Sap Cloud SDK AI

What it does

When your agent uses it

• Building applications with SAP AI Core
• Generative AI Hub
• Orchestration Service

Example prompts

• “Use the sap-cloud-sdk-ai skill to integrate SAP Cloud SDK for AI into JavaScript/TypeScript and Java applications”
• “/sap-cloud-sdk-ai”

Requirements

• Node.js
• A credential in AICORE_SERVICE_KEY

What it can do on your machine

Read from SKILL.md and the folder at commit 652a861. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • npm

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Links to these hosts (documentation or services it may open):

  • github.com

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • AICORE_SERVICE_KEY

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Sap Cloud SDK AI loads about 3.2k tokens when it runs, and up to ~35k if it reads all its reference files. Until then it costs about 114 tokens; SKILL.md has 725 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~114

When it runs · the whole SKILL.md, loaded when a task matches

~3.2k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~35k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from secondsky/sap-skills at commit 652a861, republished under its GPL-3.0 licence (© secondsky). 725 words, ~3,230 tokens.

name

sap-cloud-sdk-ai

description

Integrates SAP Cloud SDK for AI into JavaScript/TypeScript and Java applications. Use when building applications with SAP AI Core, Generative AI Hub, or Orchestration Service. Covers chat completion, embedding, streaming, function calling, content filtering, data masking, document grounding, prompt registry, and LangChain/Spring AI integration. Supports OpenAI GPT-4o, Llama, Gemini, Amazon Nova, and other foundation models via SAP BTP.

license

GPL-3.0

metadata.maintainer

Eduard Jiglau

metadata.maintainer_email

hello@sap-ai-skills.com

metadata.website

https://sap-ai-skills.com

metadata.version

2.4.1

metadata.last_verified

2026-06-15

metadata.package_evidence

docs/project/package-evidence/2026-06-15.json

npm install @sap-ai-sdk/orchestration@^2

import { OrchestrationClient } from '@sap-ai-sdk/orchestration';

const client = new OrchestrationClient({
  promptTemplating: {
    model: { name: 'gpt-4o' },
    prompt: [{ role: 'user', content: '{{?question}}' }]
  }
});

const response = await client.chatCompletion({
  placeholderValues: { question: 'What is SAP?' }
});
console.log(response.getContent());

<dependency>
  <groupId>com.sap.ai.sdk</groupId>
  <artifactId>orchestration</artifactId>
  <version>${ai-sdk.version}</version>
</dependency>

var client = new OrchestrationClient();
var config = new OrchestrationModuleConfig()
    .withLlmConfig(OrchestrationAiModel.GPT_4O);
var prompt = new OrchestrationPrompt("What is SAP?");
var result = client.chatCompletion(prompt, config);
System.out.println(result.getContent());

export AICORE_SERVICE_KEY='{"clientid":"...","clientsecret":"...","url":"...","serviceurls":{"AI_API_URL":"..."}}'

# JavaScript
cds bind -2 <AICORE_INSTANCE> && cds-tsx watch --profile hybrid

# Java
cds bind --to aicore --exec mvn spring-boot:run

// JavaScript
const stream = client.stream({
  placeholderValues: { question: 'Explain SAP CAP' }
});

for await (const chunk of stream.toContentStream()) {
  process.stdout.write(chunk);
}

// Java
client.streamChatCompletion(prompt, config)
    .forEach(chunk -> System.out.print(chunk.getDeltaContent()));

// JavaScript
const tools = [{
  type: 'function',
  function: {
    name: 'get_weather',
    parameters: { type: 'object', properties: { city: { type: 'string' } } }
  }
}];

const response = await client.chatCompletion({
  placeholderValues: { question: 'Weather in Berlin?' }
}, { tools });

const toolCalls = response.getToolCalls();

// JavaScript
import { buildAzureContentSafetyFilter } from '@sap-ai-sdk/orchestration';

const client = new OrchestrationClient({
  promptTemplating: { model: { name: 'gpt-4o' } },
  filtering: {
    input: buildAzureContentSafetyFilter({ Hate: 'ALLOW_SAFE' }),
    output: buildAzureContentSafetyFilter({ Violence: 'ALLOW_SAFE' })
  }
});

// JavaScript
const client = new OrchestrationClient({
  promptTemplating: { model: { name: 'gpt-4o' } },
  masking: {
    masking_providers: [{
      type: 'sap_data_privacy_integration',
      method: 'anonymization',
      entities: [{ type: 'profile-email' }, { type: 'profile-person' }]
    }]
  }
});

// JavaScript
const client = new OrchestrationClient({
  promptTemplating: { model: { name: 'gpt-4o' } },
  grounding: {
    grounding_input: ['{{?question}}'],
    grounding_output: ['{{?context}}'],
    data_repositories: [{ type: 'vector', id: 'my-repo-id' }]
  }
});

resources:
  - name: my-ai-core
    type: org.cloudfoundry.managed-service
    parameters:
      service: aicore
      service-plan: extended

import { OrchestrationClient } from '@sap-ai-sdk/orchestration';
import cds from '@sap/cds';

export default class AnalysisService extends cds.ApplicationService {
  async init() {
    const client = new OrchestrationClient({
      promptTemplating: {
        model: { name: 'gpt-4o' },
        prompt: [
          { role: 'system', content: 'Analyze and categorize as JSON.' },
          { role: 'user', content: '{{?input}}' }
        ]
      }
    });

    this.on('analyzeText', async (req) => {
      const response = await client.chatCompletion({
        placeholderValues: { input: req.data.text }
      });
      return response.getContent();
    });

    return super.init();
  }
}

this.on('analyzeText', async (req) => {
  const entry = await INSERT.into('Results').entries({
    text: req.data.text, status: 'processing'
  });
  cds.spawn(() => processLLM(entry.id, req.data.text, client));
  return req.reply(202, { id: entry.id, status: 'processing' });
});

const response = await client.chatCompletion({ placeholderValues });

response.getContent();          // Model output string
response.getTokenUsage();       // { prompt_tokens, completion_tokens, total_tokens }
response.getFinishReason();     // 'stop', 'length', 'tool_calls', etc.
response.getToolCalls();        // Array of function calls
response.getDeltaToolCalls();   // Partial tool calls (streaming)
response.getAllMessages();      // Full message history
response.getAssistantMessage(); // Assistant response only
response.getRefusal();          // Refusal message if blocked

const stream = client.stream({ placeholderValues });
for await (const chunk of stream.toContentStream()) {
  process.stdout.write(chunk);
}
// After stream ends:
stream.getFinishReason();
stream.getTokenUsage();

© secondsky, GPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 11 other files (references) in plugins/sap-cloud-sdk-ai/skills/sap-cloud-sdk-ai of secondsky/sap-skills.

• SKILL.md
• README.md
• agents/openai.yaml
• references/agentic-workflows.md
• references/ai-core-api-guide.md
• references/connecting-to-ai-core.md
• references/error-handling.md
• references/foundation-models-guide.md
• references/langchain-guide.md
• references/orchestration-guide.md
• references/spring-ai-guide.md
• references/v1-to-v2-migration.md

Open the folder on GitHubat commit 652a861