Semantic Kernel

1.39.4 verified Tue May 12 auth: no python install: reviewed quickstart: stale

Microsoft's open-source SDK for integrating LLMs into applications. Model-agnostic (OpenAI, Azure OpenAI, Google, Hugging Face, Mistral, etc.), supports Python, C#, and Java. Provides plugins (tools), prompt templating, multi-agent orchestration (AgentChat framework), and vector store integrations for RAG. Production-stable as of v1.x. Currently the primary Microsoft-maintained AI framework (AutoGen is maintenance-only; Microsoft Agent Framework is the future successor).

pip install --upgrade semantic-kernel

Common errors

error AttributeError: 'Kernel' object has no attribute 'run_async' ↓

cause The `run_async` method used in semantic-kernel v0.x was deprecated and replaced by `invoke` (or `invoke_prompt`, `invoke_plugin_async`) in v1.x.

fix

Replace calls like await kernel.run_async(plugin[function]) with await kernel.invoke(plugin[function]) or await kernel.invoke_prompt(...).

error ModuleNotFoundError: No module named 'semantic_kernel.orchestration' ↓

cause The module structure for semantic-kernel underwent significant changes in v1.x, leading to various modules and classes (like `orchestration` and `Planner`) being refactored or moved.

fix

Update imports to reflect the v1.x structure; for example, FunctionCallingStepwisePlanner is now found in

from semantic_kernel.planners.function_calling_stepwise_planner.function_calling_stepwise_planner import FunctionCallingStepwisePlanner

error AttributeError: 'Kernel' object has no attribute 'add_chat_service' ↓

cause In semantic-kernel v1.x, AI service registration moved from direct methods on the `Kernel` instance to methods on the `KernelBuilder` or `kernel.add_service()` for a pre-initialized kernel.

fix

Initialize the kernel using a builder pattern for service registration:

kernel = sk.KernelBuilder().add_openai_chat_service(service_id="chat_gpt", model_id="gpt-4", api_key=os.getenv("OPENAI_API_KEY")).build()

error openai.AuthenticationError: No API key provided. ↓

cause The OpenAI API key is either missing, incorrect, or not accessible via environment variables or direct configuration when initializing the OpenAI service within semantic-kernel.

fix

Ensure the OPENAI_API_KEY environment variable is set, or explicitly pass the API key during service configuration: kernel.add_service(OpenAIChatService(service_id="my_chat", model_id="gpt-4", api_key="YOUR_API_KEY")).

Warnings

breaking Azure Identity fallback authentication removed. In older versions, AzureChatCompletion would silently fall back to azure-identity DefaultAzureCredential if no api_key was provided. This implicit fallback has been removed. Code relying on it will now raise errors on import or at runtime. ↓

fix Install azure-identity explicitly (pip install azure-identity or pip install semantic-kernel[azure]) and pass credentials explicitly: AzureChatCompletion(ad_token_provider=...) or AzureChatCompletion(api_key=...)

breaking SemanticTextMemory and MemoryStoreBase are deprecated and will be removed. The entire old memory store architecture (semantic_kernel.memory, semantic_kernel.connectors.memory_stores) has been superseded by the new VectorStore API. ↓

fix Migrate to semantic_kernel.data.vector: use @vectorstoremodel, VectorStoreField, and connector-specific VectorStore classes (e.g., from semantic_kernel.connectors.memory import ChromaCollection). See: https://learn.microsoft.com/en-us/semantic-kernel/support/migration/vectorstore-python-june-2025

breaking Google connector migrated from google-generativeai SDK to the new google-genai SDK (v1.39.0, Feb 2026). If using the Google connector, the underlying dependency has changed. ↓

fix Upgrade to 1.39.0+. Uninstall google-generativeai if no longer needed. Install semantic-kernel[google] which now pulls in google-genai.

breaking Template argument encoding now throws on complex types. Previously, complex types (custom classes, anonymous types, collections) passed as prompt template arguments were silently not encoded. Now an exception is raised if automatic encoding is enabled (the default) and a complex type is passed. ↓

fix Serialize complex types to strings before passing as template arguments, or disable automatic encoding.

breaking sk_function decorator removed. The old @sk_function decorator from pre-1.0 is gone. All plugin methods must use @kernel_function. ↓

fix Replace @sk_function with @kernel_function from semantic_kernel.functions.

breaking SKContext removed. Replaced by KernelArguments. Any code importing or using SKContext will fail. ↓

fix Replace SKContext with KernelArguments from semantic_kernel.functions.

gotcha azure-identity is NOT included in the base pip install semantic-kernel. Importing AzureChatCompletion (which requires Entra ID support) will fail with ImportError if azure-identity is not installed separately. ↓

fix pip install semantic-kernel[azure] or pip install azure-identity

gotcha Microsoft Agent Framework (successor to both AutoGen and Semantic Kernel) has reached Release Candidate status (Feb 2026). Semantic Kernel remains actively maintained but Microsoft is directing new agentic projects toward Agent Framework. ↓

fix For new agentic projects, evaluate Microsoft Agent Framework. Existing SK code is stable and supported. Migration guide: https://aka.ms/autogen-to-af

gotcha Pydantic v1 is not supported. semantic-kernel requires Pydantic v2. If your project pins Pydantic v1 (e.g., via an older FastAPI or LangChain version), there will be a dependency conflict. ↓

fix Upgrade to Pydantic v2. Check for other dependencies pinning Pydantic v1.

