liwenju0 875096384b when qwen rerank model not return ok, raise exception to notice user (#3593) ... ### What problem does this PR solve? When calling the Qwen rerank model, if the model does not return correctly, an exception should be raised to notify the user, rather than simply returning a value of 0, as this would be confusing to the user. ### Type of change - [x] New Feature (non-breaking change which adds functionality)		2024-11-22 22:34:34 +08:00
..
__init__.py	Added LocalAI support for rerank models (#3446)	2024-11-18 12:05:52 +08:00
chat_model.py	Make spark model robuster to model name (#3514)	2024-11-20 20:53:44 +08:00
cv_model.py	Fix keys of Xinference deployed models, especially has the same model name with public hosted models. (#2832)	2024-10-16 10:21:08 +08:00
embedding_model.py	Add api for sessions and add max_tokens for tenant_llm (#3472)	2024-11-19 14:51:33 +08:00
rerank_model.py	when qwen rerank model not return ok, raise exception to notice user (#3593)	2024-11-22 22:34:34 +08:00
sequence2txt_model.py	fix sequence2txt error and usage total token issue (#2961)	2024-10-22 11:38:37 +08:00
tts_model.py	support sequence2txt and tts model in Xinference (#2696)	2024-10-08 10:43:18 +08:00