Add model selection to OpenAI setup for enhanced customization

[ribeirogab]

This pull request introduces a new feature to the OpenAI setup process, allowing users to select their preferred language model during configuration. Key changes include:

• Added support for OPENAI_CHAT_MODEL in environment variables to store the selected model.
• Implemented a user prompt to choose from predefined models such as gpt-4, gpt-3.5-turbo, and others.
• Updated OpenAIProvider to dynamically utilize the selected model in API requests, with a default fallback to gpt-4o-mini.
• Improved type safety by integrating ChatModel typing from OpenAI's resources.
• Enhanced tests to validate the new model selection functionality.
• Updated the package version to 0.3.0 to reflect the new feature.

This update provides users with greater flexibility and control over the language model, improving customization to better meet diverse requirements.