Commit Graph

2467 Commits (d1d06ed9fcc02e5dab7d9faa7a609c5080b80428)

Author SHA1 Message Date
yihong 5a991295e0
fix: drop some type fixme (#20344) 1 year ago
-LAN- db488bef51
refactor(api/core/workflow/enums): Rename WORKFLOW_RUN_ID to WORKFLOW_EXECUTION_ID (#20459)
Signed-off-by: -LAN- <laipz8200@outlook.com>
1 year ago
-LAN- f2e0d161a1
fix(ops_trace_manager): Adds app_id to TraceTask initialization (#20461)
Signed-off-by: -LAN- <laipz8200@outlook.com>
1 year ago
-LAN- f7fb10635f
refactor(workflow): Rename workflow node execution models (#20458)
Signed-off-by: -LAN- <laipz8200@outlook.com>
1 year ago
-LAN- 32e779eef3
refactor(workflow): Rename NodeRunMetadataKey to WorkflowNodeExecutionMetadataKey (#20457)
Signed-off-by: -LAN- <laipz8200@outlook.com>
1 year ago
-LAN- 482e50aae9
Refactor/remove db from cycle manager (#20455)
Signed-off-by: -LAN- <laipz8200@outlook.com>
1 year ago
Yeuoly d4408e0f54
fix: handle values in output arrays for CodeNode transformation (#20437) 1 year ago
Bowen Liang eee88a8012
chore: improve error logging for requests to plugin daemon (#20328) 1 year ago
Novice b2ab401279
chore: remove agent turn limits (#19930) 1 year ago
Novice 9bbd646f40
fix: inner invoke llm token too long (#20391) 1 year ago
QuantumGhost 4c7873bdd9 feat(api): inject the variable_loader all the way down for loop & iteration
# Conflicts:
#	api/core/app/apps/advanced_chat/app_generator.py
#	api/core/app/apps/workflow/app_generator.py
1 year ago
QuantumGhost 31fa5baadf feat(api): overhaul draft variable saving logic
add support for many node types
1 year ago
QuantumGhost cf034b53e0 feat(api): Move DummyLoader from workflow_entry to variable_loader
add a utility function for variable loading logic.
1 year ago
QuantumGhost 710d729b4b feat(api): Add a dummy `VariableLoader`, add a utility function
for variable loading logic.
1 year ago
QuantumGhost d720287504 feat(api): utilize `ConversationVariableUpdater` in variable assigner nodes
Removed the original logic
1 year ago
QuantumGhost 1b234de81f feat(api): Implement variable mapping extraction for VariableAssignerNode 1 year ago
QuantumGhost b376f7aeec feat(api): include the loop variables in extracted variable mappings 1 year ago
QuantumGhost 253978b8df docs(api): Update docs for `extract_variable_selector_to_variable_mapping` 1 year ago
QuantumGhost fd38cfd6b2 chore(api): remove the constructor for `VariablePool`
Replace it with `model_post_init` as suggested by
Pydantic docs.
1 year ago
QuantumGhost ed4b072467 feat(api): Implement VariableLoader in `DraftVarLoader`.
Use DraftVarLoader to load required variables when single stepping a
node.
1 year ago
QuantumGhost b7a4117341 feat(api): Introduce a VariableLoader interface.
The `VariableLoader` interface is used to load referenced variables
when running a single node.
1 year ago
QuantumGhost d83c8ade4a feat(api): Implement variable mapping extraction for `IfElseNode`
This allows us to extract referenced variables from `IfElseNode` configurations.
1 year ago
QuantumGhost c4e7489be5 docs(api): Add documentation for `extract_variable_selector_to_variable_mapping`
Add a detail description about the arguments and
the return value of
`BaseNode.extract_variable_selector_to_variable_mapping`.
1 year ago
QuantumGhost 85ab1dc8d9 fix(api): Fix incorrect handling of `Variable` types in `VariablePool` 1 year ago
QuantumGhost 7ee95dbc1c docs(api): Add a documentation about equality of `FloatSegment` 1 year ago
QuantumGhost 5aa044e392 feat(api): implement draft var related api 1 year ago
QuantumGhost c7e6b9ce9c feat(api): save output variables to draft variables while debugging workflow 1 year ago
QuantumGhost 655d55f290 feat(api): add a `version` class method to BaseNode and subclasses
This ensures that we can get the version of node while executing.

Add `node_version` to `BaseNodeEvent` to ensure that all node
related events includes node version information.
