Commit Graph

1541 Commits

Author SHA1 Message Date
Qiwen Tong
c09184fd94
update bm25 search properties (#1758)
Co-authored-by: Blade <zhangxiaobin@unixyz.cn>
2023-12-15 12:28:03 +08:00
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>
2023-12-14 09:55:30 +08:00
Garfield Dai
6b499b9a16
remove stripe and anthropic. (#1746) 2023-12-12 17:59:07 +08:00
Jyong
d5695b3170
check rerank document is not empty (#1740)
Co-authored-by: jyong <jyong@dify.ai>
2023-12-11 16:12:11 +08:00
crazywoola
994fceece3
fix: qa regex (#1738) 2023-12-11 15:53:37 +08:00
Jyong
8c451eb0e6
fix only full text search in app issue (#1736)
Co-authored-by: jyong <jyong@dify.ai>
2023-12-11 15:34:29 +08:00
Pascal M
bc54cdc537
refactor: typo in dataset docstore (#1711) 2023-12-07 09:24:52 +08:00
Pascal M
5d10cf0fe6
fix: error Class 'builtins.list' is not mapped (#1710) 2023-12-07 09:24:39 +08:00
Yeuoly
d3a2c0ed34
fix wrong syntax of type definitions (#1678) 2023-12-03 20:59:13 +08:00
Wen O.Y
a1cd043fdc
fix: Incorrect order of embedded documents in CacheEmbedding (#1671) 2023-12-03 19:07:00 +08:00
WangBooth
22bc9ddc73
Hotfix/fix documents index mismatch error in rerank (#1662)
Co-authored-by: baomi.wbm <baomi.wbm@dtwave-inc.com>
2023-11-30 22:03:20 +08:00
zxhlyh
451af66be0
feat: add jina embedding (#1647)
Co-authored-by: takatost <takatost@gmail.com>
2023-11-29 14:58:11 +08:00
WangBooth
53be4d2712
fix #1637 (#1638)
Co-authored-by: baomi.wbm <baomi.wbm@dtwave-inc.com>
2023-11-28 20:05:50 +08:00
Jyong
74b2260ba6
fix score_threshold_enabled name (#1626)
Co-authored-by: jyong <jyong@dify.ai>
2023-11-27 15:34:45 +08:00
takatost
93467cb363
fix: dataset tool missing in n-to-1 retrieve mode (#1617) 2023-11-25 16:04:22 +08:00
takatost
ea526d0822
feat: chatglm3 support (#1616) 2023-11-25 15:37:07 +08:00
takatost
0e627c920f
feat: xinference rerank model support (#1615) 2023-11-25 03:56:00 +08:00
Jyong
a5b80c9d1f
Fix/multi thread parameter (#1604) 2023-11-22 18:31:29 +08:00
Jyong
f704094a5f
fix hybrid search when document is none (#1603)
Co-authored-by: jyong <jyong@dify.ai>
2023-11-22 17:53:42 +08:00
Jyong
b930716745
fix weaviate hybrid search issue (#1600)
Co-authored-by: jyong <jyong@dify.ai>
2023-11-22 16:41:20 +08:00
takatost
4a55d5729d
feat: add anthropic claude-2.1 support (#1591) 2023-11-22 01:46:19 +08:00
takatost
c9368925a3
feat: add supported_model_types field and filter in provider list (#1581) 2023-11-21 15:06:47 +08:00
Jyong
0d9ce1bab0
fix multi retrieval with resource score issue (#1578)
Co-authored-by: jyong <jyong@dify.ai>
2023-11-21 13:47:55 +08:00
Jyong
0e08526428
fix hybrid search reranking check (#1563)
Co-authored-by: jyong <jyong@dify.ai>
2023-11-18 17:06:28 +08:00
Jyong
4588831bff
Feat/add retriever rerank (#1560)
Co-authored-by: jyong <jyong@dify.ai>
2023-11-17 22:13:37 +08:00
takatost
d654770732
feat: supports for new version of openllm (#1554) 2023-11-17 14:07:36 +08:00
Garfield Dai
8835435558
fix: change model mode. (#1520) 2023-11-13 23:13:01 +08:00
takatost
41d0a8b295
feat: [backend] vision support (#1510)
Co-authored-by: Garfield Dai <dai.hai@foxmail.com>
2023-11-13 22:05:46 +08:00
crazywoola
d0e1ea8f06
1506 remove duplicated code (#1511) 2023-11-13 19:05:32 +08:00
takatost
9de67c586f
feat: update free plan rules of spark (#1515) 2023-11-13 17:00:36 +08:00
takatost
d7ae86799c
feat: support basic feature of OpenAI new models (#1476) 2023-11-07 04:05:59 -06:00
takatost
059c089f93
fix: external data tool batch retrieve bug (#1472) 2023-11-07 01:28:22 -06:00
Garfield Dai
db43ed6f41
feat: add api-based extension & external data tool & moderation backend (#1403)
Co-authored-by: takatost <takatost@gmail.com>
2023-11-06 19:36:16 +08:00
takatost
4dfbcd0b4e
feat: support chatglm_turbo model #1443 (#1460) 2023-11-06 04:33:05 -06:00
takatost
076f3289d2
feat: add spark v3.0 llm support (#1434) 2023-10-31 03:13:11 -05:00
takatost
e122d677ad
fix: return wrong when init 0 quota in trial provider (#1394) 2023-10-21 14:02:38 -05:00
takatost
4c63cbf5b1
feat: adjust anthropic (#1387) 2023-10-20 02:27:46 -05:00
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
07285e5f8b
feat: optimize completion model agent (#1364) 2023-10-17 06:54:59 -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
takatost
f4be2b8bcd
fix: raise error in minimax stream generate (#1336) 2023-10-12 23:48:28 -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
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
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
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
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
8606d80c66
fix: request timeout when openai completion (#1265) 2023-10-01 16:00:23 +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
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
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
takatost
f9082104ed
feat: add hosted moderation (#1158) 2023-09-12 10:26:12 +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
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
c4d8bdc3db
fix: hf hosted inference check (#1128) 2023-09-09 00:29:48 +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
33562a9d8d
feat: optimize prompt (#1080) 2023-09-01 11:46:06 +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
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
yezhwi
d33a269548
refactor(file extractor): file extractor (#1059) 2023-08-31 14:45:31 +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
a43e80dd9c
add qdrant migration (#1046)
Co-authored-by: jyong <jyong@dify.ai>
2023-08-29 10:37:04 +08:00
WangBooth
ad5f27bc5f
fix openpyxl dimensions error (#1041) 2023-08-29 10:36:48 +08:00
takatost
7b3314c5db
fix: dataset desc (#1045) 2023-08-29 09:07:27 +08:00
Jyong
a55ba6e614
Fix/ignore economy dataset (#1043)
Co-authored-by: jyong <jyong@dify.ai>
2023-08-29 03:37:45 +08:00
takatost
02452421d5
fix: pub generate message text return null (#1037) 2023-08-28 16:43:54 +08:00
takatost
0796791de5
feat: hf inference endpoint stream support (#1028) 2023-08-26 19:48:34 +08:00
takatost
6c148b223d
fix: dataset query truncated (#1026) 2023-08-26 17:35:17 +08:00
Uranus
2d9616c29c
fix: xinference last token being ignored (#1013) 2023-08-25 18:15:05 +08:00
Jyong
2d604d9330
Fix/filter empty segment (#1004)
Co-authored-by: jyong <jyong@dify.ai>
2023-08-25 15:50:29 +08:00
Jyong
b1fd1b3ab3
Feat/vector db manage (#997)
Co-authored-by: jyong <jyong@dify.ai>
2023-08-24 21:27:31 +08:00
takatost
9ae91a2ec3
feat: optimize xinference request max token key and stop reason (#998) 2023-08-24 18:11:15 +08:00
takatost
701e2b334f
feat: remove unnecessary prompt of baichuan (#993) 2023-08-24 15:30:59 +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
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
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
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
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
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
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
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
takatost
f42e7d1a61
feat: add spark v2 support (#885) 2023-08-17 15:08:57 +08:00
takatost
c4d759dfba
fix: wenxin error not raise when stream mode (#884) 2023-08-17 13:40:00 +08:00
takatost
39574dcf6b
feat: optimize prompt of suggested_questions_after_answer (#881) 2023-08-17 10:46:33 +08:00
takatost
cc2d71c253
feat: optimize override app model config convert (#874) 2023-08-16 20:48:42 +08:00
takatost
2dfb3e95f6
feat: optimize error record in agent (#869) 2023-08-16 15:55:42 +08:00
Jyong
f207e180df
fix multi thread app context (#868)
Co-authored-by: jyong <jyong@dify.ai>
2023-08-16 15:39:31 +08:00
takatost
948d64bbef
fix: get_num_tokens_from_messages params error (#866) 2023-08-16 14:58:44 +08:00
takatost
7a8590980e
fix: dataset direct output (#860) 2023-08-15 22:27:31 +08:00
takatost
e8c14bb732
feat: rename title in site both rename name in app (#857) 2023-08-15 20:42:32 +08:00
takatost
cc52cdc2a9
Feat/add free provider apply (#829) 2023-08-14 12:44:35 +08:00
takatost
8e15ba6cd6
Fix/no trial provider (#823) 2023-08-13 14:56:32 +08:00
takatost
7898937eae
feat: optimize message return (#822) 2023-08-13 13:51:12 +08:00
takatost
1bd0a76a20
feat: optimize error raise (#820) 2023-08-13 00:59:36 +08:00
takatost
2f179d61dc
fix: completion error when dataset was deleted (#819) 2023-08-13 00:25:05 +08:00
takatost
f18ce203b5
feat: optimize error logging (#808) 2023-08-12 02:22:43 +08:00
takatost
b81b8637ec
feat: temp remove paid option of anthropic (#807) 2023-08-12 01:54:38 +08:00
takatost
5fa2161b05
feat: server multi models support (#799) 2023-08-12 00:57:00 +08:00
lixiaoyin
cc277227ad
fix i is not incremented due to violating the uniqueness constraint w… (#771)
Co-authored-by: 李啸吟 <746963140@qq.com>
2023-08-08 21:19:06 +08:00
Matri
dfe10e9dfe
fix: generate_more_like_this function issue (#722) 2023-08-03 11:37:09 +08:00
takatost
654985177f
fix: segment resort in dataset retrieve by index_node_id_to_position (#721) 2023-08-02 21:31:54 +08:00
takatost
e18211ffea
feat: fix azure completion choices return empty (#708) 2023-08-01 15:36:53 +08:00
Jyong
fa73aa8dbf
add embedding max retries (#699) 2023-07-31 23:28:37 +08:00
Jyong
174ebb51db
add qa thread control (#677) 2023-07-29 17:49:18 +08:00
John Wang
626c78a690
fix: agent parse result error (#676) 2023-07-29 17:00:38 +08:00
Jyong
9eaae770a6
Feat/add thread control (#675) 2023-07-29 17:00:21 +08:00
Jyong
ca60610306
logging qa error (#672) 2023-07-29 01:51:18 +08:00
Jyong
082f8b17ab
Feat/milvus support (#671)
Co-authored-by: StyleZhang <jasonapring2015@outlook.com>
Co-authored-by: JzoNg <jzongcode@gmail.com>
2023-07-28 22:19:39 +08:00
KVOJJJin
cf93d8d6e2
Feat: Q&A format segmentation support (#668)
Co-authored-by: jyong <718720800@qq.com>
Co-authored-by: StyleZhang <jasonapring2015@outlook.com>
2023-07-28 20:47:15 +08:00
John Wang
aae2fb8a30
fix: dataset retrieve npe when dataset desc is null (#669) 2023-07-28 17:40:36 +08:00
John Wang
d979955c8a
feat: optimize current time (#661) 2023-07-27 22:15:07 +08:00
John Wang
b5825142d1
feat: add current time tool in universal chat agent (#659) 2023-07-27 17:39:36 +08:00
John Wang
ba3dc8cae0
feat: fix dataset retrieve agent llm not support error (#656) 2023-07-27 15:45:52 +08:00
John Wang
4fdb37771a
feat: universal chat in explore (#649)
Co-authored-by: StyleZhang <jasonapring2015@outlook.com>
2023-07-27 13:08:57 +08:00
John Wang
e9810a6df2
fix: azure openai embedding model name error (#612) 2023-07-20 13:52:54 +08:00
John Wang
cae15013e0
fix: azure openai deployment list was deprecated suddenly (#611) 2023-07-20 13:46:39 +08:00
John Wang
eff115267f
fix: anthropic completion error in blocking mode (#591) 2023-07-18 15:12:52 +08:00
John Wang
0d3cd3b16a
fix: azure provider select error when use custom azure provider (#587) 2023-07-18 14:34:09 +08:00
John Wang
3dc82fb044
feat: remove davinci required model from azure provider (#586) 2023-07-18 14:14:56 +08:00
John Wang
7599f79a17
feat: claude api support (#572) 2023-07-17 00:14:19 +08:00
zxhlyh
a03a92e9db
Feat/chat support voice input (#532) 2023-07-07 17:50:42 +08:00
John Wang
6eee7cb42c
feat: fix azure embedding Too many inputs problem (#530) 2023-07-07 11:17:36 +08:00
John Wang
b9b0866a46
fix: generate summary error when tokens=4097 (#488) 2023-06-29 12:54:50 +08:00
John Wang
df68a7c82b
feat: Optimize the quality of the title generate (#484) 2023-06-28 19:59:20 +08:00
John Wang
9d98669e7d
fix: dataset destination error (#477) 2023-06-28 15:51:07 +08:00
John Wang
408fbb0c70
fix: title, summary, suggested questions generate (#476) 2023-06-28 15:43:33 +08:00
crazywoola
998f819b04
use sub to operate all (#475) 2023-06-28 14:58:40 +08:00
Jyong
334f46d0b6
Fix/json format (#466) 2023-06-28 13:58:50 +08:00
Jyong
2eea114ac0
fix special code (#473) 2023-06-28 13:58:36 +08:00
Jyong
c67ecff3fe
Fix/json format (#465) 2023-06-27 17:15:03 +08:00
John Wang
d5b42c09ee
fix: template parse error when history include {{any}} (#463) 2023-06-27 16:35:50 +08:00
John Wang
835bf9fd8d
fix: template parse error when pre prompt include {{}} (#462) 2023-06-27 15:51:55 +08:00
John Wang
c720f831af
feat: optimize template parse (#460) 2023-06-27 15:30:38 +08:00
John Wang
df5763be37
feat: optimize openai error raise (#459) 2023-06-27 12:34:47 +08:00
John Wang
cad1532f7c
feat: optimize index_struct copy (#442) 2023-06-25 17:52:22 +08:00
John Wang
951afcaaed
feat: optimize weaviate error msg (#441) 2023-06-25 17:05:56 +08:00
John Wang
3241e4015b
feat: upgrade langchain (#430)
Co-authored-by: jyong <718720800@qq.com>
2023-06-25 16:49:14 +08:00
lisaifei@cvte.com
23ef2262bd
fix: filter empty value in xlsx to improve vector similarity hit (#422) 2023-06-21 11:25:52 +08:00
Jyong
36dc05c4da
fix chinese encoding (#411) 2023-06-19 18:41:17 +08:00
Jyong
226f28edcb
Feature/self host notion import (#397) 2023-06-17 19:50:21 +08:00
Jyong
9253f72dea
Feat/dataset notion import (#392)
Co-authored-by: StyleZhang <jasonapring2015@outlook.com>
Co-authored-by: JzoNg <jzongcode@gmail.com>
2023-06-16 21:47:51 +08:00
John Wang
184afa69ff
feat: add gpt-3.5-turbo-16k support and update openai gpt-3.5-turbo & Embedding Ada v2 unit price (#358) 2023-06-14 12:17:43 +08:00
John Wang
ab115b5f87
fix: completion stop invalid (#355) 2023-06-13 17:47:42 +08:00
John Wang
a11f36ca60
fix: stop completion response not save to db (#351) 2023-06-13 15:47:58 +08:00
John Wang
cd136fb293
feat: add WEAVIATE_BATCH_SIZE (#349) 2023-06-13 14:49:40 +08:00
John Wang
6a3ab36101
feat: optimize weaviate batch size (#348) 2023-06-13 11:28:15 +08:00
Jyong
3d14431b96
Fix/excel data format (#334) 2023-06-09 20:21:11 +08:00
lisaifei@cvte.com
0abd67288b
feat: support xlsx file parsing (#304)
Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>
2023-06-09 15:57:19 +08:00
Jyong
2bf48514bc
fix markdown parser (#230) 2023-06-06 19:51:40 +08:00
John Wang
a3ee037d6d
feat: optimize output parse failed error (#298) 2023-06-05 11:23:51 +08:00
John Wang
490858a4d5
feat: auto rule generator (#273) 2023-05-31 22:03:15 +08:00
John Wang
44a1aa5e44
fix: dataset_tool npe (#274) 2023-05-31 17:16:27 +08:00
John Wang
75f7a96025
feat: ignore validate failed error log (#256) 2023-05-30 12:25:42 +08:00
John Wang
5ca88a4fd9
fix: raw json parse in llm router chain (#254) 2023-05-30 12:16:45 +08:00
John Wang
bb7f454ecd
fix: dataset desc npe (#246) 2023-05-29 19:56:36 +08:00
John Wang
7f48fadd41
fix: prompt template parantheses select error (#244) 2023-05-29 19:10:31 +08:00
John Wang
af2138e8b8
fix: json parse in router chain output (#243) 2023-05-29 18:25:01 +08:00
John Wang
88545184be
feat: support multi datasets router chain mode (#231) 2023-05-28 22:44:54 +08:00
John Wang
2c23caacd4
fix: introduction key error (#221) 2023-05-26 20:49:38 +08:00
John Wang
1a5acf43aa
Fix/shared lock (#210) 2023-05-25 21:31:11 +08:00
John Wang
d93365d429
fix: azure embedding not support batch (#188) 2023-05-24 18:55:07 +08:00
John Wang
4350bb9a00
Fix/human in answer (#174) 2023-05-23 19:54:04 +08:00
John Wang
056898bf21
fix: quota update error on azure openai (#172) 2023-05-23 16:16:22 +08:00
John Wang
6da5e54180
Feat/open azure validate (#163) 2023-05-23 14:16:26 +08:00
John Wang
f3219ff107
fix: template string in template error (#162) 2023-05-23 13:16:33 +08:00
John Wang
219011b62a
fix: disable template string in query (#160) 2023-05-23 12:57:26 +08:00
John Wang
90150a6ca9
Feat/optimize chat prompt (#158) 2023-05-23 12:26:28 +08:00
John Wang
9a5ae9f51f
Feat: optimize error desc (#152) 2023-05-22 17:39:28 +08:00
John Wang
54a6571462
fix: extra input for opening statement was not suitable for prompt (#143) 2023-05-22 14:32:22 +08:00
John Wang
b42cd38cc9
fix: internal error when user is none in service api call (#129) 2023-05-21 17:29:47 +08:00
John Wang
e8e8f9e97d
Fix: move pre prompt to user massasge in chat mode (#126) 2023-05-21 17:06:04 +08:00
John Wang
1b6e3ef964
Feat: optimize inner prompt (#121) 2023-05-21 11:29:10 +08:00
John Wang
8fc2663693
fix: weaviate batch insert timeout (#108) 2023-05-19 21:57:32 +08:00
John Wang
f68b05d5ec
Feat: support azure openai for temporary (#101) 2023-05-19 13:24:45 +08:00
John Wang
0587ff0fba
fix: remove empty segment in splitter (#68) 2023-05-17 15:02:58 +08:00
John Wang
815f794eef
feat: optimize split rule when use custom split segment identifier (#35) 2023-05-16 12:57:25 +08:00
John Wang
f5b2271c8c
fix: import wrong user (#32) 2023-05-15 23:30:58 +08:00
John Wang
db896255d6 Initial commit 2023-05-15 08:51:32 +08:00