Add Azure Llama client support

[clavedeluna]

Overview

Codemodder can run codemods with Azure LLama models

Description

• This is a breaking change because I thought it best to change context.llm_client > context.openai_llm_client for clarity
• now there can be both clients enabled.
• it's not necessary to add the model to the ModelRegistry, since the model used is encoded in whatever endpoint is used in CODEMODDER_AZURE_LLAMA_ENDPOINT
  I tested this out with

        from azure.ai.inference.models import SystemMessage, UserMessage

        response = self.azure_llama_llm_client.complete(
            messages=[
                SystemMessage(content="You are a helpful assistant."),
                UserMessage(content="How many feet are in a mile?"),
            ]
        )

and got the expected response

(Pdb) print(response.choices[0].message.content)
There are 5,280 feet in a mile.

Close #871

[drdavella]

LGTM but I'm not sure what's up with the failing tests.

[drdavella]

This is my fault because I did this originally but != is definitely a lot clearer here 😅

[clavedeluna]

yeah I kinda agree but I also got very used to reading this and it's nice :)

[drdavella]

This is a breaking change because I thought it best to change context.llm_client > context.openai_llm_client for clarity

I agree. I don't think there's any need for deprecation periods at this point, we should just remember to bump major versions.

[sonarqubecloud]

Quality Gate passed

Issues
1 New issue
0 Accepted issues

Measures
0 Security Hotspots
0.0% Coverage on New Code
0.0% Duplication on New Code

See analysis details on SonarCloud