Commit Graph

243 Commits (1c114eaef30de0369236fb29f8cc72baf2ad01f3)

Author SHA1 Message Date
Jyong e053215155
fix document estimate parameter (#1019)
Co-authored-by: jyong <jyong@dify.ai>
2 years ago
Jyong 38fa152cc4
fix update document index technique (#1018)
Co-authored-by: jyong <jyong@dify.ai>
2 years ago
Uranus 2d9616c29c
fix: xinference last token being ignored (#1013) 2 years ago
Jyong 915e26527b
update dataset index struct (#1012)
Co-authored-by: jyong <jyong@dify.ai>
2 years ago
Jyong 2d604d9330
Fix/filter empty segment (#1004)
Co-authored-by: jyong <jyong@dify.ai>
2 years ago
Jyong e7199826cc
embedding model available check (#1009)
Co-authored-by: jyong <jyong@dify.ai>
2 years ago
yezhwi c1602aafc7
refactor:cache in place & function name (#1001) 2 years ago
Jyong b1fd1b3ab3
Feat/vector db manage (#997)
Co-authored-by: jyong <jyong@dify.ai>
2 years ago
Jyong 5397799aac
document limit (#999)
Co-authored-by: jyong <jyong@dify.ai>
2 years ago
takatost 8e837dde1a
feat: bump version to 0.3.18 (#1000) 2 years ago
takatost 9ae91a2ec3
feat: optimize xinference request max token key and stop reason (#998) 2 years ago
takatost ef61e1487f
fix: safetensor arm complie error (#996) 2 years ago
takatost 701e2b334f
feat: remove unnecessary prompt of baichuan (#993) 2 years ago
takatost 6ebd6e7890
feat: bump version to 0.3.17 (#992) 2 years ago
takatost bd3a9b2f8d
fix: xinference-chat-stream-response (#991) 2 years ago
takatost 18d3877151
feat: optimize xinference stream (#989) 2 years ago
takatost 53e83d8697
feat: optimize baichuan prompt (#988) 2 years ago
takatost 2c30d19cbe
feat: add baichuan prompt (#985) 2 years ago
takatost 9b247fccd4
feat: adjust hf max tokens (#979) 2 years ago
John Wang 3d38aa7138 feat: bump version to 0.3.16 2 years ago
takatost 7d2552b3f2
feat: upgrade xinference to 0.2.1 which support stream response (#977) 2 years ago
yezhwi 117a209ad4
Fix:condition for dataset availability check (#973) 2 years ago
takatost a76fde3d23
feat: optimize hf inference endpoint (#975) 2 years ago
Jyong 1fc57d7358
normalize embedding (#974)
Co-authored-by: jyong <jyong@dify.ai>
2 years ago
takatost f8fbe96da4
feat: bump version to 0.3.15 (#959) 2 years ago
takatost 5cba2e7087
fix: web reader tool retrieve content empty (#957) 2 years ago
Jyong 5623839c71
update document segment (#950)
Co-authored-by: jyong <jyong@dify.ai>
2 years ago
takatost 78d3aa5fcd
fix: embedding init err (#956) 2 years ago
takatost 4f3053a8cc
fix: xinference chat completion error (#952) 2 years ago
Jyong aee15adf1b
update document segment (#948)
Co-authored-by: jyong <jyong@dify.ai>
2 years ago
takatost a3aba7a9aa
fix: provider model not delete when reset key pair (#946) 2 years ago
takatost 866ee5da91
fix: openllm generate cutoff (#945) 2 years ago
takatost e0a48c4972
fix: xinference chat support (#939) 2 years ago
Jyong 4b53bb1a32
Feat/token support (#909)
Co-authored-by: StyleZhang <jasonapring2015@outlook.com>
Co-authored-by: jyong <jyong@dify.ai>
2 years ago
takatost 4c49ecedb5
feat: optimize web reader summary in 3.5 (#933) 2 years ago
takatost 4ff1870a4b
fix: web reader tool missing nodejs (#932) 2 years ago
takatost 6c832ee328
fix: remove openllm pypi package because of this package too large (#931) 2 years ago
takatost 25264e7852
feat: add xinference embedding model support (#930) 2 years ago
takatost 18dd0d569d
fix: xinference max_tokens alisa error (#929) 2 years ago
takatost 3ea8d7a019
feat: add openllm support (#928) 2 years ago
takatost da3f10a55e
feat: server xinference support (#927) 2 years ago
takatost 22c1aafb9b
fix: document paused at format error (#925) 2 years ago
takatost 8d6d1c442b
feat: optimize generate name length (#924) 3 years ago
takatost 95b179fb39
fix: replicate text generation model validate (#923) 3 years ago
takatost 3a0a9e2d8f
fix: embedding get price definition missing (#922) 3 years ago
takatost 0a0d63457d
feat: record price unit in messages (#919) 3 years ago
takatost 920fb6d0e1
fix: embedding price config (#918) 3 years ago
Krasus.Chen fd0fc8f4fe
Fix/price calc (#862) 3 years ago
takatost 1c552ff23a
fix: azure embedding model credentials include base_model_name is invalid for openai sdk (#917) 3 years ago
takatost 5163dd38e5
fix: run extra model serval ex not return (#916) 3 years ago