genai-hub-orchestration — Claude Code skill: use & install
genai-hub-orchestration — a skill for Claude Code configures SAP AI Core Orchestration pipelines with prompt templates, content filtering, and document grounding. Model requests run through the Harmonized API.
Apache-2.0 188 installs ★ 153 updated 2026-10-22
npx skills add SAP/ai-skills-library --skill genai-hub-orchestration -a claude-codeWhat genai-hub-orchestration does
The skill sets up and executes SAP AI Core Orchestration pipelines using the Python SDK or REST API. It handles prompt templating with variable substitution, input and output content filtering via Azure Content Filter, and document grounding. Supported models map to OpenAI message format through the Harmonized API.
Running the skill requires Python 3.11+, uv, and sap-ai-sdk-gen. The older generative-ai-hub-sdk package is deprecated. Calls target the POST {DEPLOYMENT_URL}/v2/completion endpoint, where both scenario_id and executable_id are fixed to orchestration.
The service fails if an orchestration deployment is not active beforehand. When using reasoning models such as Gemini 2.5 Pro or o3, max_completion_tokens must be set to at least 1024 because reasoning tokens consume output capacity before generating visible text.
What it helps with
- configure prompt templates with variables in SAP AI Core
- set up input and output content filtering for LLM calls
- assemble a RAG pipeline with document grounding
- query multiple model providers via the Harmonized API
Example prompts for the agent
- Configure a basic SAP AI Core orchestration pipeline with a prompt template
- Add Azure content filtering to an OrchestrationService call with gpt-4o-mini
- Prepare a curl request to the /v2/completion orchestration endpoint
How to install genai-hub-orchestration
1Skills CLI (Vercel)
npx skills add SAP/ai-skills-library --skill genai-hub-orchestration -a claude-code2Manually: put the files in place
~/.claude/skills/genai-hub-orchestration/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/genai-hub-orchestration/
1Skills CLI (Vercel)
npx skills add SAP/ai-skills-library --skill genai-hub-orchestration -a codex2Manually: put the files in place
.agents/skills/genai-hub-orchestration/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add SAP/ai-skills-library --skill genai-hub-orchestration -a cursor2Manually: put the files in place
.cursor/skills/genai-hub-orchestration/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install SAP/ai-skills-library plugins/aicore-skills/skills/genai-hub-orchestration2Manually: put the files in place
.github/skills/genai-hub-orchestration/SKILL.md1Skills CLI (Vercel)
npx skills add SAP/ai-skills-library --skill genai-hub-orchestration -a gemini-cli2Platform CLI
gemini skills install https://github.com/SAP/ai-skills-library --path plugins/aicore-skills/skills/genai-hub-orchestrationManually: put the files in place
.devin/skills/genai-hub-orchestration/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add SAP/ai-skills-library --skill genai-hub-orchestration -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about genai-hub-orchestration
How to install genai-hub-orchestration in Claude Code?
Run npx skills add SAP/ai-skills-library --skill genai-hub-orchestration -a claude-code.
What does genai-hub-orchestration do?
It configures SAP AI Core Orchestration pipelines, handles prompt templating with variables, attaches content filters, and sets up document grounding.
What are the prerequisites for genai-hub-orchestration?
You need Python 3.11+, uv, sap-ai-sdk-gen, and an active orchestration deployment in SAP AI Core.
Source text
SKILL.md · Apache-2.0
---
name: genai-hub-orchestration
description: >
Configure and use the SAP AI Core Orchestration service: build prompt templates, add content
filtering, set up document grounding (RAG) pipelines, and call models via
the Harmonized API.
WHEN: user asks about the orchestration service, Harmonized API, prompt
templating with variables, content filtering, grounding, RAG pipeline, document
grounding, or building a pipeline that wraps an LLM.
DO NOT USE FOR: creating an orchestration deployment — use `aicore-lifecycle-management` for that;
credential setup — use `aicore-admin-resources`; browsing or deploying foundation models
directly without a pipeline — use `genai-hub-foundation-models`; direct LLM inference without a pipeline — use `aicore-sdk-java` or `aicore-sdk-js`
compatibility: Requires Python 3.11+, uv, and sap-ai-sdk-gen.
allowed-tools: Bash, Read
---
## Rules
1. Orchestration always requires a **running orchestration deployment** as a prerequisite — invoke `aicore-lifecycle-management` first if one does not exist.
2. The orchestration endpoint is `POST {DEPLOYMENT_URL}/v2/completion` — not `/v1/chat/completions`.
3. Orchestration `scenario_id` and `executable_id` are always `"orchestration"` — these are fixed.
4. The Harmonized API normalizes all models to OpenAI message format — the same client code works for GPT, Gemini, and Bedrock.
5. If credentials are not configured, invoke `aicore-admin-resources` first.
6. `generative-ai-hub-sdk` is deprecated — always use `sap-ai-sdk-gen`. Import namespace `gen_ai_hub` is shared by both.
