Sap Cloud Sdk Ai Python

secondsky/sap-skills/plugins/sap-cloud-sdk-ai-python/skills/sap-cloud-sdk-ai-python

作者 secondsky652a861d3ed422b71f01c8805f9ec03b14017cd8GPL-3.0收錄於 2026年10月9日更新於 2026年10月9日

Integrates the SAP Cloud SDK for AI for Python (sap-ai-sdk-gen, formerly generative-ai-hub-sdk) into Python applications. Use when building Python apps with SAP AI Core, Generative AI Hub, or the Orchestration Service: chat completion, embeddings, streaming, LangChain integration, templating, content filtering, data masking, and document grounding. Supports OpenAI GPT models, Llama, Gemini, Amazon Nova, and other foundation models via SAP BTP.

僅含說明Software Development AI & Agents

AI 產生的概覽

指導 Python 開發者使用 SAP Cloud SDK for AI（sap-ai-sdk-gen）串接 SAP AI Core、生成式 AI Hub 與協同作業服務。

功能: 此技能提供參考說明，協助使用 sap-ai-sdk-gen 套件（匯入名稱為 gen_ai_hub）建置串接 SAP AI Core 與生成式 AI Hub 的 Python 應用程式。內容涵蓋安裝、憑證解析、各供應商原生用戶端、LangChain 整合，以及協同作業服務的範本化、內容過濾、資料遮罩與文件接地模組。同時說明支援的模型系列、常見錯誤，以及從已棄用的 generative-ai-hub-sdk 移轉的方法。此技能未附帶指令碼，產出為使用指引與程式碼範例。
適用情境: 適用於撰寫透過 SAP AI Core 或生成式 AI Hub 呼叫大型語言模型、嵌入或協同作業服務的 Python 程式碼。也適用於以 SAP AI Core 為後端的 LangChain 鏈，以及從已棄用的 generative-ai-hub-sdk 套件移轉程式碼。
執行需求: 需要 sap-ai-sdk-gen Python 套件（匯入名稱 gen_ai_hub），可選安裝各供應商擴充與 LangChain 支援。需要 SAP AI Core 憑證，可透過關鍵字參數、AICORE_* 環境變數、設定檔設定檔或 VCAP_SERVICES 提供，並需具備連線至 SAP BTP 端點的網路。未附帶指令碼。

SAP Cloud SDK for AI (Python)

Package rename: The PyPI package generative-ai-hub-sdk is deprecated (v4.12.4 is the last release). Its successor is sap-ai-sdk-gen (currently v6.10.0 per public PyPI registry evidence from 2026-06-15). Code and tutorials referencing generative-ai-hub-sdk should migrate to sap-ai-sdk-gen; the import name remains gen_ai_hub.

The official Python SDK for SAP Generative AI Hub and Orchestration Service. It wraps the native SDKs of model providers (OpenAI, Amazon Bedrock, Google GenAI) and offers a harmonised LangChain integration and a full Orchestration client — all routed through SAP AI Core with unified authentication. Package freshness is registry-verified; AI Core runtime behavior and exact model availability still require target-tenant validation.

Related Skills

sap-ai-core: Platform setup, deployments, resource groups, and model management in SAP AI Core
sap-cloud-sdk-ai: JavaScript/TypeScript and Java equivalents of this SDK
sap-hana-ml: HANA-side machine learning in Python
sap-dependency-security: Pip dependency hygiene and upgrade patterns

Related external skills

If your task involves working inside Databricks (notebooks, Unity Catalog, Spark, SAP Databricks in SAP Business Data Cloud), consider installing the Databricks agent skills plugin. Ask whether you would like help installing it — never install unprompted.

