-
Notifications
You must be signed in to change notification settings - Fork 20.7k
Expand file tree
/
Copy pathrag_pipeline.py
More file actions
1475 lines (1343 loc) · 62.2 KB
/
rag_pipeline.py
File metadata and controls
1475 lines (1343 loc) · 62.2 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
import json
import logging
import re
import threading
import time
from collections.abc import Callable, Generator, Mapping, Sequence
from datetime import UTC, datetime
from typing import Any, Union, cast
from uuid import uuid4
from flask_login import current_user
from sqlalchemy import func, select
from sqlalchemy.orm import Session, sessionmaker
import contexts
from configs import dify_config
from core.app.apps.pipeline.pipeline_generator import PipelineGenerator
from core.app.entities.app_invoke_entities import InvokeFrom
from core.datasource.entities.datasource_entities import (
DatasourceMessage,
DatasourceProviderType,
GetOnlineDocumentPageContentRequest,
OnlineDocumentPagesMessage,
OnlineDriveBrowseFilesRequest,
OnlineDriveBrowseFilesResponse,
WebsiteCrawlMessage,
)
from core.datasource.online_document.online_document_plugin import OnlineDocumentDatasourcePlugin
from core.datasource.online_drive.online_drive_plugin import OnlineDriveDatasourcePlugin
from core.datasource.website_crawl.website_crawl_plugin import WebsiteCrawlDatasourcePlugin
from core.helper import marketplace
from core.rag.entities.event import (
DatasourceCompletedEvent,
DatasourceErrorEvent,
DatasourceProcessingEvent,
)
from core.repositories.factory import DifyCoreRepositoryFactory
from core.repositories.sqlalchemy_workflow_node_execution_repository import SQLAlchemyWorkflowNodeExecutionRepository
from core.workflow.nodes.node_mapping import LATEST_VERSION, NODE_TYPE_CLASSES_MAPPING
from core.workflow.workflow_entry import WorkflowEntry
from dify_graph.entities.workflow_node_execution import (
WorkflowNodeExecution,
WorkflowNodeExecutionStatus,
)
from dify_graph.enums import ErrorStrategy, NodeType, SystemVariableKey
from dify_graph.errors import WorkflowNodeRunFailedError
from dify_graph.graph_events import NodeRunFailedEvent, NodeRunSucceededEvent
from dify_graph.graph_events.base import GraphNodeEventBase
from dify_graph.node_events.base import NodeRunResult
from dify_graph.nodes.base.node import Node
from dify_graph.nodes.http_request import HTTP_REQUEST_CONFIG_FILTER_KEY, build_http_request_config
from dify_graph.repositories.workflow_node_execution_repository import OrderConfig
from dify_graph.runtime import VariablePool
from dify_graph.system_variable import SystemVariable
from dify_graph.variables.variables import VariableBase
from extensions.ext_database import db
from libs.infinite_scroll_pagination import InfiniteScrollPagination
from models import Account
from models.dataset import ( # type: ignore
Dataset,
Document,
DocumentPipelineExecutionLog,
Pipeline,
PipelineCustomizedTemplate,
PipelineRecommendedPlugin,
)
from models.enums import WorkflowRunTriggeredFrom
from models.model import EndUser
from models.workflow import (
Workflow,
WorkflowNodeExecutionModel,
WorkflowNodeExecutionTriggeredFrom,
WorkflowRun,
WorkflowType,
)
from repositories.factory import DifyAPIRepositoryFactory
from services.datasource_provider_service import DatasourceProviderService
from services.entities.knowledge_entities.rag_pipeline_entities import (
KnowledgeConfiguration,
PipelineTemplateInfoEntity,
)
from services.errors.app import WorkflowHashNotEqualError
from services.rag_pipeline.pipeline_template.pipeline_template_factory import PipelineTemplateRetrievalFactory
from services.tools.builtin_tools_manage_service import BuiltinToolManageService
from services.workflow_draft_variable_service import DraftVariableSaver, DraftVarLoader
logger = logging.getLogger(__name__)
class RagPipelineService:
def __init__(self, session_maker: sessionmaker | None = None):
"""Initialize RagPipelineService with repository dependencies."""
