Commit Graph

374 Commits

Author SHA1 Message Date
znn 7adf1a64ec fix text splitter (#22596) 2025-07-18 13:51:58 +08:00
-LAN- 2ad05e003c refactor: decouple Node and NodeData (#22581)
Signed-off-by: -LAN- <laipz8200@outlook.com>
Co-authored-by: QuantumGhost <obelisk.reg+git@gmail.com>
2025-07-18 10:08:51 +08:00
helojo 37a4ff2b67 Fix: the pict type picture was not processed in the docx (#19305)
Co-authored-by: zqgame <zqgame@zqgame.local>
2025-07-17 22:53:35 +08:00
yihong f5afd34990 fix: drop dead code phase2 unused class (#22042)
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
2025-07-17 09:33:07 +08:00
wanttobeamaster c8236637e3 tablestore vector support more method (#22225)
Co-authored-by: xiaozhiqing.xzq <xiaozhiqing.xzq@alibaba-inc.com>
2025-07-15 09:58:48 +08:00
Jacky Wu d16d203390 fix: close session before doing long latency operation (#22306) 2025-07-14 15:16:10 +08:00
luckylhb90 070fc6a118 optimize: batch embedding and qdrant write_consistency_factor parameter (#21776)
Co-authored-by: hobo.l <hobo.l@binance.com>
2025-07-10 10:16:59 +08:00
wlleiiwang 6a53cb20eb Optimize the memory usage of Tencent Vector Database (#22079)
Co-authored-by: wlleiiwang <wlleiiwang@tencent.com>
2025-07-09 15:53:06 +08:00
baonudesifeizhai b71eee95b6 fix: prevent timeout in file encoding detection for large files (#21453)
Co-authored-by: crazywoola <427733928@qq.com>
2025-07-03 17:06:49 +08:00
efrey kong c2c558f294 Fix: prevent SQL errors when metadata filter Constant value is None or blank (#21803) 2025-07-02 14:43:01 +08:00
Dongyu Li d31b6574ed Feat/kb index (#20868)
Co-authored-by: twwu <twwu@dify.ai>
2025-06-25 17:52:59 +08:00
Jin 372048a02b fix: markdown_extractor lost chunks if it starts without a header(#21308) (#21309) 2025-06-21 23:10:00 +08:00
LiuBo 518608bd2b feat: add support for Matrixone database (#20714) 2025-06-19 10:20:12 +08:00
NeatGuyCoding 762c2d8d9e Translation fix (#21194) 2025-06-19 09:36:56 +08:00
NeatGuyCoding 5c619754a7 Minor Improvements for File Validation and Configuration Handling #21179 (#21171)
Co-authored-by: tech <cto@sb>
2025-06-18 18:33:28 +08:00
Ademílson Tonato b02f595f6a feat: add search endpoint for Firecrawl Integration (#20521)
Co-authored-by: crazywoola <427733928@qq.com>
2025-06-18 14:37:03 +08:00
Rain Wang 5161e82c0d Fixes #20748 KnowledgeRetrievalNode return all external documents when reranker disabled even top-k configed (#20762) 2025-06-18 14:35:12 +08:00
kazuya-awano d1b2c6d8b0 feat: add pagenation to notion extractor (#20919) 2025-06-18 11:30:55 +08:00
kurokobo 620912252f fix: shorten connection timeout to pypi.org for deprecation check for weaviate client (#21131) 2025-06-18 09:25:52 +08:00
Bowen Liang 3b15fd919f test: run vdb test of oceanbase with docker compose in CI tests (#20945) 2025-06-16 11:05:19 +08:00
Bowen Liang f7c7f5d942 chore: bump mypy to 1.16 (#20608) 2025-06-11 01:01:33 +08:00
QuantumGhost 66042d8153 refactor(api): Decouple ParameterExtractorNode from LLMNode (#20843)
- Extract methods used by `ParameterExtractorNode` from `LLMNode` into a separate file.
- Convert `ParameterExtractorNode` into a subclass of `BaseNode`.
- Refactor code referencing the extracted methods to ensure functionality and clarity.
- Fixes the issue that `ParameterExtractorNode` returns error when executed.
- Fix relevant test cases.