breaking OpenAIChatCompletion requires an API key. Attempting to initialize OpenAIChatCompletion without an explicitly provided API key (or environment variable) will result in a ServiceInitializationError. ↓

fix Provide the OpenAI API key explicitly to OpenAIChatCompletion (e.g., api_key='...') or ensure the OPENAI_API_KEY environment variable is set.

Install

pip install --upgrade semantic-kernel[azure]

pip install --upgrade semantic-kernel[google]

pip install --upgrade semantic-kernel[all]

Install compatibility reviewed last tested: 2026-05-12

python os / libc status wheel install import disk

3.10 alpine (musl) - - 5.62s 457.8M

3.10 alpine (musl) - - 5.51s 457.8M

3.10 alpine (musl) - - 5.49s 468.2M

3.10 alpine (musl) - - 5.53s 648.4M

3.10 slim (glibc) - - 4.28s 454M

3.10 slim (glibc) - - 4.34s 454M

3.10 slim (glibc) - - 4.29s 465M

3.10 slim (glibc) - - 4.25s 639M

3.11 alpine (musl) - - 6.43s 486.9M

3.11 alpine (musl) - - 6.42s 486.9M

3.11 alpine (musl) - - 6.45s 498.9M

3.11 alpine (musl) - - 6.60s 702.3M

3.11 slim (glibc) - - 5.57s 482M

3.11 slim (glibc) - - 6.61s 482M

3.11 slim (glibc) - - 5.75s 494M

3.11 slim (glibc) - - 5.64s 692M

3.12 alpine (musl) - - 6.41s 469.7M

3.12 alpine (musl) - - 6.42s 469.7M

3.12 alpine (musl) - - 6.44s 481.4M

3.12 alpine (musl) - - 6.50s 681.8M

3.12 slim (glibc) - - 6.86s 465M

3.12 slim (glibc) - - 6.83s 465M

3.12 slim (glibc) - - 6.75s 477M

3.12 slim (glibc) - - 6.50s 672M

3.13 alpine (musl) - - 5.83s 467.7M

3.13 alpine (musl) - - 5.97s 467.7M

3.13 alpine (musl) - - 5.95s 479.2M

3.13 alpine (musl) - - 5.91s 677.4M

3.13 slim (glibc) - - 6.16s 463M

3.13 slim (glibc) - - 6.17s 463M

3.13 slim (glibc) - - 6.08s 474M

3.13 slim (glibc) - - 6.29s 667M

3.9 alpine (musl) - - - -

3.9 slim (glibc) - - - -

Imports

Kernel

wrong

from semantic_kernel.kernel import Kernel

correct

from semantic_kernel import Kernel

Import directly from the package root.

AzureChatCompletion

wrong

from semantic_kernel.connectors.ai.azure import AzureChatCompletion

correct

from semantic_kernel.connectors.ai.open_ai import AzureChatCompletion

Azure OpenAI connector lives under the openai module, not a separate azure module.

kernel_function decorator
wrong
```
from semantic_kernel import sk_function
```
correct
```
from semantic_kernel.functions import kernel_function
```
sk_function was the old decorator name (pre-1.0). Removed. Use @kernel_function.
SemanticTextMemory (DEPRECATED)
wrong
```
from semantic_kernel.memory import SemanticTextMemory
```
correct
```
from semantic_kernel.data.vector import VectorStoreField, vectorstoremodel
```
SemanticTextMemory and MemoryStoreBase are deprecated. Migrate to VectorStore/VectorStoreCollection.

KernelArguments

wrong

from semantic_kernel.orchestration import SKContext

correct

from semantic_kernel.functions import KernelArguments

SKContext was removed in 1.0. Use KernelArguments.

Quickstart stale last tested: 2026-05-12

Basic chat completion with OpenAI

import asyncio
from semantic_kernel import Kernel
from semantic_kernel.connectors.ai.open_ai import OpenAIChatCompletion
from semantic_kernel.connectors.ai.open_ai import OpenAIChatPromptExecutionSettings
from semantic_kernel.contents import ChatHistory

async def main():
    kernel = Kernel()
    kernel.add_service(OpenAIChatCompletion(ai_model_id="gpt-4o"))

    history = ChatHistory(system_message="You are a helpful assistant.")
    history.add_user_message("Hello, what can you do?")

    service = kernel.get_service(type=OpenAIChatCompletion)
    settings = OpenAIChatPromptExecutionSettings()
    response = await service.get_chat_message_content(chat_history=history, settings=settings, kernel=kernel)
    print(response.content)

asyncio.run(main())