This change allows users to configure which model to use as the default
for all evaluations, replacing the hardcoded gpt-4o default.

Changes:
- Add `defaultModel` parameter to `init()` in both JS and Python
- Add `getDefaultModel()` function to retrieve configured default model
- Update LLMClassifier and RAGAS scorers to use configurable default model
- Update documentation with examples for different use cases

This enables:
- Using different OpenAI models (gpt-4-turbo, o1, gpt-3.5-turbo, etc.)
- Using non-OpenAI models via Braintrust proxy (Claude, Gemini, Llama, etc.)
- Configuring once and having all evaluators use the preferred model

Example usage:
```javascript
init({
  client: new OpenAI({
    apiKey: process.env.BRAINTRUST_API_KEY,
    baseURL: "https://api.braintrust.dev/v1/proxy",
  }),
  defaultModel: "claude-3-5-sonnet-20241022",
});
```

Fixes #136

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>