b8cb5f5ea2
refactor(typing): Fixup typing A2 - workflow engine & nodes ( #31723 )
...
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
Co-authored-by: Asuka Minato <[email protected]
2026-01-31 18:00:56 +09:00
c2473d85dc
feat: Add summary index for knowledge. ( #31625 )
...
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
Co-authored-by: Jyong <[email protected] [email protected] [email protected] [email protected] [email protected] [email protected]
2026-01-29 13:47:35 +08:00
fe0802262c
feat: credit pool ( #30720 )
...
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2026-01-08 13:17:30 +08:00
4f0fb6df2b
chore: use from __future__ import annotations ( #30254 )
...
Co-authored-by: Dev <[email protected] [email protected] [email protected]
2026-01-06 23:57:20 +09:00
Jyong and GitHub
b49e2646ff
fix: session unbound during parent-child retrieval ( #29396 )
2025-12-10 14:08:55 +08:00
znn and GitHub
1b9165624f
adding llm_usage and error_type ( #26546 )
2025-12-10 09:19:13 +08:00
9affc546c6
Feat/support multimodal embedding ( #29115 )
...
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
2025-12-09 14:41:46 +08:00
-LAN- and GitHub
8b761319f6
Refactor workflow nodes to use generic node_data ( #28782 )
2025-11-27 20:46:56 +08:00
-LAN- and GitHub
13bf6547ee
Refactor: centralize node data hydration ( #27771 )
2025-11-27 15:41:56 +08:00
1e9142c213
feat: enhance tencent trace integration with LLM core metrics ( #27126 )
...
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
Co-authored-by: crazywoola <[email protected]
2025-10-29 15:53:30 +08:00
white-loub and GitHub
f811471b18
fix: support structured output in streaming mode for LLM node ( #27089 )
2025-10-20 14:53:25 +09:00
-LAN- and GitHub
578247ffbc
feat(graph_engine): Support pausing workflow graph executions ( #26585 )
...
Signed-off-by: -LAN- <[email protected]
2025-10-19 21:33:41 +08:00
1bd621f819
remove .value ( #26633 )
...
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2025-10-11 09:08:29 +08:00
decf0f3da0
Fix: Remove workflow/nodes from pyright exclusion ( #26461 )
...
Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com>
2025-09-30 15:39:04 +08:00
86c3c58e64
support returning structured output when using LLM API non streaming invocation ( #26451 )
...
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
2025-09-30 10:58:35 +08:00
QuantumGhost and GitHub
13fe2ca8fe
fix(api): fix single stepping variable loading ( #25908 )
2025-09-18 17:30:02 +08:00
+10
85cda47c70
feat: knowledge pipeline ( #25360 )
...
Signed-off-by: -LAN- <[email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] [email protected]
2025-09-18 12:49:10 +08:00
bab4975809
chore: add ast-grep rule to convert Optional[T] to T | None ( #25560 )
...
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
2025-09-15 13:06:33 +08:00
08dd3f7b50
Fix basedpyright type errors ( #25435 )
...
Signed-off-by: -LAN- <[email protected]
2025-09-10 01:54:26 +08:00
a78339a040
remove bare list, dict, Sequence, None, Any ( #25058 )
...
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
Co-authored-by: -LAN- <[email protected]
2025-09-06 03:32:23 +08:00
edf4a1b652
feat: add reasoning format processing to LLMNode for <think> tag handling ( #23313 )
...
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
2025-09-05 18:15:35 +08:00
dac72b078d
feat: support bool type variable frontend ( #24437 )
...
Co-authored-by: QuantumGhost <[email protected]
2025-08-26 18:16:05 +08:00
jiangbo721 and GitHub
1d776c4cd0
feat: If combining text and files, place the text prompt after the fi… ( #24472 )
2025-08-25 17:51:46 +08:00
-LAN- and GitHub
da9af7b547
[Chore/Refactor] Use centralized naive_utc_now for UTC datetime operations ( #24352 )
...
Signed-off-by: -LAN- <[email protected]
2025-08-22 23:53:05 +08:00
106ab7f2a8
Fix: safe defaults for BaseModel dict fields ( #24098 )
...
Co-authored-by: Yongtao Huang <[email protected]
2025-08-21 21:38:55 +08:00
crazywoola and GitHub
acba135de1
Revert "feat: support to upload files for visual model call when running LLM node for debugging in a single step" ( #23922 )
2025-08-14 15:52:19 +08:00
4da6ec787e
feat: support to upload files for visual model call when running LLM node for debugging in a single step ( #23521 )
...
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
2025-08-13 14:07:13 +08:00
a434f6240f
Chroe: some misc cleanup ( #23203 )
...
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
2025-07-31 15:33:39 +08:00
Will and GitHub
095bae01b2
fix: Invalid expected metadata value type error ( #22793 )
2025-07-22 22:28:16 +08:00
460a825ef1
refactor: decouple Node and NodeData ( #22581 )
...
Signed-off-by: -LAN- <[email protected] [email protected]
2025-07-18 10:08:51 +08:00
Kalo Chin and GitHub
7a69b57823
Fix jinja2 variable naming inconsistencies ( #22578 )
2025-07-17 22:16:47 +08:00
816210d744
Expose LLM usage in workflows ( #21766 )
...
Co-authored-by: crazywoola <[email protected]
2025-07-08 21:18:00 +08:00
0cb00d5fd2
refactor: move structured output support outside LLM Node ( #21565 )
...
Co-authored-by: Novice <[email protected]
2025-06-27 14:55:31 +08:00
QuantumGhost and GitHub
10b738a296
feat: Persist Variables for Enhanced Debugging Workflow ( #20699 )
...
This pull request introduces a feature aimed at improving the debugging experience during workflow editing. With the addition of variable persistence, the system will automatically retain the output variables from previously executed nodes. These persisted variables can then be reused when debugging subsequent nodes, eliminating the need for repetitive manual input.
By streamlining this aspect of the workflow, the feature minimizes user errors and significantly reduces debugging effort, offering a smoother and more efficient experience.
Key highlights of this change:
- Automatic persistence of output variables for executed nodes.
- Reuse of persisted variables to simplify input steps for nodes requiring them (e.g., `code`, `template`, `variable_assigner`).
- Enhanced debugging experience with reduced friction.
Closes #19735 .
2025-06-24 09:05:29 +08:00
-LAN- and GitHub
1e03c97663
fix(llm_node): missing parameters for structure outputs ( #20915 )
...
Signed-off-by: -LAN- <[email protected]
2025-06-11 18:56:07 +08:00
Jyong and GitHub
21a50e22d2
fix auto metadata filter ( #20845 )
2025-06-10 10:46:17 +02:00
QuantumGhost and GitHub
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
Arcaner and GitHub
ad2f25875e
fix(llm_node): update file variable mapping to use vision configs ( #20417 )
2025-06-05 09:58:24 +08:00
-LAN- and GitHub
5ccfb1f4ba
refactor: Improve model status handling and structured output ( #20586 )
...
Signed-off-by: -LAN- <[email protected]
2025-06-04 19:56:54 +08:00
-LAN- and GitHub
72fdafc180
refactor: Replaces direct DB session usage with context managers ( #20569 )
...
Signed-off-by: -LAN- <[email protected]
2025-06-03 16:16:06 +08:00
-LAN- and GitHub
a6ea15e63c
Refactor/message cycle manage and knowledge retrieval ( #20460 )
...
Signed-off-by: -LAN- <[email protected]
2025-05-30 14:36:44 +08:00
-LAN- and GitHub
32e779eef3
refactor(workflow): Rename NodeRunMetadataKey to WorkflowNodeExecutionMetadataKey ( #20457 )
...
Signed-off-by: -LAN- <[email protected]
2025-05-30 04:47:56 +08:00
-LAN- and GitHub
482e50aae9
Refactor/remove db from cycle manager ( #20455 )
...
Signed-off-by: -LAN- <[email protected]
2025-05-30 04:34:13 +08:00
Will and GitHub
58d9d35515
fix: inconsistent metadata definitions ( #19343 )
2025-05-08 16:33:28 +08:00
Novice and GitHub
0cfc82d731
fix(structured-output): reasoning model's json format parsing ( #19261 )
2025-05-06 13:16:08 +08:00
349c3cf7b8
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- <[email protected] [email protected]
2025-04-30 17:28:02 +08:00
非法操作 and GitHub
c1559a7c8e
fix: LLMResultChunk cause concatenate str and list exception ( #18852 )
2025-04-27 11:32:14 +08:00
a1158cc946
fix: Update prompt message content types to use Literal and add union type for content ( #17136 )
...
Co-authored-by: 朱庆超 <[email protected] [email protected]
2025-04-22 16:17:55 +08:00
Novice and GitHub
da9269ca97
feat: structured output ( #17877 )
2025-04-18 16:33:53 +08:00
Jacky Wu and GitHub
ed5596a8f4
fix: avoid llm node result var not init issue while do retry. ( #14286 )
2025-03-11 12:43:24 +08:00
