24927af08b
fix: db_model save to _node_execution_cache ( #19911 )
2025-05-19 17:17:43 +08:00
e69007c40d
fix create_tracing_app_config error ( #19884 )
2025-05-19 10:09:21 +08:00
c82bf51746
fix: correct type mismatch in WorkflowService node execution handling ( #19846 )
...
Signed-off-by: -LAN- <laipz8200@outlook.com >
2025-05-17 12:31:27 +08:00
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
1e9dc22f7c
fix: handle EndpointSetupFailedError in BasePluginClient ( #19613 )
2025-05-15 13:59:43 +08:00
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
3e20e3ed0c
fix: The init_azure_openai() method in the core/hosting_configuration.py file doesn't work ( #19704 ) ( #19705 )
...
Co-authored-by: crazywoola <427733928@qq.com >
2025-05-15 10:02:59 +08:00
771feb0486
fix: Referencing Metadata in the response of the External Knowledge A… ( #19637 ) ( #19644 )
...
Co-authored-by: satou.kazuhiro <satou.kazuhiro@fanuc.co.jp >
2025-05-14 15:05:28 +08:00
8e26b04d39
fix: remove error message $ symbol ( #19587 )
...
Co-authored-by: 刘江波 <jiangbo721@163.com >
Co-authored-by: crazywoola <427733928@qq.com >
2025-05-13 16:20:29 +08:00
80788e8cf4
fix: common prerequisite node workflow remove reachable node that failed to streaming llm… ( #19552 )
...
Co-authored-by: zhangshibo <zhangshibo@didiglobal.com >
2025-05-13 13:47:29 +08:00
c4e82f6042
chore: speed up api service startup time by defering the imports for trace services ( #19504 )
2025-05-13 09:13:25 +08:00
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
06a15bf2ae
chore: all model.query replace to db.session.query ( #19521 )
2025-05-12 15:19:41 +08:00
fa226ece81
fix: replace all dataset.Model.query to db.session.query(Model) ( #19509 )
2025-05-12 13:52:33 +08:00
e482628adf
refactor(workflow): revamp logging module for loop & iteration nodes ( #19484 )
2025-05-12 09:32:41 +08:00
9932f338e8
clean rag word_extractor. ( #19397 )
...
Signed-off-by: zhanluxianshen <zhanluxianshen@163.com >
2025-05-09 16:39:16 +08:00
d4b89bdde2
chore: bump pydantic to 2.11 and pydantic-settings to 2.9 ( #15049 )
2025-05-08 17:39:51 +08:00
562ef031d0
fix: inconsistent metadata definitions ( #19343 )
2025-05-08 16:33:28 +08:00
4f6d9df81b
Feat/add repo to plugin manifest ( #19337 )
2025-05-07 17:28:38 +08:00
586983272d
fix: llm_usage.total_tokens stat ( #19177 )
2025-05-07 16:42:49 +08:00
c1d8ad7b5d
fix: metadata filtering condition variable unassigned; fix External K… ( #19208 )
2025-05-07 14:52:09 +08:00
e85ddde41c
refactor: Remove RepositoryFactory ( #19176 )
...
Signed-off-by: -LAN- <laipz8200@outlook.com >
2025-05-06 21:14:51 +08:00
1641439319
fix(structured-output): reasoning model's json format parsing ( #19261 )
2025-05-06 13:16:08 +08:00
5a3baa271f
chore: avoid repeated type ignore noqa by adding flask_restful and flask_login in mypy import exclusions ( #19224 )
2025-05-06 11:58:49 +08:00
a1d3026ac5
fix basic auth if not base64 encode ( #19242 )
...
Signed-off-by: kenwoodjw <blackxin55+@gmail.com >
2025-05-06 09:18:37 +08:00
1e39a3dce3
fix: support non-ascii charactors in filename of the tool files ( #19228 )
2025-05-06 09:18:11 +08:00
6a1434db92
fix: use only supported operators in metadata filter system prompts ( #19195 )
2025-05-03 20:08:08 +08:00
59fe233202
fix: time type metadata filtering error ( #19192 )
2025-05-03 20:07:37 +08:00
9df51ddf21
fix: file name incorrect when download file ( #19183 )
2025-04-30 22:47:59 +08:00
a1ffe78fc7
feat(api): Add image multimodal support for LLMNode ( #17372 )
...
