add support for gpt-4-turbo model

[riya-amemiya]

User description

Updated to support the new models added to OpenAI.

---

Type

enhancement

---

Description

• Added support for two new models: gpt-4-turbo-2024-04-09 and gpt-4-turbo, both with a token limit of 128K. This enhances the application's compatibility with the latest models from OpenAI.

---

Changes walkthrough

	Relevant files
Enhancement	__init__.py Add Support for GPT-4 Turbo Models                                              pr_agent/algo/init.py Added support for gpt-4-turbo-2024-04-09 model with a token limit of 128K. Added support for gpt-4-turbo model with a token limit of 128K. +2/-0

---

✨ PR-Agent usage:
Comment /help on the PR to get a list of all available PR-Agent tools and their descriptions

[codiumai-pr-agent-pro]

PR-Agent was enabled for this repository. To continue using it, please link your git user with your CodiumAI identity here.

PR Description updated to latest commit (108b1af)

• Copy walkthrough table to "Files Changed" Tab

[codiumai-pr-agent-pro]

PR-Agent was enabled for this repository. To continue using it, please link your git user with your CodiumAI identity here.

PR Review

⏱️ Estimated effort to review [1-5]	1, because the changes are straightforward and involve adding two new model configurations to an existing dictionary of models. The modifications are clear and limited to a single file, making the review process quick and easy.
🏅 Score	95
🧪 Relevant tests	No
🔍 Possible issues	No
🔒 Security concerns	No
🔀 Multiple PR themes	No

---

✨ Review tool usage guide:

---

Overview:
The review tool scans the PR code changes, and generates a PR review which includes several types of feedbacks, such as possible PR issues, security threats and relevant test in the PR. More feedbacks can be added by configuring the tool.

The tool can be triggered automatically every time a new PR is opened, or can be invoked manually by commenting on any PR.

• When commenting, to edit configurations related to the review tool (pr_reviewer section), use the following template:

/review --pr_reviewer.some_config1=... --pr_reviewer.some_config2=...

• With a configuration file, use the following template:

[pr_reviewer]
some_config1=...
some_config2=...

See the review usage page for a comprehensive guide on using this tool.

[codiumai-pr-agent-pro]

PR-Agent was enabled for this repository. To continue using it, please link your git user with your CodiumAI identity here.

PR Code Suggestions

Category

Suggestions

Maintainability

Use a constant for the token limit value to improve maintainability. Consider using a constant for the token limit value (128000) to avoid repetition and to make future updates easier. This will improve maintainability, especially if the token limit needs to be updated across multiple model configurations. pr_agent/algo/init.py [13-15] -'gpt-4-turbo-preview': 128000, # 128K, but may be limited by config.max_model_tokens -'gpt-4-turbo-2024-04-09': 128000, # 128K, but may be limited by config.max_model_tokens -'gpt-4-turbo': 128000, # 128K, but may be limited by config.max_model_tokens +MAX_TOKENS = 128000 # 128K, but may be limited by config.max_model_tokens +'gpt-4-turbo-preview': MAX_TOKENS, +'gpt-4-turbo-2024-04-09': MAX_TOKENS, +'gpt-4-turbo': MAX_TOKENS,

---

✨ Improve tool usage guide:

---

Overview:
The improve tool scans the PR code changes, and automatically generates suggestions for improving the PR code. The tool can be triggered automatically every time a new PR is opened, or can be invoked manually by commenting on a PR.

• When commenting, to edit configurations related to the improve tool (pr_code_suggestions section), use the following template:

/improve --pr_code_suggestions.some_config1=... --pr_code_suggestions.some_config2=...

• With a configuration file, use the following template:

[pr_code_suggestions]
some_config1=...
some_config2=...

See the improve usage page for a comprehensive guide on using this tool.

[mrT23]

@riya-amemiya looks good.

If the new model (gpt-4-turbo-2024-04-09) will show superior results over the prev one, maybe in time we will consider making it the new default model.

We might consider also possible usage for the vision mode