Closes #20840.
2025-06-10 11:47:50 +08:00
yihong 5a185c4ce9 fix: clean up two unreachable code (#20773)
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
2025-06-07 23:06:46 +08:00
jefferyvvv e230915fcf fix: opensearch vector search falls back to keyword search (#20723)
Co-authored-by: wenjun.gu <wenjun.gu@envision-energy.com>
2025-06-06 16:29:15 +08:00
jefferyvvv 66818f4312 fix: opensearch metadata filtering returns empty (#20701)
Co-authored-by: wenjun.gu <wenjun.gu@envision-energy.com>
Co-authored-by: crazywoola <427733928@qq.com>
2025-06-06 09:10:01 +08:00
jefferyvvv 5755965bd0 fix: opensearch fulltext search with metadata filtering dsl error (#20702)
Co-authored-by: wenjun.gu <wenjun.gu@envision-energy.com>
2025-06-05 23:09:00 +08:00
kenwoodjw 00ea85cbe5 fix: autocorrect everything in web (#20605)
Signed-off-by: kenwoodjw <blackxin55+@gmail.com>
2025-06-04 14:12:24 +08:00
zhaobingshuang 154f7aa58b fix: #20560 When elasticsearch is used as the vector database, the Retrieval Test fails to filter the data after setting the Score Threshold, and the score of the recalled results is empty (#20561) 2025-06-03 13:24:26 +08:00
Cheney Zhang bf43256840 check zilliz cloud of full-text search (#20519) 2025-06-02 18:04:13 +08:00
Dongyu Li 88900765a1 update knowledge base api (#20426) 2025-05-30 14:45:30 +08:00
-LAN- 34eb5d4f72 Refactor/message cycle manage and knowledge retrieval (#20460)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-05-30 14:36:44 +08:00
yihong 879986dcba fix: drop some type fixme (#20344) 2025-05-30 14:10:09 +08:00
-LAN- 03db78adc6 Refactor/remove db from cycle manager (#20455)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-05-30 04:34:13 +08:00
rouxiaomin a0ecb066bf feat(qdrant):add replication_factor when create collection in qdrant (#20133)
Co-authored-by: 刘敏 <min.liu@tongdun.net>
2025-05-27 14:46:04 +08:00
He Huang 5d8a89aca3 Refactor OpenSearch config to separate use_ssl and verify_certs flags (#20075)
Co-authored-by: he.huang <he.huang1@outlook.com>
Co-authored-by: crazywoola <427733928@qq.com>
2025-05-22 10:14:38 +08:00
wlleiiwang 485d847e21 tencent vectordb compatible with version 1.1.3 and below (#20056)
Co-authored-by: wlleiiwang <wlleiiwang@tencent.com>
2025-05-21 20:24:05 +08:00
-LAN- 8e48c5245a refactor: Use typed SQLAlchemy base model and fix type errors (#19980)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-05-21 15:38:03 +08:00
Darlewo 0c131f048b fix: multiple retrieve reranking_enabled switch (#19958) 2025-05-20 15:22:03 +08:00
Amir Mohsen Asaran e5c89062aa Feat(WaterCrawl error handling): add custom exceptions and error handling (#19948) 2025-05-20 10:25:16 +08:00
-LAN- 9073106299 feat(workflow): domain model for workflow node execution (#19430)
Signed-off-by: -LAN- <laipz8200@outlook.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2025-05-17 00:56:16 +08:00
k-kayashima 4a461b390e Fix: Ensure unique index names for pgvector knowledge tables (#19672)
Co-authored-by: crazywoola <427733928@qq.com>
2025-05-15 11:43:44 +08:00
非法操作 59a986ad6a chore: model.query change to db.session.query (#19551)
Co-authored-by: QuantumGhost <obelisk.reg+git@gmail.com>
2025-05-13 09:13:12 +08:00
非法操作 06a15bf2ae chore: all model.query replace to db.session.query (#19521) 2025-05-12 15:19:41 +08:00
非法操作 fa226ece81 fix: replace all dataset.Model.query to db.session.query(Model) (#19509) 2025-05-12 13:52:33 +08:00
湛露先生 9932f338e8 clean rag word_extractor. (#19397)
Signed-off-by: zhanluxianshen <zhanluxianshen@163.com>
2025-05-09 16:39:16 +08:00
Will c1d8ad7b5d fix: metadata filtering condition variable unassigned; fix External K… (#19208) 2025-05-07 14:52:09 +08:00
Hao Cheng 6a1434db92 fix: use only supported operators in metadata filter system prompts (#19195) 2025-05-03 20:08:08 +08:00
Will 59fe233202 fix: time type metadata filtering error (#19192) 2025-05-03 20:07:37 +08:00
Bowen Liang af7a907960 immediately return initialed tiktokenizer instance and remove dead code in usage of tiktokenizer (#17957) 2025-04-30 16:07:20 +08:00
QuantumGhost 487b107e6f Enhance Code Consistency Across Repository with .editorconfig (#19023) 2025-04-29 18:04:33 +08:00