Commit Graph

147 Commits (ed37439ef791e68964f5eaed90d8df41934787ad)

Author SHA1 Message Date
Jyong af92f19291
filter excel empty sheet (#8194) 1 year ago
Nam Vu 2d7954c7da
Fix variable typo (#8084) 1 year ago
ChengZi 2060db8e11
fix: change milvus init args from (host, port) to (url, token) (#8019)
Signed-off-by: ChengZi <chen.zhang@zilliz.com>
1 year ago
Byeongjin Kang d489b8b3e0
feat: return page number of pdf documents upon retrieval (#7749) 1 year ago
Jyong 0e71f6db84
fix spliter length missed (#7987) 1 year ago
KVOJJJin 14af87527f
Feat:remove estimation of embedding cost (#7950)
Co-authored-by: jyong <718720800@qq.com>
1 year ago
Sumkor 571415d1a4
fix: split text keep separator (#7930) 1 year ago
Jyong d8b6c053a2
fix rerank model value is empty string (#7937) 1 year ago
Jyong 01581dd35f
improve the notion table extract (#7925) 1 year ago
Jyong 6f33351eb3
ignore linked images when image id is none (#7890) 1 year ago
Jyong 60001a62c4
fixed chunk_overlap is None (#7703) 1 year ago
Kenn 122ce41020
feat: rewrite Elasticsearch index and search code to achieve Elasticsearch vector and full-text search (#7641)
Co-authored-by: haokai <haokai@shuwen.com>
Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>
Co-authored-by: Bowen Liang <bowenliang@apache.org>
Co-authored-by: wellCh4n <wellCh4n@foxmail.com>
1 year ago
Qin Liu 162faee4f2
fix: set score_threshold to zero if it is None for MyScale vectordb (#7640)
Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>
1 year ago
Jyong 7ae728a9a3
fix nltk averaged_perceptron_tagger download and fix score limit is none (#7582)
Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>
1 year ago
张皮皮 f29685f8a1
fix score_threshold is none, return all top K documents (#7581) 1 year ago
Byeongjin Kang 0223fc6fd5
feat: add pgvector full_text_search (#7396) 1 year ago
mochi ba79088ffc
Fix SQL parser Error in MyScale vdb. (#7255) 1 year ago
miendinh f104b930cf
feat: support elasticsearch vector database (#3558)
Co-authored-by: miendinh <miendinh@users.noreply.github.com>
Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>
Co-authored-by: crazywoola <427733928@qq.com>
2 years ago
Bowen Liang ccb6ddd840
chore: bump Ruff to 0.5.7 (#7174) 2 years ago
Joe 425174e82f
feat: update ops trace (#7102) 2 years ago
Jyong 12095f8cd6
extract docx filter comment element (#7092) 2 years ago
Jyong 169cde6c3c
add nltk punkt resource (#7063) 2 years ago
8bitpd 40c6f3c724
fix: add redis lock to AnalyticdbVector init (#6859)
Co-authored-by: xiaozeyu <xiaozeyu.xzy@alibaba-inc.com>
2 years ago
-LAN- df8f8c9a2c
feat(api/core/rag/datasource/vdb/analyticdb/analyticdb_vector.py): Checking config before init analyticdb (#7050) 2 years ago
Jyong 80c94f02e9
add vector field for other vectordb (#7051) 2 years ago
chenxu9741 72c75b75cf
feat: Add hyperlink parsing to the DOCX document. (#7017) 2 years ago
Bryan eece50acec
fix: tran list issue (#7009)
Co-authored-by: libing <libing@healink.cn>
2 years ago
Jyong 28d4e5b045
Fix/reranking mode is null (#7012) 2 years ago
yanghx c53875ce8c
fix #6902 .docx handles images within tables and handles cross-column tables (#6951) 2 years ago
Joe f97a51ce24
fix: reranking disable timer error (#6910) 2 years ago
Bowen Liang 6aa02f8c63
dep: bump pgvecto-rs client from 0.1.x to 0.2.x (#6891) 2 years ago
Jyong 44801df8f8
fix score threshold limit be None (#6900) 2 years ago
Jyong 8157fccf6d
delete weight_type (#6865) 2 years ago
-LAN- a98284b1ef
refactor(api): Switch to `dify_config` (#6750)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2 years ago
Bowen Liang b414ea41d6
dep: initial support for Milvus 2.4.x (#6084) 2 years ago
Jyong cf258b7a67
add xlsx support hyperlink extract (#6722) 2 years ago
Yeuoly 79cb23e8ac
security/SSRF vulns (#6682) 2 years ago
灰灰 5e4ac11df3
fix: code block segmentation problem of markdown document (#6465) 2 years ago
tmuife 16b4f560cd
fix bugs(when using Oracle23ai as Vector DB) (#6658) 2 years ago
Jyong e4bb943fe5
Feat/delete single dataset retrival (#6570) 2 years ago
崔亮 0569c547ee
fix the issue of MILVUS_DATABASE has no effect. (#6424) 2 years ago
tmuife 06fc1bce9e
Add search by full text when using Oracle23ai as vector DB (#6559) 2 years ago
Sangmin Ahn 093b8ca475
fix: escape double quotation marks in the vector DB search query (#6506) 2 years ago
-LAN- cd7fa8027a
fix(api/core/model_manager.py): Avoid mutation during iteration. (#6536) 2 years ago
-LAN- 5e6fc58db3
Feat/environment variables in workflow (#6515)
Co-authored-by: JzoNg <jzongcode@gmail.com>
2 years ago
Jyong f38034e455
clean vector collection redis cache (#6494) 2 years ago
Waffle 2ba05b041f
refactor(myscale):Set the default value of the myscale vector db in DifyConfig. (#6441) 2 years ago
leoterry dc847ba145
Fix the vector retrieval sorting issue (#6431)
Co-authored-by: weifj <“weifj@tuyuansu.com.cn”>
2 years ago
Poorandy c8f5dfcf17
refactor(rag): switch to dify_config. (#6410)
Co-authored-by: -LAN- <laipz8200@outlook.com>
2 years ago
Jyong 0de224b153
fix wrong using of RetrievalMethod Enum (#6345) 2 years ago