youngkingdom/dify
1
0
Fork 0
mirror of https://github.com/langgenius/dify.git synced 2026-04-27 14:08:18 +08:00
Code Issues Packages Projects Releases Wiki Activity

refactor: select in console datasets document controller (#34029)

Browse Source 
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
This commit is contained in:
tmimmanuel
2026-03-25 04:47:25 +01:00
committed by GitHub
parent 4c32acf857
commit d87263f7c3
55 changed files with 233 additions and 195 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
api/controllers/console/datasets/datasets.py
View File

@ -29,6 +29,7 @@ from core.provider_manager import ProviderManager
from core.rag.datasource.vdb.vector_type import VectorType
from core.rag.extractor.entity.datasource_type import DatasourceType
from core.rag.extractor.entity.extract_setting import ExtractSetting, NotionInfo, WebsiteInfo
from core.rag.index_processor.constant.index_type import IndexTechniqueType
from core.rag.retrieval.retrieval_methods import RetrievalMethod
from dify_graph.model_runtime.entities.model_entities import ModelType
from extensions.ext_database import db
@ -355,7 +356,7 @@ class DatasetListApi(Resource):
for item in data:
# convert embedding_model_provider to plugin standard format
if item["indexing_technique"] == "high_quality" and item["embedding_model_provider"]:
if item["indexing_technique"] == IndexTechniqueType.HIGH_QUALITY and item["embedding_model_provider"]:
item["embedding_model_provider"] = str(ModelProviderID(item["embedding_model_provider"]))
item_model = f"{item['embedding_model']}:{item['embedding_model_provider']}"
if item_model in model_names:
@ -436,7 +437,7 @@ class DatasetApi(Resource):
except services.errors.account.NoPermissionError as e:
raise Forbidden(str(e))
data = cast(dict[str, Any], marshal(dataset, dataset_detail_fields))
if dataset.indexing_technique == "high_quality":
if dataset.indexing_technique == IndexTechniqueType.HIGH_QUALITY:
if dataset.embedding_model_provider:
provider_id = ModelProviderID(dataset.embedding_model_provider)
data["embedding_model_provider"] = str(provider_id)
@ -454,7 +455,7 @@ class DatasetApi(Resource):
for embedding_model in embedding_models:
model_names.append(f"{embedding_model.model}:{embedding_model.provider.provider}")
if data["indexing_technique"] == "high_quality":
if data["indexing_technique"] == IndexTechniqueType.HIGH_QUALITY:
item_model = f"{data['embedding_model']}:{data['embedding_model_provider']}"
if item_model in model_names:
data["embedding_available"] = True
@ -485,7 +486,7 @@ class DatasetApi(Resource):
current_user, current_tenant_id = current_account_with_tenant()
# check embedding model setting
if (
payload.indexing_technique == "high_quality"
payload.indexing_technique == IndexTechniqueType.HIGH_QUALITY
and payload.embedding_model_provider is not None
and payload.embedding_model is not None
):

