feat: GPT4Generator

[ZanSara]

Related Issues

• fixes OpenAI LLM Generators for Haystack 2.0 #5623

Proposed Changes:

• Adds GPT4Generator, a small subclass of GPT35Generator that sets a different default model.
• Adds its unit tests
• Expand GPT35Generator's e2e tests to also test the subclass

How did you test it?

Local tests run

Notes for the reviewer

Checklist

• I have read the contributors guidelines and the code of conduct
• I have updated the related issue with new insights and changes
• I added unit tests and updated the docstrings
• I've used one of the conventional commit types for my PR title: fix:, feat:, build:, chore:, ci:, docs:, style:, refactor:, perf:, test:.
• I documented my code
• I ran pre-commit hooks and fixed any issue

[anakin87]

In general, it looks good to me.

I am only a bit worried about the e2e test error:
openai.error.RateLimitError: Rate limit reached for default-gpt-4 ... on tokens per min. Limit: 40000 / min.

[ZanSara]

@anakin87 I tried to lower the amount of tokens sent, but I can't tell if that will help or if OpenAI is just unreliable today. On my local machine it fails once every 3-4 executions, on CI seems to fail a lot more often. And the error message makes no sense because the rate is always much lower than the threshold 😅

[coveralls]

Pull Request Test Coverage Report for Build 6162263615

• 0 of 0 changed or added relevant lines in 0 files are covered.
• 2 unchanged lines in 1 file lost coverage.
• Overall coverage increased (+0.02%) to 48.942%

---

Files with Coverage Reduction	New Missed Lines	%
preview/components/generators/openai/gpt35.py	2	96.15%

Totals
Change from base Build 6162162895:	0.02%
Covered Lines:	11847
Relevant Lines:	24206

---

💛 - Coveralls

[anakin87]

LGTM!