if session_maker is None:
session_maker = sessionmaker(bind=db.engine, expire_on_commit=False)
self._node_execution_service_repo = DifyAPIRepositoryFactory.create_api_workflow_node_execution_repository(
session_maker
)
self._workflow_run_repo = DifyAPIRepositoryFactory.create_api_workflow_run_repository(session_maker)
@classmethod
def get_pipeline_templates(cls, type: str = "built-in", language: str = "en-US") -> dict:
if type == "built-in":
mode = dify_config.HOSTED_FETCH_PIPELINE_TEMPLATES_MODE
retrieval_instance = PipelineTemplateRetrievalFactory.get_pipeline_template_factory(mode)()
result = retrieval_instance.get_pipeline_templates(language)
if not result.get("pipeline_templates") and language != "en-US":
template_retrieval = PipelineTemplateRetrievalFactory.get_built_in_pipeline_template_retrieval()
result = template_retrieval.fetch_pipeline_templates_from_builtin("en-US")
return result
else:
mode = "customized"
retrieval_instance = PipelineTemplateRetrievalFactory.get_pipeline_template_factory(mode)()
result = retrieval_instance.get_pipeline_templates(language)
return result
@classmethod
def get_pipeline_template_detail(cls, template_id: str, type: str = "built-in") -> dict | None:
"""
Get pipeline template detail.
:param template_id: template id
:return:
"""
if type == "built-in":
mode = dify_config.HOSTED_FETCH_PIPELINE_TEMPLATES_MODE
retrieval_instance = PipelineTemplateRetrievalFactory.get_pipeline_template_factory(mode)()
built_in_result: dict | None = retrieval_instance.get_pipeline_template_detail(template_id)
return built_in_result
else:
mode = "customized"
retrieval_instance = PipelineTemplateRetrievalFactory.get_pipeline_template_factory(mode)()
customized_result: dict | None = retrieval_instance.get_pipeline_template_detail(template_id)
return customized_result
@classmethod
def update_customized_pipeline_template(cls, template_id: str, template_info: PipelineTemplateInfoEntity):
"""
Update pipeline template.
:param template_id: template id
:param template_info: template info
"""
customized_template: PipelineCustomizedTemplate | None = (
db.session.query(PipelineCustomizedTemplate)
.where(
PipelineCustomizedTemplate.id == template_id,
PipelineCustomizedTemplate.tenant_id == current_user.current_tenant_id,
)
.first()
)
if not customized_template:
raise ValueError("Customized pipeline template not found.")
# check template name is exist
template_name = template_info.name
if template_name:
template = (
db.session.query(PipelineCustomizedTemplate)
.where(
PipelineCustomizedTemplate.name == template_name,
PipelineCustomizedTemplate.tenant_id == current_user.current_tenant_id,
PipelineCustomizedTemplate.id != template_id,
)
.first()
)
if template:
raise ValueError("Template name is already exists")
customized_template.name = template_info.name
customized_template.description = template_info.description
customized_template.icon = template_info.icon_info.model_dump()
customized_template.updated_by = current_user.id
db.session.commit()
return customized_template
@classmethod
def delete_customized_pipeline_template(cls, template_id: str):
"""
Delete customized pipeline template.
"""
customized_template: PipelineCustomizedTemplate | None = (
db.session.query(PipelineCustomizedTemplate)
.where(
PipelineCustomizedTemplate.id == template_id,
PipelineCustomizedTemplate.tenant_id == current_user.current_tenant_id,
)
.first()
)
if not customized_template:
raise ValueError("Customized pipeline template not found.")