7
api/controllers/console/datasets/datasets_document.py
View File

@ -27,6 +27,7 @@ from core.model_manager import ModelManager
from core.plugin.impl.exc import PluginDaemonClientSideError
from core.rag.extractor.entity.datasource_type import DatasourceType
from core.rag.extractor.entity.extract_setting import ExtractSetting, NotionInfo, WebsiteInfo
from core.rag.index_processor.constant.index_type import IndexTechniqueType
from dify_graph.model_runtime.entities.model_entities import ModelType
from dify_graph.model_runtime.errors.invoke import InvokeAuthorizationError
from extensions.ext_database import db
@ -449,7 +450,7 @@ class DatasetInitApi(Resource):
raise Forbidden()
knowledge_config = KnowledgeConfig.model_validate(console_ns.payload or {})
if knowledge_config.indexing_technique == "high_quality":
if knowledge_config.indexing_technique == IndexTechniqueType.HIGH_QUALITY:
if knowledge_config.embedding_model is None or knowledge_config.embedding_model_provider is None:
raise ValueError("embedding model and embedding model provider are required for high quality indexing.")
try:
@ -463,7 +464,7 @@ class DatasetInitApi(Resource):
is_multimodal = DatasetService.check_is_multimodal_model(
current_tenant_id, knowledge_config.embedding_model_provider, knowledge_config.embedding_model
)
knowledge_config.is_multimodal = is_multimodal
knowledge_config.is_multimodal = is_multimodal # pyrefly: ignore[bad-assignment]
except InvokeAuthorizationError:
raise ProviderNotInitializeError(
"No Embedding Model available. Please configure a valid provider in the Settings -> Model Provider."
@ -1337,7 +1338,7 @@ class DocumentGenerateSummaryApi(Resource):
raise BadRequest("document_list cannot be empty.")
# Check if dataset configuration supports summary generation
if dataset.indexing_technique != "high_quality":
if dataset.indexing_technique != IndexTechniqueType.HIGH_QUALITY:
raise ValueError(
f"Summary generation is only available for 'high_quality' indexing technique. "
f"Current indexing technique: {dataset.indexing_technique}"

9
api/controllers/console/datasets/datasets_segments.py
View File

@ -26,6 +26,7 @@ from controllers.console.wraps import (
)
from core.errors.error import LLMBadRequestError, ProviderTokenNotInitError
from core.model_manager import ModelManager
from core.rag.index_processor.constant.index_type import IndexTechniqueType
from dify_graph.model_runtime.entities.model_entities import ModelType
from extensions.ext_database import db
from extensions.ext_redis import redis_client
@ -279,7 +280,7 @@ class DatasetDocumentSegmentApi(Resource):
DatasetService.check_dataset_permission(dataset, current_user)
except services.errors.account.NoPermissionError as e:
raise Forbidden(str(e))
if dataset.indexing_technique == "high_quality":
if dataset.indexing_technique == IndexTechniqueType.HIGH_QUALITY:
# check embedding model setting
try:
model_manager = ModelManager()
@ -333,7 +334,7 @@ class DatasetDocumentSegmentAddApi(Resource):
if not current_user.is_dataset_editor:
raise Forbidden()
# check embedding model setting
if dataset.indexing_technique == "high_quality":
if dataset.indexing_technique == IndexTechniqueType.HIGH_QUALITY:
try:
model_manager = ModelManager()
model_manager.get_model_instance(
@ -383,7 +384,7 @@ class DatasetDocumentSegmentUpdateApi(Resource):
document = DocumentService.get_document(dataset_id, document_id)
if not document:
raise NotFound("Document not found.")
if dataset.indexing_technique == "high_quality":
if dataset.indexing_technique == IndexTechniqueType.HIGH_QUALITY:
# check embedding model setting
try:
model_manager = ModelManager()
@ -569,7 +570,7 @@ class ChildChunkAddApi(Resource):
if not current_user.is_dataset_editor:
raise Forbidden()
# check embedding model setting
if dataset.indexing_technique == "high_quality":
if dataset.indexing_technique == IndexTechniqueType.HIGH_QUALITY:
try:
model_manager = ModelManager()
model_manager.get_model_instance(