Enhance `LLMNode` with multimodal capability, introducing support for
image outputs.
This implementation extracts base64-encoded images from LLM responses,
saves them to the storage service, and records the file metadata in the
`ToolFile` table. In conversations, these images are rendered as
markdown-based inline images.
Additionally, the images are included in the LLMNode's output as
file variables, enabling subsequent nodes in the workflow to utilize them.
To integrate file outputs into workflows, adjustments to the frontend code
are necessary.
For multimodal output functionality, updates to related model configurations
are required. Currently, this capability has been applied exclusively to
Google's Gemini models.
Close #15814 .
Signed-off-by: -LAN- <laipz8200@outlook.com >
Co-authored-by: -LAN- <laipz8200@outlook.com >
2025-04-30 17:28:02 +08:00
af7a907960
immediately return initialed tiktokenizer instance and remove dead code in usage of tiktokenizer ( #17957 )
2025-04-30 16:07:20 +08:00
a482b6d088
feat: support remove first and remove last in variable assigner ( #19144 )
...
Signed-off-by: -LAN- <laipz8200@outlook.com >
2025-04-30 15:50:00 +08:00
0abc9c2889
fix: inconsistent case expression in _process_metadata_filter_func ( #19146 )
2025-04-30 15:14:01 +08:00
19e1688daa
fix: metadata filter not work ( #19020 )
...
Co-authored-by: 金鹏程 <jinpengcheng01@corp.netease.com >
Co-authored-by: crazywoola <427733928@qq.com >
2025-04-30 11:06:03 +08:00
487b107e6f
Enhance Code Consistency Across Repository with .editorconfig ( #19023 )
2025-04-29 18:04:33 +08:00
e25e049371
Fix: the issue of getting empty environment variables. ( #19085 )
2025-04-29 18:01:11 +08:00
62f98143c6
feat: add AWS Managed IAM auth for OpenSearch vector DB ( #18963 )
2025-04-29 15:10:08 +08:00
cb10db5f45
feat: support access milvus with token ( #19034 )
2025-04-29 14:52:13 +08:00
97a92f2fc7
fix: fix rerank model runner usage ( #19008 )
2025-04-29 14:51:21 +08:00
c0935d77b5
feat(api): use json_repair to fix invalid json while generating structured output ( #18977 )
...
When generating JSON schema using an LLM in the structured output feature,
models may occasionally return invalid JSON, which prevents clients from correctly
parsing the response and can lead to UI breakage.
This commit addresses the issue by introducing `json_repair` to automatically
fix invalid JSON strings returned by the LLM, ensuring smoother functionality
and better client-side handling of structured outputs.
Co-authored-by: lizb <lizb@sugon.com >
2025-04-29 12:39:13 +08:00
c0bf6d03e0
fix(workflow_cycle_manage): failed nodes were not updated in workflow_node_executions ( #18994 )
2025-04-29 10:31:08 +08:00
4adceec60f
remove unstructured api key check ( #18989 )
2025-04-28 17:26:30 +08:00
edfb6ea16c
feat (document_extractor): support .properties file ( #18969 )
2025-04-28 15:28:11 +08:00
ca5b12c9bc
refactor(plugin/backwards_invocation/app): Remove unnecessary .value from StrEnum ( #18896 )
...
Signed-off-by: -LAN- <laipz8200@outlook.com >
2025-04-28 14:50:59 +08:00
cfa9b91ee1
feat: add VTT data transform to Document extractor ( #18936 )
2025-04-28 13:45:15 +08:00
3f51b0ed7b
fix: when cot_agent call tool like searxng lost some response content ( #16781 )
2025-04-28 09:27:46 +08:00
636c26d18b
refactor: Refactors repository imports structure ( #18901 )
...
Signed-off-by: -LAN- <laipz8200@outlook.com >
2025-04-27 17:29:03 +08:00
9d7fc07e45
feat: add interfaces of OAuth handler methods for authorization ( #18889 )
2025-04-27 16:00:37 +08:00
63802d8104
refactor: rename plugin manager to plugin client and rename path from manager to impl ( #18876 )
2025-04-27 14:22:25 +08:00
84b076bf93
fix: LLMResultChunk cause concatenate str and list exception ( #18852 )
2025-04-27 11:32:14 +08:00
非法操作