When to Use This Skill

Use this skill when:

Building Python applications that call LLMs through SAP AI Core / Generative AI Hub
Using the gen_ai_hub Python package (installed as sap-ai-sdk-gen)
Integrating OpenAI, Amazon Bedrock, or Google GenAI models via SAP's proxy
Implementing LangChain chains with SAP AI Core as the backend
Using the Orchestration Service from Python (templating, filtering, masking, grounding)
Migrating code from the deprecated generative-ai-hub-sdk to sap-ai-sdk-gen
Generating embeddings through SAP AI Core
Working with SAP RPT-1 (Relational Pretrained Transformer) for tabular predictions

Quick Start
Installation
Authentication
Available Modules
Supported Models
Core Features
Bundled Resources

Quick Start

Native OpenAI Chat Completion

python

from gen_ai_hub.proxy.native.openai import chat
messages = [    {"role": "system", "content": "You are a helpful assistant."},    {"role": "user", "content": "What is SAP BTP?"}]
response = chat.completions.create(    model_name="gpt-4o-mini",    messages=messages)print(response.choices[0].message.content)

from gen_ai_hub.proxy.native.openai import chat
messages = [    {"role": "system", "content": "You are a helpful assistant."},    {"role": "user", "content": "What is SAP BTP?"}]
response = chat.completions.create(    model_name="gpt-4o-mini",    messages=messages)print(response.choices[0].message.content)

Orchestration Service

python

from gen_ai_hub.orchestration_v2 import (    OrchestrationConfig, OrchestrationService,    ModuleConfig, PromptTemplatingModuleConfig,    Template, UserMessage, LLMModelDetails)
config = OrchestrationConfig(    modules=ModuleConfig(        prompt_templating=PromptTemplatingModuleConfig(            prompt=Template(                template=[UserMessage(role="user", content="{{?question}}")]            ),            model=LLMModelDetails(name="gpt-4o-mini")        )    ))
service = OrchestrationService(config=config)response = service.run(placeholder_values={"question": "What is SAP?"})print(response.final_result.choices[0].message.content)

from gen_ai_hub.orchestration_v2 import (    OrchestrationConfig, OrchestrationService,    ModuleConfig, PromptTemplatingModuleConfig,    Template, UserMessage, LLMModelDetails)
config = OrchestrationConfig(    modules=ModuleConfig(        prompt_templating=PromptTemplatingModuleConfig(            prompt=Template(                template=[UserMessage(role="user", content="{{?question}}")]            ),            model=LLMModelDetails(name="gpt-4o-mini")        )    ))
service = OrchestrationService(config=config)response = service.run(placeholder_values={"question": "What is SAP?"})print(response.final_result.choices[0].message.content)

Installation

bash

# All providers + LangChain supportpip install "sap-ai-sdk-gen[all]"
# Default (OpenAI only, no LangChain)pip install sap-ai-sdk-gen
# Specific providers (without LangChain)pip install "sap-ai-sdk-gen[google, amazon]"

# All providers + LangChain supportpip install "sap-ai-sdk-gen[all]"
# Default (OpenAI only, no LangChain)pip install sap-ai-sdk-gen
# Specific providers (without LangChain)pip install "sap-ai-sdk-gen[google, amazon]"

Authentication

The SDK reads credentials via AICoreV2Client.from_env(), which resolves credentials in this order:

Keyword arguments passed to GenAIHubProxyClient(...)
Environment variables — AICORE_CLIENT_ID, AICORE_CLIENT_SECRET, AICORE_AUTH_URL, AICORE_BASE_URL, AICORE_RESOURCE_GROUP
Config file — $AICORE_HOME/config.json (or path set by AICORE_CONFIG); use AICORE_PROFILE to select a named profile
VCAP_SERVICES — automatic on Cloud Foundry/Kyma when the AI Core service is bound

Local Development (Environment Variables)

bash

export AICORE_CLIENT_ID="sb-..."export AICORE_CLIENT_SECRET="..."export AICORE_AUTH_URL="https://<tenant>.authentication.sap.hana.ondemand.com/oauth/token"export AICORE_BASE_URL="https://api.ai.prod.eu-central-1.aws.ml.hana.ondemand.com/v2"export AICORE_RESOURCE_GROUP="default"

export AICORE_CLIENT_ID="sb-..."export AICORE_CLIENT_SECRET="..."export AICORE_AUTH_URL="https://<tenant>.authentication.sap.hana.ondemand.com/oauth/token"export AICORE_BASE_URL="https://api.ai.prod.eu-central-1.aws.ml.hana.ondemand.com/v2"export AICORE_RESOURCE_GROUP="default"

