Rick ee8ea3de16 fix: increase max_tokens from 5 to 16 for some specific models like gpt-5-codex in ping test, add PING_MAX_TOKENS configuration for model validation ping requests (#235)

2025-12-09 12:57:43 +08:00

..

openai_compatible

fix: increase max_tokens from 5 to 16 for some specific models like gpt-5-codex in ping test, add PING_MAX_TOKENS configuration for model validation ping requests (#235)

2025-12-09 12:57:43 +08:00

__init__.py

refactor: update model provider to use ModelFactory for instance mana… (#223)

2025-10-20 14:27:20 +08:00

ai_model.py

fix: corrected latency accuracy (#189)

2025-09-16 16:15:20 +08:00

audio.mp3

refactor all

2024-09-03 23:03:15 +08:00

large_language_model.py

fix: corrected latency accuracy (#189)

2025-09-16 16:15:20 +08:00

moderation_model.py

fix: corrected latency accuracy (#189)

2025-09-16 16:15:20 +08:00

rerank_model.py

feat: support multimodal embeddings (#237)

2025-12-08 19:40:56 +08:00

speech2text_model.py

fix: corrected latency accuracy (#189)

2025-09-16 16:15:20 +08:00

text_embedding_model.py

feat: support multimodal embeddings (#237)

2025-12-08 19:40:56 +08:00

tts_model.py

fix: corrected latency accuracy (#189)

2025-09-16 16:15:20 +08:00