[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6QWJS70BDKECRCRHQC5CC3X":3,"skill-same:01M6QWJS70BDKECRCRHQC5CC3X":128},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":23,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":54,"commitSha":55,"skillDirectory":56,"forksCount":57,"repositoryHtmlUrl":58,"repositoryHomepageUrl":59,"ownerHtmlUrl":60,"ownerBlogUrl":61,"ownerDescription":62,"updatedAt":63,"install":64,"resources":77},"01M6QWJS70BDKECRCRHQC5CC3X","sap-ai-core",null,"Guides development with SAP AI Core and SAP AI Launchpad for enterprise AI\u002FML workloads on SAP BTP. Use when: deploying generative AI models (GPT, Claude, Llama, Gemini, Mistral), building orchestration workflows with templating\u002Ffiltering\u002Fgrounding, 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, or integrating AI capabilities into SAP applications. Covers service plans (Free\u002FStandard\u002FExtended), model providers (Azure OpenAI, AWS Bedrock, GCP Vertex AI, Mistral, IBM), orchestration modules, embeddings, tool calling, and structured outputs.","VRIL-LABS\u002Fskill-jam","VRIL-LABS","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F272046472?v=4","01M6QR9PNWM28WZYJJASER1RG2","𝗩𝗥𝗜𝗟 𝗟𝗔𝗕𝗦","01M6QR9PT6Q6JDCQ97EQBDX6E4",2,"GPL-3.0","https:\u002F\u002Fgithub.com\u002FVRIL-LABS\u002Fskill-jam\u002Fblob\u002Fmain\u002Fskills\u002Fai-ml\u002Fsap-skills-main\u002Fsap-skills-main\u002Fplugins\u002Fsap-ai-core\u002Fskills\u002Fsap-ai-core\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"sap ai core","core","sap","modules","generative","implementing","btp","bedrock","guides","free","enterprise ai","generative ai","pii","gcp","vector","capabilities","training","rag","azure openai","workflows","2026-11-10 10:12:30",false,"---\nname: sap-ai-core\ndescription: |\n  Guides development with SAP AI Core and SAP AI Launchpad for enterprise AI\u002FML workloads on SAP BTP. Use when: deploying generative AI models (GPT, Claude, Llama, Gemini, Mistral), building orchestration workflows with templating\u002Ffiltering\u002Fgrounding, 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, or integrating AI capabilities into SAP applications. Covers service plans (Free\u002FStandard\u002FExtended), model providers (Azure OpenAI, AWS Bedrock, GCP Vertex AI, Mistral, IBM), orchestration modules, embeddings, tool calling, and structured outputs.\nlicense: GPL-3.0\nmetadata:\n  version: \"1.1.1\"\n  last_verified: \"2026-02-25\"\n  production_tested: \"Yes, examples verified against SAP documentation\"\n---\n\n# SAP AI Core & AI Launchpad Skill\n\n## Related Skills\n\n- **sap-btp-cloud-platform**: Use for platform context, BTP account setup, and service integration\n- **sap-cap-capire**: Use for building AI-powered applications with CAP or integrating AI services\n- **sap-cloud-sdk-ai**: Use for SDK integration, AI service calls, and Java\u002FJavaScript implementations\n- **sap-btp-best-practices**: Use for production deployment patterns and AI governance guidelines\n\n## Table of Contents\n\n1. [Overview](#overview)\n2. [Quick Start](#quick-start)\n3. [Service Plans](#service-plans)\n4. [Model Providers](#model-providers)\n5. [Orchestration](#orchestration)\n6. [Content Filtering](#content-filtering)\n7. [Data Masking](#data-masking)\n8. [Grounding (RAG)](#grounding-rag)\n9. [Tool Calling](#tool-calling)\n10. [Structured Output](#structured-output)\n11. [Embeddings](#embeddings)\n12. [ML Training](#ml-training)\n13. [Deployments](#deployments)\n14. [Bundled Resources](#bundled-resources)\n14. [SAP AI Launchpad](#sap-ai-launchpad)\n15. [API Reference](#api-reference)\n16. [Common Patterns](#common-patterns)\n17. [Troubleshooting](#troubleshooting)\n18. [References](#references)\n\n## Overview\n\nSAP AI Core is a service on SAP Business Technology Platform (BTP) that manages AI asset execution in a standardized, scalable, hyperscaler-agnostic manner. SAP AI Launchpad provides the management UI for AI runtimes including the Generative AI Hub.