Commit Graph

77 Commits

Author SHA1 Message Date
wdeveloper16
12814b55d2 refactor(api): migrate core RAG layer to SQLAlchemy 2.0 select() API (#34965) 2026-04-11 16:32:20 +00:00
carlos4s
86fd94767c refactor(api): use sessionmaker in relyt & tidb_vector VDB services (#34848) 2026-04-10 03:16:25 +00:00
carlos4s
d360929af1 refactor(api): use sessionmaker in pgvecto_rs VDB service (#34818) 2026-04-09 05:49:03 +00:00
tmimmanuel
1a4eb47e1d refactor(api): tighten types in trivial lint and config fixes (#34773)
Co-authored-by: tmimmanuel <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>
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
2026-04-08 23:14:44 +00:00
carlos4s
4c70bfa8b8 refactor(api): use sessionmaker in trigger provider service & dataset… (#34774) 2026-04-08 23:13:38 +00:00
corevibe555
624db69f12 refactor(api): remove duplicated RAG entities from services layer (#34689) 2026-04-07 23:36:59 +00:00
corevibe555
80a7843f45 refactor(api): migrate consumers to shared RAG domain entities from core/rag/entities/ (#34692) 2026-04-07 23:22:56 +00:00
Renzo
72adb5468c refactor: migrate session.query to select API in retrieval_service (#34638) 2026-04-07 04:46:30 +00:00
jimmyzhuu
b23ea0397a fix: apply Baidu Vector DB connection timeout when initializing Mochow client (#34328) 2026-04-01 06:16:09 +00:00
Dream
c51cd42cb4 refactor(api): replace json.loads with Pydantic validation in controllers and infra layers (#34277)
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
2026-04-01 05:41:44 +00:00
Full Stack Engineer
09ee8ea1f5 fix: support qa_preview shape in IndexProcessor preview formatting (#34151)
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
Co-authored-by: Crazywoola <100913391+crazywoola@users.noreply.github.com>
2026-04-01 04:22:23 +00:00
Renzo
4bd388669a refactor: core/app pipeline, core/datasource, and core/indexing_runner (#34359)
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
2026-04-01 02:20:56 +00:00
99
f27d669f87 chore: normalize frozenset literals and myscale typing (#34327) 2026-03-31 08:21:22 +00:00
Renzo
456684dfc3 refactor: core/rag docstore, datasource, embedding, rerank, retrieval (#34203)
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
Co-authored-by: Asuka Minato <i@asukaminato.eu.org>
2026-03-30 08:09:49 +00:00
99
40591a7c50 refactor(api): use standalone graphon package (#34209)
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
2026-03-27 21:05:32 +00:00
99
52e7492cbc refactor(api): rename dify_graph to graphon (#34095) 2026-03-25 21:58:56 +08:00
-LAN-
56593f20b0 refactor(api): continue decoupling dify_graph from API concerns (#33580)
Signed-off-by: -LAN- <laipz8200@outlook.com>
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
Co-authored-by: WH-2099 <wh2099@pm.me>
2026-03-25 20:32:24 +08:00
tmimmanuel
a946015ebf test: replace indexing_technique string literals with IndexTechnique (#34042) 2026-03-25 12:39:58 +09:00
Rajat Agarwal
6f137fdb00 test: unit test cases for rag.cleaner, rag.data_post_processor and rag.datasource (#32521) 2026-03-25 02:19:15 +08:00
tmimmanuel
8b634a9bee refactor: use EnumText for ApiToolProvider.schema_type_str and Docume… (#33983) 2026-03-24 13:27:50 +09:00
kurokobo
30deeb6f1c feat(firecrawl): follow pagination when crawl status is completed (#33864)
Co-authored-by: Crazywoola <100913391+crazywoola@users.noreply.github.com>
2026-03-23 21:19:32 +08:00
wangxiaolei
40846c262c perf: tidb_on_qdrant_vector delete_by_ids use batch delete (#33846) 2026-03-22 21:09:43 +09:00
BitToby
b2a388b7bf refactor(api): type Firecrawl API responses with TypedDict (#33691) 2026-03-19 04:00:06 +09:00
BitToby
