mirror of https://github.com/microsoft/semantic-kernel.git synced 2026-10-12 11:19:56 +00:00

Files

T

Evan Mattson 46f5ea15a2 Python: Introduce Pydantic settings (#6193 )

### Motivation and Context

SK Python is tightly coupled to the use of a `.env` file to read all
secrets, keys, endpoints, and more. This doesn't scale well for users
who wish to be able to use environment variables with their SK
Applications. By introducing Pydantic Settings, it is possible to use
both environment variables as well as have a fall-back to a `.env` file
(via a `env_file_path` parameter), if desired.

By introducing Pydantic Settings, we are removing the requirement to
have to create Text/Embedding/Chat completion objects with an `api_key`
or other previously required information (in the case of
AzureChatCompletion that means an `endpoint`, an `api_key`, a
`deployment_name`, and an `api_version`). When the AI connector is
created, the Pydantic settings are loaded either via env vars or the
fall-back `.env` file, and that means the user can create a chat
completion object like:

```python
chat_completion = OpenAIChatCompletion(service_id="test")
```

or, to optionally override the `ai_model_id` env var:

```python
chat_completion = OpenAIChatCompletion(service_id="test", ai_model_id="gpt-4-1106")
```
Note: we have left the ability to specific an `api_key`/`org_id` for
`OpenAIChatCompletion` or a `deployment_name`, `endpoint`, `base_url`,
and `api_version` for `AzureChatCompletion` as before, but if your
settings are configured to use env vars/.env file then there is no need
to pass this information.

<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
  1. Why is this change required?
  2. What problem does it solve?
  3. What scenario does it contribute to?
  4. If it fixes an open issue, please link to the issue here.
-->

### Description

The PR introduces the use of Pydantic settings and removes the use of
the python-dotenv library.
- Closes #1779 
- Updates notebooks, samples, code and tests to remove the explicit
config of api_key or other previous .env files values.
- Adds new unit test config using monkeypatch to simulate env variables
for testing
- All unit and integration tests passing

<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->

### Contribution Checklist

<!-- Before submitting this PR, please make sure: -->

- [X] The code builds clean without any errors or warnings
- [X] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [X] All unit tests pass, and I have added new tests where possible
- [ ] I didn't break anyone 😄

2024-05-16 11:44:40 +00:00

5.1 KiB

Raw Blame History

Basic Loading of the Kernel

To run the notebooks we recommend using Poetry and starting a shell with a virtual environment prepared to use SK.

See DEV_SETUP.md for more information.

In [ ]:

!python -m pip install semantic-kernel==0.9.8b1

In [ ]:

from semantic_kernel import Kernel, kernel

kernel = Kernel()

Configuring API Keys and Endpoints

Option 1: using OpenAI

Add your OpenAI Key key to either your environment variables or to the .env file in the same folder (org Id only if you have multiple orgs):

OPENAI_API_KEY="sk-..."
OPENAI_ORG_ID=""

The environment variables names should match the names used in the .env file, as shown above.

If using the .env file, please configure the env_file_path parameter with a valid path when creating the ChatCompletion class:

chat_completion = OpenAIChatCompletion(service_id="test", env_file_path=<path_to_file>)

Use "keyword arguments" to instantiate an OpenAI Chat Completion service and add it to the kernel:

Option 2: using Azure OpenAI

Add your Azure Open AI Service key settings to either your system's environment variables or to the .env file in the same folder:

AZURE_OPENAI_API_KEY="..."
AZURE_OPENAI_ENDPOINT="https://..."
AZURE_OPENAI_CHAT_DEPLOYMENT_NAME="..."
AZURE_OPENAI_TEXT_DEPLOYMENT_NAME="..."
AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAME="..."

The environment variables names should match the names used in the .env file, as shown above.

If using the .env file, please configure the env_file_path parameter with a valid path when creating the ChatCompletion class:

chat_completion = AzureChatCompletion(service_id="test", env_file_path=<path_to_file>)

When using the kernel for AI requests, the kernel needs some settings like URL and credentials to the AI models.

The SDK currently supports OpenAI and Azure OpenAI, among other connectors.

If you need an Azure OpenAI key, go here.

In [ ]:

from services import Service

# Select a service to use for this notebook (available services: OpenAI, AzureOpenAI, HuggingFace)
selectedService = Service.OpenAI

In [ ]:

service_id = None
if selectedService == Service.OpenAI:
    from semantic_kernel.connectors.ai.open_ai import OpenAIChatCompletion

    service_id = "oai_chat_gpt"
    kernel.add_service(
        OpenAIChatCompletion(service_id=service_id, ai_model_id="gpt-3.5-turbo-1106"),
    )
elif selectedService == Service.AzureOpenAI:
    from semantic_kernel.connectors.ai.open_ai import AzureChatCompletion

    service_id = "aoai_chat_completion"
    kernel.add_service(
        AzureChatCompletion(service_id=service_id),
    )

Great, now that you're familiar with setting up the Semantic Kernel, let's see how we can use it to run prompts.

5.1 KiB Raw Blame History

Basic Loading of the Kernel

Configuring API Keys and Endpoints

Option 1: using OpenAI

Option 2: using Azure OpenAI

5.1 KiB

Raw Blame History