\n\n### Core Capabilities\n\n| Capability | Description |\n|------------|-------------|\n| **Generative AI Hub** | Access to LLMs from multiple providers with unified API |\n| **Orchestration** | Modular pipeline for templating, filtering, grounding, masking |\n| **ML Training** | Argo Workflows-based batch pipelines for model training |\n| **Inference Serving** | Deploy models as HTTPS endpoints for predictions |\n| **Grounding\u002FRAG** | Vector database integration for contextual AI |\n\n### Three Components\n\n1. **SAP AI Core**: Execution engine for AI workflows and model serving\n2. **SAP AI Launchpad**: Management UI for AI runtimes and GenAI Hub\n3. **AI API**: Standardized lifecycle management across runtimes\n\n## Quick Start\n\n### Prerequisites\n\n- SAP BTP enterprise account\n- SAP AI Core service instance (Extended plan for GenAI)\n- Service key with credentials\n\n### 1. Get Authentication Token\n\n```bash\n# Set environment variables from service key\nexport AI_API_URL=\"\u003Cyour-ai-api-url>\"\nexport AUTH_URL=\"\u003Cyour-auth-url>\"\nexport CLIENT_ID=\"\u003Cyour-client-id>\"\nexport CLIENT_SECRET=\"\u003Cyour-client-secret>\"\n\n# Get OAuth token\nAUTH_TOKEN=$(curl -s -X POST \"$AUTH_URL\u002Foauth\u002Ftoken\" \\\n  -H \"Content-Type: application\u002Fx-www-form-urlencoded\" \\\n  -d \"grant_type=client_credentials&client_id=$CLIENT_ID&client_secret=$CLIENT_SECRET\" \\\n  | jq -r '.access_token')\n```\n\n### 2. Create Orchestration Deployment\n\n```bash\n# Check for existing orchestration deployment\ncurl -X GET \"$AI_API_URL\u002Fv2\u002Flm\u002Fdeployments\" \\\n  -H \"Authorization: Bearer $AUTH_TOKEN\" \\\n  -H \"AI-Resource-Group: default\" \\\n  -H \"Content-Type: application\u002Fjson\"\n\n# Create orchestration deployment if needed\ncurl -X POST \"$AI_API_URL\u002Fv2\u002Flm\u002Fdeployments\" \\\n  -H \"Authorization: Bearer $AUTH_TOKEN\" \\\n  -H \"AI-Resource-Group: default\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\n    \"configurationId\": \"\u003Corchestration-config-id>\"\n  }'\n```\n\n### 3. Use Harmonized API for Model Inference\n\n```bash\nORCHESTRATION_URL=\"\u003Cdeployment-url>\"\n\ncurl -X POST \"$ORCHESTRATION_URL\u002Fv2\u002Fcompletion\" \\\n  -H \"Authorization: Bearer $AUTH_TOKEN\" \\\n  -H \"AI-Resource-Group: default\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\n    \"config\": {\n      \"module_configurations\": {\n        \"llm_module_config\": {\n          \"model_name\": \"gpt-4o\",\n          \"model_version\": \"latest\",\n          \"model_params\": {\n            \"max_tokens\": 1000,\n            \"temperature\": 0.7\n          }\n        },\n        \"templating_module_config\": {\n          \"template\": [\n            {\"role\": \"system\", \"content\": \"You are a helpful assistant.\"},\n            {\"role\": \"user\", \"content\": \"{{?user_query}}\"}\n          ]\n        }\n      }\n    },\n    \"input_params\": {\n      \"user_query\": \"What is SAP AI Core?\"\n    }\n  }'\n```\n\n## Service Plans\n\n| Plan | Cost | GenAI Hub | Support | Resource Groups |\n|------|------|-----------|---------|-----------------|\n| **Free** | Free | No | Community only | Default only |\n| **Standard** | Per resource + baseline | No | Full SLA | Multiple |\n| **Extended** | Per resource + tokens | Yes | Full SLA | Multiple |\n\n**Key Restrictions:**\n- Free and Standard mutually exclusive in same subaccount\n- Free → Standard upgrade possible; downgrade not supported\n- Max 50 resource groups per tenant\n\n## Model Providers\n\nSAP AI Core provides access to models from six providers:\n- **Azure OpenAI**: GPT-4o, GPT-4 Turbo, GPT-3.5\n- **SAP Open Source**: Llama, Falcon, Mistral variants\n- **Google Vertex AI**: Gemini Pro, PaLM 2\n- **AWS Bedrock**: Claude, Amazon Titan\n- **Mistral AI**: Mistral Large, Medium, Small\n- **IBM**: Granite models\n\nFor detailed provider configurations and model lists, see `references\u002Fmodel-providers.md`.\n\n## Orchestration\n\nThe orchestration service provides unified access to multiple models through a modular pipeline with 8 execution stages:\n1. Grounding → 2. Templating (mandatory) → 3. Input Translation → 4. Data Masking → 5. Input Filtering → 6. Model Configuration (mandatory) → 7. Output Filtering → 8. Output Translation\n\nFor complete orchestration module configurations, examples, and advanced patterns, see `references\u002Forchestration-modules.md`.\n\n## Content Filtering\n\n**Azure Content Safety**: Filters content across 4 categories (Hate, Violence, Sexual, SelfHarm) with severity levels 0-6. Azure OpenAI blocks severity 4+ automatically. Additional features include PromptShield and Protected Material detection.\n\n**Llama Guard 3**: Covers 14 categories including violent crimes, privacy violations, and code interpreter abuse.\n\n## Data Masking\n\n**Two PII protection methods**:\n- **Anonymization**: `MASKED_ENTITY` (non-reversible)\n- **Pseudonymization**: `MASKED_ENTITY_ID` (reversible)\n\n**Supported entities** (25 total): Personal data, IDs, financial information, SAP-specific IDs, and sensitive attributes. For complete entity list and implementation details, see `references\u002Forchestration-modules.md`.