 Bowen LiangandGitHub
|
bb33ffc332
|
feat: initial support for Milvus 2.4.x (#3795)
|
2024-06-19 13:55:44 +08:00 |
|
|
baojingyuandGitHub
|
d160d1ed02
|
feat: support opensearch approximate k-NN (#5322)
|
2024-06-19 12:44:33 +08:00 |
|
|
sinoandGitHub
|
be3512aa57
|
fix: unable to reindex documents (#5276)
|
2024-06-17 17:19:43 +08:00 |
|
|
takatostandGitHub
|
12c815c597
|
fix: ExtractSetting optional value missing None as default val (#5238)
|
2024-06-15 02:58:47 +08:00 |
|
|
|
ba5f8afaa8
|
Feat/firecrawl data source (#5232)
Co-authored-by: Nicolas <[email protected]>
Co-authored-by: chenhe <[email protected]>
Co-authored-by: takatost <[email protected]>
|
2024-06-15 02:46:02 +08:00 |
|
|
quicksandandGitHub
|
4080f7b8ad
|
feat: support tencent vector db (#3568)
|
2024-06-14 19:25:17 +08:00 |
|
|
saga.reyandGitHub
|
edf2047f04
|
fix: milvus_vector default dataset index_struct type from weaviate to milvus (#5098)
|
2024-06-14 02:36:01 +08:00 |
|
|
Bowen LiangandGitHub
|
f976740b57
|
improve: mordernizing validation by migrating pydantic from 1.x to 2.x (#4592)
|
2024-06-14 01:05:37 +08:00 |
|
|
Bowen LiangandGitHub
|
cdc08a434f
|
feat: support Chroma vector store (#5015)
|
2024-06-13 18:02:18 +08:00 |
|
|
Ikko Eltociear AshimineandGitHub
|
a40f68cf94
|
chore: update qdrant_vector.py (#5128)
|
2024-06-13 15:35:14 +08:00 |
|
|
Bowen LiangandGitHub
|
bdad993901
|
improve: generalize vector factory classes and vector type (#5033)
|
2024-06-08 22:29:24 +08:00 |
|
|
JyongandGitHub
|
3b60c28b3a
|
deal the external image when extract docx image (#5024)
|
2024-06-07 20:00:39 +08:00 |
|
|
JyongandGitHub
|
237b8fe3d9
|
add meta.doc_id index for tidb (#4963)
|
2024-06-05 20:45:43 +08:00 |
|
|
JyongandGitHub
|
02e4de5166
|
fix some tidb bugs (#4960)
|
2024-06-05 19:14:18 +08:00 |
|
|
WeaxsandGitHub
|
0797f9bc05
|
feat: support tidb vector (#4588)
|
2024-06-05 18:19:53 +08:00 |
|
|
YCandGitHub
|
9f8ca75a81
|
fixing a bug of handling header row when parsing xls file, and tune xls/xlsx parsing result to be more structured (#3600)
|
2024-06-05 15:28:43 +08:00 |
|
|
Bowen LiangandGitHub
|
f32b440c4a
|
chore: fix indention violations by applying E111 to E117 ruff rules (#4925)
|
2024-06-05 14:05:15 +08:00 |
|
|
JasonVVandGitHub
|
7749b71fff
|
Optimize knowledge retrieval performance by batching dataset quries. (#4917)
|
2024-06-05 13:30:32 +08:00 |
|
|
takatostandGitHub
|
d1dbbc1e33
|
feat: backend model load balancing support (#4927)
|
2024-06-05 00:13:04 +08:00 |
|
|
JyongandGitHub
|
b6631cd878
|
modify rerank and splitter code directory (#4924)
|
2024-06-04 20:07:25 +08:00 |
|
|
Bowen LiangandGitHub
|
58db719a2c
|
dep: bump pandas from 1.x to 2.x (#4820)
|
2024-06-04 13:24:28 +08:00 |
|
|
Oliver LeeandGitHub
|
176d91937d
|
fix 'NoneType' and new ContentType supported. (#4818)
|
2024-05-31 14:19:33 +08:00 |
|
|
JyongandGitHub
|
1b2d862973
|
add error msg for hit test (#4704)
|
2024-05-28 14:54:53 +08:00 |
|
|
|
026175c8f7
|
feat: update notion extractor (#3898)
Co-authored-by: duyalei <>
|
2024-05-24 20:30:48 +08:00 |
|
|
JyongandGitHub
|
24624491cd
|
add qdrant metadata.doc_id index when create qdrant collection (#4570)
|
2024-05-23 18:11:01 +08:00 |
|
|
JyongandGitHub
|
233c4150d1
|
support images and tables extract from docx (#4619)
