310 Commits

Author SHA1 Message Date
Jasonfish
1f722cde22
fix(api): Some params were ignored when creating empty Datasets through API (#17932) 2025-04-14 10:24:01 +08:00
Yongtao Huang
5d72003ebb
Remove dead code (#17899) 2025-04-11 20:33:52 +08:00
briqt
91cfa90503
Fix external knowledge Issues: (#17685) (#17843) 2025-04-11 15:37:27 +08:00
yihong
f04d52c044
fix: autocorrect everything in api (#17859)
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
2025-04-11 15:24:39 +08:00
wlleiiwang
9d20561af4
create db if not exists (#17796)
Co-authored-by: wlleiiwang <wlleiiwang@tencent.com>
2025-04-10 18:03:22 +08:00
Jyong
8b3be4224d
revert batch query (#17707) 2025-04-09 20:25:36 +08:00
wlleiiwang
f148f1efa2
fix: Check collection exists before drop it. (#17692)
Co-authored-by: wlleiiwang <wlleiiwang@tencent.com>
2025-04-09 19:14:32 +08:00
Jyong
abfcd9d3b6
fix segment query index not effect (#17704) 2025-04-09 19:09:08 +08:00
Han
f1e4d5ed6c
Fix Performance Issues: (#17083)
Co-authored-by: Wang Han <wanghan@zhejianglab.org>
2025-04-09 11:22:53 +08:00
Steven Li
abead647e2
fix: Extract docx file fails when the file contains an invalid link (#17576) 2025-04-08 13:59:33 +08:00
Amir Mohsen Asaran
f54905e685
feat: Integrate WaterCrawl.dev as a new knowledge base provider (#16396)
Co-authored-by: crazywoola <427733928@qq.com>
2025-04-07 12:43:23 +08:00
wlleiiwang
42a42a7962
FEAT: support Tencent vectordb to full text search (#16865)
Co-authored-by: wlleiiwang <wlleiiwang@tencent.com>
2025-04-07 09:50:03 +08:00
crazywoola
3e698074e7
Fix/17466 cannot create a knowledge base by adding files (#17470) 2025-04-06 00:03:05 +08:00
Panpan
fc3f14c0ee
fix: keep image url (#17430) 2025-04-04 15:55:48 +08:00
Perfecto
16c722d1d8
fix: move hardcoded text to language settings (#16990) (#17133) 2025-04-02 22:35:51 +08:00
Jyong
6104b91d3f
add doc support in knowledge base for unstructured (#17352) 2025-04-02 21:35:01 +08:00
Jiang
fd1e40d22e
Lindorm VDB bugfix (#17357)
Co-authored-by: jiangzhijie <jiangzhijie.jzj@alibaba-inc.com>
2025-04-02 21:31:59 +08:00
Jiang
ff388fe3e6
optimize lindorm vdb add_texts (#17212)
Co-authored-by: jiangzhijie <jiangzhijie.jzj@alibaba-inc.com>
2025-04-01 11:06:35 +08:00
非法操作
44f911a0a8
chore: docstring not match the function parameter (#17162) 2025-03-31 13:19:15 +08:00
jiangbo721
a1aa325ce3
Chore/code format and Repair commit_id 3254018d more deleted codes and Fix naming error ambiguity between workflow_run_id and workflow_id (#17075)
Co-authored-by: 刘江波 <jiangbo721@163.com>
2025-03-29 14:15:53 +08:00
wanttobeamaster
7f70cadacb
feat: support Tablestore vector database (#16601)
Co-authored-by: xiaozhiqing.xzq <xiaozhiqing.xzq@alibaba-inc.com>
2025-03-27 15:53:33 +08:00
wlleiiwang
a743d5dc71
feat: tencent vectordb: use grpc client and set upsert batch size (#16016)
Co-authored-by: wlleiiwang <wlleiiwang@tencent.com>
2025-03-27 12:20:16 +08:00
Jyong
30792a1e1a
install pandoc (#16825) 2025-03-26 22:34:10 +08:00
yourchanges
59a86dabee
fix: fix missing oceanbase config enable_hybrid_search init (#16852)
Co-authored-by: 李远军 <4842@9ji.com>
2025-03-26 21:15:54 +08:00
Jyong
6a857e01f6
fix multiple metadata filter's confusing setting (#16771) 2025-03-26 14:16:21 +08:00
taokuizu
0c2a459c30
fix typo in _process_metadata_filter_func (#16780) 2025-03-26 09:01:41 +08:00
Jyong
2174225259
fix milvus filter search (#16725) 2025-03-25 16:22:43 +08:00
hsiong
6157f57872
feat: Add OceanBase hybrid search features (#16652)
Co-authored-by: 李远军 <4842@9ji.com>
Co-authored-by: yourchanges <yourchanges@gmail.com>
2025-03-25 14:32:00 +08:00
kenwoodjw
a113356695
fix: pgvector metadata filter (#16688)
Signed-off-by: kenwoodjw <blackxin55+@gmail.com>
2025-03-25 11:34:33 +08:00
Jiang
fc8c765215
Fix/vdb lindorm (#16660)
Co-authored-by: jiangzhijie <jiangzhijie.jzj@alibaba-inc.com>
2025-03-25 09:19:06 +08:00
Jyong
86a1859d02
Metadata variable value fix (#16665) 2025-03-25 09:07:11 +08:00
Jyong
1be0d26c1f
fix metadata filter not affect in keyword-search and fulltext-search (#16644) 2025-03-24 18:35:16 +08:00
chenhuan0728
770c461a8f
feat: add openGauss PQ acceleration feature (#16432)
Co-authored-by: chenhuan <huan.chen0728@foxmail>
2025-03-24 15:16:40 +08:00
Jyong
d135677c25
add vdb document id index (#16244)
Co-authored-by: crazywoola <427733928@qq.com>
2025-03-20 01:38:15 +08:00
Jyong
a8879057c0
fix tidb metadata filter (#16237) 2025-03-19 19:44:56 +08:00
Jyong
81325df368
fix weaviate metadata filter (#16230) 2025-03-19 18:26:53 +08:00
Jyong
b8ef3149ef
metadata expect value check error (#16210) 2025-03-19 17:48:01 +08:00
Jyong
c3c957bb80
change recreate_collection function to create_collection (#16212) 2025-03-19 17:13:08 +08:00
Jyong
abeaea4f79
Support knowledge metadata filter (#15982) 2025-03-18 16:42:19 +08:00
Jyong
33ba7e659b
fix vector db sql injection (#16096) 2025-03-18 15:07:29 +08:00
LittleFish-15
223ab5a38f
feat: support openGauss vector database (#15865) 2025-03-17 19:42:54 +08:00
huangzhuo1949
695a7400a9
fix:delete empty table bug (#15517)
Co-authored-by: huangzhuo <huangzhuo1@xiaomi.com>
2025-03-17 10:53:26 +08:00
Jyong
84a866028a
fix document could be None (#15818) 2025-03-14 16:40:01 +08:00
Yuichiro Utsumi
5f9d236d22
Feat: Add pg_bigm for keyword search in pgvector (#13876)
Signed-off-by: Yuichiro Utsumi <utsumi.yuichiro@fujitsu.com>
2025-03-13 16:32:34 +08:00
Jyong
a8e8c37fdd
improve text split (#15719) 2025-03-13 15:29:33 +08:00
kenwoodjw
087bb60b31
fix: preserve Unicode characters in keyword search queries (#15522)
Signed-off-by: kenwoodjw <blackxin55+@gmail.com>
2025-03-12 18:34:42 +08:00
Jyong
f77f7e1437
fix text split (#15426) 2025-03-11 00:24:27 +08:00
Jyong
435564f0f2
fix parent-child retrival count (#15119) 2025-03-06 22:32:38 +08:00
engchina
9c1db7dca7
modify oracle lexer name Fixes #15106 (#15108)
Co-authored-by: engchina <atjapan2015@gmail.com>
2025-03-06 18:58:51 +08:00
llinvokerl
d04f40c274
Fix empty results issue in full-text search with Milvus vector database (#14885)
Co-authored-by: liusurong.lsr <liusurong.lsr@alibaba-inc.com>
2025-03-05 12:27:01 +08:00