\n\n## Grounding (RAG)\n\nIntegrate external data from SharePoint, S3, SFTP, SAP Build Work Zone, and DMS. Supports PDF, HTML, DOCX, images, and more. Limit: 2,000 documents per pipeline with daily refresh. For detailed setup, see `references\u002Fgrounding-rag.md`.\n\n## Tool Calling\n\nEnable LLMs to execute functions through a 5-step workflow: define tools → receive tool_calls → execute functions → return results → LLM incorporates responses. Templates available in `templates\u002Ftool-definition.json`.\n\n## Structured Output\n\nForce model responses to match JSON schemas using strict validation. Useful for structured data extraction and API responses.\n\n## Embeddings\n\nGenerate semantic embeddings for RAG and similarity search via `\u002Fv2\u002Fembeddings` endpoint. Supports document, query, and text input types.\n\n## ML Training\n\nUses Argo Workflows for training pipelines. Key requirements: create `default` object store secret, define workflow template, create configuration with parameters, and execute training. For complete workflow patterns, see `references\u002Fml-operations.md`.\n\n## Deployments\n\nDeploy models via two-step process: create configuration (with model binding), then create deployment with TTL. Statuses: Pending → Running → Stopping → Stopped\u002FDead. Templates in `templates\u002Fdeployment-config.json`.\n\n## SAP AI Launchpad\n\nWeb-based UI with 4 key applications:\n- **Workspaces**: Manage connections and resource groups\n- **ML Operations**: Train, deploy, monitor models\n- **Generative AI Hub**: Prompt experimentation and orchestration\n- **Functions Explorer**: Explore available AI functions\n\nRequired roles include `genai_manager`, `genai_experimenter`, `prompt_manager`, `orchestration_executor`, and `mloperations_editor`. For complete guide, see `references\u002Fai-launchpad-guide.md`.\n\n## API Reference\n\n### Core Endpoints\n\nKey endpoints: `\u002Fv2\u002Flm\u002Fscenarios`, `\u002Fv2\u002Flm\u002Fconfigurations`, `\u002Fv2\u002Flm\u002Fdeployments`, `\u002Fv2\u002Flm\u002Fexecutions`, `\u002Flm\u002Fmeta`. For complete API reference with examples, see `references\u002Fapi-reference.md`.\n\n## Common Patterns\n\n**Simple Chat**: Basic model invocation with templating module\n**RAG with Grounding**: Combine vector search with LLM for context-aware responses\n**Secure Enterprise Chat**: Filtering + masking + grounding for PII protection\nTemplates available in `templates\u002Forchestration-workflow.json`.\n        \"masking_providers\": [{\n  ## Troubleshooting\n\n**Common Issues**:\n- 401 Unauthorized: Refresh OAuth token\n- 403 Forbidden: Check IAM roles, request quota increase\n- 404 Not Found: Verify AI-Resource-Group header\n- Deployment DEAD: Check deployment logs\n- Training failed: Create `default` object store secret\n\nRequest quota increases via support ticket (Component: `CA-ML-AIC`).\n\n## Bundled Resources\n\n### Reference Documentation\n1. `references\u002Forchestration-modules.md` - All orchestration modules in detail\n2. `references\u002Fgenerative-ai-hub.md` - Complete GenAI hub documentation\n3. `references\u002Fmodel-providers.md` - Model providers and configurations\n4. `references\u002Fapi-reference.md` - Complete API endpoint reference\n5. `references\u002Fgrounding-rag.md` - Grounding and RAG implementation\n6. `references\u002Fml-operations.md` - ML operations and training\n7. `references\u002Fadvanced-features.md` - Chat, applications, security, auditing\n8. `references\u002Fai-launchpad-guide.md` - Complete SAP AI Launchpad UI guide\n\n### Templates\n1. `templates\u002Fdeployment-config.json` - Deployment configuration template\n2. `templates\u002Forchestration-workflow.json` - Orchestration workflow template\n3. `templates\u002Ftool-definition.json` - Tool calling definition template\n\n### Official Sources\n- SAP AI Core Guide: [https:\u002F\u002Fhelp.sap.com\u002Fdocs\u002Fsap-ai-core](https:\u002F\u002Fhelp.sap.com\u002Fdocs\u002Fsap-ai-core)\n- SAP AI Launchpad Guide: [https:\u002F\u002Fhelp.sap.com\u002Fdocs\u002Fsap-ai-launchpad](https:\u002F\u002Fhelp.sap.com\u002Fdocs\u002Fsap-ai-launchpad)\n- SAP Note 3437766: Model token rates and limits\n","# SAP AI Core & AI Launchpad Skill\n\n## Related Skills\n\n- **sap-btp-cloud-platform**: Use for platform context, BTP account setup, and service integration\n- **sap-cap-capire**: Use for building AI-powered applications with CAP or integrating AI services\n- **sap-cloud-sdk-ai**: Use for SDK integration, AI service calls, and Java\u002FJavaScript implementations\n- **sap-btp-best-practices**: Use for production deployment patterns and AI