takatost
|
a18dde9b0d
|
feat: add cohere llm and embedding (#2115)
|
2 years ago |
crazywoola
|
8438d820ad
|
Feat/2070 glm 4 and glm 3 turbo (#2114)
|
2 years ago |
|
crazywoola
|
1f48e3d44a
|
feat: support legacy doc (#2100)
|
2 years ago |
Garfield Dai
|
0a5de0ff0b
|
fix: empty keywords moderation. (#2108)
|
2 years ago |
|
takatost
|
9c4bad8f1e
|
fix: arg missing when call method `on_message_replace_func` in output… (#2106)
|
2 years ago |
Jyong
|
ee9c7e204f
|
delete document cache embedding (#2101)
Co-authored-by: jyong <jyong@dify.ai>
|
2 years ago |
Joshua
|
09a8db10d4
|
Add jina-embeddings-v2-base-de model configuration (#2094)
|
2 years ago |
|
Jyong
|
869690c485
|
fix notion estimate (#2090)
Co-authored-by: jyong <jyong@dify.ai>
|
2 years ago |
|
Jyong
|
a3c7c07ecc
|
use redis to cache embeddings (#2085)
Co-authored-by: jyong <jyong@dify.ai>
|
2 years ago |
|
takatost
|
1a6ad05a23
|
feat: service api add llm usage (#2051)
|
2 years ago |
|
takatost
|
1d91535ba6
|
fix: azure customize model name duplicate (#2073)
|
2 years ago |
|
takatost
|
8799c888e3
|
fix: free quota type apply button missing (#2069)
Co-authored-by: StyleZhang <jasonapring2015@outlook.com>
|
2 years ago |
|
crazywoola
|
d7209d9057
|
feat: add abab5.5s-chat (#2063)
|
2 years ago |
|
Jyong
|
a61df6cb03
|
timeout parameter error (#2052)
Co-authored-by: jyong <jyong@dify.ai>
|
2 years ago |
|
Jyong
|
790b885d0a
|
fix multi-dataset retrieve score limit (#2050)
Co-authored-by: jyong <jyong@dify.ai>
|
2 years ago |
Ricky
|
1a2eacc5a6
|
Add jina-embeddings-v2-base-zh model configuration (#2049)
|
2 years ago |
|
takatost
|
b582fc13c3
|
fix: qwen top_p min/max wrong (#2044)
|
2 years ago |
|
Jyong
|
add33cb5e6
|
fix SQL slow query (#2043)
Co-authored-by: jyong <jyong@dify.ai>
|
2 years ago |
|
Garfield Dai
|
83105d0d8f
|
fix: dataset and moderation. (#2042)
|
2 years ago |
|
Jyong
|
cb7a608d75
|
ascii filter Unicode U+FFFE (#2038)
Co-authored-by: jyong <jyong@dify.ai>
|
2 years ago |
Yeuoly
|
149102927b
|
fix: openai tool tokens (#2026)
|
2 years ago |
|
Garfield Dai
|
cb7be3767c
|
feat: huggingface llm add new params. (#2014)
|
2 years ago |
|
takatost
|
34bf2877c8
|
fix: tongyi stream generate not incremental and add qwen max models (#2013)
|
2 years ago |
|
Jyong
|
a63a9c7d45
|
text spliter length method use default embedding model tokenizer (#2011)
Co-authored-by: jyong <jyong@dify.ai>
|
2 years ago |
|
takatost
|
1779cea6e3
|
fix: model provider credentials null value validate failed (#2009)
|
2 years ago |
Bowen Liang
|
cc9e74123c
|
improve: introduce isort for linting Python imports (#1983)
|
2 years ago |
|
takatost
|
cca9edc97a
|
feat: ollama support (#2003)
|
2 years ago |
|
takatost
|
5e97eb1840
|
fix: azure openai stream response usage missing (#1998)
|
2 years ago |
|
Yeuoly
|
c9e4147b11
|
optimize baichuan invalid key error (#1996)
|
2 years ago |
|
takatost
|
bf7045566d
|
fix: azure openai model parameters wrong when using hosting credentials (#1993)
|
2 years ago |
|
Yeuoly
|
ebd11e7482
|
fix: baichuan max chunks (#1990)
|
2 years ago |
|
Jyong
|