Config File Profile

bash

# ~/.aicore/config.json{  "AICORE_CLIENT_ID": "sb-...",  "AICORE_CLIENT_SECRET": "...",  "AICORE_AUTH_URL": "https://<tenant>.authentication.sap.hana.ondemand.com/oauth/token",  "AICORE_BASE_URL": "https://api.ai.prod.eu-central-1.aws.ml.hana.ondemand.com/v2",  "AICORE_RESOURCE_GROUP": "default"}

# ~/.aicore/config.json{  "AICORE_CLIENT_ID": "sb-...",  "AICORE_CLIENT_SECRET": "...",  "AICORE_AUTH_URL": "https://<tenant>.authentication.sap.hana.ondemand.com/oauth/token",  "AICORE_BASE_URL": "https://api.ai.prod.eu-central-1.aws.ml.hana.ondemand.com/v2",  "AICORE_RESOURCE_GROUP": "default"}

For detailed auth setup and troubleshooting, see references/getting-started-auth.md.

Available Modules

Module	Import Path	Purpose
Proxy (native clients)	`gen_ai_hub.proxy.native.*`	Direct model access per provider
LangChain integration	`gen_ai_hub.proxy.langchain`	`init_llm`, `init_embedding_model`, `ChatOpenAI`, etc.
Orchestration	`gen_ai_hub.orchestration_v2`	Templating, filtering, masking, grounding
Document Grounding	`gen_ai_hub.document_grounding`	Pipeline, Vector, Retrieval APIs
Prompt Registry	`gen_ai_hub.prompt_registry`	Template management and config storage
Evaluations	`gen_ai_hub.evaluations`	Model evaluation runs and metrics
SAP RPT-1	`gen_ai_hub.proxy.native.sap`	Tabular prediction (classification, regression)

Native Clients by Provider

Provider	Import	Key Classes
OpenAI	`gen_ai_hub.proxy.native.openai`	`OpenAI`, `completions`, `chat`, `embeddings`, `responses`
Amazon Bedrock	`gen_ai_hub.proxy.native.amazon`	`Session`, `ClientWrapper`
Google GenAI	`gen_ai_hub.proxy.native.google_genai`	`Client`
SAP RPT-1	`gen_ai_hub.proxy.native.sap`	`RPTClient`, `RPTRequest`

Supported Models

The Generative AI Hub catalog includes models from multiple providers. Check SAP's model catalog and the target tenant catalog for the authoritative model IDs. Example families:

Provider	Example Families
OpenAI	GPT-family chat, multimodal, reasoning, and embedding models
Anthropic (via Bedrock)	Claude-family models
Amazon	Nova/Titan-family models
Google	Gemini-family models
Mistral	Mistral-family models
SAP	RPT-family tabular prediction models where enabled

Core Features

Chat Completion with OpenAI Client

python

from gen_ai_hub.proxy.native.openai import OpenAI
client = OpenAI()response = client.chat.completions.create(    model="gpt-4o-mini",    messages=[{"role": "user", "content": "Explain CAP in one paragraph."}])print(response.choices[0].message.content)

from gen_ai_hub.proxy.native.openai import OpenAI
client = OpenAI()response = client.chat.completions.create(    model="gpt-4o-mini",    messages=[{"role": "user", "content": "Explain CAP in one paragraph."}])print(response.choices[0].message.content)

Streaming

python

from gen_ai_hub.proxy.native.openai import OpenAI
client = OpenAI()stream = client.chat.completions.create(    model="gpt-4o-mini",    messages=[{"role": "user", "content": "Explain SAP CAP."}],    stream=True)for chunk in stream:    if chunk.choices[0].delta.content:        print(chunk.choices[0].delta.content, end="")

from gen_ai_hub.proxy.native.openai import OpenAI
client = OpenAI()stream = client.chat.completions.create(    model="gpt-4o-mini",    messages=[{"role": "user", "content": "Explain SAP CAP."}],    stream=True)for chunk in stream:    if chunk.choices[0].delta.content:        print(chunk.choices[0].delta.content, end="")