governance guidelines\n\n## Table of Contents\n\n1. [Overview](#overview)\n2. [Quick Start](#quick-start)\n3. [Service Plans](#service-plans)\n4. [Model Providers](#model-providers)\n5. [Orchestration](#orchestration)\n6. [Content Filtering](#content-filtering)\n7. [Data Masking](#data-masking)\n8. [Grounding (RAG)](#grounding-rag)\n9. [Tool Calling](#tool-calling)\n10. [Structured Output](#structured-output)\n11. [Embeddings](#embeddings)\n12. [ML Training](#ml-training)\n13. [Deployments](#deployments)\n14. [Bundled Resources](#bundled-resources)\n14. [SAP AI Launchpad](#sap-ai-launchpad)\n15. [API Reference](#api-reference)\n16. [Common Patterns](#common-patterns)\n17. [Troubleshooting](#troubleshooting)\n18. [References](#references)\n\n## Overview\n\nSAP AI Core is a service on SAP Business Technology Platform (BTP) that manages AI asset execution in a standardized, scalable, hyperscaler-agnostic manner. SAP AI Launchpad provides the management UI for AI runtimes including the Generative AI Hub.\n\n### Core Capabilities\n\n| Capability | Description |\n|------------|-------------|\n| **Generative AI Hub** | Access to LLMs from multiple providers with unified API |\n| **Orchestration** | Modular pipeline for templating, filtering, grounding, masking |\n| **ML Training** | Argo Workflows-based batch pipelines for model training |\n| **Inference Serving** | Deploy models as HTTPS endpoints for predictions |\n| **Grounding\u002FRAG** | Vector database integration for contextual AI |\n\n### Three Components\n\n1. **SAP AI Core**: Execution engine for AI workflows and model serving\n2. **SAP AI Launchpad**: Management UI for AI runtimes and GenAI Hub\n3. **AI API**: Standardized lifecycle management across runtimes\n\n## Quick Start\n\n### Prerequisites\n\n- SAP BTP enterprise account\n- SAP AI Core service instance (Extended plan for GenAI)\n- Service key with credentials\n\n### 1. Get Authentication Token\n\n```bash\n# Set environment variables from service key\nexport AI_API_URL=\"\u003Cyour-ai-api-url>\"\nexport AUTH_URL=\"\u003Cyour-auth-url>\"\nexport CLIENT_ID=\"\u003Cyour-client-id>\"\nexport CLIENT_SECRET=\"\u003Cyour-client-secret>\"\n\n# Get OAuth token\nAUTH_TOKEN=$(curl -s -X POST \"$AUTH_URL\u002Foauth\u002Ftoken\" \\\n  -H \"Content-Type: application\u002Fx-www-form-urlencoded\" \\\n  -d \"grant_type=client_credentials&client_id=$CLIENT_ID&client_secret=$CLIENT_SECRET\" \\\n  | jq -r '.access_token')\n```\n\n### 2. Create Orchestration Deployment\n\n```bash\n# Check for existing orchestration deployment\ncurl -X GET \"$AI_API_URL\u002Fv2\u002Flm\u002Fdeployments\" \\\n  -H \"Authorization: Bearer $AUTH_TOKEN\" \\\n  -H \"AI-Resource-Group: default\" \\\n  -H \"Content-Type: application\u002Fjson\"\n\n# Create orchestration deployment if needed\ncurl -X POST \"$AI_API_URL\u002Fv2\u002Flm\u002Fdeployments\" \\\n  -H \"Authorization: Bearer $AUTH_TOKEN\" \\\n  -H \"AI-Resource-Group: default\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\n    \"configurationId\": \"\u003Corchestration-config-id>\"\n  }'\n```\n\n### 3. Use Harmonized API for Model Inference\n\n```bash\nORCHESTRATION_URL=\"\u003Cdeployment-url>\"\n\ncurl -X POST \"$ORCHESTRATION_URL\u002Fv2\u002Fcompletion\" \\\n  -H \"Authorization: Bearer $AUTH_TOKEN\" \\\n  -H \"AI-Resource-Group: default\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\n    \"config\": {\n      \"module_configurations\": {\n        \"llm_module_config\": {\n          \"model_name\": \"gpt-4o\",\n          \"model_version\": \"latest\",\n          \"model_params\": {\n            \"max_tokens\": 1000,\n            \"temperature\": 0.7\n          }\n        },\n        \"templating_module_config\": {\n          \"template\": [\n            {\"role\": \"system\", \"content\": \"You are a helpful assistant.\"},\n            {\"role\": \"user\", \"content\": \"{{?user_query}}\"}\n          ]\n        }\n      }\n    },\n    \"input_params\": {\n      \"user_query\": \"What is SAP AI Core?\"\n    }\n  }'\n```\n\n## Service Plans\n\n| Plan | Cost | GenAI Hub | Support | Resource Groups |\n|------|------|-----------|---------|-----------------|\n| **Free** | Free | No | Community only | Default only |\n| **Standard** | Per resource + baseline | No | Full SLA | Multiple |\n| **Extended** | Per resource + tokens | Yes | Full SLA | Multiple |\n\n**Key Restrictions:**\n- Free and Standard mutually exclusive in same subaccount\n- Free → Standard upgrade possible; downgrade not supported\n- Max 50 resource groups per tenant\n\n## Model Providers\n\nSAP AI Core provides access to models from six providers:\n- **Azure OpenAI**: GPT-4o, GPT-4 Turbo, GPT-3.5\n- **SAP Open Source**: Llama, Falcon, Mistral variants\n- **Google Vertex AI**: Gemini Pro, PaLM 2\n- **AWS Bedrock**: Claude, Amazon Titan\n- **Mistral AI**: Mistral Large, Medium, Small\n- **IBM**: Granite models\n\nFor detailed provider configurations and model lists, see `references\u002Fmodel-providers.md`.