17 commits

Author	SHA1	Message	Date
jinli.yl	7b09f0bd2b	fix empty content insight bug && modify print memory	2024-07-22 10:46:26 +08:00
jinli.yl	9b0f222c22	fix cn prompt problem	2024-07-18 15:46:34 +08:00
jinli.yl	c875492b1c	code format	2024-07-14 16:52:30 +08:00
fuqingxu	33195dae24	generate docstring with Qwen-Max agent	2024-07-12 18:24:49 +08:00
jinli.yl	523b752a3d	[dev] fix demo config	2024-07-08 23:26:10 +08:00
jinli.yl	1f76a8f353	[dev] modify format_time_infer& get_language_value	2024-07-02 20:51:29 +08:00
jinli.yl	34d06868e2	[dev] del global key in config & modify workflow	2024-07-02 19:47:15 +08:00
xianzhe.xxz	7f84987762	add async support for rank/generation/embedding models	2024-07-01 10:47:03 +08:00
jinli.yl	8bfec9c246	[dev] fix bugs when command is empty & add kwargs to operation~	2024-06-28 20:45:24 +08:00
jinli.yl	5f1bcf50d8	[dev] add memory base worker & add role name to messages	2024-06-28 16:08:42 +08:00
jinli.yl	862b55f2b0	[dev] rename prepare service function & reformat llm model data struct	2024-06-27 16:43:59 +08:00
jinli.yl	093946e999	[dev] modify test for llm	2024-06-27 14:46:41 +08:00
jinli.yl	02bb9718be	[dev] format model response	2024-06-26 18:27:39 +08:00
hs	e84733f810	memory stream & some workers	2024-06-25 19:20:10 +08:00
jinli.yl	322f48117f	[dev] delete asyncio from base model	2024-06-25 12:23:39 +08:00
xianzhe.xxz	ffc1c5261d	update module names, add stream support for llm	2024-06-24 18:18:54 +08:00
jinli.yl	31316a9080	[test] add test for llm models	2024-06-24 15:50:29 +08:00

Renamed from memory_scope/models/base_generation_model.py (Browse further)