logan/server-26
1
0
Fork 0
Code Issues 84 Pull Requests Actions Packages Projects Releases Wiki Activity

AI providers: correlation decision and transcript correction move to OpenAI gpt-4o-mini

Browse Source 
One funded account (OpenAI) now covers extraction, embeddings, summaries,
the ambiguous-scene correlation call and transcript correction; Groq stays
optional for STT. New app/internal/llm.py picks the provider from the model
name, so setting either model back to a gemini-* ID needs no code change.
Usage accounting for replay runs now covers both providers.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
Logan Cusano
2026-11-08 01:25:21 -05:00
co-authored by Claude Opus 5.5
parent 3e9ca4be06
commit 0060ccde75
12 changed files with 180 additions and 50 deletions
Download Patch File Download Diff File Expand all files Collapse all files
drb-c2-core/.env.example
+3
View File
@@ -38,6 +38,9 @@ NWS_AREA=NY
# OpenAI — transcription (whisper-1, and the STT fallback), extraction, embeddings
OPENAI_API_KEY=
# Since 2026-11-08 OpenAI also serves the correlation decision and transcript
# correction (CORR_CHEAP_MODEL / TRANSCRIPT_CORRECTION_MODEL, default gpt-4o-mini).
# GEMINI_API_KEY is only needed if you point either of those at a gemini-* model.
# OpenAI transcription model: whisper-1 | gpt-4o-mini-transcribe | gpt-4o-transcribe
STT_MODEL=whisper-1