\n\n## Orchestration\n\nThe orchestration service provides unified access to multiple models through a modular pipeline with 8 execution stages:\n1. Grounding → 2. Templating (mandatory) → 3. Input Translation → 4. Data Masking → 5. Input Filtering → 6. Model Configuration (mandatory) → 7. Output Filtering → 8. Output Translation\n\nFor complete orchestration module configurations, examples, and advanced patterns, see `references\u002Forchestration-modules.md`.\n\n## Content Filtering\n\n**Azure Content Safety**: Filters content across 4 categories (Hate, Violence, Sexual, SelfHarm) with severity levels 0-6. Azure OpenAI blocks severity 4+ automatically. Additional features include PromptShield and Protected Material detection.\n\n**Llama Guard 3**: Covers 14 categories including violent crimes, privacy violations, and code interpreter abuse.\n\n## Data Masking\n\n**Two PII protection methods**:\n- **Anonymization**: `MASKED_ENTITY` (non-reversible)\n- **Pseudonymization**: `MASKED_ENTITY_ID` (reversible)\n\n**Supported entities** (25 total): Personal data, IDs, financial information, SAP-specific IDs, and sensitive attributes. For complete entity list and implementation details, see `references\u002Forchestration-modules.md`.\n\n## Grounding (RAG)\n\nIntegrate external data from SharePoint, S3, SFTP, SAP Build Work Zone, and DMS. Supports PDF, HTML, DOCX, images, and more. Limit: 2,000 documents per pipeline with daily refresh. For detailed setup, see `references\u002Fgrounding-rag.md`.\n\n## Tool Calling\n\nEnable LLMs to execute functions through a 5-step workflow: define tools → receive tool_calls → execute functions → return results → LLM incorporates responses. Templates available in `templates\u002Ftool-definition.json`.\n\n## Structured Output\n\nForce model responses to match JSON schemas using strict validation. Useful for structured data extraction and API responses.\n\n## Embeddings\n\nGenerate semantic embeddings for RAG and similarity search via `\u002Fv2\u002Fembeddings` endpoint. Supports document, query, and text input types.\n\n## ML Training\n\nUses Argo Workflows for training pipelines. Key requirements: create `default` object store secret, define workflow template, create configuration with parameters, and execute training. For complete workflow patterns, see `references\u002Fml-operations.md`.\n\n## Deployments\n\nDeploy models via two-step process: create configuration (with model binding), then create deployment with TTL. Statuses: Pending → Running → Stopping → Stopped\u002FDead. Templates in `templates\u002Fdeployment-config.json`.\n\n## SAP AI Launchpad\n\nWeb-based UI with 4 key applications:\n- **Workspaces**: Manage connections and resource groups\n- **ML Operations**: Train, deploy, monitor models\n- **Generative AI Hub**: Prompt experimentation and orchestration\n- **Functions Explorer**: Explore available AI functions\n\nRequired roles include `genai_manager`, `genai_experimenter`, `prompt_manager`, `orchestration_executor`, and `mloperations_editor`. For complete guide, see `references\u002Fai-launchpad-guide.md`.\n\n## API Reference\n\n### Core Endpoints\n\nKey endpoints: `\u002Fv2\u002Flm\u002Fscenarios`, `\u002Fv2\u002Flm\u002Fconfigurations`, `\u002Fv2\u002Flm\u002Fdeployments`, `\u002Fv2\u002Flm\u002Fexecutions`, `\u002Flm\u002Fmeta`. For complete API reference with examples, see `references\u002Fapi-reference.md`.\n\n## Common Patterns\n\n**Simple Chat**: Basic model invocation with templating module\n**RAG with Grounding**: Combine vector search with LLM for context-aware responses\n**Secure Enterprise Chat**: Filtering + masking + grounding for PII protection\nTemplates available in `templates\u002Forchestration-workflow.json`.\n        \"masking_providers\": [{\n  ## Troubleshooting\n\n**Common Issues**:\n- 401 Unauthorized: Refresh OAuth token\n- 403 Forbidden: Check IAM roles, request quota increase\n- 404 Not Found: Verify AI-Resource-Group header\n- Deployment DEAD: Check deployment logs\n- Training failed: Create `default` object store secret\n\nRequest quota increases via support ticket (Component: `CA-ML-AIC`).