semantic-kernel

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

Files

T

History

Evan Mattson 1a84cb64b2 Python: prompt template config and kernel args support for agents (#10298 )

### Motivation and Context

To bring the SK Python framework closer to .Net parity, we need to
support the ability to specify a prompt template config and kernel
arguments for ChatCompletion Agents as well as for Assistant Agents.

<!-- 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

This PR adds support for:
- being able to specify a prompt template config for SK agents.
- allows kernel arguments to be passed to the agent as well as during
invoke - invoke args, similar to other kwargs, take precedence over
agent level config.
- adds test coverage
- creates agent templating samples for both ChatCompletionAgents and
OpenAI/AzureAssistantAgents
- closes #8022 
- closes #8699

<!-- 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
- [X] I didn't break anyone 😄

2025-01-28 04:41:16 +00:00

concepts

Python: prompt template config and kernel args support for agents (#10298 )

2025-01-28 04:41:16 +00:00

demos

Python: OpenAPI plugin updates to promote plugin to preview (#9670 )

2024-11-21 15:27:32 +00:00

getting_started

Python: fix mypy pre-commit setup, mypy fixes (#9498 )

2024-11-07 11:33:41 +00:00

getting_started_with_agents

Python: prompt template config and kernel args support for agents (#10298 )

2025-01-28 04:41:16 +00:00

getting_started_with_processes

Python: remove mistaken on_activate func (#9839 )

2024-11-29 10:14:39 +00:00

learn_resources

Python: prompt template config and kernel args support for agents (#10298 )

2025-01-28 04:41:16 +00:00

__init__.py

Python: Adjust the learn file imports based on a previous refactor. (#6545 )

2024-06-04 19:40:12 +00:00

README.md

Python: Add a samples README and a demos README. (#8543 )

2024-09-05 16:45:46 +00:00

service_settings.py

Python: fix mypy pre-commit setup, mypy fixes (#9498 )

2024-11-07 11:33:41 +00:00

sk_service_configurator.py

Python: updates to cicd and notebooks (#6485 )

2024-06-03 13:58:02 +00:00

README.md

Semantic Kernel Samples

Type	Description
`getting_started`	Take this step by step tutorial to get started with Semantic Kernel and get introduced to the key concepts.
`getting_started_with_agents`	Take this step by step tutorial to get started with Semantic Kernel Agents and get introduced to the key concepts.
`concepts`	This section contains focused samples which illustrate all of the concepts included in Semantic Kernel.
`demos`	Look here to find a sample which demonstrate how to use many of Semantic Kernel features.
`learn_resources`	Code snippets that are related to online documentation sources like Microsoft Learn, DevBlogs and others