FEAT: Adding AzureChatCompletionsTarget #687
Open
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
romanlutz
reviewed
Feb 4, 2025
romanlutz
approved these changes
Feb 12, 2025
| # %% [markdown] | ||
| # # Azure Chat Completions Target | ||
| # | ||
| # This will allow you to easily interact with models in [Azure AI Foundry](https://ai.azure.com/), such as DeepSeek R1, Phi-4, Mistral, and LLAMA. |
There was a problem hiding this comment.
Can we explain why and how this is different from Azure ML Chat Target and Azure Open AI? I honestly don't fully know either.
Comment on lines
-254
to
+255
| session.add_all(entries) | ||
| for entry in entries: | ||
| session.merge(entry) |
There was a problem hiding this comment.
Behavior is the same, right? How does it help?
| @@ -130,7 +130,7 @@ def to_dict(self): | |||
| } | |||
|
|
|||
| def __str__(self): | |||
| if self.scorer_class_identifier: | |||
| if self.scorer_class_identifier and self.scorer_class_identifier.get("__type__"): | |||
There was a problem hiding this comment.
Suggested change
| if self.scorer_class_identifier and self.scorer_class_identifier.get("__type__"): | |
| if self.scorer_class_identifier and "__type__" in self.scorer_class_identifier: |
nit
| logger = logging.getLogger(__name__) | ||
|
|
||
|
|
||
| class AzureChatCompletionsTarget(PromptChatTarget): |
There was a problem hiding this comment.
This class needs a docstring. I would love to have the difference between this, AOAI, and AML explained as well. Maybe that should be explained on all of these three 😆
| finish_reason = azure_completion.choices[0].finish_reason | ||
|
|
||
| # finish_reason should be stop if things were a success | ||
| if finish_reason != "stop": |
There was a problem hiding this comment.
isn't there a finish reason like token limit? So it's kind of a partial success?
|
|
||
| if scores: | ||
| # need to insert the prompt first since it has a primary key constraint | ||
| # this will be re-inserted by prompt_normalizer, but that's okay |
There was a problem hiding this comment.
as in, there won't be duplicates, right?
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
This target supports Azure Foundry deployed models, including Phi-4, DeepSeek-R1, Ministral, Llama 3.1, and more.
Memory updates