kunthawat/ALwrity
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Fix LLM provider selection in podcast handlers

Browse Source 
- 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
This commit is contained in:
ajaysi
2026-04-01 06:54:37 +05:30
parent d06ab77e60
commit 746a5eeeb9
2 changed files with 5 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
backend/api/podcast/handlers/analysis.py
View File

@@ -80,7 +80,7 @@ Return JSON with:
prompt=prompt, prompt=prompt,
user_id=user_id, user_id=user_id,
json_struct=None, json_struct=None,
preferred_provider="huggingface", preferred_provider=None,
flow_type="premium_tool", flow_type="premium_tool",
) )
@@ -279,7 +279,7 @@ Requirements:
prompt=prompt, prompt=prompt,
user_id=user_id, user_id=user_id,
json_struct=None, json_struct=None,
preferred_provider="huggingface", preferred_provider=None,
flow_type="premium_tool", flow_type="premium_tool",
) )
except HTTPException: except HTTPException:

6
backend/services/llm_providers/main_text_generation.py
View File

@@ -94,7 +94,7 @@ def llm_text_gen(
primary_provider = provider_list[0] primary_provider = provider_list[0]
if primary_provider in ['wavespeed', 'wave']: if primary_provider in ['wavespeed', 'wave']:
gpt_provider = "wavespeed" 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']: elif primary_provider in ['gemini', 'google']:
gpt_provider = "google" gpt_provider = "google"
model = "gemini-2.0-flash-001" model = "gemini-2.0-flash-001"
@@ -111,7 +111,7 @@ def llm_text_gen(
elif preferred_provider: elif preferred_provider:
if preferred_provider in ['wavespeed', 'wave']: if preferred_provider in ['wavespeed', 'wave']:
gpt_provider = "wavespeed" 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']: elif preferred_provider in ['openai', 'gpt']:
gpt_provider = "openai" gpt_provider = "openai"
model = os.getenv('OPENAI_MODEL', 'gpt-4o-mini') 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 from services.llm_providers.wavespeed_provider import wavespeed_text_response
response_text = wavespeed_text_response( response_text = wavespeed_text_response(
prompt=prompt, prompt=prompt,
model=model or "Qwen/Qwen2.5-7B-Instruct", model=model or "openai/gpt-oss-120b:cerebras",
temperature=temperature, temperature=temperature,
max_tokens=max_tokens, max_tokens=max_tokens,
top_p=top_p, top_p=top_p,