 Jyong
|
5e66a60f1c
add embedding cache and clean embedding cache job (#3087)
|
il y a 1 an |
|
Jyong
|
a94d86da6d
add keyword table s3 storage support (#3065)
|
il y a 1 an |
|
Jyong
|
c3d0cf940c
add tenant id index for document and document_segment table (#2873)
|
il y a 1 an |
 Bowen Liang
|
801d135390
generalize the generation of new collection name by dataset id (#2620)
|
il y a 1 an |
|
Jyong
|
6c4e6bf1d6
Feat/dify rag (#2528)
|
il y a 1 an |
|
Bowen Liang
|
843280f82b
enhancement: introduce Ruff for Python linter for reordering and removing unused imports with automated pre-commit and sytle check (#2366)
|
il y a 1 an |
 KVOJJJin
|
89fcf4ea7c
Feat: chunk overlap supported (#2209)
|
il y a 1 an |
 crazywoola
|
ec1659cba0
fix: saving error in empty dataset (#2098)
|
il y a 1 an |
|
Bowen Liang
|
cc9e74123c
improve: introduce isort for linting Python imports (#1983)
|
il y a 1 an |
|
Jyong
|
5e34f938c1
Feat/add unstructured support (#1780)
|
il y a 1 an |
|
Jyong
|
a71f2863ac
Annotation management (#1767)
|
il y a 1 an |
|
Jyong
|
74b2260ba6
fix score_threshold_enabled name (#1626)
|
il y a 1 an |
|
Jyong
|
4588831bff
Feat/add retriever rerank (#1560)
|
il y a 1 an |
|
Jyong
|
269a465fc4
Feat/improve vector database logic (#1193)
|
il y a 1 an |
|
Jyong
|
a55ba6e614
Fix/ignore economy dataset (#1043)
|
il y a 1 an |
|
Jyong
|
db7156dafd
Feature/mutil embedding model (#908)
|
il y a 1 an |
 takatost
|
5fa2161b05
feat: server multi models support (#799)
|
il y a 1 an |
|
KVOJJJin
|
cf93d8d6e2
Feat: Q&A format segmentation support (#668)
|
il y a 1 an |
|
John Wang
|
3241e4015b
feat: upgrade langchain (#430)
|
il y a 1 an |
|
Jyong
|
9253f72dea
Feat/dataset notion import (#392)
|
il y a 1 an |
 John Wang
|
db896255d6
Initial commit
|
il y a 1 an |