|
2024-05-23 18:05:23 +08:00 |
|
|
Rain ChenandGitHub
|
c255a20d7c
|
allow to config max segmentation tokens length for RAG document using environment variable (#4375)
|
2024-05-20 13:20:27 +08:00 |
|
|
majianandGitHub
|
b5204111da
|
Add UNSTRUCTURED_API_KEY env support (#4369)
|
2024-05-20 13:14:17 +08:00 |
|
|
Bowen LiangandGitHub
|
04ad46dd31
|
chore: skip unnecessary key checks prior to accessing a dictionary (#4497)
|
2024-05-19 18:30:45 +08:00 |
|
|
|
97b65f9b4b
|
Optimize webscraper (#4392)
Co-authored-by: luowei <glpat-EjySCyNjWiLqAED-YmwM>
Co-authored-by: crazywoola <[email protected]>
Co-authored-by: crazywoola <[email protected]>
|
2024-05-15 15:23:16 +08:00 |
|
|
kerlionandGitHub
|
98140ae5d9
|
fix the issue of MILVUS_DATABASE has no effect. (#4353)
|
2024-05-14 19:54:31 +08:00 |
|
|
LiuVaayneandGitHub
|
875249eb00
|
Feat/vector db pgvector (#3879)
|
2024-05-10 17:20:30 +08:00 |
|
|
Bowen LiangandGitHub
|
142814d451
|
chore: skip deprecated field_schema param in creating payload index on Qdrant (#3903)
|
2024-04-30 16:16:10 +08:00 |
|
|
JyongandGitHub
|
3e9dbe3e0a
|
add pgvecto_rs support and upgrade SQLAlchemy (#3833)
|
2024-04-29 11:58:17 +08:00 |
|
|
呆萌闷油瓶andGitHub
|
0940f01634
|
enhancement:support Qdrant gRPC mode (#3929)
|
2024-04-28 15:33:32 +08:00 |
|
|
Bowen LiangandGitHub
|
045827043d
|
test: improve vector store tests (#3855)
|
2024-04-26 19:18:42 +08:00 |
|
|
Bowen LiangandGitHub
|
7919596a21
|
fix: UP031 style rule violation (#3866)
|
2024-04-26 11:24:08 +08:00 |
|
|
Bowen LiangandGitHub
|
45dd1683fd
|
test: add tests covering all methods of vector store (#3849)
|
2024-04-25 22:27:30 +08:00 |
|
|
|
1be222af2e
|
fix: using api can not execute relyt vector database (#3766)
Co-authored-by: jingsi <[email protected]>
|
2024-04-25 19:46:20 +08:00 |
|
|
呆萌闷油瓶andGitHub
|
78988ed60e
|
fix:still enable SSL verification when using qdrant based on HTTP protocol (#3805)
|
2024-04-25 13:04:31 +08:00 |
|
|
Bowen LiangandGitHub
|
9cec8c1750
|
test: add unit tests for vector stores of Milvus, Qdrant and Weaviate (#3688)
|
2024-04-24 21:52:42 +08:00 |
|
|
|
f257f2c396
|
Knowledge optimization (#3755)
Co-authored-by: crazywoola <[email protected]>
Co-authored-by: JzoNg <[email protected]>
|
2024-04-24 15:02:29 +08:00 |
|
|
Bowen LiangandGitHub
|
2867d29021
|
fix: milvus usage with create_collection (#3683)
|
2024-04-23 17:37:40 +08:00 |
|
|
|
33397836a5
|
feat: support relyt vector database (#3367)
Co-authored-by: jingsi <[email protected]>
|
2024-04-15 11:52:34 +08:00 |
|
|
JyongandGitHub
|
0737e930cb
|
chore: remove Langchain tools import (#3407)
|
2024-04-12 16:26:09 +08:00 |
|
|
chenxu9741andGitHub
|
ad65c891e7
|
add xls file suport (#3321)
|
2024-04-12 14:53:44 +08:00 |
|
|
|
b00466f025
|
feat:api Add support for extracting EPUB files in ExtractProcessor (#3254)
Co-authored-by: crazywoola <[email protected]>
|
2024-04-12 11:25:02 +08:00 |
|
|
|
1f302990c6
|
add segment with keyword issue (#3351)
Co-authored-by: StyleZhang <[email protected]>
|
2024-04-11 16:57:02 +08:00 |
|
|
JyongandGitHub
|
6164604462
|
fix dataset retrival in dataset mode (#3334)
|
2024-04-11 02:11:21 +08:00 |
|
|
JyongandGitHub
|
b6de97ad53
|
Remove langchain dataset retrival agent logic (#3311)
|
2024-04-10 20:37:22 +08:00 |
|