Embeddings

python

from gen_ai_hub.proxy.native.openai import embeddings
response = embeddings.create(    input="Every decoding is another encoding.",    model_name="text-embedding-3-small")print(response.data[0].embedding)

from gen_ai_hub.proxy.native.openai import embeddings
response = embeddings.create(    input="Every decoding is another encoding.",    model_name="text-embedding-3-small")print(response.data[0].embedding)

LangChain Integration

python

from gen_ai_hub.proxy.langchain import init_llm, init_embedding_model
llm = init_llm("gpt-4o-mini", max_tokens=300)result = llm.invoke("What is SAP BTP?")print(result.content)
embeddings = init_embedding_model("text-embedding-3-small")vector = embeddings.embed_query("SAP Business Technology Platform")

from gen_ai_hub.proxy.langchain import init_llm, init_embedding_model
llm = init_llm("gpt-4o-mini", max_tokens=300)result = llm.invoke("What is SAP BTP?")print(result.content)
embeddings = init_embedding_model("text-embedding-3-small")vector = embeddings.embed_query("SAP Business Technology Platform")

Content Filtering (via Orchestration)

python

from gen_ai_hub.orchestration_v2 import (    OrchestrationConfig, OrchestrationService,    ModuleConfig, PromptTemplatingModuleConfig,    Template, UserMessage, LLMModelDetails,    FilteringModuleConfig, InputFiltering, OutputFiltering,    AzureContentSafetyInput, AzureContentSafetyOutput, AzureThreshold)
config = OrchestrationConfig(    modules=ModuleConfig(        prompt_templating=PromptTemplatingModuleConfig(            prompt=Template(template=[UserMessage(role="user", content="{{?question}}")]),            model=LLMModelDetails(name="gpt-4o-mini")        ),        filtering=FilteringModuleConfig(            input=InputFiltering(filters=[                AzureContentSafetyInput(hate=AzureThreshold.ALLOW_SAFE, violence=AzureThreshold.ALLOW_SAFE)            ]),            output=OutputFiltering(filters=[                AzureContentSafetyOutput(hate=AzureThreshold.ALLOW_SAFE, violence=AzureThreshold.ALLOW_SAFE)            ])        )    ))
service = OrchestrationService(config=config)response = service.run(placeholder_values={"question": "Explain SAP."})

from gen_ai_hub.orchestration_v2 import (    OrchestrationConfig, OrchestrationService,    ModuleConfig, PromptTemplatingModuleConfig,    Template, UserMessage, LLMModelDetails,    FilteringModuleConfig, InputFiltering, OutputFiltering,    AzureContentSafetyInput, AzureContentSafetyOutput, AzureThreshold)
config = OrchestrationConfig(    modules=ModuleConfig(        prompt_templating=PromptTemplatingModuleConfig(            prompt=Template(template=[UserMessage(role="user", content="{{?question}}")]),            model=LLMModelDetails(name="gpt-4o-mini")        ),        filtering=FilteringModuleConfig(            input=InputFiltering(filters=[                AzureContentSafetyInput(hate=AzureThreshold.ALLOW_SAFE, violence=AzureThreshold.ALLOW_SAFE)            ]),            output=OutputFiltering(filters=[                AzureContentSafetyOutput(hate=AzureThreshold.ALLOW_SAFE, violence=AzureThreshold.ALLOW_SAFE)            ])        )    ))
service = OrchestrationService(config=config)response = service.run(placeholder_values={"question": "Explain SAP."})