24bdedf802
|
fix get embedding model provider in empty dataset (#1986)
Co-authored-by: jyong <jyong@dify.ai>
|
2 years ago |
|
Jyong
|
9dee9e7ade
|
fix rerank issue when doing economy search (#1978)
Co-authored-by: jyong <jyong@dify.ai>
|
2 years ago |
|
takatost
|
33901384c6
|
fix: httpx socks package missing (#1977)
|
2 years ago |
Charlie.Wei
|
7a221d0858
|
Fix hosting cloud version limit (#1975)
Co-authored-by: luowei <glpat-EjySCyNjWiLqAED-YmwM>
Co-authored-by: crazywoola <427733928@qq.com>
Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>
|
2 years ago |
|
Jyong
|
60ee98f578
|
zhipu embedding token method (#1976)
Co-authored-by: jyong <jyong@dify.ai>
|
2 years ago |
|
Charlie.Wei
|
5b24d7129e
|
Azure openai init (#1929)
Co-authored-by: luowei <glpat-EjySCyNjWiLqAED-YmwM>
Co-authored-by: crazywoola <427733928@qq.com>
Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>
|
2 years ago |
|
Bowen Liang
|
b8592ad412
|
fix: indentation violations in YAML files (#1972)
|
2 years ago |
Chenhe Gu
|
344821ed35
|
enforce utf-8 encoding for provider response (#1973)
|
2 years ago |
|
Chenhe Gu
|
5ff701ca3f
|
correct xorbits spelling (#1965)
|
2 years ago |
|
takatost
|
0c746f5c5a
|
fix: generate not stop when pressing stop link (#1961)
|
2 years ago |
|
Garfield Dai
|
a8cedea15a
|
fix: check result should be string. (#1959)
|
2 years ago |
|
Chenhe Gu
|
87832ede17
|
delete remnant 'required': false (#1955)
|
2 years ago |
|
Jyong
|
28b26f67e2
|
optimize qa prompt (#1957)
Co-authored-by: jyong <jyong@dify.ai>
|
2 years ago |
|
Chenhe Gu
|
b934232411
|
change API key field to 'required' (#1953)
|
2 years ago |
|
takatost
|
2f120786fd
|
feat: reorder togetherai (#1951)
|
2 years ago |
|
Chenhe Gu
|
6075fee556
|
Add Together.ai's OpenAI API-compatible inference endpoints (#1947)
|
2 years ago |
|
Chenhe Gu
|
de584807e1
|
fix streaming (#1944)
|
2 years ago |
|
Garfield Dai
|
cf1f6f3961
|
fix: text completion app cannot get data. (#1942)
|
2 years ago |
|
takatost
|
28883e80d4
|
fix: gpt-4-32k model name empty in OpenAI response (#1941)
|
2 years ago |
|
takatost
|
a0f74cdd9d
|
fix: llm result usage none (#1940)
|
2 years ago |
|
takatost
|
296bf443a8
|
feat: reuse decoding_rsa_key & decoding_cipher_rsa & optimize construct (#1937)
|
2 years ago |
|
takatost
|
af7be9bdd7
|
Feat/optimize entity construct (#1935)
|
2 years ago |
|
takatost
|
2cfd5568e1
|
fix: vision fail in complete app (#1933)
|
2 years ago |
|
takatost
|
faf40a42bc
|
feat: optimize memory & invoke error output (#1931)
|
2 years ago |
|
takatost
|
3fa5204b0c
|
feat: optimize performance (#1928)
|
2 years ago |
|
Yeuoly
|
5a756ca981
|
fix: xinference cache (#1926)
|
2 years ago |
Liu Peng
|
01f9feff9f
|
fix a typo in file agent_app_runner.py (#1927)
|
2 years ago |
|
takatost
|
b4225bedb5
|
fix: app create raise error when no available model providers (#1921)
|
2 years ago |
waltcow
|
a82b4d315a
|
Fix comparison bug in ApplicationQueueManager (#1919)
|
2 years ago |
|
Jyong
|
4a3d15b6de
|
fix customer spliter character (#1915)
Co-authored-by: jyong <jyong@dify.ai>
|
