Reduce AI costs: switch tagging to gpt-4o-mini, add custom base URL support
Some checks failed
Build and Push Docker Image / build (push) Has been cancelled

- Change AI tagging to use AI_MODELS.QUICK (gpt-4o-mini) instead of gpt-4o for
  10-15x cost reduction on classification tasks
- Add openai_base_url system setting for OpenAI-compatible providers
  (OpenRouter, Groq, Together AI, local models)
- Reset OpenAI client singleton when API key, base URL, or model changes
- Add base URL field to AI settings form with provider examples

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
Matt
2026-02-16 15:34:59 +01:00
parent f12c29103c
commit 014bb15890
5 changed files with 74 additions and 4 deletions

View File

@@ -201,6 +201,12 @@ export const settingsRouter = router({
clearStorageProviderCache()
}
// Reset OpenAI client if API key or base URL changed
if (input.settings.some((s) => s.key === 'openai_api_key' || s.key === 'openai_base_url' || s.key === 'ai_model')) {
const { resetOpenAIClient } = await import('@/lib/openai')
resetOpenAIClient()
}
// Audit log
await logAudit({
prisma: ctx.prisma,