Skip to content

refactor: migrate from Qwen/Ollama to OpenAI-only stack#1

Open
NabhyaIoT2026 wants to merge 2 commits intomainfrom
openai
Open

refactor: migrate from Qwen/Ollama to OpenAI-only stack#1
NabhyaIoT2026 wants to merge 2 commits intomainfrom
openai

Conversation

@NabhyaIoT2026
Copy link
Contributor

  • Replace nomic-embed-text (Ollama) with text-embedding-3-small (OpenAI)
  • Replace qwen2.5:7b (Ollama) interviewer with gpt-4o-mini (OpenAI)
  • Rename qwen_interviewer.py -> openai_interviewer.py
  • Add OPENAI_INTERVIEWER_MODEL + OPENAI_INTERVIEWER_TEMPERATURE config
  • Remove requests dependency (no more Ollama REST calls)
  • Simulate mode (OpenAI answers) is now the default
  • Meta-evaluation is now OFF by default (use --meta-eval to enable)
  • Add --interactive flag to type answers manually
  • Update all print messages and docstrings to remove Qwen/Ollama refs

- Replace nomic-embed-text (Ollama) with text-embedding-3-small (OpenAI)
- Replace qwen2.5:7b (Ollama) interviewer with gpt-4o-mini (OpenAI)
- Rename qwen_interviewer.py -> openai_interviewer.py
- Add OPENAI_INTERVIEWER_MODEL + OPENAI_INTERVIEWER_TEMPERATURE config
- Remove requests dependency (no more Ollama REST calls)
- Simulate mode (OpenAI answers) is now the default
- Meta-evaluation is now OFF by default (use --meta-eval to enable)
- Add --interactive flag to type answers manually
- Update all print messages and docstrings to remove Qwen/Ollama refs
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant