Commit Graph

401 Commits

Author SHA1 Message Date
Garfield Dai
fe14130b3c
refactor advanced prompt core. (#1350) 2023-10-18 20:02:52 +08:00
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>
2023-10-18 05:07:36 -05:00
takatost
7c9b585a47
feat: support weixin ernie-bot-4 and chat mode (#1375) 2023-10-18 02:35:24 -05:00
takatost
c039f4af83
fix: app model config detached in completion thread (#1366) 2023-10-17 08:18:08 -05:00
takatost
07285e5f8b
feat: optimize completion model agent (#1364) 2023-10-17 06:54:59 -05:00
takatost
2feb16d957
feat: bump version to 0.3.28 (#1349) 2023-10-14 11:49:56 -05:00
Garfield Dai
695841a3cf
Feat/advanced prompt enhancement (#1340) 2023-10-13 16:47:01 +08:00
takatost
3efaa713da
feat: use xinference client instead of xinference (#1339) 2023-10-13 02:46:09 -05:00
takatost
9822f687f7
fix: max tokens of OpenAI gpt-3.5-turbo-instruct to 4097 (#1338) 2023-10-13 02:07:07 -05:00
Charlie.Wei
298ad6782d
Add Message Suggested Api (#1326)
Co-authored-by: luowei <glpat-EjySCyNjWiLqAED-YmwM>
2023-10-13 14:07:32 +08:00
takatost
f4be2b8bcd
fix: raise error in minimax stream generate (#1336) 2023-10-12 23:48:28 -05:00
takatost
7dea485d57
feat: bump version to 0.3.27 (#1331) 2023-10-12 10:37:48 -05:00
Garfield Dai
42a5b3ec17
feat: advanced prompt backend (#1301)
Co-authored-by: takatost <takatost@gmail.com>
2023-10-12 10:13:10 -05:00
takatost
2d1cb076c6
fix: dataset segment not exist return agent response (#1329) 2023-10-12 04:40:20 -05:00
Jyong
289c93d081
Feat/improve document delete logic (#1325)
Co-authored-by: jyong <jyong@dify.ai>
2023-10-12 13:30:44 +08:00
takatost
9cba1c8bf4
fix: retriever_resource missing (#1317) 2023-10-11 14:37:11 -05:00
takatost
cbf095465c
feat: remove llm client use (#1316) 2023-10-11 14:02:53 -05:00
takatost
ff493d017b
fix: minimax tests (#1313) 2023-10-11 07:49:26 -05:00
Jyong
7f6ad9653e
Fix/grpc gevent compatible (#1314)
Co-authored-by: jyong <jyong@dify.ai>
2023-10-11 20:48:35 +08:00
takatost
2851a9f04e
feat: optimize minimax llm call (#1312) 2023-10-11 07:17:41 -05:00
takatost
c536f85b2e
fix: compatibility issues with the tongyi model. (#1310) 2023-10-11 05:16:26 -05:00
takatost
b1352ff8b7
feat: using random sampling to check if it violates the review mechan… (#1308) 2023-10-11 04:11:20 -05:00
Jyong
cc63c8499f
bump version to 0.3.26 (#1307)
Co-authored-by: jyong <jyong@dify.ai>
2023-10-11 16:11:24 +08:00
Jyong
f191b8b8d1
milvus docker compose env (#1306)
Co-authored-by: jyong <jyong@dify.ai>
2023-10-11 16:05:37 +08:00
Jyong
5003db987d
milvus secure check fix (#1305)
Co-authored-by: jyong <jyong@dify.ai>
2023-10-11 13:11:06 +08:00
Jyong
07aab5e868
Feat/add milvus vector db (#1302)
Co-authored-by: jyong <jyong@dify.ai>
2023-10-10 21:56:24 +08:00
takatost
875dfbbf0e
fix: openllm completion start with prompt, remove it (#1303) 2023-10-10 04:44:19 -05:00
Charlie.Wei
9e7efa45d4
document segmentApi Add get&update&delete operate (#1285)
Co-authored-by: luowei <glpat-EjySCyNjWiLqAED-YmwM>
2023-10-10 13:27:06 +08:00
takatost
8bf892b306
feat: bump version to 0.3.25 (#1300) 2023-10-10 13:03:49 +08:00
takatost
8480b0197b
fix: prompt for baichuan text generation models (#1299) 2023-10-10 13:01:18 +08:00
takatost
4ab4bcc074
feat: support openllm embedding (#1293) 2023-10-09 23:09:35 -05:00
takatost
1d4f019de4
feat: add baichuan llm support (#1294)
Co-authored-by: zxhlyh <jasonapring2015@outlook.com>
2023-10-09 23:09:26 -05:00
takatost
677aacc8e3
feat: upgrade xinference client to 0.5.2 (#1292) 2023-10-09 08:12:58 -05:00
takatost
fda937175d
feat: qdrant support in docker compose (#1286) 2023-10-08 12:04:04 -05:00
takatost
024250803a
feat: move login_required wrapper outside (#1281) 2023-10-08 05:21:32 -05:00
takatost
373e90ee6d
fix: detached model in completion thread (#1269) 2023-10-02 22:27:25 +08:00
takatost
41d4c5b424
fix: count down thread in completion db not commit (#1267) 2023-10-02 10:19:26 +08:00
takatost
86a9dea428
fix: db not commit when streaming output (#1266) 2023-10-01 16:41:52 +08:00
takatost
8606d80c66
fix: request timeout when openai completion (#1265) 2023-10-01 16:00:23 +08:00
takatost
5bffa1d918
feat: bump version to 0.3.24 (#1262) 2023-09-28 18:32:06 +08:00
zxhlyh
c9b0fe47bf
Fix/notion sync (#1258) 2023-09-28 14:39:13 +08:00
Jyong
5e511e01bf
Fix/dataset api key delete (#1255)
Co-authored-by: jyong <jyong@dify.ai>
2023-09-28 10:41:41 +08:00
takatost
a31466d34e
fix: db session not commit before long llm call running (#1251) 2023-09-27 21:40:26 +08:00
takatost
d38eac959b
fix: wenxin model name invalid when llm call (#1248) 2023-09-27 16:29:13 +08:00
Jyong
46154c6705
Feat/dataset service api (#1245)
Co-authored-by: jyong <jyong@dify.ai>
Co-authored-by: StyleZhang <jasonapring2015@outlook.com>
2023-09-27 16:06:32 +08:00
Garfield Dai
54ff03c35d
fix: dataset query error. (#1244) 2023-09-27 15:24:54 +08:00
Garfield Dai
18c710c906
feat: support binding context var (#1227)
Co-authored-by: Joel <iamjoel007@gmail.com>
2023-09-27 14:53:22 +08:00
zxhlyh
227f9fb77d
Feat/api jwt (#1212) 2023-09-25 12:49:16 +08:00
Jyong
724e053732
Fix/qdrant data issue (#1203)
Co-authored-by: jyong <jyong@dify.ai>
2023-09-22 14:21:26 +08:00
Garfield Dai
e409895c02
Feat/huggingface embedding support (#1211)
Co-authored-by: StyleZhang <jasonapring2015@outlook.com>
2023-09-22 13:59:02 +08:00
takatost
32d9b6181c
fix: transaction not commit during long LLM calls (#1213) 2023-09-22 12:43:06 +08:00
takatost
2b018fade2
fix: transaction hangs due to message commit block during long LLM calls (#1206) 2023-09-21 11:22:10 +08:00
takatost
5809edd74b
feat: bump version to 0.3.23 (#1198) 2023-09-20 00:14:36 +08:00
takatost
435f804c6f
fix: gpt-3.5-turbo-instruct context size to 8192 (#1196) 2023-09-19 02:10:22 +08:00
takatost
ae3f1ac0a9
feat: support gpt-3.5-turbo-instruct model (#1195) 2023-09-19 02:05:04 +08:00
Jyong
269a465fc4
Feat/improve vector database logic (#1193)
Co-authored-by: jyong <jyong@dify.ai>
2023-09-18 18:15:41 +08:00
takatost
827c97f0d3
feat: add zhipuai (#1188) 2023-09-18 17:32:31 +08:00
takatost
c8bd76cd66
fix: inference embedding validate (#1187) 2023-09-16 03:09:36 +08:00
charli117
20bab6edec
Restore the application template (#1174)
Co-authored-by: luowei <glpat-EjySCyNjWiLqAED-YmwM>
2023-09-14 08:28:32 -05:00
charli117
67bed54f32
Mermaid front end rendering (#1166)
Co-authored-by: luowei <glpat-EjySCyNjWiLqAED-YmwM>
2023-09-14 14:09:23 +08:00
Matri
fc68c81791
fix: correct invite url (#1173) 2023-09-14 12:07:34 +08:00
Jyong
5d9070bc60
Feat/add blocking mode resource return (#1171)
Co-authored-by: jyong <jyong@dify.ai>
2023-09-13 18:53:35 +08:00
takatost
f9082104ed
feat: add hosted moderation (#1158) 2023-09-12 10:26:12 +08:00
takatost
983834cd52
feat: spark check (#1134) 2023-09-11 17:31:03 +08:00
takatost
24cb992843
feat: bump version to 0.3.22 (#1153) 2023-09-11 12:04:06 +08:00
Jyong
642842d61b
Feat:dataset retiever resource (#1123)
Co-authored-by: jyong <jyong@dify.ai>
Co-authored-by: StyleZhang <jasonapring2015@outlook.com>