2 years ago |
|
Garfield Dai
|
665318da3d
|
fix: remove useless code. (#1913)
|
2 years ago |
|
takatost
|
a938e1f184
|
fix: notion_indexing_estimate embedding_model_instance NPE (#1907)
|
2 years ago |
|
takatost
|
7c7ee633c1
|
fix: spark credentials validate (#1906)
|
2 years ago |
|
crazywoola
|
18af84e193
|
fix: array oob in azure openai embeddings (#1905)
|
2 years ago |
|
takatost
|
025b859c7e
|
fix: tongyi generate error (#1904)
|
2 years ago |
newsouther
|
0e239a4f71
|
fix: read file encoding error (#1902)
Co-authored-by: maple <1071520@gi>
|
2 years ago |
|
takatost
|
6a2eb5f442
|
fix: customize model schema fetch failed raise error (#1900)
|
2 years ago |
|
takatost
|
0c5892bcb6
|
fix: zhipuai chatglm turbo prompts must user, assistant in sequence (#1899)
|
2 years ago |
|
takatost
|
bb7af56e69
|
fix: zhipuai history format wrong (#1897)
|
2 years ago |
|
Chenhe Gu
|
77f9e8ce0f
|
add example api url endpoint in placeholder (#1887)
Co-authored-by: takatost <takatost@gmail.com>
|
2 years ago |
|
Jyong
|
5ca4c4a44d
|
add qdrant client timeout limit (#1894)
Co-authored-by: jyong <jyong@dify.ai>
|
2 years ago |
|
takatost
|
6333cf43a8
|
fix: anthropic messages empty raise errors (#1893)
|
2 years ago |
|
Garfield Dai
|
91ee62d1ab
|
fix: huggingface and replicate. (#1888)
|
2 years ago |
|
takatost
|
ede69b4659
|
fix: gemini block error (#1877)
Co-authored-by: chenhe <guchenhe@gmail.com>
|
2 years ago |
|
waltcow
|
61aaeff413
|
Fix variable name in AgentApplicationRunner (#1884)
|
2 years ago |
|
crazywoola
|
4d502ea44d
|
fix: openai embedding list out of bound (#1879)
|
2 years ago |
|
Yeuoly
|
9134849744
|
fix: remove tiktoken from text splitter (#1876)
|
2 years ago |
|
Garfield Dai
|
fcf8512956
|
fix: more like this. (#1875)
|
2 years ago |
|
takatost
|
ae975b10e9
|
fix: openai origin credential not start with { (#1874)
|
2 years ago |
|
Yeuoly
|
b43f1441a9
|
Fix/model runtime (#1873)
|
2 years ago |
|
takatost
|
5a2aa83030
|
fix: ciphertext error (#1872)
|
2 years ago |
|
Yeuoly
|
c6d59681ff
|
fix: xinference secret server_url (#1869)
|
2 years ago |
|
takatost
|
3b668c0bb1
|
fix: IntegrityError import wrong (#1868)
|
2 years ago |
|
takatost
|
4aed1fe8a8
|
fix: Azure text-davinci-003 missing (#1867)
|
2 years ago |
|
takatost
|
2381264a3f
|
fix: provider create cause IntegrityError (#1866)
|
2 years ago |
|
takatost
|
7be77c19f5
|
fix: default model parameter precision (#1864)
|
2 years ago |
|
takatost
|
82247c0f14
|
fix: agent strategy missing in app model config (#1863)
|
2 years ago |
|
takatost
|
d069c668f8
|
Model Runtime (#1858)
Co-authored-by: StyleZhang <jasonapring2015@outlook.com>
Co-authored-by: Garfield Dai <dai.hai@foxmail.com>
Co-authored-by: chenhe <guchenhe@gmail.com>
Co-authored-by: jyong <jyong@dify.ai>
Co-authored-by: Joel <iamjoel007@gmail.com>
Co-authored-by: Yeuoly <admin@srmxy.cn>
|
2 years ago |
|
waltcow
|
06d2d8cea3
|
Refactor BaseVectorIndex delete method (#1853)
|
2 years ago |
|
Charlie.Wei
|
6b57e4e0ff
|
Fix chitchat lost context (#1828)
Co-authored-by: luowei <glpat-EjySCyNjWiLqAED-YmwM>