db.session.delete(customized_template)
db.session.commit()
def get_draft_workflow(self, pipeline: Pipeline) -> Workflow | None:
"""
Get draft workflow
"""
# fetch draft workflow by rag pipeline
workflow = (
db.session.query(Workflow)
.where(
Workflow.tenant_id == pipeline.tenant_id,
Workflow.app_id == pipeline.id,
Workflow.version == "draft",
)
.first()
)
# return draft workflow
return workflow
def get_published_workflow(self, pipeline: Pipeline) -> Workflow | None:
"""
Get published workflow
"""
if not pipeline.workflow_id:
return None
# fetch published workflow by workflow_id
workflow = (
db.session.query(Workflow)
.where(
Workflow.tenant_id == pipeline.tenant_id,
Workflow.app_id == pipeline.id,
Workflow.id == pipeline.workflow_id,
)
.first()
)
return workflow
def get_all_published_workflow(
self,
*,
session: Session,
pipeline: Pipeline,
page: int,
limit: int,
user_id: str | None,
named_only: bool = False,
) -> tuple[Sequence[Workflow], bool]:
"""
Get published workflow with pagination
"""
if not pipeline.workflow_id:
return [], False
stmt = (
select(Workflow)
.where(Workflow.app_id == pipeline.id)
.order_by(Workflow.version.desc())
.limit(limit + 1)
.offset((page - 1) * limit)
)
if user_id:
stmt = stmt.where(Workflow.created_by == user_id)
if named_only:
stmt = stmt.where(Workflow.marked_name != "")
workflows = session.scalars(stmt).all()
has_more = len(workflows) > limit
if has_more:
workflows = workflows[:-1]
return workflows, has_more
def sync_draft_workflow(
self,
*,
pipeline: Pipeline,
graph: dict,
unique_hash: str | None,
account: Account,
environment_variables: Sequence[VariableBase],
conversation_variables: Sequence[VariableBase],
rag_pipeline_variables: list,
) -> Workflow:
"""
Sync draft workflow
:raises WorkflowHashNotEqualError
"""
# fetch draft workflow by app_model
workflow = self.get_draft_workflow(pipeline=pipeline)
if workflow and workflow.unique_hash != unique_hash:
raise WorkflowHashNotEqualError()
# create draft workflow if not found
if not workflow:
workflow = Workflow(
tenant_id=pipeline.tenant_id,
app_id=pipeline.id,
features="{}",
type=WorkflowType.RAG_PIPELINE.value,
version="draft",
graph=json.dumps(graph),
created_by=account.id,
environment_variables=environment_variables,
conversation_variables=conversation_variables,
rag_pipeline_variables=rag_pipeline_variables,
)
db.session.add(workflow)
db.session.flush()
pipeline.workflow_id = workflow.id
# update draft workflow if found
else:
workflow.graph = json.dumps(graph)
workflow.updated_by = account.id
workflow.updated_at = datetime.now(UTC).replace(tzinfo=None)
workflow.environment_variables = environment_variables
workflow.conversation_variables = conversation_variables
workflow.rag_pipeline_variables = rag_pipeline_variables
# commit db session changes
db.session.commit()
# trigger workflow events TODO
# app_draft_workflow_was_synced.send(pipeline, synced_draft_workflow=workflow)
# return draft workflow
return workflow
def publish_workflow(
self,
*,
session: Session,
pipeline: Pipeline,
account: Account,
) -> Workflow:
draft_workflow_stmt = select(Workflow).where(
Workflow.tenant_id == pipeline.tenant_id,
Workflow.app_id == pipeline.id,
Workflow.version == "draft",
)
draft_workflow = session.scalar(draft_workflow_stmt)
if not draft_workflow:
raise ValueError("No valid workflow found.")
# create new workflow
workflow = Workflow.new(
tenant_id=pipeline.tenant_id,
app_id=pipeline.id,
type=draft_workflow.type,
version=str(datetime.now(UTC).replace(tzinfo=None)),
graph=draft_workflow.graph,
features=draft_workflow.features,
created_by=account.id,
environment_variables=draft_workflow.environment_variables,
conversation_variables=draft_workflow.conversation_variables,
rag_pipeline_variables=draft_workflow.rag_pipeline_variables,
marked_name="",
marked_comment="",
)
# commit db session changes
session.add(workflow)
graph = workflow.graph_dict
nodes = graph.get("nodes", [])
from services.dataset_service import DatasetService
for node in nodes:
if node.get("data", {}).get("type") == "knowledge-index":
knowledge_configuration = node.get("data", {})
knowledge_configuration = KnowledgeConfiguration.model_validate(knowledge_configuration)
# update dataset
dataset = pipeline.retrieve_dataset(session=session)
if not dataset:
raise ValueError("Dataset not found")
DatasetService.update_rag_pipeline_dataset_settings(
session=session,
dataset=dataset,
knowledge_configuration=knowledge_configuration,
has_published=pipeline.is_published,
)
# return new workflow
return workflow
def get_default_block_configs(self) -> list[dict]:
"""
Get default block configs
"""
# return default block config
default_block_configs: list[dict[str, Any]] = []
for node_type, node_class_mapping in NODE_TYPE_CLASSES_MAPPING.items():
node_class = node_class_mapping[LATEST_VERSION]
filters = None
if node_type is NodeType.HTTP_REQUEST:
filters = {
HTTP_REQUEST_CONFIG_FILTER_KEY: build_http_request_config(
max_connect_timeout=dify_config.HTTP_REQUEST_MAX_CONNECT_TIMEOUT,
max_read_timeout=dify_config.HTTP_REQUEST_MAX_READ_TIMEOUT,
max_write_timeout=dify_config.HTTP_REQUEST_MAX_WRITE_TIMEOUT,
max_binary_size=dify_config.HTTP_REQUEST_NODE_MAX_BINARY_SIZE,
max_text_size=dify_config.HTTP_REQUEST_NODE_MAX_TEXT_SIZE,
ssl_verify=dify_config.HTTP_REQUEST_NODE_SSL_VERIFY,
ssrf_default_max_retries=dify_config.SSRF_DEFAULT_MAX_RETRIES,
)
}
default_config = node_class.get_default_config(filters=filters)
if default_config:
default_block_configs.append(dict(default_config))
return default_block_configs
def get_default_block_config(self, node_type: str, filters: dict | None = None) -> Mapping[str, object] | None:
"""
Get default config of node.