16
api/controllers/service_api/dataset/dataset.py
View File

@ -15,6 +15,7 @@ from controllers.service_api.wraps import (
cloud_edition_billing_rate_limit_check,
)
from core.provider_manager import ProviderManager
from core.rag.index_processor.constant.index_type import IndexTechniqueType
from dify_graph.model_runtime.entities.model_entities import ModelType
from fields.dataset_fields import dataset_detail_fields
from fields.tag_fields import DataSetTag
@ -153,9 +154,14 @@ class DatasetListApi(DatasetApiResource):
data = marshal(datasets, dataset_detail_fields)
for item in data:
if item["indexing_technique"] == "high_quality" and item["embedding_model_provider"]: # type: ignore
item["embedding_model_provider"] = str(ModelProviderID(item["embedding_model_provider"])) # type: ignore
item_model = f"{item['embedding_model']}:{item['embedding_model_provider']}" # type: ignore
if (
item["indexing_technique"] == IndexTechniqueType.HIGH_QUALITY # pyrefly: ignore[bad-index]
and item["embedding_model_provider"] # pyrefly: ignore[bad-index]
):
item["embedding_model_provider"] = str( # pyrefly: ignore[unsupported-operation]
ModelProviderID(item["embedding_model_provider"]) # pyrefly: ignore[bad-index]
)
item_model = f"{item['embedding_model']}:{item['embedding_model_provider']}" # pyrefly: ignore[bad-index]
if item_model in model_names:
item["embedding_available"] = True # type: ignore
else:
@ -265,7 +271,7 @@ class DatasetApi(DatasetApiResource):
for embedding_model in embedding_models:
model_names.append(f"{embedding_model.model}:{embedding_model.provider.provider}")
if data.get("indexing_technique") == "high_quality":
if data.get("indexing_technique") == IndexTechniqueType.HIGH_QUALITY:
item_model = f"{data.get('embedding_model')}:{data.get('embedding_model_provider')}"
if item_model in model_names:
data["embedding_available"] = True
@ -315,7 +321,7 @@ class DatasetApi(DatasetApiResource):
# check embedding model setting
embedding_model_provider = payload.embedding_model_provider
embedding_model = payload.embedding_model
if payload.indexing_technique == "high_quality" or embedding_model_provider:
if payload.indexing_technique == IndexTechniqueType.HIGH_QUALITY or embedding_model_provider:
if embedding_model_provider and embedding_model:
DatasetService.check_embedding_model_setting(
dataset.tenant_id, embedding_model_provider, embedding_model

9
api/controllers/service_api/dataset/segment.py
View File

@ -17,6 +17,7 @@ from controllers.service_api.wraps import (
)
from core.errors.error import LLMBadRequestError, ProviderTokenNotInitError
from core.model_manager import ModelManager
from core.rag.index_processor.constant.index_type import IndexTechniqueType
from dify_graph.model_runtime.entities.model_entities import ModelType
from extensions.ext_database import db
from fields.segment_fields import child_chunk_fields, segment_fields
@ -103,7 +104,7 @@ class SegmentApi(DatasetApiResource):
if not document.enabled:
raise NotFound("Document is disabled.")
# check embedding model setting
if dataset.indexing_technique == "high_quality":
if dataset.indexing_technique == IndexTechniqueType.HIGH_QUALITY:
try:
model_manager = ModelManager()
model_manager.get_model_instance(
@ -157,7 +158,7 @@ class SegmentApi(DatasetApiResource):
if not document:
raise NotFound("Document not found.")
# check embedding model setting
if dataset.indexing_technique == "high_quality":
if dataset.indexing_technique == IndexTechniqueType.HIGH_QUALITY:
try:
model_manager = ModelManager()
model_manager.get_model_instance(
@ -262,7 +263,7 @@ class DatasetSegmentApi(DatasetApiResource):
document = DocumentService.get_document(dataset_id, document_id)
if not document:
raise NotFound("Document not found.")
if dataset.indexing_technique == "high_quality":
if dataset.indexing_technique == IndexTechniqueType.HIGH_QUALITY:
# check embedding model setting
try:
model_manager = ModelManager()
@ -358,7 +359,7 @@ class ChildChunkApi(DatasetApiResource):
raise NotFound("Segment not found.")
# check embedding model setting
if dataset.indexing_technique == "high_quality":
if dataset.indexing_technique == IndexTechniqueType.HIGH_QUALITY:
try:
model_manager = ModelManager()
model_manager.get_model_instance(