1e39a3dce3
fix: support non-ascii charactors in filename of the tool files ( #19228 )
2025-05-06 09:18:11 +08:00
e7bf16ab27
chore: required pip and performance improvment in mypy checks ( #19225 )
2025-05-06 09:16:43 +08:00
c4d865409e
Fix appURL construction when basePath is empty ( #19234 )
2025-05-05 22:35:41 +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
bbd9fd3a17
chore: bump celery from 5.4 to 5.5 ( #19190 )
2025-05-03 20:07:04 +08:00
fcf5d31932
feat: Plugin page related document supports multiple languages ( #19197 )
2025-05-03 20:03:56 +08:00
eeb4bf1eea
fix: fix API tool integration test ( #19187 )
2025-05-01 14:49:43 +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
04aadbe19a
fix: mouse scrolling zooming can not function anymore ( #19160 )
2025-04-30 16:57:48 +08:00
7248057d11
ci: add diff to lint ci ( #17874 )
...
Signed-off-by: yihong0618 <zouzou0208@gmail.com >
Co-authored-by: -LAN- <laipz8200@outlook.com >
2025-04-30 16:27:25 +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
cb9b7b410c
fix(i18n): add functions to retrieve document and pricing page languages ( #19142 )
2025-04-30 14:58:49 +08:00
de7d784ecd
fix: fix render undefined when text children is empty ( #19135 )
2025-04-30 14:17:41 +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
8bd8a07758
fix: fix import LexicalErrorBoundary error ( #19124 )
2025-04-30 11:05:47 +08:00
6ec2e661f5
feat(logAndAnn): add control option for question editing feature ( #19117 )
2025-04-30 10:57:23 +08:00
4270ffeb39
add Accept-Ranges header for audio/video files ( #19119 )
2025-04-30 10:51:27 +08:00
7212404f4c
fix(api): resolve external knowledge API error due to excessive URL validation ( #19003 )
...
The `validators.url` method from the `validators==0.21.0` library enforces a
URL length limit of less than 90 characters, which led to failures in external
knowledge API requests for long URLs.
This PR addresses the issue by replacing `validators.url` with
`urllib.parse.urlparse`, effectively removing the restrictive URL length check.
Additionally, the unused `validators` dependency has been removed.
Fixes #18981 .
Signed-off-by: kenwoodjw <blackxin55+@gmail.com >
2025-04-29 22:32:38 +08:00
8d3f0c2bce
fix: Chinese input deletes extra character in Safari within Workspaces ( #18193 ) ( #19088 )
2025-04-29 18:47:35 +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
2f6b39e08a
fix: change provider should change the content ( #19075 )
2025-04-29 15:49:31 +08:00
13511b567b
fix: image preview triggers binary download ( #19070 )
2025-04-29 15:38:33 +08:00
487519a07c
fix: remove redundant Mermaid graph direction enforcement ( #19024 )
2025-04-29 15:10:38 +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
20855a8b93
fix(web): fix the wrong components usage( #18995 ) ( #19065 )
2025-04-29 14:39:59 +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
0de9276836
chore: improve diagram picture of docker compose ( #19054 )
2025-04-29 11:43:50 +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
1e038f6480
test(graph-engine-test): modify the assert condition ( #19041 )
2025-04-29 09:51:42 +08:00
72fa979a50
chore: Improve FILES_URL Configuration Comments ( #19040 )
2025-04-29 09:05:04 +08:00
bb9df4fba6
fix: fix embedded chatbot styles on a relatively wide screen ( #19030 )
2025-04-29 08:58:10 +08:00
285720406c
fixes: fix entrypoint script with missing environment variables ( #19039 )
2025-04-29 08:57:58 +08:00
8b1ee452fd
feat: clean up message_files table first before proceeding to find orphaned files ( #19035 )
2025-04-29 08:57:42 +08:00
bf95e73604
refactor: switch to dynamic versioning in package configuration ( #19019 )
...
Signed-off-by: -LAN- <laipz8200@outlook.com >
2025-04-28 19:51:50 +08:00
4adceec60f
remove unstructured api key check ( #18989 )
2025-04-28 17:26:30 +08:00
4d76595e6d
add MAX_TASK_PRE_CHILD for celery ( #18985 )
2025-04-28 17:06:00 +08:00
8b542cdea1
chore: Bump version to 1.3.1 ( #18962 )
...
Signed-off-by: -LAN- <laipz8200@outlook.com >
2025-04-28 16:45:17 +08:00
164142c97f
feat: Upload a folder to knowledgebase ( #17026 )
...
Co-authored-by: Silow9 <soulskytony@gmail.com >
2025-04-28 15:31:22 +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
54d17430c2
feat: improve embedded chatbot styles ( #18692 )
2025-04-28 14:38:59 +08:00
a3e6ecba7c
if as_attachment is in the url, add it to the sign_url ( #18930 )
2025-04-28 14:25:59 +08:00
a61732c3e1
fix: header padding ( #18957 )
2025-04-28 13:57:44 +08:00
Bowen Liang