:param node_type: node type
:param filters: filter by node config parameters.
:return:
"""
node_type_enum = NodeType(node_type)
# return default block config
if node_type_enum not in NODE_TYPE_CLASSES_MAPPING:
return None
node_class = NODE_TYPE_CLASSES_MAPPING[node_type_enum][LATEST_VERSION]
final_filters = dict(filters) if filters else {}
if node_type_enum is NodeType.HTTP_REQUEST and HTTP_REQUEST_CONFIG_FILTER_KEY not in final_filters:
final_filters[HTTP_REQUEST_CONFIG_FILTER_KEY] = build_http_request_config(
max_connect_timeout=dify_config.HTTP_REQUEST_MAX_CONNECT_TIMEOUT,
max_read_timeout=dify_config.HTTP_REQUEST_MAX_READ_TIMEOUT,
max_write_timeout=dify_config.HTTP_REQUEST_MAX_WRITE_TIMEOUT,
max_binary_size=dify_config.HTTP_REQUEST_NODE_MAX_BINARY_SIZE,
max_text_size=dify_config.HTTP_REQUEST_NODE_MAX_TEXT_SIZE,
ssl_verify=dify_config.HTTP_REQUEST_NODE_SSL_VERIFY,
ssrf_default_max_retries=dify_config.SSRF_DEFAULT_MAX_RETRIES,
)
default_config = node_class.get_default_config(filters=final_filters or None)
if not default_config:
return None
return default_config
def run_draft_workflow_node(
self, pipeline: Pipeline, node_id: str, user_inputs: dict, account: Account
) -> WorkflowNodeExecutionModel | None:
"""
Run draft workflow node
"""
# fetch draft workflow by app_model
draft_workflow = self.get_draft_workflow(pipeline=pipeline)
if not draft_workflow:
raise ValueError("Workflow not initialized")
# run draft workflow node
start_at = time.perf_counter()
node_config = draft_workflow.get_node_config_by_id(node_id)
eclosing_node_type_and_id = draft_workflow.get_enclosing_node_type_and_id(node_config)
if eclosing_node_type_and_id:
_, enclosing_node_id = eclosing_node_type_and_id
else:
enclosing_node_id = None
workflow_node_execution = self._handle_node_run_result(
getter=lambda: WorkflowEntry.single_step_run(
workflow=draft_workflow,
node_id=node_id,
user_inputs=user_inputs,
user_id=account.id,
variable_pool=VariablePool(
system_variables=SystemVariable.default(),
user_inputs=user_inputs,
environment_variables=[],
conversation_variables=[],
rag_pipeline_variables=[],
),
variable_loader=DraftVarLoader(
engine=db.engine,
app_id=pipeline.id,
tenant_id=pipeline.tenant_id,
),
),
start_at=start_at,
tenant_id=pipeline.tenant_id,
node_id=node_id,
)
workflow_node_execution.workflow_id = draft_workflow.id
# Create repository and save the node execution
repository = DifyCoreRepositoryFactory.create_workflow_node_execution_repository(
session_factory=db.engine,
user=account,
app_id=pipeline.id,
triggered_from=WorkflowNodeExecutionTriggeredFrom.SINGLE_STEP,
)
repository.save(workflow_node_execution)
# Convert node_execution to WorkflowNodeExecution after save
workflow_node_execution_db_model = self._node_execution_service_repo.get_execution_by_id(
workflow_node_execution.id
)
with Session(bind=db.engine) as session, session.begin():
draft_var_saver = DraftVariableSaver(
session=session,
app_id=pipeline.id,
node_id=workflow_node_execution.node_id,
node_type=NodeType(workflow_node_execution.node_type),
enclosing_node_id=enclosing_node_id,
node_execution_id=workflow_node_execution.id,
user=account,
)
draft_var_saver.save(
process_data=workflow_node_execution.process_data,
outputs=workflow_node_execution.outputs,
)
session.commit()
return workflow_node_execution_db_model
def run_datasource_workflow_node(
self,
pipeline: Pipeline,
node_id: str,
