Commit Graph
3276 Commits
Author SHA1 Message Date
Boris FeldandGitHub c939f04b1a Add support for tracking conversation with Opik Tracer (#20063) 2025-05-22 16:11:50 +08:00
jameshui1997andGitHub 648393cc7b fix: improve tracing provider validation logic in OpsTraceManager (#20042) 2025-05-22 14:08:36 +08:00
6f48af2610 Refactor OpenSearch config to separate use_ssl and verify_certs flags (#20075)
Co-authored-by: he.huang <[email protected]>
Co-authored-by: crazywoola <[email protected]>
2025-05-22 10:14:38 +08:00
adca981eee fix: uninitialized variable error on empty knowledge retrieval(agent) (#20025)
Co-authored-by: crazywoola <[email protected]>
2025-05-22 10:09:07 +08:00
-LAN-andGitHub 6b3666f826 feat: Split WorkflowCycleManager (#20071)
Signed-off-by: -LAN- <[email protected]>
2025-05-22 09:49:25 +08:00
heysztandGitHub 02929b2cce Fix/fix trace provider delete err (#20070) 2025-05-21 23:51:42 +08:00
-LAN-andGitHub d31235ca13 feat: Introduce WorkflowExecution Domain Entity and Repository, Replace WorkflowRun Direct Usage, and Unify Stream Response Logic (#20067)
Signed-off-by: -LAN- <[email protected]>
2025-05-21 22:01:53 +08:00
7d230acf40 tencent vectordb compatible with version 1.1.3 and below (#20056)
Co-authored-by: wlleiiwang <[email protected]>
2025-05-21 20:24:05 +08:00
QuantumGhostandGitHub 13dc1c8795 Simplify execution_metadata Handling for WorkflowNodeExecution (#20062)
Currently, `WorkflowNodeExecution.execution_metadata_dict` returns `None` when metadata is absent in the database. This requires all callers to perform `None` checks when processing metadata, leading to more complex caller-side logic.

This pull request updates the `execution_metadata_dict` method to return an empty dictionary instead of `None` when metadata is absent. This change would simplify the caller logic, as it removes the need for explicit `None` checks and provides a more consistent data structure to work with.
2025-05-21 18:38:16 +08:00
-LAN-andGitHub 57bcb616bc fix(sqlalchemy_workflow_node_execution_repository): Missing triggered_from while querying WorkflowNodeExecution (#20044)
Signed-off-by: -LAN- <[email protected]>
2025-05-21 16:37:44 +08:00
-LAN-andGitHub 3196dc2d61 refactor: Use typed SQLAlchemy base model and fix type errors (#19980)
Signed-off-by: -LAN- <[email protected]>
2025-05-21 15:38:03 +08:00
PanpanandGitHub ef3569e667 feat: support chatflow start node custom input field hidden (#19678) 2025-05-21 13:52:21 +08:00
36b321735e fix create_tracing_app_config error (#19884) (#20004)
Co-authored-by: codly <[email protected]>
2025-05-21 10:45:10 +08:00
c58678d84d chore: Reduce the invocation of the plugin interface (#19629)
Co-authored-by: hobo.l <[email protected]>
Co-authored-by: crazywoola <[email protected]>
2025-05-20 16:55:21 +08:00
87f9d11d65 fix: ensure Decimal values in metadata are JSON serializable (fixes #19936) (#19955)
Co-authored-by: crazywoola <[email protected]>
2025-05-20 15:38:31 +08:00
DarlewoandGitHub 8cb3b4aef2 fix: multiple retrieve reranking_enabled switch (#19958) 2025-05-20 15:22:03 +08:00
Amir Mohsen AsaranandGitHub c9ee60e197 Feat(WaterCrawl error handling): add custom exceptions and error handling (#19948) 2025-05-20 10:25:16 +08:00
QuantumGhostandGitHub 6a9e0b1005 feat(api): Introduce WorkflowDraftVariable Model (#19737)
- Introduce `WorkflowDraftVariable` model and the corresponding migration.
- Implement `EnumText`,  a custom column type for SQLAlchemy designed
  to work seamlessly with enumeration classes based on `StrEnum`.
