Commit Graph

250 Commits (08abbb8dba15ca6476e8c73facee030dd67a314f)

Author SHA1 Message Date
Garfield Dai 695841a3cf
Feat/advanced prompt enhancement (#1340) 2 years ago
takatost 3efaa713da
feat: use xinference client instead of xinference (#1339) 2 years ago
takatost 9822f687f7
fix: max tokens of OpenAI gpt-3.5-turbo-instruct to 4097 (#1338) 2 years ago
takatost f4be2b8bcd
fix: raise error in minimax stream generate (#1336) 2 years ago
Garfield Dai 42a5b3ec17
feat: advanced prompt backend (#1301)
Co-authored-by: takatost <takatost@gmail.com>
2 years ago
takatost 2d1cb076c6
fix: dataset segment not exist return agent response (#1329) 2 years ago
Jyong 289c93d081
Feat/improve document delete logic (#1325)
Co-authored-by: jyong <jyong@dify.ai>
2 years ago
takatost 9cba1c8bf4
fix: retriever_resource missing (#1317) 2 years ago
takatost cbf095465c
feat: remove llm client use (#1316) 2 years ago
Jyong 7f6ad9653e
Fix/grpc gevent compatible (#1314)
Co-authored-by: jyong <jyong@dify.ai>
2 years ago
takatost 2851a9f04e
feat: optimize minimax llm call (#1312) 2 years ago
takatost c536f85b2e
fix: compatibility issues with the tongyi model. (#1310) 2 years ago
takatost b1352ff8b7
feat: using random sampling to check if it violates the review mechan… (#1308) 2 years ago
Jyong 5003db987d
milvus secure check fix (#1305)
Co-authored-by: jyong <jyong@dify.ai>
3 years ago
Jyong 07aab5e868
Feat/add milvus vector db (#1302)
Co-authored-by: jyong <jyong@dify.ai>
3 years ago
takatost 875dfbbf0e
fix: openllm completion start with prompt, remove it (#1303) 3 years ago
takatost 8480b0197b
fix: prompt for baichuan text generation models (#1299) 3 years ago
takatost 4ab4bcc074
feat: support openllm embedding (#1293) 3 years ago
takatost 1d4f019de4
feat: add baichuan llm support (#1294)
Co-authored-by: zxhlyh <jasonapring2015@outlook.com>
3 years ago
takatost 024250803a
feat: move login_required wrapper outside (#1281) 3 years ago
takatost 373e90ee6d
fix: detached model in completion thread (#1269) 3 years ago
takatost 41d4c5b424
fix: count down thread in completion db not commit (#1267) 3 years ago
takatost 8606d80c66
fix: request timeout when openai completion (#1265) 3 years ago
takatost a31466d34e
fix: db session not commit before long llm call running (#1251) 3 years ago
takatost d38eac959b
fix: wenxin model name invalid when llm call (#1248) 3 years ago
Jyong 46154c6705
Feat/dataset service api (#1245)
Co-authored-by: jyong <jyong@dify.ai>
Co-authored-by: StyleZhang <jasonapring2015@outlook.com>
3 years ago
Garfield Dai 18c710c906
feat: support binding context var (#1227)
Co-authored-by: Joel <iamjoel007@gmail.com>
3 years ago
zxhlyh 227f9fb77d
Feat/api jwt (#1212) 3 years ago
Jyong 724e053732
Fix/qdrant data issue (#1203)
Co-authored-by: jyong <jyong@dify.ai>
3 years ago
Garfield Dai e409895c02
Feat/huggingface embedding support (#1211)
Co-authored-by: StyleZhang <jasonapring2015@outlook.com>
3 years ago
takatost 32d9b6181c
fix: transaction not commit during long LLM calls (#1213) 3 years ago
takatost 2b018fade2
fix: transaction hangs due to message commit block during long LLM calls (#1206) 3 years ago
takatost 435f804c6f
fix: gpt-3.5-turbo-instruct context size to 8192 (#1196) 3 years ago
takatost ae3f1ac0a9
feat: support gpt-3.5-turbo-instruct model (#1195) 3 years ago
Jyong 269a465fc4
Feat/improve vector database logic (#1193)
Co-authored-by: jyong <jyong@dify.ai>
3 years ago
takatost 827c97f0d3
feat: add zhipuai (#1188) 3 years ago
takatost c8bd76cd66
fix: inference embedding validate (#1187) 3 years ago
takatost f9082104ed
feat: add hosted moderation (#1158) 3 years ago
Jyong 642842d61b
Feat:dataset retiever resource (#1123)
Co-authored-by: jyong <jyong@dify.ai>
Co-authored-by: StyleZhang <jasonapring2015@outlook.com>
3 years ago
Joel 2d5ad0d208
feat: support optional query content (#1097)
Co-authored-by: Garfield Dai <dai.hai@foxmail.com>
3 years ago
takatost c4d8bdc3db
fix: hf hosted inference check (#1128) 3 years ago
takatost a7cdb745c1
feat: support spark v2 validate (#1086) 3 years ago
takatost 73c86ee6a0
fix: prompt of title generation (#1084) 3 years ago
takatost 33562a9d8d