\n\n## Bundled Resources\n\n### Reference Documentation\n1. `references\u002Forchestration-modules.md` - All orchestration modules in detail\n2. `references\u002Fgenerative-ai-hub.md` - Complete GenAI hub documentation\n3. `references\u002Fmodel-providers.md` - Model providers and configurations\n4. `references\u002Fapi-reference.md` - Complete API endpoint reference\n5. `references\u002Fgrounding-rag.md` - Grounding and RAG implementation\n6. `references\u002Fml-operations.md` - ML operations and training\n7. `references\u002Fadvanced-features.md` - Chat, applications, security, auditing\n8. `references\u002Fai-launchpad-guide.md` - Complete SAP AI Launchpad UI guide\n\n### Templates\n1. `templates\u002Fdeployment-config.json` - Deployment configuration template\n2. `templates\u002Forchestration-workflow.json` - Orchestration workflow template\n3. `templates\u002Ftool-definition.json` - Tool calling definition template\n\n### Official Sources\n- SAP AI Core Guide: [https:\u002F\u002Fhelp.sap.com\u002Fdocs\u002Fsap-ai-core](https:\u002F\u002Fhelp.sap.com\u002Fdocs\u002Fsap-ai-core)\n- SAP AI Launchpad Guide: [https:\u002F\u002Fhelp.sap.com\u002Fdocs\u002Fsap-ai-launchpad](https:\u002F\u002Fhelp.sap.com\u002Fdocs\u002Fsap-ai-launchpad)\n- SAP Note 3437766: Model token rates and limits\n",{"name":5,"license":15,"metadata":49,"description":53},{"version":50,"last_verified":51,"production_tested":52},"1.1.1","2026-02-25","Yes, examples verified against SAP documentation","Guides development with SAP AI Core and SAP AI Launchpad for enterprise AI\u002FML workloads on SAP BTP. Use when: deploying generative AI models (GPT, Claude, Llama, Gemini, Mistral), building orchestration workflows with templating\u002Ffiltering\u002Fgrounding, 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, or integrating AI capabilities into SAP applications. Covers service plans (Free\u002FStandard\u002FExtended), model providers (Azure OpenAI, AWS Bedrock, GCP Vertex AI, Mistral, IBM), orchestration modules, embeddings, tool calling, and structured outputs.\n","main","5b00ad8b9f0787969474ff5e9ec417bb55f23827","skills\u002Fai-ml\u002Fsap-skills-main\u002Fsap-skills-main\u002Fplugins\u002Fsap-ai-core\u002Fskills\u002Fsap-ai-core",0,"https:\u002F\u002Fgithub.com\u002FVRIL-LABS\u002Fskill-jam","https:\u002F\u002Fvril.li","https:\u002F\u002Fgithub.com\u002FVRIL-LABS","vril.li","𝗥𝗲𝘀𝗲𝗮𝗿𝗰𝗵 𝗮𝗻𝗱 𝗗𝗲𝘃𝗲𝗹𝗼𝗽𝗺𝗲𝗻𝘁 𝗖𝗼𝗻𝘀𝗼𝗿𝘁𝗶𝘂𝗺","2026-08-24 09:21:38",{"source":8,"skillName":5,"commands":65,"prompt":75,"zipAvailable":76},[66,69,72],{"tool":67,"command":68},"npx","npx skills add VRIL-LABS\u002Fskill-jam --skill sap-ai-core",{"tool":70,"command":71},"bunx","bunx skills add VRIL-LABS\u002Fskill-jam --skill sap-ai-core",{"tool":73,"command":74},"pnpm","pnpm dlx skills add VRIL-LABS\u002Fskill-jam --skill sap-ai-core","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVRIL-LABS\u002Fskill-jam\u002Fblob\u002Fmain\u002Fskills\u002Fai-ml\u002Fsap-skills-main\u002Fsap-skills-main\u002Fplugins\u002Fsap-ai-core\u002Fskills\u002Fsap-ai-core\u002FSKILL.md",true,[78,84,88,92,96,100,104,108,112,116,120,124],{"path":79,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":82,"sourceHtmlUrl":83},"README.md","REFERENCE","参考文档",5994,"https:\u002F\u002Fgithub.com\u002FVRIL-LABS\u002Fskill-jam\u002Fblob\u002Fmain\u002Fskills\u002Fai-ml\u002Fsap-skills-main\u002Fsap-skills-main\u002Fplugins\u002Fsap-ai-core\u002Fskills\u002Fsap-ai-core\u002FREADME.md",{"path":85,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":86,"sourceHtmlUrl":87},"references\u002Fadvanced-features.md",19266,"https:\u002F\u002Fgithub.com\u002FVRIL-LABS\u002Fskill-jam\u002Fblob\u002Fmain\u002Fskills\u002Fai-ml\u002Fsap-skills-main\u002Fsap-skills-main\u002Fplugins\u002Fsap-ai-core\u002Fskills\u002Fsap-ai-core\u002Freferences\u002Fadvanced-features.md",{"path":89,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":90,"sourceHtmlUrl":91},"references\u002Fai-launchpad-guide.md",16020,"https:\u002F\u002Fgithub.com\u002FVRIL-LABS\u002Fskill-jam\u002Fblob\u002Fmain\u002Fskills\u002Fai-ml\u002Fsap-skills-main\u002Fsap-skills-main\u002Fplugins\u002Fsap-ai-core\u002Fskills\u002Fsap-ai-core\u002Freferences\u002Fai-launchpad-guide.md",{"path":93,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":94,"sourceHtmlUrl":95},"references\u002Fapi-reference.md",13220,"https:\u002F\u002Fgithub.com\u002FVRIL-LABS\u002Fskill-jam\u002Fblob\u002Fmain\u002Fskills\u002Fai-ml\u002Fsap-skills-main\u002Fsap-skills-main\u002Fplugins\u002Fsap-ai-core\u002Fskills\u002Fsap-ai-core\u002Freferences\u002Fapi-reference.md",{"path":97,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":98,"sourceHtmlUrl":99},"references\u002Fgenerative-ai-hub.md",11204,"https:\u002F\u002Fgithub.com\u002FVRIL-LABS\u002Fskill-jam\u002Fblob\u002Fmain\u002Fskills\u002Fai-ml\u002Fsap-skills-main\u002Fsap-skills-main\u002Fplugins\u002Fsap-ai-core\u002Fskills\u002Fsap-ai-core\u002Freferences\u002Fgenerative-ai-hub.md",{"path":101,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":102,"sourceHtmlUrl":103},"references\u002Fgrounding-rag.md",14371,"https:\u002F\u002Fgithub.com\u002FVRIL-LABS\u002Fskill-jam\u002Fblob\u002Fmain\u002Fskills\u002Fai-ml\u002Fsap-skills-main\u002Fsap-skills-main\u002Fplugins\u002Fsap-ai-core\u002Fskills\u002Fsap-ai-core\u002Freferences\u002Fgrounding-rag.md",{"path":105,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":106,"sourceHtmlUrl":107},"references\u002Fml-operations.md",13699,"https:\u002F\u002Fgithub.com\u002FVRIL-LABS\u002Fskill-jam\u002Fblob\u002Fmain\u002Fskills\u002Fai-ml\u002Fsap-skills-main\u002Fsap-skills-main\u002Fplugins\u002Fsap-ai-core\u002Fskills\u002Fsap-ai-core\u002Freferences\u002Fml-operations.md",{"path":109,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":110,"sourceHtmlUrl":111},"references\u002Fmodel-providers.md",10617,"https:\u002F\u002Fgithub.com\u002FVRIL-LABS\u002Fskill-jam\u002Fblob\u002Fmain\u002Fskills\u002Fai-ml\u002Fsap-skills-main\u002Fsap-skills-main\u002Fplugins\u002Fsap-ai-core\u002Fskills\u002Fsap-ai-core\u002Freferences\u002Fmodel-providers.md",{"path":113,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":114,"sourceHtmlUrl":115},"references\u002Forchestration-modules.md",14364,"https:\u002F\u002Fgithub.com\u002FVRIL-LABS\u002Fskill-jam\u002Fblob\u002Fmain\u002Fskills\u002Fai-ml\u002Fsap-skills-main\u002Fsap-skills-main\u002Fplugins\u002Fsap-ai-core\u002Fskills\u002Fsap-ai-core\u002Freferences\u002Forchestration-modules.md",{"path":117,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":118,"sourceHtmlUrl":119},"templates\u002Fdeployment-config.json",1578,"https:\u002F\u002Fgithub.com\u002FVRIL-LABS\u002Fskill-jam\u002Fblob\u002Fmain\u002Fskills\u002Fai-ml\u002Fsap-skills-main\u002Fsap-skills-main\u002Fplugins\u002Fsap-ai-core\u002Fskills\u002Fsap-ai-core\u002Ftemplates\u002Fdeployment-config.json",{"path":121,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":122,"sourceHtmlUrl":123},"templates\u002Forchestration-workflow.json",6272,"https:\u002F\u002Fgithub.com\u002FVRIL-LABS\u002Fskill-jam\u002Fblob\u002Fmain\u002Fskills\u002Fai-ml\u002Fsap-skills-main\u002Fsap-skills-main\u002Fplugins\u002Fsap-ai-core\u002Fskills\u002Fsap-ai-core\u002Ftemplates\u002Forchestration-workflow.json",{"path":125,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":126,"sourceHtmlUrl":127},"templates\u002Ftool-definition.json",8408,"https:\u002F\u002Fgithub.com\u002FVRIL-LABS\u002Fskill-jam\u002Fblob\u002Fmain\u002Fskills\u002Fai-ml\u002Fsap-skills-main\u002Fsap-skills-main\u002Fplugins\u002Fsap-ai-core\u002Fskills\u002Fsap-ai-core\u002Ftemplates\u002Ftool-definition.json",[129,158,172,188,223,246],{"skillNo":130,"name":131,"nameZh":6,"description":132,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":133,"licenseFileUrl":6,"sourceHtmlUrl":134,"categories":135,"keywords":137,"publishedAt":44},"01M6R2CQRG190P09DAHMF8M5QP","three-best-practices","Three.js performance optimization and best practices guidelines. Use when writing, reviewing, or optimizing Three.js code. Triggers on tasks involving 3D scenes, WebGL\u002FWebGPU rendering, geometries, materials, textures, lighting, shaders, or TSL.","MIT","https:\u002F\u002Fgithub.com\u002FVRIL-LABS\u002Fskill-jam\u002Fblob\u002Fmain\u002Fskills\u002Fweb-frontend\u002Fneversight-skills_feed-three-best-practices-1.0.2\u002FSKILL.md",[136],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153,154,155,156,157],"best practices","three","three best practices","writing","performance","webgpu","guidelines","tasks","code","shaders","Optimization","3D","use","agent-skills","scenes","lighting","triggers","rendering","when","best practices guidelines",{"skillNo":159,"name":160,"nameZh":6,"description":161,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":133,"licenseFileUrl":6,"sourceHtmlUrl":162,"categories":163,"keywords":164,"publishedAt":44},"01M6R2BPMDYK9XKWPARY0S5MS3","javascript-best-practices","Modern JavaScript best practices and performance optimization guidelines. Use when writing, reviewing, or refactoring JavaScript code to ensure optimal performance, maintainability, and modern patterns.","https:\u002F\u002Fgithub.com\u002FVRIL-LABS\u002Fskill-jam\u002Fblob\u002Fmain\u002Fskills\u002Fweb-frontend\u002Fneversight-skills_feed-javascript-best-practices-1.0.2\u002FSKILL.md",[],[165,138,166,141,142,144,146,148,167,168,150,169,170,171,156],"javascript","JavaScript