Co-authored-by: crazywoola <427733928@qq.com>
Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>
|
2 years ago |
Bannings
|
0b7e0cadc0
|
Fix Azure OpenAI Provider BASE_MODELS (#1813)
Co-authored-by: xifan <xifan@gaoding.com>
|
2 years ago |
|
Charlie.Wei
|
64642fabc4
|
Parse base64 eml file (#1796)
Co-authored-by: luowei <glpat-EjySCyNjWiLqAED-YmwM>
Co-authored-by: crazywoola <427733928@qq.com>
Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>
|
2 years ago |
|
Jyong
|
df1509983c
|
ppt & pptx improve (#1790)
Co-authored-by: jyong <jyong@dify.ai>
|
2 years ago |
|
Jyong
|
5e34f938c1
|
Feat/add unstructured support (#1780)
Co-authored-by: jyong <jyong@dify.ai>
|
2 years ago |
|
Jyong
|
2fd56cb01c
|
Fix/vdb index issue (#1776)
Co-authored-by: jyong <jyong@dify.ai>
|
2 years ago |
|
Jyong
|
ebc2cdad2e
|
fix annotation query exception (#1771)
Co-authored-by: jyong <jyong@dify.ai>
|
2 years ago |
zxhlyh
|
5bb841935e
|
feat: custom webapp logo (#1766)
|
2 years ago |
|
Jyong
|
a71f2863ac
|
Annotation management (#1767)
Co-authored-by: jyong <jyong@dify.ai>
|
2 years ago |
Qiwen Tong
|
c09184fd94
|
update bm25 search properties (#1758)
Co-authored-by: Blade <zhangxiaobin@unixyz.cn>
|
2 years ago |
|
Charlie.Wei
|
b0d8d196e1
|
azure openai add gpt-4-1106-preview、gpt-4-vision-preview models (#1751)
Co-authored-by: luowei <glpat-EjySCyNjWiLqAED-YmwM>
Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>
|
2 years ago |
|
Garfield Dai
|
6b499b9a16
|
remove stripe and anthropic. (#1746)
|
2 years ago |
|
Jyong
|
d5695b3170
|
check rerank document is not empty (#1740)
Co-authored-by: jyong <jyong@dify.ai>
|
2 years ago |
|
crazywoola
|
994fceece3
|
fix: qa regex (#1738)
|
2 years ago |
|
Jyong
|
8c451eb0e6
|
fix only full text search in app issue (#1736)
Co-authored-by: jyong <jyong@dify.ai>
|
2 years ago |
Pascal M
|
bc54cdc537
|
refactor: typo in dataset docstore (#1711)
|
2 years ago |
|
Pascal M
|
5d10cf0fe6
|
fix: error Class 'builtins.list' is not mapped (#1710)
|
2 years ago |
|
Yeuoly
|
d3a2c0ed34
|
fix wrong syntax of type definitions (#1678)
|
2 years ago |
Wen O.Y
|
a1cd043fdc
|
fix: Incorrect order of embedded documents in CacheEmbedding (#1671)
|
2 years ago |
WangBooth
|
22bc9ddc73
|
Hotfix/fix documents index mismatch error in rerank (#1662)
Co-authored-by: baomi.wbm <baomi.wbm@dtwave-inc.com>
|
2 years ago |
|
zxhlyh
|
451af66be0
|
feat: add jina embedding (#1647)
Co-authored-by: takatost <takatost@gmail.com>
|
2 years ago |
|
WangBooth
|
53be4d2712
|
fix #1637 (#1638)
Co-authored-by: baomi.wbm <baomi.wbm@dtwave-inc.com>
|
2 years ago |
|
Jyong
|
74b2260ba6
|
fix score_threshold_enabled name (#1626)
Co-authored-by: jyong <jyong@dify.ai>
|
2 years ago |
|
takatost
|
93467cb363
|
fix: dataset tool missing in n-to-1 retrieve mode (#1617)
|
2 years ago |
|
takatost
|
ea526d0822
|
feat: chatglm3 support (#1616)
|
2 years ago |
|
takatost
|
0e627c920f
|
feat: xinference rerank model support (#1615)
|
2 years ago |
|
Jyong
|
a5b80c9d1f
|
Fix/multi thread parameter (#1604)
|
2 years ago |
|
Jyong
|
f704094a5f
|
