Add GPT-4o Mini model to OpenAI provider

[radleta]

trafficstars

User description

Background

The addition of the GPT-4o Mini model to the OpenAI provider will enhance the application's capabilities by providing a model with a higher token limit and support for the function call API. This is necessary for users requiring extensive token usage and advanced API functionalities.

Link to the issue: Add gpt-4o-mini #7479

Changes 🏗️

This pull request includes:

• Adding the GPT-4o Mini model to the OpenAI provider in the openai.py file.
  • Prompt token cost: 0.15/1,000,000
  • Completion token cost: 0.6/1,000,000
  • Maximum token limit: 128,000
  • Support for function call API

PR Quality Scorecard ✨

• [x] Have you used the PR description template?   +2 pts
• [x] Is your pull request atomic, focusing on a single change?   +5 pts
• [x] Have you linked the GitHub issue(s) that this PR addresses?   +5 pts
• [x] Have you documented your changes clearly and comprehensively?   +5 pts
• [ ] Have you changed or added a feature?   -4 pts
  • [ ] Have you added/updated corresponding documentation?   +4 pts
  • [ ] Have you added/updated corresponding integration tests?   +5 pts
• [ ] Have you changed the behavior of AutoGPT?   -5 pts
  • [ ] Have you also run agbenchmark to verify that these changes do not regress performance?   +10 pts

---

PR Type

Enhancement

---

Description

• Added the GPT-4o Mini model to the OpenAI provider in the openai.py file.
• Defined new model names GPT4_O_MINI_v1, GPT4_O_MINI_ROLLING, and GPT4_O_MINI.
• Set prompt token cost to 0.15/1,000,000 and completion token cost to 0.6/1,000,000 for GPT-4o Mini.
• Established a maximum token limit of 128,000 for GPT-4o Mini.
• Enabled support for the function call API for the GPT-4o Mini model.

---

Changes walkthrough 📝

	Relevant files
Enhancement	openai.py Add GPT-4o Mini model to OpenAI provider                                  forge/forge/llm/providers/openai.py Added new GPT-4o Mini model to the OpenAI provider. Defined new model names and mapping for GPT-4o Mini. Set token costs and maximum token limit for GPT-4o Mini. Enabled function call API support for GPT-4o Mini. +12/-0

---

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

[netlify[bot]]

✅ Deploy Preview for auto-gpt-docs ready!

Name	Link
🔨 Latest commit	28d3d16fc4e482124e6ccdc54fd97e85ebd19cc6
🔍 Latest deploy log	https://app.netlify.com/sites/auto-gpt-docs/deploys/66c5be3af97e20000781fe1d
😎 Deploy Preview	https://deploy-preview-7694--auto-gpt-docs.netlify.app
📱 Preview on mobile	Toggle QR Code... Use your smartphone camera to open QR code link.

---

To edit notification comments on pull requests, go to your Netlify site configuration.

[codecov[bot]]

Codecov Report

All modified and coverable lines are covered by tests :white_check_mark:

Project coverage is 57.88%. Comparing base (0767b17) to head (28d3d16). Report is 222 commits behind head on master.

Additional details and impacted files

@@            Coverage Diff             @@
##           master    #7694      +/-   ##
==========================================
+ Coverage   49.63%   57.88%   +8.25%     
==========================================
  Files         146      106      -40     
  Lines        8926     5768    -3158     
  Branches     1242      720     -522     
==========================================
- Hits         4430     3339    -1091     
+ Misses       4348     2316    -2032     
+ Partials      148      113      -35     

Flag	Coverage Δ
Linux	57.88% <100.00%> (+8.44%)	:arrow_up:
Windows	?
agbenchmark	?
autogpt-agent	?
forge	57.88% <100.00%> (-0.16%)	:arrow_down:
macOS	?

Flags with carried forward coverage won't be shown. Click here to find out more.

:umbrella: View full report in Codecov by Sentry.
:loudspeaker: Have feedback on the report? Share it here.

[qodo-merge-pro[bot]]

PR Description updated to latest commit (https://github.com/Significant-Gravitas/AutoGPT/commit/eaa95ea123822a020220baa593a52aa1a50fb8fd)

• [ ] Copy walkthrough table to "Files Changed" Tab

[qodo-merge-pro[bot]]

PR Reviewer Guide 🔍

⏱️ Estimated effort to review: 2 🔵🔵⚪⚪⚪

🧪 No relevant tests

🔒 No security concerns identified

⚡ Key issues to review Consistency Check Ensure that the token costs and API capabilities for GPT4_O_MINI align with OpenAI's official specifications to maintain consistency across model implementations.

[qodo-merge-pro[bot]]

PR Code Suggestions ✨

Category	Suggestion	Score
Maintainability	Standardize the naming convention for model identifiers Consider using a consistent naming convention for the model identifiers. The new model identifier GPT4_O_MINI_v1 uses both uppercase and lowercase with an underscore and a hyphen, which is inconsistent with other model identifiers that use only uppercase and underscores. forge/forge/llm/providers/openai.py [79] -GPT4_O_MINI_v1 = "gpt-4o-mini-2024-07-18" +GPT4_O_MINI_V1 = "gpt-4o-mini-2024-07-18" [ ] Apply this suggestion Suggestion importance[1-10]: 8 Why: The suggestion improves code consistency and readability by standardizing the naming convention, which is important for maintainability.	8

[radleta]

PR Code Suggestions ✨

Category Suggestion                                                                                                                                    Score Maintainability Standardize the naming convention for model identifiers Consider using a consistent naming convention for the model identifiers. The new model identifier GPT4_O_MINI_v1 uses both uppercase and lowercase with an underscore and a hyphen, which is inconsistent with other model identifiers that use only uppercase and underscores.

forge/forge/llm/providers/openai.py [79]

-GPT4_O_MINI_v1 = "gpt-4o-mini-2024-07-18"
+GPT4_O_MINI_V1 = "gpt-4o-mini-2024-07-18"
 

• [ ] Apply this suggestion

Suggestion importance[1-10]: 8 8

This suggestion isn't consistent with the casing of the other model names. They use lower case "v1" not "V1" as recommended.

[ntindle]

PR Code Suggestions ✨

Category Suggestion                                                                                                                                    Score Maintainability Standardize the naming convention for model identifiers Consider using a consistent naming convention for the model identifiers. The new model identifier GPT4_O_MINI_v1 uses both uppercase and lowercase with an underscore and a hyphen, which is inconsistent with other model identifiers that use only uppercase and underscores. forge/forge/llm/providers/openai.py [79]

-GPT4_O_MINI_v1 = "gpt-4o-mini-2024-07-18"
+GPT4_O_MINI_V1 = "gpt-4o-mini-2024-07-18"
 

• [ ] Apply this suggestion

Suggestion importance[1-10]: 8 8

This suggestion isn't consistent with the casing of the other model names. They use lower case "v1" not "V1" as recommended.

No worries, not all of them are always applicable

[ntindle]

@Pwuts do you know anything about this chromedriver error?

[Pwuts]

@ntindle looks like dark magic to me

[vishesh10]

Hey @ntindle @Pwuts, I have created the PR to address this chromedriver issue along with the support for GPT-4o mini model. https://github.com/Significant-Gravitas/AutoGPT/pull/8007

Thanks

[ntindle]

superseeded by #8007