skilld at 620a19a. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 2 weeks ago.

Activeupdated 2 months ago

Capability

Other metadata
metadata
{
  "maintainer": "Eduard Jiglau",
  "maintainer_email": "hello@sap-ai-skills.com",
  "website": "https://sap-ai-skills.com",
  "version": "2.4.1",
  "last_verified": "2026-06-12",
  "production_tested": "No; documentation-audited only, no live tenant/runtime evidence",
  "runtime_verification": "pending tenant evidence"
}

README badge

README badge for secondsky/sap-skills/sap-ai-core