fix hybrid search when document is none (#1603)
Co-authored-by: jyong <jyong@dify.ai>
|
2 years ago |
|
Jyong
|
b930716745
|
fix weaviate hybrid search issue (#1600)
Co-authored-by: jyong <jyong@dify.ai>
|
2 years ago |
|
takatost
|
4a55d5729d
|
feat: add anthropic claude-2.1 support (#1591)
|
2 years ago |
|
takatost
|
c9368925a3
|
feat: add `supported_model_types` field and filter in provider list (#1581)
|
2 years ago |
|
Jyong
|
0d9ce1bab0
|
fix multi retrieval with resource score issue (#1578)
Co-authored-by: jyong <jyong@dify.ai>
|
2 years ago |
|
Jyong
|
0e08526428
|
fix hybrid search reranking check (#1563)
Co-authored-by: jyong <jyong@dify.ai>
|
2 years ago |
|
Jyong
|
4588831bff
|
Feat/add retriever rerank (#1560)
Co-authored-by: jyong <jyong@dify.ai>
|
2 years ago |
|
takatost
|
d654770732
|
feat: supports for new version of openllm (#1554)
|
2 years ago |
|
Garfield Dai
|
8835435558
|
fix: change model mode. (#1520)
|
2 years ago |
|
takatost
|
41d0a8b295
|
feat: [backend] vision support (#1510)
Co-authored-by: Garfield Dai <dai.hai@foxmail.com>
|
2 years ago |
|
crazywoola
|
d0e1ea8f06
|
1506 remove duplicated code (#1511)
|
2 years ago |
|
takatost
|
9de67c586f
|
feat: update free plan rules of spark (#1515)
|
2 years ago |
|
takatost
|
d7ae86799c
|
feat: support basic feature of OpenAI new models (#1476)
|
2 years ago |
|
takatost
|
059c089f93
|
fix: external data tool batch retrieve bug (#1472)
|
2 years ago |
|
Garfield Dai
|
db43ed6f41
|
feat: add api-based extension & external data tool & moderation backend (#1403)
Co-authored-by: takatost <takatost@gmail.com>
|
2 years ago |
|
takatost
|
4dfbcd0b4e
|
feat: support chatglm_turbo model #1443 (#1460)
|
2 years ago |
|
takatost
|
076f3289d2
|
feat: add spark v3.0 llm support (#1434)
|
2 years ago |
|
takatost
|
e122d677ad
|
fix: return wrong when init 0 quota in trial provider (#1394)
|
2 years ago |
|
takatost
|
4c63cbf5b1
|
feat: adjust anthropic (#1387)
|
2 years ago |
|
Garfield Dai
|
fe14130b3c
|
refactor advanced prompt core. (#1350)
|
2 years ago |
wayne.wang
|
52ebffa857
|
fix: app config zhipu chatglm_std model, but it still use chatglm_lit… (#1377)
Co-authored-by: wayne.wang <wayne.wang@beibei.com>
|
2 years ago |
|
takatost
|
7c9b585a47
|
feat: support weixin ernie-bot-4 and chat mode (#1375)
|
2 years ago |
|
takatost
|
07285e5f8b
|
feat: optimize completion model agent (#1364)
|
2 years ago |
|
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>
|
2 years ago |
|
Jyong
|
07aab5e868
|
Feat/add milvus vector db (#1302)
Co-authored-by: jyong <jyong@dify.ai>
|
2 years ago |
|
takatost
|
875dfbbf0e
|
fix: openllm completion start with prompt, remove it (#1303)
|
2 years ago |
|
takatost
|
8480b0197b
|
fix: prompt for baichuan text generation models (#1299)
|
2 years ago |
|
takatost
|
4ab4bcc074
|
feat: support openllm embedding (#1293)
|
2 years ago |
|
takatost
|
1d4f019de4
|
feat: add baichuan llm support (#1294)
Co-authored-by: zxhlyh <jasonapring2015@outlook.com>
|
2 years ago |
|
takatost
|
024250803a
|
feat: move login_required wrapper outside (#1281)
|
