Fix Azure OpenAI setup problems

[jayden5744]

Background

• See this issue: Azure OpenAI setup fails with error AttributeError: 'ConfigSettings' object has no attribute 'get_azure_deployment_id_for_model' #4838

Changes

• Setting azure config values to openai
• Recover the missing 'get_azure_deployment_id_for_model' function from that commit(Use Configuration of rearch #4803)

Documentation

x

Test Plan

CI

PR Quality Checklist

• My pull request is atomic and focuses on a single change.
• I have thoroughly tested my changes with multiple different prompts.
• I have considered potential risks and mitigations for my changes.
• I have documented my changes clearly and comprehensively.
• I have not snuck in any "extra" small tweaks changes.
• I have run the following commands against my code to ensure it passes our linters:

  black .
  isort .
  mypy
  autoflake --remove-all-unused-imports --recursive --ignore-init-module-imports --ignore-pass-after-docstring autogpt tests --in-place

[netlify]

✅ Deploy Preview for auto-gpt-docs canceled.

Name	Link
🔨 Latest commit	21a5ba7
🔍 Latest deploy log	https://app.netlify.com/sites/auto-gpt-docs/deploys/64a75fd2e91b5f00085e5ebf

[codecov]

Codecov Report

Patch coverage: 64.70% and project coverage change: +0.16 🎉

Comparison is base (e4a337f) 50.05% compared to head (21a5ba7) 50.21%.

Additional details and impacted files

@@            Coverage Diff             @@
##           master    #4875      +/-   ##
==========================================
+ Coverage   50.05%   50.21%   +0.16%     
==========================================
  Files         116      116              
  Lines        4799     4809      +10     
  Branches      643      645       +2     
==========================================
+ Hits         2402     2415      +13     
+ Misses       2218     2215       -3     
  Partials      179      179              

Impacted Files	Coverage Δ
autogpt/llm/utils/__init__.py	49.25% <0.00%> (-1.48%)	⬇️
autogpt/memory/vector/utils.py	78.12% <0.00%> (-5.21%)	⬇️
autogpt/config/config.py	83.89% <91.66%> (+4.75%)	⬆️

☔ View full report in Codecov by Sentry.
📢 Do you have feedback about the report comment? Let us know in this issue.

[lc0rp]

@jayden5744, thanks for the PR. Please write some tests!

[github-actions]

This pull request has conflicts with the base branch, please resolve those so we can evaluate the pull request.

[github-actions]

Conflicts have been resolved! 🎉 A maintainer will review the pull request shortly.

[collijk]

@jayden5744 Overall great work. I've added some changes to reduce code duplication and avoid setting global parameters.

[jayden5744]

@collijk
My existing code excludes the code below,

# autogpt/config/config.py
if config_dict["use_azure"]: # line 294 
      azure_config = cls.load_azure_config(config_dict["azure_config_file"])
      config_dict.update(azure_config)
     
     # Add the three lines of code below
      openai.api_type = azure_config["openai_api_type"]
      openai.api_base = azure_config["openai_api_base"]
      openai.api_version = azure_config["openai_api_version"]

which causes the error openai.error.AuthenticationError: Incorrect API key provided to occur when calling the openai api without changing to the azure settings.
I need to fix this again.

[collijk]

@jayden5744

We specifically don't want to do

     # Add the three lines of code below
      openai.api_type = azure_config["openai_api_type"]
      openai.api_base = azure_config["openai_api_base"]
      openai.api_version = azure_config["openai_api_version"]

as this reaches into module namespace and has global impacts. These should be passed as arguments to the API call (as they are now). I'm setting up some testing on azure tomorrow (we unfortunately don't have access as part of our CI) and will try to reproduce your issue.