From 746a5eeeb997fd0dc2469735ae2c91df7ae3f7e5 Mon Sep 17 00:00:00 2001 From: ajaysi Date: Wed, 1 Apr 2026 06:54:37 +0530 Subject: [PATCH] Fix LLM provider selection in podcast handlers - Remove hardcoded preferred_provider=huggingface in podcast handlers - Set preferred_provider=None to respect GPT_PROVIDER env var - Change default model from Qwen to gpt-oss-120b:cerebras (the model user had access to) - WaveSpeed will now use gpt-oss-120b model instead of Qwen --- backend/api/podcast/handlers/analysis.py | 4 ++-- backend/services/llm_providers/main_text_generation.py | 6 +++--- 2 files changed, 5 insertions(+), 5 deletions(-) diff --git a/backend/api/podcast/handlers/analysis.py b/backend/api/podcast/handlers/analysis.py index 3131c4a3..a5ac2fd3 100644 --- a/backend/api/podcast/handlers/analysis.py +++ b/backend/api/podcast/handlers/analysis.py @@ -80,7 +80,7 @@ Return JSON with: prompt=prompt, user_id=user_id, json_struct=None, - preferred_provider="huggingface", + preferred_provider=None, flow_type="premium_tool", ) @@ -279,7 +279,7 @@ Requirements: prompt=prompt, user_id=user_id, json_struct=None, - preferred_provider="huggingface", + preferred_provider=None, flow_type="premium_tool", ) except HTTPException: diff --git a/backend/services/llm_providers/main_text_generation.py b/backend/services/llm_providers/main_text_generation.py index 47d4a1d0..6e82c49c 100644 --- a/backend/services/llm_providers/main_text_generation.py +++ b/backend/services/llm_providers/main_text_generation.py @@ -94,7 +94,7 @@ def llm_text_gen( primary_provider = provider_list[0] if primary_provider in ['wavespeed', 'wave']: gpt_provider = "wavespeed" - model = os.getenv('WAVESPEED_TEXT_MODEL', 'Qwen/Qwen2.5-7B-Instruct') + model = os.getenv('WAVESPEED_TEXT_MODEL', 'openai/gpt-oss-120b:cerebras') elif primary_provider in ['gemini', 'google']: gpt_provider = "google" model = "gemini-2.0-flash-001" @@ -111,7 +111,7 @@ def llm_text_gen( elif preferred_provider: if preferred_provider in ['wavespeed', 'wave']: gpt_provider = "wavespeed" - model = os.getenv('WAVESPEED_TEXT_MODEL', 'Qwen/Qwen2.5-7B-Instruct') + model = os.getenv('WAVESPEED_TEXT_MODEL', 'openai/gpt-oss-120b:cerebras') elif preferred_provider in ['openai', 'gpt']: gpt_provider = "openai" model = os.getenv('OPENAI_MODEL', 'gpt-4o-mini') @@ -363,7 +363,7 @@ def llm_text_gen( from services.llm_providers.wavespeed_provider import wavespeed_text_response response_text = wavespeed_text_response( prompt=prompt, - model=model or "Qwen/Qwen2.5-7B-Instruct", + model=model or "openai/gpt-oss-120b:cerebras", temperature=temperature, max_tokens=max_tokens, top_p=top_p,