2 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 |
|
takatost
|
9adbeadeec
|
feat: claude paid optimize (#890)
|
3 years ago |
|
takatost
|
2f7b234cc5
|
fix: max token not exist in generate summary when calc rest tokens (#891)
|
3 years ago |
|
takatost
|
0cc0b6e052
|
fix: error raise status code not exist (#888)
|
3 years ago |
|
takatost
|
f42e7d1a61
|
feat: add spark v2 support (#885)
|
3 years ago |
|
takatost
|
c4d759dfba
|
fix: wenxin error not raise when stream mode (#884)
|
3 years ago |
|
takatost
|
39574dcf6b
|
feat: optimize prompt of suggested_questions_after_answer (#881)
|
3 years ago |
|
takatost
|
cc2d71c253
|
feat: optimize override app model config convert (#874)
|
3 years ago |
|
takatost
|
2dfb3e95f6
|
feat: optimize error record in agent (#869)
|
3 years ago |
|
Jyong
|
f207e180df
|
fix multi thread app context (#868)
Co-authored-by: jyong <jyong@dify.ai>
|
3 years ago |
|
takatost
|
948d64bbef
|
fix: get_num_tokens_from_messages params error (#866)
|
3 years ago |
|
takatost
|
7a8590980e
|
fix: dataset direct output (#860)
|
3 years ago |
|
takatost
|
e8c14bb732
|
feat: rename title in site both rename name in app (#857)
|
3 years ago |
|
takatost
|
cc52cdc2a9
|
Feat/add free provider apply (#829)
|
3 years ago |
|
takatost
|
8e15ba6cd6
|
Fix/no trial provider (#823)
|
3 years ago |
|
takatost
|
7898937eae
|
feat: optimize message return (#822)
|
3 years ago |
|
takatost
|
1bd0a76a20
|
feat: optimize error raise (#820)
|
3 years ago |
|
takatost
|
2f179d61dc
|
fix: completion error when dataset was deleted (#819)
|
3 years ago |
|
takatost
|
f18ce203b5
|
feat: optimize error logging (#808)
|
3 years ago |
|
takatost
|
b81b8637ec
|
feat: temp remove paid option of anthropic (#807)
|
3 years ago |
|
takatost
|
5fa2161b05
|
feat: server multi models support (#799)
|
3 years ago |
lixiaoyin
|
cc277227ad
|
fix i is not incremented due to violating the uniqueness constraint w… (#771)
Co-authored-by: 李啸吟 <746963140@qq.com>
|
3 years ago |
Matri
|
dfe10e9dfe
|
fix: generate_more_like_this function issue (#722)
|
3 years ago |
|
takatost
|
654985177f
|
fix: segment resort in dataset retrieve by index_node_id_to_position (#721)
|
3 years ago |
|
takatost
|
e18211ffea
|
feat: fix azure completion choices return empty (#708)
|
3 years ago |
|
Jyong
|
fa73aa8dbf
|
add embedding max retries (#699)
|
3 years ago |
|
Jyong
|
174ebb51db
|
add qa thread control (#677)
|
3 years ago |
|
John Wang
|
626c78a690
|
fix: agent parse result error (#676)
|
3 years ago |
|
Jyong
|
9eaae770a6
|
Feat/add thread control (#675)
|
3 years ago |
|
Jyong
|
ca60610306
|
logging qa error (#672)
|
3 years ago |
|
Jyong
|
082f8b17ab
|
Feat/milvus support (#671)
Co-authored-by: StyleZhang <jasonapring2015@outlook.com>
Co-authored-by: JzoNg <jzongcode@gmail.com>
|
3 years ago |
KVOJJJin
|
cf93d8d6e2
|
Feat: Q&A format segmentation support (#668)
Co-authored-by: jyong <718720800@qq.com>
Co-authored-by: StyleZhang <jasonapring2015@outlook.com>
|
3 years ago |
|
John Wang
|
aae2fb8a30
|
fix: dataset retrieve npe when dataset desc is null (#669)
|
3 years ago |