2025-05-19 22:59:56 +08:00
非法操作andGitHub bbebf9ad3e fix: db_model save to _node_execution_cache (#19911) 2025-05-19 17:17:43 +08:00
heysztandGitHub 11146b6bae fix create_tracing_app_config error (#19884) 2025-05-19 10:09:21 +08:00
-LAN-andGitHub 7d0106b220 fix: correct type mismatch in WorkflowService node execution handling (#19846)
Signed-off-by: -LAN- <[email protected]>
2025-05-17 12:31:27 +08:00
4977bb21ec feat(workflow): domain model for workflow node execution (#19430)
Signed-off-by: -LAN- <[email protected]>
Co-authored-by: Copilot <[email protected]>
2025-05-17 00:56:16 +08:00
YeuolyandGitHub ff0feaf34e fix: handle EndpointSetupFailedError in BasePluginClient (#19613) 2025-05-15 13:59:43 +08:00
b292990075 Fix: Ensure unique index names for pgvector knowledge tables (#19672)
Co-authored-by: crazywoola <[email protected]>
2025-05-15 11:43:44 +08:00
303c6ecc1d fix: The init_azure_openai() method in the core/hosting_configuration.py file doesn't work (#19704) (#19705)
Co-authored-by: crazywoola <[email protected]>
2025-05-15 10:02:59 +08:00
1b4fea1794 fix: Referencing Metadata in the response of the External Knowledge A… (#19637) (#19644)
Co-authored-by: satou.kazuhiro <[email protected]>
2025-05-14 15:05:28 +08:00
fabfc7d4d8 fix: remove error message $ symbol (#19587)
Co-authored-by: 刘江波 <[email protected]>
Co-authored-by: crazywoola <[email protected]>
2025-05-13 16:20:29 +08:00
57b3912227 fix: common prerequisite node workflow remove reachable node that failed to streaming llm… (#19552)
Co-authored-by: zhangshibo <[email protected]>
2025-05-13 13:47:29 +08:00
Bowen LiangandGitHub 0b22e8b544 chore: speed up api service startup time by defering the imports for trace services (#19504) 2025-05-13 09:13:25 +08:00
085bd1aa93 chore: model.query change to db.session.query (#19551)
Co-authored-by: QuantumGhost <[email protected]>
2025-05-13 09:13:12 +08:00
非法操作andGitHub 14cd71ed0a chore: all model.query replace to db.session.query (#19521) 2025-05-12 15:19:41 +08:00
非法操作andGitHub b00f94df64 fix: replace all dataset.Model.query to db.session.query(Model) (#19509) 2025-05-12 13:52:33 +08:00
LeanDeRandGitHub c720e0dd04 refactor(workflow): revamp logging module for loop & iteration nodes (#19484) 2025-05-12 09:32:41 +08:00
湛露先生andGitHub 1119790b02 clean rag word_extractor. (#19397)
Signed-off-by: zhanluxianshen <[email protected]>
2025-05-09 16:39:16 +08:00
Bowen LiangandGitHub cbc8ebd8f5 chore: bump pydantic to 2.11 and pydantic-settings to 2.9 (#15049) 2025-05-08 17:39:51 +08:00
WillandGitHub 58d9d35515 fix: inconsistent metadata definitions (#19343) 2025-05-08 16:33:28 +08:00
YeuolyandGitHub 3258a91d5d Feat/add repo to plugin manifest (#19337) 2025-05-07 17:28:38 +08:00
WillandGitHub 0358859467 fix: llm_usage.total_tokens stat (#19177) 2025-05-07 16:42:49 +08:00
WillandGitHub bfa652f2d0 fix: metadata filtering condition variable unassigned; fix External K… (#19208) 2025-05-07 14:52:09 +08:00
-LAN-andGitHub f23cf98317 refactor: Remove RepositoryFactory (#19176)
Signed-off-by: -LAN- <[email protected]>
2025-05-06 21:14:51 +08:00
NoviceandGitHub 0cfc82d731 fix(structured-output): reasoning model's json format parsing (#19261) 2025-05-06 13:16:08 +08:00
Bowen LiangandGitHub 8537abfff8 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
kenwoodjwandGitHub c5568f756f fix basic auth if not base64 encode (#19242)
Signed-off-by: kenwoodjw <[email protected]>
2025-05-06 09:18:37 +08:00
Bowen LiangandGitHub 22f5af9987 fix: support non-ascii charactors in filename of the tool files (#19228) 2025-05-06 09:18:11 +08:00
Hao ChengandGitHub 9bcf837f17 fix: use only supported operators in metadata filter system prompts (#19195) 2025-05-03 20:08:08 +08:00
WillandGitHub a212a63e6a fix: time type metadata filtering error (#19192) 2025-05-03 20:07:37 +08:00
非法操作andGitHub 1ca6dbcdc8 fix: file name incorrect when download file (#19183) 2025-04-30 22:47:59 +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]>
Co-authored-by: -LAN- <[email protected]>
2025-04-30 17:28:02 +08:00
Bowen LiangandGitHub 12c96b93d9 immediately return initialed tiktokenizer instance and remove dead code in usage of tiktokenizer (#17957) 2025-04-30 16:07:20 +08:00
-LAN-andGitHub bcc95e520b feat: support remove first and remove last in variable assigner (#19144)
Signed-off-by: -LAN- <[email protected]>
2025-04-30 15:50:00 +08:00