user_inputs: dict,
account: Account,
datasource_type: str,
is_published: bool,
credential_id: str | None = None,
) -> Generator[Mapping[str, Any], None, None]:
"""
Run published workflow datasource
"""
try:
if is_published:
# fetch published workflow by app_model
workflow = self.get_published_workflow(pipeline=pipeline)
else:
workflow = self.get_draft_workflow(pipeline=pipeline)
if not workflow:
raise ValueError("Workflow not initialized")
# run draft workflow node
datasource_node_data = None
datasource_nodes = workflow.graph_dict.get("nodes", [])
for datasource_node in datasource_nodes:
if datasource_node.get("id") == node_id:
datasource_node_data = datasource_node.get("data", {})
break
if not datasource_node_data:
raise ValueError("Datasource node data not found")
variables_map = {}
datasource_parameters = datasource_node_data.get("datasource_parameters", {})
for key, value in datasource_parameters.items():
param_value = value.get("value")
if not param_value:
variables_map[key] = param_value
elif isinstance(param_value, str):
# handle string type parameter value, check if it contains variable reference pattern
pattern = r"\{\{#([a-zA-Z0-9_]{1,50}(?:\.[a-zA-Z0-9_][a-zA-Z0-9_]{0,29}){1,10})#\}\}"
match = re.match(pattern, param_value)
if match:
# extract variable path and try to get value from user inputs
full_path = match.group(1)
last_part = full_path.split(".")[-1]
variables_map[key] = user_inputs.get(last_part, param_value)
else:
variables_map[key] = param_value
elif isinstance(param_value, list) and param_value:
# handle list type parameter value, check if the last element is in user inputs
last_part = param_value[-1]
variables_map[key] = user_inputs.get(last_part, param_value)
else:
# other type directly use original value
variables_map[key] = param_value
from core.datasource.datasource_manager import DatasourceManager
datasource_runtime = DatasourceManager.get_datasource_runtime(
provider_id=f"{datasource_node_data.get('plugin_id')}/{datasource_node_data.get('provider_name')}",
datasource_name=datasource_node_data.get("datasource_name"),
tenant_id=pipeline.tenant_id,
datasource_type=DatasourceProviderType(datasource_type),
)
datasource_provider_service = DatasourceProviderService()
credentials = datasource_provider_service.get_datasource_credentials(
tenant_id=pipeline.tenant_id,
provider=datasource_node_data.get("provider_name"),
plugin_id=datasource_node_data.get("plugin_id"),
credential_id=credential_id,
)
if credentials:
datasource_runtime.runtime.credentials = credentials
match datasource_type:
case DatasourceProviderType.ONLINE_DOCUMENT:
datasource_runtime = cast(OnlineDocumentDatasourcePlugin, datasource_runtime)
online_document_result: Generator[OnlineDocumentPagesMessage, None, None] = (
datasource_runtime.get_online_document_pages(
user_id=account.id,
datasource_parameters=user_inputs,
provider_type=datasource_runtime.datasource_provider_type(),
)
)
start_time = time.time()
start_event = DatasourceProcessingEvent(
total=0,
completed=0,
)
yield start_event.model_dump()
try:
for online_document_message in online_document_result:
end_time = time.time()
online_document_event = DatasourceCompletedEvent(
data=online_document_message.result, time_consuming=round(end_time - start_time, 2)
)
yield online_document_event.model_dump()
except Exception as e:
logger.exception("Error during online document.")