Data Masking (via Orchestration)

python

from gen_ai_hub.orchestration_v2 import (    OrchestrationConfig, OrchestrationService,    ModuleConfig, PromptTemplatingModuleConfig,    Template, UserMessage, LLMModelDetails,    MaskingModuleConfig, MaskingProviderConfig,    DPIStandardEntity, MaskingMethod, DataMaskingProviderName)
config = OrchestrationConfig(    modules=ModuleConfig(        prompt_templating=PromptTemplatingModuleConfig(            prompt=Template(template=[UserMessage(role="user", content="{{?text}}")]),            model=LLMModelDetails(name="gpt-4o-mini")        ),        masking=MaskingModuleConfig(            masking_providers=[                MaskingProviderConfig(                    type=DataMaskingProviderName.SAP_DATA_PRIVACY_INTEGRATION,                    method=MaskingMethod.ANONYMIZATION,                    entities=[                        DPIStandardEntity(type="profile-email"),                        DPIStandardEntity(type="profile-person")                    ]                )            ]        )    ))
service = OrchestrationService(config=config)response = service.run(placeholder_values={"text": "Contact [email protected] for details."})

from gen_ai_hub.orchestration_v2 import (    OrchestrationConfig, OrchestrationService,    ModuleConfig, PromptTemplatingModuleConfig,    Template, UserMessage, LLMModelDetails,    MaskingModuleConfig, MaskingProviderConfig,    DPIStandardEntity, MaskingMethod, DataMaskingProviderName)
config = OrchestrationConfig(    modules=ModuleConfig(        prompt_templating=PromptTemplatingModuleConfig(            prompt=Template(template=[UserMessage(role="user", content="{{?text}}")]),            model=LLMModelDetails(name="gpt-4o-mini")        ),        masking=MaskingModuleConfig(            masking_providers=[                MaskingProviderConfig(                    type=DataMaskingProviderName.SAP_DATA_PRIVACY_INTEGRATION,                    method=MaskingMethod.ANONYMIZATION,                    entities=[                        DPIStandardEntity(type="profile-email"),                        DPIStandardEntity(type="profile-person")                    ]                )            ]        )    ))
service = OrchestrationService(config=config)response = service.run(placeholder_values={"text": "Contact [email protected] for details."})

Document Grounding (via Orchestration)

python

from gen_ai_hub.orchestration_v2 import (    OrchestrationConfig, OrchestrationService,    ModuleConfig, PromptTemplatingModuleConfig,    Template, UserMessage, LLMModelDetails,    GroundingModuleConfig, DocumentGroundingConfig,    DocumentGroundingFilter, DocumentGroundingPlaceholders,    GroundingSearchConfig, DataRepositoryType, GroundingType)
config = OrchestrationConfig(    modules=ModuleConfig(        prompt_templating=PromptTemplatingModuleConfig(            prompt=Template(template=[UserMessage(role="user", content="{{?question}}")]),            model=LLMModelDetails(name="gpt-4o-mini")        ),        grounding=GroundingModuleConfig(            type=GroundingType.DOCUMENT_GROUNDING_SERVICE,            config=DocumentGroundingConfig(                placeholders=DocumentGroundingPlaceholders(                    input=["{{?question}}"],                    output="{{?context}}"                ),                filters=[                    DocumentGroundingFilter(                        id="my-vector-repo-id",                        data_repository_type=DataRepositoryType.VECTOR,                        search_config=GroundingSearchConfig(max_chunk_count=5)                    )                ]            )        )    ))
service = OrchestrationService(config=config)response = service.run(placeholder_values={"question": "What is the refund policy?"})

from gen_ai_hub.orchestration_v2 import (    OrchestrationConfig, OrchestrationService,    ModuleConfig, PromptTemplatingModuleConfig,    Template, UserMessage, LLMModelDetails,    GroundingModuleConfig, DocumentGroundingConfig,    DocumentGroundingFilter, DocumentGroundingPlaceholders,    GroundingSearchConfig, DataRepositoryType, GroundingType)
config = OrchestrationConfig(    modules=ModuleConfig(        prompt_templating=PromptTemplatingModuleConfig(            prompt=Template(template=[UserMessage(role="user", content="{{?question}}")]),            model=LLMModelDetails(name="gpt-4o-mini")        ),        grounding=GroundingModuleConfig(            type=GroundingType.DOCUMENT_GROUNDING_SERVICE,            config=DocumentGroundingConfig(                placeholders=DocumentGroundingPlaceholders(                    input=["{{?question}}"],                    output="{{?context}}"                ),                filters=[                    DocumentGroundingFilter(                        id="my-vector-repo-id",                        data_repository_type=DataRepositoryType.VECTOR,                        search_config=GroundingSearchConfig(max_chunk_count=5)                    )                ]            )        )    ))
service = OrchestrationService(config=config)response = service.run(placeholder_values={"question": "What is the refund policy?"})