2023-09-10 15:17:43 +08:00
KVOJJJin
e161c511af
Feat:csv & docx support (#1139)
Co-authored-by: jyong <jyong@dify.ai>
2023-09-10 15:17:22 +08:00
takatost
f29e82685e
feat: bump version to 0.3.21 (#1145) 2023-09-10 12:34:54 +08:00
takatost
3a5ae96e7b
fix: TRANSFORMERS_OFFLINE orders in Dockerfile (#1144) 2023-09-10 12:26:13 +08:00
takatost
b63a685386
feat: set transformers offline default true (#1143) 2023-09-10 12:20:58 +08:00
takatost
877da82b06
feat: cache huggingface gpt2 tokenizer files (#1138) 2023-09-10 12:16:21 +08:00
Joel
2d5ad0d208
feat: support optional query content (#1097)
Co-authored-by: Garfield Dai <dai.hai@foxmail.com>
2023-09-10 00:12:34 +08:00
takatost
1ade70aa1e
feat: bump version to 0.3.20 (#1135) 2023-09-09 23:47:14 +08:00
takatost
2658c4d57b
fix: answer returned null when response_mode was blocking (#1133) 2023-09-09 23:22:21 +08:00
takatost
6effcd3755
feat: optimize celery start cmd (#1129) 2023-09-09 13:48:29 +08:00
takatost
c4d8bdc3db
fix: hf hosted inference check (#1128) 2023-09-09 00:29:48 +08:00
Matri
a5d21f3b09
fix: shortening invite url (#1100)
Co-authored-by: MatriQi <matri@aifi.io>
2023-09-07 17:15:57 +08:00
takatost
a7cdb745c1
feat: support spark v2 validate (#1086) 2023-09-01 20:53:32 +08:00
takatost
73c86ee6a0
fix: prompt of title generation (#1084) 2023-09-01 14:55:58 +08:00
takatost
48eb590065
feat: optimize last_active_at update (#1083) 2023-09-01 13:58:26 +08:00
takatost
33562a9d8d
feat: optimize prompt (#1080) 2023-09-01 11:46:06 +08:00
Rhon Joe
c9194ba382
chore(api): api image multistage build (#1069) 2023-09-01 11:13:22 +08:00
takatost
a199fa6388
feat: optimize high load sql query of document segment (#1078) 2023-09-01 10:52:39 +08:00
takatost
4c8608dc61
feat: optimize conversation title generation output must be a valid JSON (#1077) 2023-09-01 10:31:42 +08:00
takatost
df6604a734
feat: optimize generation of conversation title (#1075) 2023-09-01 02:28:37 +08:00
takatost
1ca86cf9ce
feat: bump version to 0.3.19 (#1074) 2023-08-31 21:42:58 +08:00
takatost
78e26f8b75
fix: summary no docs (#1073) 2023-08-31 20:19:26 +08:00
takatost
2191312bb9
fix: segments query missing idx hit (#1072) 2023-08-31 19:39:44 +08:00
takatost
fcc6b41ab7
feat: decrease claude model request time by set max top_k to 10 (#1071) 2023-08-31 18:23:44 +08:00
takatost
d75e8aeafa
feat: disable anthropic retry (#1067) 2023-08-31 16:44:46 +08:00
takatost
2eba98a465
feat: optimize anthropic connection pool (#1066) 2023-08-31 16:18:59 +08:00
takatost
a7a7aab7a0
fix: csv import error (#1063) 2023-08-31 15:42:28 +08:00
crazywoola
86bfbb47d5
chore: doc issue (#1062) 2023-08-31 14:54:16 +08:00
yezhwi
d33a269548
refactor(file extractor): file extractor (#1059) 2023-08-31 14:45:31 +08:00
Matri
d3f8ea2df0
Feat/support to invite multiple users (#1011) 2023-08-31 01:18:31 +08:00
Jyong
7df56ed617
fix error weaviate vector (#1058)
Co-authored-by: jyong <jyong@dify.ai>
2023-08-30 20:34:17 +08:00
KVOJJJin
c67f345d0e
Fix: disable operations of dataset when embedding unavailable (#1055)
Co-authored-by: jyong <jyong@dify.ai>
2023-08-30 17:27:19 +08:00
yezhwi
8b8e510bfe
fix: handle AttributeError for datasets and index (#1052) 2023-08-30 11:14:16 +08:00
takatost
417c19577a
feat: add LocalAI local embedding model support (#1021)
Co-authored-by: StyleZhang <jasonapring2015@outlook.com>
2023-08-29 22:22:02 +08:00
Jyong
b5953039de
recreate qdrant vector (#1049)
Co-authored-by: jyong <jyong@dify.ai>
2023-08-29 15:00:36 +08:00