2737 Commits

Author SHA1 Message Date
NeatGuyCoding
918bb9a2f7
bug: fix sequence number may be duplicated when multi-threads running the same workflow #21047 (#21153) 2025-06-18 16:10:11 +08:00
Dongyu Li
2cf980026e feat(datasource): change datasource result type to event-stream 2025-06-18 16:04:47 +08:00
Dongyu Li
224111081b feat(datasource): change datasource result type to event-stream 2025-06-18 16:04:40 +08:00
jyong
6f67a34349 r2 qa index 2025-06-18 14:37:18 +08:00
Ademílson Tonato
9e73e8b9e8
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
47e0f92c0f
Fixes #20748 KnowledgeRetrievalNode return all external documents when reranker disabled even top-k configed (#20762) 2025-06-18 14:35:12 +08:00
湛露先生
6d033d4064
clean duplicate validate for dataset_configs (#20775)
Signed-off-by: zhanluxianshen <zhanluxianshen@163.com>
2025-06-18 14:34:58 +08:00
湛露先生
ab290ed968
unreachable-code for lb model fetch. (#20797)
Signed-off-by: zhanluxianshen <zhanluxianshen@163.com>
2025-06-18 14:33:49 +08:00
-LAN-
879f839d75
refactor(graph_engine): Merge duplicated if block (#20784)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-06-18 14:33:29 +08:00
zxhlyh
e51d308312 Merge branch 'feat/rag-pipeline' into deploy/rag-dev 2025-06-18 13:47:36 +08:00
kazuya-awano
45c89bd6de
feat: add pagenation to notion extractor (#20919) 2025-06-18 11:30:55 +08:00
jyong
ac917bb56d r2 2025-06-18 11:05:52 +08:00
jyong
f7a4e5d1a6 Merge branch 'main' into feat/r2 2025-06-18 10:57:44 +08:00
kurokobo
4689e8953e
fix: shorten connection timeout to pypi.org for deprecation check for weaviate client (#21131) 2025-06-18 09:25:52 +08:00
jyong
66de2e1f0a Merge remote-tracking branch 'origin/feat/r2' into feat/r2
# Conflicts:
#	api/core/workflow/graph_engine/entities/event.py
#	api/services/rag_pipeline/rag_pipeline.py
2025-06-17 19:07:15 +08:00
jyong
7f7ea92a45 r2 2025-06-17 19:06:17 +08:00
Dongyu Li
cf66d111ba feat(datasource): change datasource result type to event-stream 2025-06-17 18:29:02 +08:00
Dongyu Li
739ebf2117 feat(datasource): change datasource result type to event-stream 2025-06-17 18:24:09 +08:00
W_OOD
0476937f55
fix(agent_node):Fix spelling errors. (#21094) 2025-06-17 17:48:43 +08:00
-LAN-
0dcacdf83d
feat: add a flask_context_manager. (#21061)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-06-17 16:31:29 +08:00
jyong
1d2ee9020c r2 2025-06-17 14:04:55 +08:00
Dongyu Li
f37e28a368 feat(datasource): Comment out the datasource_file_manager. 2025-06-17 13:54:25 +08:00
Dongyu Li
c5976f5a09 feat(datasource): change datasource result type to event-stream 2025-06-17 13:51:41 +08:00
jyong
b277acc298 Merge branch 'main' into feat/r2 2025-06-16 14:08:02 +08:00
jyong
8d47d8ce4f Merge remote-tracking branch 'origin/feat/r2' into feat/r2
# Conflicts:
#	api/core/datasource/website_crawl/website_crawl_plugin.py
#	api/services/rag_pipeline/rag_pipeline.py
2025-06-16 13:50:33 +08:00
jyong
41fef8a21f r2 2025-06-16 13:48:43 +08:00
yihong
909259da37
fix: delete some dead code using vulture (#20999)
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
2025-06-16 12:07:41 +08:00
Bowen Liang
366ddb05ae
test: run vdb test of oceanbase with docker compose in CI tests (#20945) 2025-06-16 11:05:19 +08:00
Harry
5ccb8d9736 feat: online document 2025-06-13 18:22:15 +08:00
Harry
0908f310fc feat: webcrawl 2025-06-13 17:47:51 +08:00
jyong
b2b95412b9 r2 2025-06-13 15:04:22 +08:00
-LAN-
c05e47ebc0
refactor(sqlalchemy_workflow_execution_repository): Use the max funtion for getting next_sequence_number. (#20966) 2025-06-13 09:42:02 +08:00
Takuya Ono
af83120832
🐛 Fix(Gemini LLM): Support Gemini 0.2.x plugin on agent app (#20794)
Co-authored-by: QuantumGhost <obelisk.reg+git@gmail.com>
2025-06-12 00:49:38 +08:00
-LAN-
1e03c97663
fix(llm_node): missing parameters for structure outputs (#20915)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-06-11 18:56:07 +08:00
jyong
1d8b390584 Merge branch 'main' into feat/r2
# Conflicts:
#	docker/docker-compose.middleware.yaml
2025-06-11 17:16:27 +08:00
jyong
5f08a9314c r2 2025-06-11 17:10:20 +08:00
jyong
66fa68fa18 r2 2025-06-11 16:36:36 +08:00
Yeuoly
d6d8cca053
refactor: replace compact response generation with length-prefixed response for backwards invocation api (#20903) 2025-06-11 16:01:50 +08:00
Bowen Liang
0f3d4d0b6e
chore: bump mypy to 1.16 (#20608) 2025-06-11 01:01:33 +08:00
jyong
95a24156de r2 2025-06-10 18:20:32 +08:00
jyong
e934503fa0 r2 2025-06-10 18:16:30 +08:00
Jyong
21a50e22d2
fix auto metadata filter (#20845) 2025-06-10 10:46:17 +02:00
QuantumGhost
c439e82038
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
jyong
ad3d9cf782 r2 2025-06-10 10:00:20 +08:00
QuantumGhost
a97ff587d2
fix(api): Resolve error encountered when executing QuestionClassifieNode (#20829)
The `QuestionClassifierNode` class extends `LLMNode`, meaning that, per the Liskov Substitution Principle, `QuestionClassifierNodeData` **SHOULD** be compatible in contexts where `LLMNodeData` is expected.

However, the absence of the `structured_output_enabled` attribute violates this principle, causing `QuestionClassifierNode` to fail during execution.

This commit implements a quick and temporary workaround. A proper resolution would involve refactoring to decouple `QuestionClassifierNode` from `LLMNode` to address the underlying design issue.

Fixes #20725.
2025-06-10 00:34:51 +08:00
jyong
47664f8fd3 r2 2025-06-09 14:00:34 +08:00
yihong
65c7c01d90
fix: clean up two unreachable code (#20773)
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
2025-06-07 23:06:46 +08:00
Bharat Ramanathan
e6e76852d5
Add support for W&B dedicated cloud instances in Weave tracing integration (#20765)
Co-authored-by: crazywoola <427733928@qq.com>
2025-06-07 23:06:23 +08:00
jyong
21a3509bef r2 2025-06-06 17:14:43 +08:00
jefferyvvv
37c3283450
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