1 year ago
-LAN- f59fb94dae
feat(agent_node): ensure that the enum-checking syntax is compatible with Python 3.11. (#20373)
Signed-off-by: -LAN- <laipz8200@outlook.com>
1 year ago
teawoong Kim 400ae664bb
fix(http): force multipart/form-data even without files(#20322) (#20323) 1 year ago
-LAN- eaaf551497
fix: Instance <Account> is not bound to a Session (#20347)
Signed-off-by: -LAN- <laipz8200@outlook.com>
1 year ago
-LAN- f233a64eb5
fix(workflow): fetch user failed when workflow run in parallel mode (#20321)
Signed-off-by: -LAN- <laipz8200@outlook.com>
1 year ago
rouxiaomin 4c4887c5fc
feat(qdrant):add replication_factor when create collection in qdrant (#20133)
Co-authored-by: 刘敏 <min.liu@tongdun.net>
1 year ago
-LAN- d3bfcd498b
fix: Refactor web reader to use readabilipy (#19789)
Signed-off-by: -LAN- <laipz8200@outlook.com>
1 year ago
-LAN- 9c9d3d7bd0
feat: document extractor chardet encoding (#20269)
Signed-off-by: -LAN- <laipz8200@outlook.com>
1 year ago
Good Wood 756f35f480
feat: add pagination for plugin page (#20151) 1 year ago
-LAN- 55503ce771
fix: persist workflow execution status on partial success and failure (#20264)
Signed-off-by: -LAN- <laipz8200@outlook.com>
1 year ago
-LAN- b357eca307
fix: Copy request context and current user in app generators. (#20240)
Signed-off-by: -LAN- <laipz8200@outlook.com>
1 year ago
非法操作 acd4b9a8ac
fix: not save workflow_run_id of chatflow message (#20257) 1 year ago
cooper.wu 2cad98f01f
fix: #18132 when deepseek llm model, auto_generate name can't work (#18646)
Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>
1 year ago
Heyang Wang b9b5d43dc6
fix: add 'floatfmt' when extract number from excel ( #20153 ) (#20193)
Co-authored-by: wangheyang <wangheyang@corp.netease.com>
Co-authored-by: crazywoola <427733928@qq.com>
1 year ago
Boris Feld c939f04b1a
Add support for tracking conversation with Opik Tracer (#20063) 1 year ago
jameshui1997 648393cc7b
fix: improve tracing provider validation logic in OpsTraceManager (#20042) 1 year ago
He Huang 6f48af2610
Refactor OpenSearch config to separate use_ssl and verify_certs flags (#20075)
Co-authored-by: he.huang <he.huang1@outlook.com>
Co-authored-by: crazywoola <427733928@qq.com>
1 year ago
zhudongwork adca981eee
fix: uninitialized variable error on empty knowledge retrieval(agent) (#20025)
Co-authored-by: crazywoola <427733928@qq.com>
1 year ago
-LAN- 6b3666f826
feat: Split WorkflowCycleManager (#20071)
Signed-off-by: -LAN- <laipz8200@outlook.com>
1 year ago
heyszt 02929b2cce
Fix/fix trace provider delete err (#20070) 1 year ago
-LAN- d31235ca13
feat: Introduce WorkflowExecution Domain Entity and Repository, Replace WorkflowRun Direct Usage, and Unify Stream Response Logic (#20067)
Signed-off-by: -LAN- <laipz8200@outlook.com>
1 year ago
wlleiiwang 7d230acf40
tencent vectordb compatible with version 1.1.3 and below (#20056)
Co-authored-by: wlleiiwang <wlleiiwang@tencent.com>
1 year ago
QuantumGhost 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.
1 year ago
-LAN- 57bcb616bc
fix(sqlalchemy_workflow_node_execution_repository): Missing `triggered_from` while querying WorkflowNodeExecution (#20044)
Signed-off-by: -LAN- <laipz8200@outlook.com>
1 year ago
-LAN- 3196dc2d61
refactor: Use typed SQLAlchemy base model and fix type errors (#19980)
Signed-off-by: -LAN- <laipz8200@outlook.com>
1 year ago
Panpan ef3569e667
feat: support chatflow start node custom input field hidden (#19678) 1 year ago
俊晨 36b321735e
fix create_tracing_app_config error (#19884) (#20004)
Co-authored-by: codly <codly.fun@gmail.com>
1 year ago
luckylhb90 c58678d84d
chore: Reduce the invocation of the plugin interface (#19629)
Co-authored-by: hobo.l <hobo.l@binance.com>
Co-authored-by: crazywoola <427733928@qq.com>
1 year ago
Zihe JI 87f9d11d65
fix: ensure Decimal values in metadata are JSON serializable (fixes #19936) (#19955)
Co-authored-by: crazywoola <427733928@qq.com>
1 year ago
Darlewo 8cb3b4aef2
fix: multiple retrieve reranking_enabled switch (#19958) 1 year ago
Amir Mohsen Asaran c9ee60e197
Feat(WaterCrawl error handling): add custom exceptions and error handling (#19948) 1 year ago
QuantumGhost 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`.