|
John Wang
|
d979955c8a
|
feat: optimize current time (#661)
|
3 years ago |
|
John Wang
|
b5825142d1
|
feat: add current time tool in universal chat agent (#659)
|
3 years ago |
|
John Wang
|
ba3dc8cae0
|
feat: fix dataset retrieve agent llm not support error (#656)
|
3 years ago |
|
John Wang
|
4fdb37771a
|
feat: universal chat in explore (#649)
Co-authored-by: StyleZhang <jasonapring2015@outlook.com>
|
3 years ago |
|
John Wang
|
e9810a6df2
|
fix: azure openai embedding model name error (#612)
|
3 years ago |
|
John Wang
|
cae15013e0
|
fix: azure openai deployment list was deprecated suddenly (#611)
|
3 years ago |
|
John Wang
|
eff115267f
|
fix: anthropic completion error in blocking mode (#591)
|
3 years ago |
|
John Wang
|
0d3cd3b16a
|
fix: azure provider select error when use custom azure provider (#587)
|
3 years ago |
|
John Wang
|
3dc82fb044
|
feat: remove davinci required model from azure provider (#586)
|
3 years ago |
|
John Wang
|
7599f79a17
|
feat: claude api support (#572)
|
3 years ago |
|
zxhlyh
|
a03a92e9db
|
Feat/chat support voice input (#532)
|
3 years ago |
|
John Wang
|
6eee7cb42c
|
feat: fix azure embedding Too many inputs problem (#530)
|
3 years ago |
|
John Wang
|
b9b0866a46
|
fix: generate summary error when tokens=4097 (#488)
|
3 years ago |
|
John Wang
|
df68a7c82b
|
feat: Optimize the quality of the title generate (#484)
|
3 years ago |
|
John Wang
|
9d98669e7d
|
fix: dataset destination error (#477)
|
3 years ago |
|
John Wang
|
408fbb0c70
|
fix: title, summary, suggested questions generate (#476)
|
3 years ago |
|
crazywoola
|
998f819b04
|
use sub to operate all (#475)
|
3 years ago |
|
Jyong
|
334f46d0b6
|
Fix/json format (#466)
|
3 years ago |
|
Jyong
|
2eea114ac0
|
fix special code (#473)
|
3 years ago |
|
Jyong
|
c67ecff3fe
|
Fix/json format (#465)
|
3 years ago |
|
John Wang
|
d5b42c09ee
|
fix: template parse error when history include {{any}} (#463)
|
3 years ago |
|
John Wang
|
835bf9fd8d
|
fix: template parse error when pre prompt include {{}} (#462)
|
3 years ago |
|
John Wang
|
c720f831af
|
feat: optimize template parse (#460)
|
3 years ago |
|
John Wang
|
df5763be37
|
feat: optimize openai error raise (#459)
|
3 years ago |
|
John Wang
|
cad1532f7c
|
feat: optimize index_struct copy (#442)
|
3 years ago |
|
John Wang
|
951afcaaed
|
feat: optimize weaviate error msg (#441)
|
3 years ago |
|
John Wang
|
3241e4015b
|
feat: upgrade langchain (#430)
Co-authored-by: jyong <718720800@qq.com>
|
3 years ago |
lisaifei@cvte.com
|
23ef2262bd
|
fix: filter empty value in xlsx to improve vector similarity hit (#422)
|
3 years ago |
|
Jyong
|
36dc05c4da
|
fix chinese encoding (#411)
|
3 years ago |
|
Jyong
|
226f28edcb
|
Feature/self host notion import (#397)
|
3 years ago |
|
Jyong
|
9253f72dea
|
Feat/dataset notion import (#392)
Co-authored-by: StyleZhang <jasonapring2015@outlook.com>
Co-authored-by: JzoNg <jzongcode@gmail.com>
|
3 years ago |
|
John Wang
|
184afa69ff
|
feat: add gpt-3.5-turbo-16k support and update openai gpt-3.5-turbo & Embedding Ada v2 unit price (#358)
|
3 years ago |
|
John Wang