yield DatasourceErrorEvent(error=str(e)).model_dump()
case DatasourceProviderType.ONLINE_DRIVE:
datasource_runtime = cast(OnlineDriveDatasourcePlugin, datasource_runtime)
online_drive_result: Generator[OnlineDriveBrowseFilesResponse, None, None] = (
datasource_runtime.online_drive_browse_files(
user_id=account.id,
request=OnlineDriveBrowseFilesRequest(
bucket=user_inputs.get("bucket"),
prefix=user_inputs.get("prefix", ""),
max_keys=user_inputs.get("max_keys", 20),
next_page_parameters=user_inputs.get("next_page_parameters"),
),
provider_type=datasource_runtime.datasource_provider_type(),
)
)
start_time = time.time()
start_event = DatasourceProcessingEvent(
total=0,
completed=0,
)
yield start_event.model_dump()
for online_drive_message in online_drive_result:
end_time = time.time()
online_drive_event = DatasourceCompletedEvent(
data=online_drive_message.result,
time_consuming=round(end_time - start_time, 2),
total=None,
completed=None,
)
yield online_drive_event.model_dump()
case DatasourceProviderType.WEBSITE_CRAWL:
datasource_runtime = cast(WebsiteCrawlDatasourcePlugin, datasource_runtime)
website_crawl_result: Generator[WebsiteCrawlMessage, None, None] = (
datasource_runtime.get_website_crawl(
user_id=account.id,
datasource_parameters=variables_map,
provider_type=datasource_runtime.datasource_provider_type(),
)
)
start_time = time.time()
try:
for website_crawl_message in website_crawl_result:
end_time = time.time()
crawl_event: DatasourceCompletedEvent | DatasourceProcessingEvent
if website_crawl_message.result.status == "completed":
crawl_event = DatasourceCompletedEvent(
data=website_crawl_message.result.web_info_list or [],
total=website_crawl_message.result.total,
completed=website_crawl_message.result.completed,
time_consuming=round(end_time - start_time, 2),
)
else:
crawl_event = DatasourceProcessingEvent(
total=website_crawl_message.result.total,
completed=website_crawl_message.result.completed,
)
yield crawl_event.model_dump()
except Exception as e:
logger.exception("Error during website crawl.")
yield DatasourceErrorEvent(error=str(e)).model_dump()
case _:
raise ValueError(f"Unsupported datasource provider: {datasource_runtime.datasource_provider_type}")
except Exception as e:
logger.exception("Error in run_datasource_workflow_node.")
yield DatasourceErrorEvent(error=str(e)).model_dump()
def run_datasource_node_preview(
self,
pipeline: Pipeline,
node_id: str,
user_inputs: dict,
account: Account,
datasource_type: str,
is_published: bool,
credential_id: str | None = None,
) -> Mapping[str, Any]:
"""
Run published workflow datasource
"""
try:
if is_published:
# fetch published workflow by app_model
workflow = self.get_published_workflow(pipeline=pipeline)
else:
workflow = self.get_draft_workflow(pipeline=pipeline)
if not workflow:
raise ValueError("Workflow not initialized")
# run draft workflow node
datasource_node_data = None
datasource_nodes = workflow.graph_dict.get("nodes", [])
for datasource_node in datasource_nodes:
if datasource_node.get("id") == node_id:
datasource_node_data = datasource_node.get("data", {})
break
if not datasource_node_data:
raise ValueError("Datasource node data not found")
datasource_parameters = datasource_node_data.get("datasource_parameters", {})
for key, value in datasource_parameters.items():
if not user_inputs.get(key):
user_inputs[key] = value["value"]
from core.datasource.datasource_manager import DatasourceManager
datasource_runtime = DatasourceManager.get_datasource_runtime(
provider_id=f"{datasource_node_data.get('plugin_id')}/{datasource_node_data.get('provider_name')}",
datasource_name=datasource_node_data.get("datasource_name"),
tenant_id=pipeline.tenant_id,
datasource_type=DatasourceProviderType(datasource_type),
)
datasource_provider_service = DatasourceProviderService()
credentials = datasource_provider_service.get_datasource_credentials(
tenant_id=pipeline.tenant_id,
provider=datasource_node_data.get("provider_name"),
plugin_id=datasource_node_data.get("plugin_id"),
credential_id=credential_id,
)
if credentials:
datasource_runtime.runtime.credentials = credentials
match datasource_type:
case DatasourceProviderType.ONLINE_DOCUMENT:
datasource_runtime = cast(OnlineDocumentDatasourcePlugin, datasource_runtime)
online_document_result: Generator[DatasourceMessage, None, None] = (
datasource_runtime.get_online_document_page_content(
user_id=account.id,
datasource_parameters=GetOnlineDocumentPageContentRequest(
workspace_id=user_inputs.get("workspace_id", ""),
page_id=user_inputs.get("page_id", ""),
type=user_inputs.get("type", ""),
),
provider_type=datasource_type,
)
)
try:
variables: dict[str, Any] = {}
for online_document_message in online_document_result:
if online_document_message.type == DatasourceMessage.MessageType.VARIABLE:
assert isinstance(online_document_message.message, DatasourceMessage.VariableMessage)
variable_name = online_document_message.message.variable_name
variable_value = online_document_message.message.variable_value
if online_document_message.message.stream:
if not isinstance(variable_value, str):
raise ValueError("When 'stream' is True, 'variable_value' must be a string.")