1 year ago
非法操作 bbebf9ad3e
fix: db_model save to _node_execution_cache (#19911) 1 year ago
heyszt 11146b6bae
fix create_tracing_app_config error (#19884) 1 year ago
-LAN- 7d0106b220
fix: correct type mismatch in WorkflowService node execution handling (#19846)
Signed-off-by: -LAN- <laipz8200@outlook.com>
1 year ago
-LAN- 4977bb21ec
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>
1 year ago
Yeuoly ff0feaf34e
fix: handle EndpointSetupFailedError in BasePluginClient (#19613) 1 year ago
k-kayashima b292990075
Fix: Ensure unique index names for pgvector knowledge tables (#19672)
Co-authored-by: crazywoola <427733928@qq.com>
1 year ago
zhaobingshuang 303c6ecc1d
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>
1 year ago
satohk 1b4fea1794
fix: Referencing Metadata in the response of the External Knowledge A… (#19637) (#19644)
Co-authored-by: satou.kazuhiro <satou.kazuhiro@fanuc.co.jp>
1 year ago
jiangbo721 fabfc7d4d8
fix: remove error message $ symbol (#19587)
Co-authored-by: 刘江波 <jiangbo721@163.com>
Co-authored-by: crazywoola <427733928@qq.com>
1 year ago
SSebo 57b3912227
fix: common prerequisite node workflow remove reachable node that failed to streaming llm… (#19552)
Co-authored-by: zhangshibo <zhangshibo@didiglobal.com>
1 year ago
Bowen Liang 0b22e8b544
chore: speed up api service startup time by defering the imports for trace services (#19504) 1 year ago
非法操作 085bd1aa93
chore: model.query change to db.session.query (#19551)
Co-authored-by: QuantumGhost <obelisk.reg+git@gmail.com>
1 year ago
非法操作 14cd71ed0a
chore: all model.query replace to db.session.query (#19521) 1 year ago
非法操作 b00f94df64
fix: replace all dataset.Model.query to db.session.query(Model) (#19509) 1 year ago
LeanDeR c720e0dd04
refactor(workflow): revamp logging module for loop & iteration nodes (#19484) 1 year ago
湛露先生 1119790b02
clean rag word_extractor. (#19397)
Signed-off-by: zhanluxianshen <zhanluxianshen@163.com>
1 year ago
Bowen Liang cbc8ebd8f5
chore: bump pydantic to 2.11 and pydantic-settings to 2.9 (#15049) 1 year ago
Will 58d9d35515
fix: inconsistent metadata definitions (#19343) 1 year ago
Yeuoly 3258a91d5d
Feat/add repo to plugin manifest (#19337) 1 year ago
Will 0358859467
fix: llm_usage.total_tokens stat (#19177) 1 year ago
Will bfa652f2d0
fix: metadata filtering condition variable unassigned; fix External K… (#19208) 1 year ago
-LAN- f23cf98317
refactor: Remove RepositoryFactory (#19176)
Signed-off-by: -LAN- <laipz8200@outlook.com>
1 year ago
Novice 0cfc82d731
fix(structured-output): reasoning model's json format parsing (#19261) 1 year ago
Bowen Liang 8537abfff8
chore: avoid repeated type ignore noqa by adding flask_restful and flask_login in mypy import exclusions (#19224) 1 year ago
kenwoodjw c5568f756f
fix basic auth if not base64 encode (#19242)
Signed-off-by: kenwoodjw <blackxin55+@gmail.com>
1 year ago
Bowen Liang 22f5af9987
fix: support non-ascii charactors in filename of the tool files (#19228) 1 year ago
Hao Cheng 9bcf837f17
fix: use only supported operators in metadata filter system prompts (#19195) 1 year ago
Will a212a63e6a
fix: time type metadata filtering error (#19192) 1 year ago
非法操作 1ca6dbcdc8
fix: file name incorrect when download file (#19183) 1 year ago
QuantumGhost 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- <laipz8200@outlook.com>
Co-authored-by: -LAN- <laipz8200@outlook.com>
1 year ago
Bowen Liang 12c96b93d9
immediately return initialed tiktokenizer instance and remove dead code in usage of tiktokenizer (#17957) 1 year ago
-LAN- bcc95e520b
feat: support remove first and remove last in variable assigner (#19144)
Signed-off-by: -LAN- <laipz8200@outlook.com>
1 year ago
Will 69b43a955f
fix: inconsistent case expression in _process_metadata_filter_func (#19146) 1 year ago
kingpc 65b7a783fe
fix: metadata filter not work (#19020)
Co-authored-by: 金鹏程 <jinpengcheng01@corp.netease.com>
Co-authored-by: crazywoola <427733928@qq.com>
1 year ago
QuantumGhost bd1bbfee4b
Enhance Code Consistency Across Repository with `.editorconfig` (#19023) 1 year ago
feiyang_deepnova 226afd4550
Fix: the issue of getting empty environment variables. (#19085) 1 year ago
Ahmad Zidan 8266815cda
feat: add AWS Managed IAM auth for OpenSearch vector DB (#18963) 1 year ago
Ethan 8b4ea01810
feat: support access milvus with token (#19034) 1 year ago
Panpan 83187b30c0
fix: fix rerank model runner usage (#19008) 1 year ago
Ganondorf a147d2a200
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>
1 year ago
Kevin9703 94cc0b7a12
fix(workflow_cycle_manage): failed nodes were not updated in workflow_node_executions (#18994) 1 year ago