7. **If the user's request does not explicitly specify an approach, use `AskUserQuestion` to ask whether they prefer the REST API (curl) or the Python SDK before writing or running any code.**
---
## Deployment Prerequisite
Before using the orchestration service, a deployment must be running:
```bash
# Check for an existing orchestration deployment:
uv run skills/aicore-lifecycle-management/scripts/get_deployments.py --scenario orchestration
# If none exists, create a configuration first (reuse if "orchestration" config already exists):
uv run skills/aicore-lifecycle-management/scripts/get_configurations.py --scenario-id orchestration --json | jq '.[] | select(.name == "orchestration")'
uv run skills/aicore-lifecycle-management/scripts/create_configuration.py \
--name orchestration \
--scenario-id orchestration \
--executable-id orchestration
# Then deploy (takes up to 10 minutes):
uv run skills/aicore-lifecycle-management/scripts/create_deployment.py --configuration-id <config-id> --wait --timeout 600
```
---
## Workflow
| Step | Action | Key Gate |
| ---- | ----------------------------------------------------------------------------------- | --------------------------------------------- |
| 1 | Verify orchestration deployment is RUNNING | `get_deployments.py --scenario orchestration` |
| 2 | **If approach not stated: ask curl (REST API) or Python SDK** via `AskUserQuestion` | User preference |
| 3 | Choose pipeline features (templating only / + filtering / + grounding) | User intent |
| 4 | Select template from `assets/` or build from scratch | See asset map below |
| 5 | Run and verify output | `uv run assets/<template>.py` |
---
## Asset Map
| Use case | Template |
| -------------------------------------------- | ----------------------------------- |
| Basic chat via orchestration pipeline | `assets/orchestration_basic.py` |
| Chat with content filtering (input + output) | `assets/orchestration_filtering.py` |
| RAG with document grounding | `assets/rag_grounding.py` |
---
## Python SDK — Key Patterns
### Basic pipeline
```python
from gen_ai_hub.orchestration.service import OrchestrationService
from gen_ai_hub.orchestration.models.config import OrchestrationConfig
from gen_ai_hub.orchestration.models.llm import LLM
from gen_ai_hub.orchestration.models.template import Template, TemplateValue
from gen_ai_hub.orchestration.models.message import SystemMessage, UserMessage
config = OrchestrationConfig(
template=Template(messages=[
SystemMessage("You are a helpful assistant."),
UserMessage("{{?user_query}}"),
]),
llm=LLM(name="gpt-4o-mini", version="latest"),
)
svc = OrchestrationService(config=config)
result = svc.run(template_values=[TemplateValue("user_query", "Hello")])
print(result.orchestration_result.choices[0].message.content)
```
### Add content filtering
```python
from gen_ai_hub.orchestration.models.content_filtering import (
ContentFiltering,
InputFiltering,
OutputFiltering,
)
from gen_ai_hub.orchestration.models.azure_content_filter import AzureContentFilter
filtering = ContentFiltering(
input_filtering=InputFiltering(filters=[AzureContentFilter(hate=2, violence=2, sexual=2, self_harm=2)]),
output_filtering=OutputFiltering(filters=[AzureContentFilter(hate=2, violence=2, sexual=2, self_harm=2)]),
)
config = OrchestrationConfig(template=..., llm=..., filtering=filtering)
```
---
## REST API (curl)
```bash
export TOKEN=$(uv run skills/aicore-admin-resources/scripts/get_token.py)
export DEPLOYMENT_URL=$(uv run skills/aicore-lifecycle-management/scripts/get_deployments.py \
--scenario orchestration --json 2>/dev/null | jq -r '.[0].deployment_url')
export RESOURCE_GROUP=$(uv run skills/aicore-admin-resources/scripts/check_setup.py 2>/dev/null | jq -r '.resource_group')
curl --request POST "${DEPLOYMENT_URL}/v2/completion" \
--header "Authorization: Bearer ${TOKEN}" \
--header "AI-Resource-Group: ${RESOURCE_GROUP}" \
--header "content-type: application/json" \
--data-raw '{
"config": {
"modules": {
"prompt_templating": {
"prompt": {
"template": [
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "{{?user_query}}"}
]
},
"model": {
"name": "gpt-4o-mini",
"params": {"max_completion_tokens": 512}
}
}
}
},
"placeholder_values": {"user_query": "What is SAP AI Core?"},
"messages_history": []
}'
```
Extract the answer with: `jq '.final_result.choices[0].message.content'`
> **Reasoning models** (Gemini 2.5 Pro, o3): set `max_completion_tokens` to at least **1024** — reasoning tokens consume the budget before the visible response.
---
## Handoffs
- **No orchestration deployment running?** → invoke `aicore-lifecycle-management`
- **Credential/auth error?** → invoke `aicore-admin-resources`
- **Need to find a model name?** → invoke `genai-hub-foundation-models`
- **Want full Java SDK boilerplate (non-orchestration)?** → invoke `aicore-sdk-java`
- **Want full JS SDK boilerplate (non-orchestration)?** → invoke `aicore-sdk-js`
---
## When to Load Reference Files
| Trigger | Load |
| -------------------------------------------------------- | ----------------------------- |
| REST API details, request/response shape, Harmonized API | `references/ORCHESTRATION.md` |
| Document grounding setup, GroundingModule config, RAG | `references/GROUNDING.md` |
© SAP · Apache-2.0 · SAP/ai-skills-library