.Net: Make AzureOpenAI service/model deployment configurable #10786
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Motivation, Context, and Description
This PR reads Azure OpenAI related configuration: deployment, model, and version from a config file instead of using hardcoded values. Additionally, it adds a configuration property that points to an AI chat service for the agent to use. At the moment, only the Azure OpenAI service is supported, but other services like OpenAI will be added in one of the next PRs.
It also copies some values from the host configuration to environment variables so that the Agent API service can access them. This allows us to keep the host/deployment configuration in one place - the host rather than having the same config in two projects: the host and the API service. The host uses it for deployment and provisioning of Azure resources, while the service uses it to access the provisioned resources.
Next steps include:
Note: This PR targets the
feature-agents-hosting
feature branch.Contributes to: #10149