jandres/dify
1
0
Fork 0
mirror of https://github.com/langgenius/dify.git synced 2026-01-08 07:14:14 +00:00
Code Issues Actions 12 Packages Projects Releases Wiki Activity

rm type ignore (#25715)

Browse Source 
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: -LAN- <laipz8200@outlook.com>
This commit is contained in:
Asuka Minato
2025-10-21 12:26:58 +09:00
committed by GitHub
parent c11cdf7468
commit 32c715c4d0
78 changed files with 229 additions and 204 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
api/services/app_dsl_service.py
View File

@@ -7,7 +7,7 @@ from enum import StrEnum
from urllib.parse import urlparse
from uuid import uuid4
import yaml # type: ignore
import yaml
from Crypto.Cipher import AES
from Crypto.Util.Padding import pad, unpad
from packaging import version
@@ -563,7 +563,7 @@ class AppDslService:
else:
cls._append_model_config_export_data(export_data, app_model)
return yaml.dump(export_data, allow_unicode=True) # type: ignore
return yaml.dump(export_data, allow_unicode=True)
@classmethod
def _append_workflow_export_data(

81
api/services/dataset_service.py
View File

@@ -241,9 +241,9 @@ class DatasetService:
dataset.created_by = account.id
dataset.updated_by = account.id
dataset.tenant_id = tenant_id
dataset.embedding_model_provider = embedding_model.provider if embedding_model else None # type: ignore
dataset.embedding_model = embedding_model.model if embedding_model else None # type: ignore
dataset.retrieval_model = retrieval_model.model_dump() if retrieval_model else None # type: ignore
dataset.embedding_model_provider = embedding_model.provider if embedding_model else None
dataset.embedding_model = embedding_model.model if embedding_model else None
dataset.retrieval_model = retrieval_model.model_dump() if retrieval_model else None
dataset.permission = permission or DatasetPermissionEnum.ONLY_ME
dataset.provider = provider
db.session.add(dataset)
@@ -1416,6 +1416,8 @@ class DocumentService:
# check document limit
assert isinstance(current_user, Account)
assert current_user.current_tenant_id is not None
assert knowledge_config.data_source
assert knowledge_config.data_source.info_list.file_info_list
features = FeatureService.get_features(current_user.current_tenant_id)
@@ -1424,15 +1426,16 @@ class DocumentService:
count = 0
if knowledge_config.data_source:
if knowledge_config.data_source.info_list.data_source_type == "upload_file":
upload_file_list = knowledge_config.data_source.info_list.file_info_list.file_ids # type: ignore
upload_file_list = knowledge_config.data_source.info_list.file_info_list.file_ids
count = len(upload_file_list)
elif knowledge_config.data_source.info_list.data_source_type == "notion_import":
notion_info_list = knowledge_config.data_source.info_list.notion_info_list
for notion_info in notion_info_list: # type: ignore
notion_info_list = knowledge_config.data_source.info_list.notion_info_list or []
for notion_info in notion_info_list:
count = count + len(notion_info.pages)
elif knowledge_config.data_source.info_list.data_source_type == "website_crawl":
website_info = knowledge_config.data_source.info_list.website_info_list
count = len(website_info.urls) # type: ignore
assert website_info
count = len(website_info.urls)
batch_upload_limit = int(dify_config.BATCH_UPLOAD_LIMIT)
if features.billing.subscription.plan == "sandbox" and count > 1:
@@ -1444,7 +1447,7 @@ class DocumentService:
# if dataset is empty, update dataset data_source_type
if not dataset.data_source_type:
dataset.data_source_type = knowledge_config.data_source.info_list.data_source_type # type: ignore
dataset.data_source_type = knowledge_config.data_source.info_list.data_source_type
if not dataset.indexing_technique:
if knowledge_config.indexing_technique not in Dataset.INDEXING_TECHNIQUE_LIST:
@@ -1481,7 +1484,7 @@ class DocumentService:
knowledge_config.retrieval_model.model_dump()
if knowledge_config.retrieval_model
else default_retrieval_model
) # type: ignore
)
documents = []
if knowledge_config.original_document_id:
@@ -1523,11 +1526,12 @@ class DocumentService:
db.session.flush()
lock_name = f"add_document_lock_dataset_id_{dataset.id}"
with redis_client.lock(lock_name, timeout=600):
assert dataset_process_rule
position = DocumentService.get_documents_position(dataset.id)
document_ids = []
duplicate_document_ids = []
if knowledge_config.data_source.info_list.data_source_type == "upload_file": # type: ignore
upload_file_list = knowledge_config.data_source.info_list.file_info_list.file_ids # type: ignore
if knowledge_config.data_source.info_list.data_source_type == "upload_file":
upload_file_list = knowledge_config.data_source.info_list.file_info_list.file_ids
for file_id in upload_file_list:
file = (
db.session.query(UploadFile)
@@ -1540,7 +1544,7 @@ class DocumentService:
raise FileNotExistsError()
file_name = file.name
data_source_info = {
data_source_info: dict[str, str | bool] = {