feat: optimize prompt (#1080) 3 years ago
takatost a199fa6388
feat: optimize high load sql query of document segment (#1078) 3 years ago
takatost 4c8608dc61
feat: optimize conversation title generation output must be a valid JSON (#1077) 3 years ago
takatost df6604a734
feat: optimize generation of conversation title (#1075) 3 years ago
takatost 78e26f8b75
fix: summary no docs (#1073) 3 years ago
takatost 2191312bb9
fix: segments query missing idx hit (#1072) 3 years ago
takatost fcc6b41ab7
feat: decrease claude model request time by set max top_k to 10 (#1071) 3 years ago
takatost d75e8aeafa
feat: disable anthropic retry (#1067) 3 years ago
takatost 2eba98a465
feat: optimize anthropic connection pool (#1066) 3 years ago
takatost a7a7aab7a0
fix: csv import error (#1063) 3 years ago
yezhwi d33a269548
refactor(file extractor): file extractor (#1059) 3 years ago
yezhwi 8b8e510bfe
fix: handle AttributeError for datasets and index (#1052) 3 years ago
takatost 417c19577a
feat: add LocalAI local embedding model support (#1021)
Co-authored-by: StyleZhang <jasonapring2015@outlook.com>
3 years ago
Jyong a43e80dd9c
add qdrant migration (#1046)
Co-authored-by: jyong <jyong@dify.ai>
3 years ago
WangBooth ad5f27bc5f
fix openpyxl dimensions error (#1041) 3 years ago
takatost 7b3314c5db
fix: dataset desc (#1045) 3 years ago
Jyong a55ba6e614
Fix/ignore economy dataset (#1043)
Co-authored-by: jyong <jyong@dify.ai>
3 years ago
takatost 02452421d5
fix: pub generate message text return null (#1037) 3 years ago
takatost 0796791de5
feat: hf inference endpoint stream support (#1028) 3 years ago
takatost 6c148b223d
fix: dataset query truncated (#1026) 3 years ago
Uranus 2d9616c29c
fix: xinference last token being ignored (#1013) 3 years ago
Jyong 2d604d9330
Fix/filter empty segment (#1004)
Co-authored-by: jyong <jyong@dify.ai>
3 years ago
Jyong b1fd1b3ab3
Feat/vector db manage (#997)
Co-authored-by: jyong <jyong@dify.ai>
3 years ago
takatost 9ae91a2ec3
feat: optimize xinference request max token key and stop reason (#998) 3 years ago
takatost 701e2b334f
feat: remove unnecessary prompt of baichuan (#993) 3 years ago
takatost bd3a9b2f8d
fix: xinference-chat-stream-response (#991) 3 years ago
takatost 18d3877151
feat: optimize xinference stream (#989) 3 years ago
takatost 53e83d8697
feat: optimize baichuan prompt (#988) 3 years ago
takatost 2c30d19cbe
feat: add baichuan prompt (#985) 3 years ago
takatost 9b247fccd4
feat: adjust hf max tokens (#979) 3 years ago
takatost a76fde3d23
feat: optimize hf inference endpoint (#975) 3 years ago
Jyong 1fc57d7358
normalize embedding (#974)
Co-authored-by: jyong <jyong@dify.ai>
3 years ago
takatost 5cba2e7087
fix: web reader tool retrieve content empty (#957) 3 years ago
Jyong 5623839c71
update document segment (#950)
Co-authored-by: jyong <jyong@dify.ai>
3 years ago
takatost 78d3aa5fcd
fix: embedding init err (#956) 3 years ago
takatost 4f3053a8cc
fix: xinference chat completion error (#952) 3 years ago
takatost 866ee5da91
fix: openllm generate cutoff (#945) 3 years ago
takatost e0a48c4972
fix: xinference chat support (#939) 3 years ago
Jyong 4b53bb1a32
Feat/token support (#909)
Co-authored-by: StyleZhang <jasonapring2015@outlook.com>
Co-authored-by: jyong <jyong@dify.ai>
3 years ago
takatost 4c49ecedb5
feat: optimize web reader summary in 3.5 (#933) 3 years ago
takatost 6c832ee328
fix: remove openllm pypi package because of this package too large (#931) 3 years ago
takatost 25264e7852
feat: add xinference embedding model support (#930) 3 years ago
takatost 18dd0d569d
fix: xinference max_tokens alisa error (#929) 3 years ago
takatost 3ea8d7a019
feat: add openllm support (#928) 3 years ago
takatost da3f10a55e
feat: server xinference support (#927) 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
takatost 2a27dad2fb
fix: run model serval ex not return (#915) 3 years ago
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>
3 years ago
takatost d9afebe216
feat: optimize output parse (#906) 3 years ago
takatost 1d9cc5ca05
fix: universal chat when default model invalid (#905) 3 years ago
takatost edb06f6aed
fix: react router agent direct output (#904) 3 years ago