if variable_name not in variables:
variables[variable_name] = ""
variables[variable_name] += variable_value
else:
variables[variable_name] = variable_value
return variables
except Exception as e:
logger.exception("Error during get online document content.")
raise RuntimeError(str(e))
# TODO Online Drive
case _:
raise ValueError(f"Unsupported datasource provider: {datasource_runtime.datasource_provider_type}")
except Exception as e:
logger.exception("Error in run_datasource_node_preview.")
raise RuntimeError(str(e))
def run_free_workflow_node(
self, node_data: dict, tenant_id: str, user_id: str, node_id: str, user_inputs: dict[str, Any]
) -> WorkflowNodeExecution:
"""
Run draft workflow node
"""
# run draft workflow node
start_at = time.perf_counter()
workflow_node_execution = self._handle_node_run_result(
getter=lambda: WorkflowEntry.run_free_node(
node_id=node_id,
node_data=node_data,
tenant_id=tenant_id,
user_id=user_id,
user_inputs=user_inputs,
),
start_at=start_at,
tenant_id=tenant_id,
node_id=node_id,
)
return workflow_node_execution
def _handle_node_run_result(
self,
getter: Callable[[], tuple[Node, Generator[GraphNodeEventBase, None, None]]],
start_at: float,
tenant_id: str,
node_id: str,
) -> WorkflowNodeExecution:
"""
Handle node run result
:param getter: Callable[[], tuple[BaseNode, Generator[RunEvent | InNodeEvent, None, None]]]
:param start_at: float
:param tenant_id: str
:param node_id: str
"""
try:
node_instance, generator = getter()
node_run_result: NodeRunResult | None = None
for event in generator:
if isinstance(event, (NodeRunSucceededEvent, NodeRunFailedEvent)):
node_run_result = event.node_run_result
if node_run_result:
# sign output files
node_run_result.outputs = WorkflowEntry.handle_special_values(node_run_result.outputs) or {}
break
if not node_run_result:
raise ValueError("Node run failed with no run result")
# single step debug mode error handling return
if node_run_result.status == WorkflowNodeExecutionStatus.FAILED and node_instance.error_strategy:
node_error_args: dict[str, Any] = {
"status": WorkflowNodeExecutionStatus.EXCEPTION,
"error": node_run_result.error,
"inputs": node_run_result.inputs,
"metadata": {"error_strategy": node_instance.error_strategy},
}
if node_instance.error_strategy is ErrorStrategy.DEFAULT_VALUE:
node_run_result = NodeRunResult(
**node_error_args,
outputs={
**node_instance.default_value_dict,
"error_message": node_run_result.error,
"error_type": node_run_result.error_type,
},
)
else:
node_run_result = NodeRunResult(
**node_error_args,
outputs={
"error_message": node_run_result.error,
"error_type": node_run_result.error_type,
},
)
run_succeeded = node_run_result.status in (
WorkflowNodeExecutionStatus.SUCCEEDED,
WorkflowNodeExecutionStatus.EXCEPTION,
)
error = node_run_result.error if not run_succeeded else None
except WorkflowNodeRunFailedError as e:
node_instance = e._node # type: ignore
run_succeeded = False
node_run_result = None
error = e._error # type: ignore
workflow_node_execution = WorkflowNodeExecution(
id=str(uuid4()),
workflow_id=node_instance.workflow_id,
index=1,
node_id=node_id,
node_type=node_instance.node_type,
title=node_instance.title,
elapsed_time=time.perf_counter() - start_at,
finished_at=datetime.now(UTC).replace(tzinfo=None),
created_at=datetime.now(UTC).replace(tzinfo=None),
)
if run_succeeded and node_run_result:
# create workflow node execution
inputs = WorkflowEntry.handle_special_values(node_run_result.inputs) if node_run_result.inputs else None
process_data = (
WorkflowEntry.handle_special_values(node_run_result.process_data)
if node_run_result.process_data
else None
)
outputs = WorkflowEntry.handle_special_values(node_run_result.outputs) if node_run_result.outputs else None
workflow_node_execution.inputs = inputs
workflow_node_execution.process_data = process_data
workflow_node_execution.outputs = outputs
