Spaces:
Sleeping
Sleeping
Commit History
-
fix(llm): switch to openai/gpt-oss-120b — Groq decommissioned Llama 3.3 70B
AdityaGroq retired llama-3.3-70b-versatile in August 2026; every query returned model_not_found, surfacing in the UI as "Failed to process query." Switch to openai/gpt-oss-120b and update the model labels in the header badge, homepage hero, tech chips and README. Also fix the Docker HEALTHCHECK to honour $PORT instead of hardcoding 7860.f09b47c
-
Deploy ASK Docs — Groq (Llama 3.3 70B) + local MiniLM embeddings
Aditya9f0bed6