Skip to content

Add configprovider to openai text generation and model config#1043

Closed
JaJamyG wants to merge 11 commits intomicrosoft:mainfrom
JaJamyG:context-open-ai
Closed

Add configprovider to openai text generation and model config#1043
JaJamyG wants to merge 11 commits intomicrosoft:mainfrom
JaJamyG:context-open-ai

Conversation

@JaJamyG
Copy link

@JaJamyG JaJamyG commented Mar 25, 2025

Motivation and Context (Why the change? What's the scenario?)

I want to be able to change models from openai text generation in runtime.

High level description (Approach, Design)

The ability to change gpt models in runtime, to ask question to open ai

@JaJamyG JaJamyG requested a review from dluc as a code owner March 25, 2025 18:25
@JaJamyG
Copy link
Author

JaJamyG commented Mar 25, 2025

@JaJamyG please read the following Contributor License Agreement(CLA). If you agree with the CLA, please reply with the following information.

@microsoft-github-policy-service agree [company="{your company}"]

Options:

  • (default - no company specified) I have sole ownership of intellectual property rights to my Submissions and I am not making Submissions in the course of work for my employer.
@microsoft-github-policy-service agree
  • (when company given) I am making Submissions in the course of work for my employer (or my employer has intellectual property rights in my Submissions by contract or applicable law). I have permission from my employer to make Submissions and enter into this Agreement on behalf of my employer. By signing below, the defined term “You” includes me and my employer.
@microsoft-github-policy-service agree company="Microsoft"

Contributor License Agreement

@microsoft-github-policy-service agree

@JaJamyG
Copy link
Author

JaJamyG commented Mar 26, 2025

fixes #1042

dluc
dluc reviewed May 8, 2025
View reviewed changes
dluc
dluc reviewed May 8, 2025
View reviewed changes
Copy link
Collaborator

@dluc dluc left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Did you try overriding the model?

I tested the PR, and requests are always sent to the model defined in the configuration, not the one in the context.

I suspect that the client used internally (Semantic Kernel) doesn't support passing the model ID in the request.

@dluc dluc added the waiting for author Waiting for author to reply or address comments label May 9, 2025
@JaJamyG
Copy link
Author

JaJamyG commented Aug 14, 2025

Sorry for the long delay. The PR slipped my mind, but I’ve tested it now.
I initialized it with GPT-4. When I asked a question, I used GPT-4-mini as the argument, and when SK returned the answer, it gave me the GPT-4-mini version.

I want to create a small project where I can test it in more detail.

@dluc
Copy link
Collaborator

dluc commented Nov 3, 2025

Closing as part of repository maintenance - no further action planned on this issue.

@dluc dluc closed this Nov 3, 2025
@microsoft microsoft locked and limited conversation to collaborators Nov 3, 2025
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.

Reviewers

@dluc dluc dluc left review comments

Assignees

No one assigned

Labels

waiting for author Waiting for author to reply or address comments

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

2 participants

@JaJamyG @dluc