Best Practices","refactoring","performance optimization","patterns","maintainability","name",{"skillNo":173,"name":174,"nameZh":6,"description":175,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":133,"licenseFileUrl":6,"sourceHtmlUrl":176,"categories":177,"keywords":181,"publishedAt":44},"01M6R2B41BN09FYH76BAC5FT7X","css-best-practices","Guidelines for building modern, performant, and accessible CSS using MDN best practices. Use this when styling components, fixing layout shifts, or optimizing CSS performance.","https:\u002F\u002Fgithub.com\u002FVRIL-LABS\u002Fskill-jam\u002Fblob\u002Fmain\u002Fskills\u002Fweb-frontend\u002Fneversight-skills_feed-css-best-practices-1.0.3\u002FSKILL.md",[178],{"categoryNo":179,"categoryName":180,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",[182,138,183,142,184,144,150,185,186,187,156],"css","css best practices","components","styling","layout","for",{"skillNo":189,"name":190,"nameZh":6,"description":191,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":133,"licenseFileUrl":6,"sourceHtmlUrl":192,"categories":193,"keywords":206,"publishedAt":44},"01M6R2A1CEF123TZCNM1XJ2XQ4","frontend-dev","Full-stack frontend development combining premium UI design, cinematic animations,\nAI-generated media assets, persuasive copywriting, and visual art. Builds complete,\nvisually striking web pages with real media, advanced motion, and compelling copy.\nUse when: building landing pages, marketing sites, product pages, dashboards,\ngenerating media assets (image\u002Fvideo\u002Faudio\u002Fmusic), writing conversion copy,\ncreating generative art, or implementing cinematic scroll animations.","https:\u002F\u002Fgithub.com\u002FVRIL-LABS\u002Fskill-jam\u002Fblob\u002Fmain\u002Fskills\u002Fweb-frontend\u002Fminimax-ai-skills-frontend-dev-1.0.1\u002FSKILL.md",[194,195,198,201],{"categoryNo":179,"categoryName":180,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":196,"categoryName":197,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":199,"categoryName":200,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体",{"categoryNo":202,"categoryName":203,"taxonomyType":204,"taxonomyTypeDesc":205},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",[207,208,209,210,141,211,182,212,213,214,215,216,217,218,219,220,221,29,222,28],"frontend","dev","frontend dev","design","image","react","ui","Video","Media","Audio","Tailwind","stack","music","aida","framer motion","framer",{"skillNo":224,"name":225,"nameZh":6,"description":226,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":133,"licenseFileUrl":6,"sourceHtmlUrl":227,"categories":228,"keywords":229,"publishedAt":44},"01M6R20VQ98KDX4J37TGE0FNHW","exa-rate-limits","Implement Exa rate limiting, backoff, and idempotency patterns.\nUse when handling rate limit errors, implementing retry logic,\nor optimizing API request throughput for Exa.\nTrigger with phrases like \"exa rate limit\", \"exa throttling\",\n\"exa 429\", \"exa retry\", \"exa backoff\".","https:\u002F\u002Fgithub.com\u002FVRIL-LABS\u002Fskill-jam\u002Fblob\u002Fmain\u002Fskills\u002Fsearch-research\u002Fjeremylongshore-claude-code-plugins-plus-skills-exa-rate-limits-1.0.0\u002FSKILL.md",[],[230,231,232,233,234,235,236,237,238,169,239,240,241,242,243,29,187,244,245,156],"exa","exa rate limits","rate","limits","throttling","api","read","write","edit","io","throughput","retry","errors","limit","rate limit","request",{"skillNo":247,"name":248,"nameZh":6,"description":249,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":133,"licenseFileUrl":6,"sourceHtmlUrl":250,"categories":251,"keywords":255,"publishedAt":44},"01M6R20FV0TM7ZZTZNG7JQ1A82","exa-deploy-integration","Deploy Exa integrations to Vercel, Fly.io, and Cloud Run platforms.\nUse when deploying Exa-powered applications to production,\nconfiguring platform-specific secrets, or setting up deployment pipelines.\nTrigger with phrases like \"deploy exa\", \"exa Vercel\",\n\"exa production deploy\", \"exa Cloud Run\", \"exa Fly.io\".","https:\u002F\u002Fgithub.com\u002FVRIL-LABS\u002Fskill-jam\u002Fblob\u002Fmain\u002Fskills\u002Fsearch-research\u002Fjeremylongshore-claude-code-plugins-plus-skills-exa-deploy-integration-1.0.0\u002FSKILL.md",[252],{"categoryNo":253,"categoryName":254,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000011","运维与部署",[256,257,230,258,259,260,261,262,263,264,236,237,238,265,266,267,239,268,269,156],"deploy","integration","exa deploy integration","deployment","run","secrets","fly","Bash","integrations","vercel","up","platform","trigger","cloud run"]