Common Errors

Error	Cause	Solution
`No credentials found in any source`	Missing AI Core service key/env vars	Set all `AICORE_*` environment variables or create a config file profile
`No deployment found`	Model not deployed in AI Core	Deploy the model in your resource group, or use `deployment_id` directly
`AICORE_RESOURCE_GROUP not set`	Missing resource group	Set `AICORE_RESOURCE_GROUP` env var or pass `resource_group` to the client
`ModuleNotFoundError: No module named 'gen_ai_hub'`	Wrong package installed	Install `sap-ai-sdk-gen` (not `generative-ai-hub-sdk`)
Import from `generative_ai_hub_sdk` fails	Using deprecated package name	The package was renamed; import from `gen_ai_hub` (installed via `sap-ai-sdk-gen`)
`ValidationError` on proxy client init	Incomplete credentials	Verify all four required env vars: `AICORE_CLIENT_ID`, `AICORE_CLIENT_SECRET`, `AICORE_AUTH_URL`, `AICORE_BASE_URL`

Bundled Resources

Reference Documentation

references/getting-started-auth.md - Installation, authentication, and config setup
references/native-clients-guide.md - Native client usage for OpenAI, Amazon, Google, and SAP RPT-1
references/orchestration-guide.md - Orchestration service: templating, filtering, masking, grounding, embeddings
references/langchain-guide.md - LangChain integration: LLM/embedding init, chains, structured outputs
references/troubleshooting.md - Common errors, version compatibility, migration from generative-ai-hub-sdk

Documentation Sources

Keep this skill updated using these sources:

PyPI: https://pypi.org/pypi/sap-ai-sdk-gen/json — package metadata and README
SDK Reference: https://help.sap.com/doc/generative-ai-hub-sdk/CLOUD/en-US/_reference/gen_ai_hub.html
SAP Samples: https://github.com/SAP-samples/btp-gen-ai-hub-sdk-samples
AI Core Help: https://help.sap.com/docs/sap-ai-core
Deprecated Package: https://pypi.org/pypi/generative-ai-hub-sdk/json (for migration notes)

來源與署名

來源：secondsky/sap-skills位於plugins/sap-cloud-sdk-ai-python/skills/sap-cloud-sdk-ai-python提交652a861

授權條款： GPL-3.0

內容歸原作者所有。SourceWeft 從公開儲存庫中收錄這些內容。

檢舉或申請下架

Sap Cloud Sdk Ai Python

SAP Cloud SDK for AI (Python)

Related Skills

Related external skills

When to Use This Skill

Table of Contents

Quick Start

Native OpenAI Chat Completion

Orchestration Service

Installation

Authentication

Local Development (Environment Variables)

Config File Profile

Available Modules

Native Clients by Provider

Supported Models

Core Features

Chat Completion with OpenAI Client

Streaming

Embeddings

LangChain Integration

Content Filtering (via Orchestration)

Data Masking (via Orchestration)

Document Grounding (via Orchestration)

Common Errors

Bundled Resources

Reference Documentation

Documentation Sources

來源與署名

更多來自 secondsky/sap-skills 的技能

Sap Sac Scripting

Sap Sac Planning

Sap Sqlscript

Sap Hana Ml

Sap Btp Master Data Integration

Sap Fiori Tools

更多Software Development技能

Playground

M5 Onboard

Cardputer Buddy

Web Design Guidelines

Vercel React Native Skills

Vercel React Best Practices