workflow_node_execution.metadata = node_run_result.metadata
if node_run_result.status == WorkflowNodeExecutionStatus.SUCCEEDED:
workflow_node_execution.status = WorkflowNodeExecutionStatus.SUCCEEDED
elif node_run_result.status == WorkflowNodeExecutionStatus.EXCEPTION:
workflow_node_execution.status = WorkflowNodeExecutionStatus.EXCEPTION
workflow_node_execution.error = node_run_result.error
else:
# create workflow node execution
workflow_node_execution.status = WorkflowNodeExecutionStatus.FAILED
workflow_node_execution.error = error
# update document status
variable_pool = node_instance.graph_runtime_state.variable_pool
invoke_from = variable_pool.get(["sys", SystemVariableKey.INVOKE_FROM])
if invoke_from:
if invoke_from.value == InvokeFrom.PUBLISHED_PIPELINE:
document_id = variable_pool.get(["sys", SystemVariableKey.DOCUMENT_ID])
if document_id:
document = db.session.query(Document).where(Document.id == document_id.value).first()
if document:
document.indexing_status = "error"
document.error = error
db.session.add(document)
db.session.commit()
return workflow_node_execution
def update_workflow(
self, *, session: Session, workflow_id: str, tenant_id: str, account_id: str, data: dict
) -> Workflow | None:
"""
Update workflow attributes
:param session: SQLAlchemy database session
:param workflow_id: Workflow ID
:param tenant_id: Tenant ID
:param account_id: Account ID (for permission check)
:param data: Dictionary containing fields to update
:return: Updated workflow or None if not found
"""
stmt = select(Workflow).where(Workflow.id == workflow_id, Workflow.tenant_id == tenant_id)
workflow = session.scalar(stmt)
if not workflow:
return None
allowed_fields = ["marked_name", "marked_comment"]
for field, value in data.items():
if field in allowed_fields:
setattr(workflow, field, value)
workflow.updated_by = account_id
workflow.updated_at = datetime.now(UTC).replace(tzinfo=None)
return workflow
def get_first_step_parameters(self, pipeline: Pipeline, node_id: str, is_draft: bool = False) -> list[dict]:
"""
Get first step parameters of rag pipeline
"""
workflow = (
self.get_draft_workflow(pipeline=pipeline) if is_draft else self.get_published_workflow(pipeline=pipeline)
)
if not workflow:
raise ValueError("Workflow not initialized")
datasource_node_data = None
datasource_nodes = workflow.graph_dict.get("nodes", [])
for datasource_node in datasource_nodes:
if datasource_node.get("id") == node_id:
datasource_node_data = datasource_node.get("data", {})
break
if not datasource_node_data:
raise ValueError("Datasource node data not found")
variables = workflow.rag_pipeline_variables
if variables:
variables_map = {item["variable"]: item for item in variables}
else:
return []
datasource_parameters = datasource_node_data.get("datasource_parameters", {})
user_input_variables_keys = []
user_input_variables = []
for _, value in datasource_parameters.items():
if value.get("value") and isinstance(value.get("value"), str):
pattern = r"\{\{#([a-zA-Z0-9_]{1,50}(?:\.[a-zA-Z0-9_][a-zA-Z0-9_]{0,29}){1,10})#\}\}"
match = re.match(pattern, value["value"])
if match:
full_path = match.group(1)
last_part = full_path.split(".")[-1]
user_input_variables_keys.append(last_part)
elif value.get("value") and isinstance(value.get("value"), list):
last_part = value.get("value")[-1]
user_input_variables_keys.append(last_part)
for key, value in variables_map.items():
if key in user_input_variables_keys:
user_input_variables.append(value)
return user_input_variables
def get_second_step_parameters(self, pipeline: Pipeline, node_id: str, is_draft: bool = False) -> list[dict]:
"""
Get second step parameters of rag pipeline
"""
workflow = (
self.get_draft_workflow(pipeline=pipeline) if is_draft else self.get_published_workflow(pipeline=pipeline)
)
if not workflow:
raise ValueError("Workflow not initialized")
# get second step node