232 Commits

Author	SHA1	Message	Date
takatost	ef61e1487f	fix: safetensor arm complie error (#996)	2023-08-24 17:38:10 +08:00
takatost	701e2b334f	feat: remove unnecessary prompt of baichuan (#993)	2023-08-24 15:30:59 +08:00
takatost	6ebd6e7890	feat: bump version to 0.3.17 (#992)	2023-08-24 15:12:47 +08:00
takatost	bd3a9b2f8d	fix: xinference-chat-stream-response (#991)	2023-08-24 14:39:34 +08:00
takatost	18d3877151	feat: optimize xinference stream (#989)	2023-08-24 13:58:34 +08:00
takatost	53e83d8697	feat: optimize baichuan prompt (#988)	2023-08-24 12:07:10 +08:00
takatost	2c30d19cbe	feat: add baichuan prompt (#985)	2023-08-24 10:22:36 +08:00
takatost	9b247fccd4	feat: adjust hf max tokens (#979)	2023-08-23 22:24:50 +08:00
John Wang	3d38aa7138	feat: bump version to 0.3.16	2023-08-23 20:16:54 +08:00
takatost	7d2552b3f2	feat: upgrade xinference to 0.2.1 which support stream response (#977)	2023-08-23 20:15:45 +08:00
yezhwi	117a209ad4	Fix:condition for dataset availability check (#973)	2023-08-23 19:57:27 +08:00
takatost	a76fde3d23	feat: optimize hf inference endpoint (#975)	2023-08-23 19:47:50 +08:00
Jyong	1fc57d7358	normalize embedding (#974) ... Co-authored-by: jyong <jyong@dify.ai>	2023-08-23 19:10:11 +08:00
takatost	f8fbe96da4	feat: bump version to 0.3.15 (#959)	2023-08-22 18:20:33 +08:00
takatost	5cba2e7087	fix: web reader tool retrieve content empty (#957)	2023-08-22 18:01:16 +08:00
Jyong	5623839c71	update document segment (#950) ... Co-authored-by: jyong <jyong@dify.ai>	2023-08-22 17:59:24 +08:00
takatost	78d3aa5fcd	fix: embedding init err (#956)	2023-08-22 17:43:59 +08:00
takatost	4f3053a8cc	fix: xinference chat completion error (#952)	2023-08-22 15:58:04 +08:00
Jyong	aee15adf1b	update document segment (#948) ... Co-authored-by: jyong <jyong@dify.ai>	2023-08-22 15:19:09 +08:00
takatost	a3aba7a9aa	fix: provider model not delete when reset key pair (#946)	2023-08-22 13:48:58 +08:00
takatost	866ee5da91	fix: openllm generate cutoff (#945)	2023-08-22 13:43:36 +08:00
takatost	e0a48c4972	fix: xinference chat support (#939)	2023-08-21 20:44:29 +08:00
Jyong	4b53bb1a32	Feat/token support (#909) ... Co-authored-by: StyleZhang <jasonapring2015@outlook.com> Co-authored-by: jyong <jyong@dify.ai>	2023-08-21 13:57:18 +08:00
takatost	4c49ecedb5	feat: optimize web reader summary in 3.5 (#933)	2023-08-21 11:58:01 +08:00
takatost	4ff1870a4b	fix: web reader tool missing nodejs (#932)	2023-08-21 11:26:11 +08:00
takatost	6c832ee328	fix: remove openllm pypi package because of this package too large (#931)	2023-08-21 02:12:28 +08:00
takatost	25264e7852	feat: add xinference embedding model support (#930)	2023-08-20 19:35:07 +08:00
takatost	18dd0d569d	fix: xinference max_tokens alisa error (#929)	2023-08-20 19:12:52 +08:00
takatost	3ea8d7a019	feat: add openllm support (#928)	2023-08-20 19:04:33 +08:00
takatost	da3f10a55e	feat: server xinference support (#927)	2023-08-20 17:46:41 +08:00
takatost	22c1aafb9b	fix: document paused at format error (#925)	2023-08-20 01:54:12 +08:00
takatost	8d6d1c442b	feat: optimize generate name length (#924)	2023-08-19 23:34:38 +08:00
takatost	95b179fb39	fix: replicate text generation model validate (#923)	2023-08-19 21:40:42 +08:00
takatost	3a0a9e2d8f	fix: embedding get price definition missing (#922)	2023-08-19 21:31:40 +08:00
takatost	0a0d63457d	feat: record price unit in messages (#919)	2023-08-19 18:51:40 +08:00
takatost	920fb6d0e1	fix: embedding price config (#918)	2023-08-19 16:54:08 +08:00
Krasus.Chen	fd0fc8f4fe	Fix/price calc (#862)	2023-08-19 16:41:35 +08:00
takatost	1c552ff23a	fix: azure embedding model credentials include base_model_name is invalid for openai sdk (#917)	2023-08-19 16:24:18 +08:00
takatost	5163dd38e5	fix: run extra model serval ex not return (#916)	2023-08-19 14:35:16 +08:00
takatost	2a27dad2fb	fix: run model serval ex not return (#915)	2023-08-19 14:16:41 +08:00
takatost	930f74c610	feat: remove unuse envs (#912)	2023-08-18 21:34:28 +08:00
takatost	09ea27f1ee	feat: optimize service api authorization header invalid error (#910)	2023-08-18 20:32:44 +08:00
Jyong	db7156dafd	Feature/mutil embedding model (#908) ... Co-authored-by: JzoNg <jzongcode@gmail.com> Co-authored-by: jyong <jyong@dify.ai> Co-authored-by: StyleZhang <jasonapring2015@outlook.com>	2023-08-18 17:37:31 +08:00
takatost	d9afebe216	feat: optimize output parse (#906)	2023-08-18 17:00:40 +08:00
takatost	1d9cc5ca05	fix: universal chat when default model invalid (#905)	2023-08-18 16:20:42 +08:00
takatost	edb06f6aed	fix: react router agent direct output (#904)	2023-08-18 14:31:20 +08:00
takatost	6ca3bcbcfd	fix: sensitive_word_avoidance npe (#902)	2023-08-18 11:43:56 +08:00
takatost	9adbeadeec	feat: claude paid optimize (#890)	2023-08-17 16:56:20 +08:00
takatost	2f7b234cc5	fix: max token not exist in generate summary when calc rest tokens (#891)	2023-08-17 16:33:32 +08:00
takatost	0cc0b6e052	fix: error raise status code not exist (#888)	2023-08-17 15:33:35 +08:00