|
ab115b5f87
|
fix: completion stop invalid (#355)
|
3 years ago |
|
John Wang
|
a11f36ca60
|
fix: stop completion response not save to db (#351)
|
3 years ago |
|
John Wang
|
cd136fb293
|
feat: add WEAVIATE_BATCH_SIZE (#349)
|
3 years ago |
|
John Wang
|
6a3ab36101
|
feat: optimize weaviate batch size (#348)
|
3 years ago |
|
Jyong
|
3d14431b96
|
Fix/excel data format (#334)
|
3 years ago |
lisaifei@cvte.com
|
0abd67288b
|
feat: support xlsx file parsing (#304)
Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>
|
3 years ago |
|
Jyong
|
2bf48514bc
|
fix markdown parser (#230)
|
3 years ago |
|
John Wang
|
a3ee037d6d
|
feat: optimize output parse failed error (#298)
|
3 years ago |
|
John Wang
|
490858a4d5
|
feat: auto rule generator (#273)
|
3 years ago |
|
John Wang
|
44a1aa5e44
|
fix: dataset_tool npe (#274)
|
3 years ago |
|
John Wang
|
75f7a96025
|
feat: ignore validate failed error log (#256)
|
3 years ago |
|
John Wang
|
5ca88a4fd9
|
fix: raw json parse in llm router chain (#254)
|
3 years ago |
|
John Wang
|
bb7f454ecd
|
fix: dataset desc npe (#246)
|
3 years ago |
|
John Wang
|
7f48fadd41
|
fix: prompt template parantheses select error (#244)
|
3 years ago |
|
John Wang
|
af2138e8b8
|
fix: json parse in router chain output (#243)
|
3 years ago |
|
John Wang
|
88545184be
|
feat: support multi datasets router chain mode (#231)
|
3 years ago |
|
John Wang
|
2c23caacd4
|
fix: introduction key error (#221)
|
3 years ago |
|
John Wang
|
1a5acf43aa
|
Fix/shared lock (#210)
|
3 years ago |
|
John Wang
|
d93365d429
|
fix: azure embedding not support batch (#188)
|
3 years ago |
|
John Wang
|
4350bb9a00
|
Fix/human in answer (#174)
|
3 years ago |
|
John Wang
|
056898bf21
|
fix: quota update error on azure openai (#172)
|
3 years ago |
|
John Wang
|
6da5e54180
|
Feat/open azure validate (#163)
|
3 years ago |
|
John Wang
|
f3219ff107
|
fix: template string in template error (#162)
|
3 years ago |
|
John Wang
|
219011b62a
|
fix: disable template string in query (#160)
|
3 years ago |
|
John Wang
|
90150a6ca9
|
Feat/optimize chat prompt (#158)
|
3 years ago |
|
John Wang
|
9a5ae9f51f
|
Feat: optimize error desc (#152)
|
3 years ago |
|
John Wang
|
54a6571462
|
fix: extra input for opening statement was not suitable for prompt (#143)
|
3 years ago |
|
John Wang
|
b42cd38cc9
|
fix: internal error when user is none in service api call (#129)
|
3 years ago |
|
John Wang
|
e8e8f9e97d
|
Fix: move pre prompt to user massasge in chat mode (#126)
|
3 years ago |
|
John Wang
|
1b6e3ef964
|
Feat: optimize inner prompt (#121)
|
3 years ago |
|
John Wang
|
8fc2663693
|
fix: weaviate batch insert timeout (#108)
|
3 years ago |
|
John Wang
|
f68b05d5ec
|
Feat: support azure openai for temporary (#101)
|
3 years ago |
|
John Wang
|
0587ff0fba
|
fix: remove empty segment in splitter (#68)
|
3 years ago |
|
John Wang
|
815f794eef
|
feat: optimize split rule when use custom split segment identifier (#35)
|
3 years ago |
|
John Wang
|
f5b2271c8c
|
fix: import wrong user (#32)
|
3 years ago |
John Wang
|
db896255d6
|
Initial commit
|
3 years ago |