485da15a4d refactor(api): replace dict/Mapping with TypedDict in core/rag retrieval_service.py (#33615)
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
2026-03-18 11:49:09 +09:00
wangxiaolei
915ee385db fix: fix weaviate_vector test failed (#33511) 2026-03-16 14:32:09 +08:00
Sage
3920d67b8e feat(api): Making WeaviateClient a singleton
Co-authored-by: lijiezhao <lijiezhao@perfect99.com>
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
2026-03-16 13:38:28 +08:00
RickDamon
ac8021fe27 fix: add doc_type to Weaviate properties and default Vector attributes (#33398)
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
2026-03-15 19:25:24 +08:00
-LAN-
fb41b215c8 refactor(api): move workflow knowledge nodes and trigger nodes (#33445) 2026-03-15 15:24:59 +08:00
tmimmanuel
e64f4d6039 refactor: replace sa.String with EnumText in mapped_column for type s… (#33332)
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-14 13:38:27 +09:00
wangxiaolei
54637144c5 fix: fix parse mailto / http link in table cell (#33224)
Co-authored-by: Oz <oz-agent@warp.dev>
2026-03-11 10:02:33 +08:00
rajatagarwal-oss
a0ed350871 test: unit test for core.rag module (#32630) 2026-03-10 14:10:24 +08:00
-LAN-
4fd6b52808 refactor(api): move model_runtime into dify_graph (#32858) 2026-03-02 20:15:32 +08:00
-LAN-
c917838f9c refactor: move workflow package to dify_graph (#32844) 2026-03-02 18:42:30 +08:00
-LAN-
20fcc95db9 test(api): add autospec to MagicMock-based patch usage (#32752) 2026-03-01 04:30:45 +08:00
-LAN-
a694533fc9 refactor(workflow): inject credential/model access ports into LLM nodes (#32569)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2026-02-27 14:36:41 +08:00
wangxiaolei
3348b89436 refactor: decouple database operations from knowledge retrieval nodes (#31981)
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
2026-02-09 13:56:55 +08:00
盐粒 Yanli
dbfc47e8b0 fix: SSRF in WordExtractor URL download (credit to @EaEa0001 ) (#31678)
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2026-01-29 14:01:21 +08:00
Zhiqiang Yang
114a34e008 fix: correct docx hyperlink extraction (#30360) 2026-01-06 11:24:26 +08:00
hsiong
be3ef9f050 fix: #30511 [Bug] knowledge_retrieval_node fails when using Rerank Model: "Working outside of application context" and add regression test (#30549)
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
2026-01-05 15:02:21 +08:00
wangxiaolei
473f8ef29c feat: skip rerank if only one dataset is retrieved (#30075)
Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>
2026-01-04 20:22:51 +08:00
Zhiqiang Yang
cad7101534 feat: support image extraction in PDF RAG extractor (#30399)
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
2025-12-31 15:49:06 +08:00
wangxiaolei
9007109a6b fix: [xxx](xxx) render as xxx](xxx) (#30392)
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
2025-12-31 10:30:15 +08:00
wangxiaolei
30dd50ff83 feat: allow fail fast (#30262) 2025-12-30 09:27:40 +08:00
wangxiaolei
8611301722 fix: fix DatasetRetrieval._process_metadata_filter_func miss in operator (#30199) 2025-12-26 16:34:50 +08:00
wangxiaolei
61d255a6e6 chore: bypass InsufficientPrivilege on Azure PostgreSQL (#30191) 2025-12-26 14:35:05 +08:00
wangxiaolei
111a39b549 fix: fix firecrawl url concat (#30008) 2025-12-24 09:40:32 +08:00
wangxiaolei
32605181bd feat: first use INTERNAL_FILES_URL first, then FILES_URL (#29962) 2025-12-21 16:53:37 +08:00
wangxiaolei
78ca5ad142 fix: fix fixed_separator (#29861) 2025-12-18 16:50:44 +08:00
wangxiaolei
4fce99379e test(api): add a test for detect_file_encodings (#29778)
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
2025-12-17 14:33:30 +08:00
wangxiaolei
8f3fd9a728 perf: commit once (#29590) 2025-12-15 11:40:26 +08:00