mirror of https://github.com/microsoft/semantic-kernel.git synced 2026-10-12 02:19:06 +00:00

Files

T

0a477b198c Python: Update examples and notebooks to stop using text-davinci-003 (#2359 )

### Motivation and Context

text-davinci-003 is being retired by Azure OpenAI and is no longer
supported for new deployments

Resolves - https://github.com/microsoft/semantic-kernel/issues/2309

<!-- 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

Update examples and notebooks to use gpt-35-turbo / gpt-3.5-turbo
instead

<!-- 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: -->

- [ ] The code builds clean without any errors or warnings
- [ ] 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
- [ ] All unit tests pass, and I have added new tests where possible
- [ ] I didn't break anyone 😄

Signed-off-by: karthikmurali60 <[email protected]>
Co-authored-by: Lee Miller <[email protected]>
Co-authored-by: Gil LaHaye <[email protected]>

2023-08-23 17:24:56 +00:00

3.3 KiB

Raw Permalink Blame History

Setup

Step 1: Import Semantic Kernel SDK from pypi.org

In [ ]:

!python -m pip install semantic-kernel==0.3.1.dev0

In [ ]:

import semantic_kernel as sk

kernel = sk.Kernel()

Option 1: using OpenAI

Step 2: Add your Open AI Key key to a .env file in the same folder (org Id only if you have multiple orgs):

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

and add OpenAI Chat Completion to the kernel:

In [ ]:

from semantic_kernel.connectors.ai.open_ai import OpenAIChatCompletion

api_key, org_id = sk.openai_settings_from_dot_env()

kernel.add_chat_service("chat-gpt", OpenAIChatCompletion("gpt-3.5-turbo", api_key, org_id))

Option 2: using Azure OpenAI

Step 2: Add your Azure Open AI Service key settings to a .env file in the same folder:

AZURE_OPENAI_API_KEY="..."
AZURE_OPENAI_ENDPOINT="https://..."
AZURE_OPENAI_DEPLOYMENT_NAME="..."

and add Azure OpenAI Chat Completion to the kernel:

In [ ]:

from semantic_kernel.connectors.ai.open_ai import AzureChatCompletion

deployment, api_key, endpoint = sk.azure_openai_settings_from_dot_env()

kernel.add_chat_service("chat_completion", AzureChatCompletion("gpt-35-turbo", endpoint, api_key))

Run a Semantic Function

Step 3: Load a Skill and run a semantic function:

In [ ]:

skill = kernel.import_semantic_skill_from_directory("../../samples/skills", "FunSkill")
joke_function = skill["Joke"]

print(joke_function("time travel to dinosaur age"))

3.3 KiB Raw Permalink Blame History

Setup

Option 1: using OpenAI

Option 2: using Azure OpenAI

Run a Semantic Function

3.3 KiB

Raw Permalink Blame History