"upload_file_id": file_id,
}
# check duplicate
@@ -1557,7 +1561,7 @@ class DocumentService:
.first()
)
if document:
document.dataset_process_rule_id = dataset_process_rule.id # type: ignore
document.dataset_process_rule_id = dataset_process_rule.id
document.updated_at = naive_utc_now()
document.created_from = created_from
document.doc_form = knowledge_config.doc_form
@@ -1571,8 +1575,8 @@ class DocumentService:
continue
document = DocumentService.build_document(
dataset,
dataset_process_rule.id, # type: ignore
knowledge_config.data_source.info_list.data_source_type, # type: ignore
dataset_process_rule.id,
knowledge_config.data_source.info_list.data_source_type,
knowledge_config.doc_form,
knowledge_config.doc_language,
data_source_info,
@@ -1587,7 +1591,7 @@ class DocumentService:
document_ids.append(document.id)
documents.append(document)
position += 1
elif knowledge_config.data_source.info_list.data_source_type == "notion_import": # type: ignore
elif knowledge_config.data_source.info_list.data_source_type == "notion_import":
notion_info_list = knowledge_config.data_source.info_list.notion_info_list # type: ignore
if not notion_info_list:
raise ValueError("No notion info list found.")
@@ -1616,15 +1620,15 @@ class DocumentService:
"credential_id": notion_info.credential_id,
"notion_workspace_id": workspace_id,
"notion_page_id": page.page_id,
"notion_page_icon": page.page_icon.model_dump() if page.page_icon else None,
"notion_page_icon": page.page_icon.model_dump() if page.page_icon else None, # type: ignore
"type": page.type,
}
# Truncate page name to 255 characters to prevent DB field length errors
truncated_page_name = page.page_name[:255] if page.page_name else "nopagename"
document = DocumentService.build_document(
dataset,
dataset_process_rule.id, # type: ignore
knowledge_config.data_source.info_list.data_source_type, # type: ignore
dataset_process_rule.id,
knowledge_config.data_source.info_list.data_source_type,
knowledge_config.doc_form,
knowledge_config.doc_language,
data_source_info,
@@ -1644,8 +1648,8 @@ class DocumentService:
# delete not selected documents
if len(exist_document) > 0:
clean_notion_document_task.delay(list(exist_document.values()), dataset.id)
elif knowledge_config.data_source.info_list.data_source_type == "website_crawl": # type: ignore
website_info = knowledge_config.data_source.info_list.website_info_list # type: ignore
elif knowledge_config.data_source.info_list.data_source_type == "website_crawl":
website_info = knowledge_config.data_source.info_list.website_info_list
if not website_info:
raise ValueError("No website info list found.")
urls = website_info.urls
@@ -1663,8 +1667,8 @@ class DocumentService:
document_name = url
document = DocumentService.build_document(
dataset,
dataset_process_rule.id, # type: ignore
knowledge_config.data_source.info_list.data_source_type, # type: ignore
dataset_process_rule.id,
knowledge_config.data_source.info_list.data_source_type,
knowledge_config.doc_form,
knowledge_config.doc_language,
data_source_info,
@@ -2071,7 +2075,7 @@ class DocumentService:
# update document data source
if document_data.data_source:
file_name = ""
data_source_info = {}
data_source_info: dict[str, str | bool] = {}
if document_data.data_source.info_list.data_source_type == "upload_file":
if not document_data.data_source.info_list.file_info_list:
raise ValueError("No file info list found.")
@@ -2128,7 +2132,7 @@ class DocumentService:
"url": url,
"provider": website_info.provider,
"job_id": website_info.job_id,
"only_main_content": website_info.only_main_content, # type: ignore
"only_main_content": website_info.only_main_content,
"mode": "crawl",
}
document.data_source_type = document_data.data_source.info_list.data_source_type
@@ -2154,7 +2158,7 @@ class DocumentService:
db.session.query(DocumentSegment).filter_by(document_id=document.id).update(
{DocumentSegment.status: "re_segment"}
) # type: ignore
)
db.session.commit()
# trigger async task
document_indexing_update_task.delay(document.dataset_id, document.id)
@@ -2164,25 +2168,26 @@ class DocumentService:
def save_document_without_dataset_id(tenant_id: str, knowledge_config: KnowledgeConfig, account: Account):
assert isinstance(current_user, Account)
assert current_user.current_tenant_id is not None
assert knowledge_config.data_source
features = FeatureService.get_features(current_user.current_tenant_id)
if features.billing.enabled:
count = 0
if knowledge_config.data_source.info_list.data_source_type == "upload_file": # type: ignore
if knowledge_config.data_source.info_list.data_source_type == "upload_file":
upload_file_list = (
knowledge_config.data_source.info_list.file_info_list.file_ids # type: ignore
if knowledge_config.data_source.info_list.file_info_list # type: ignore
knowledge_config.data_source.info_list.file_info_list.file_ids
if knowledge_config.data_source.info_list.file_info_list
else []
)
count = len(upload_file_list)
elif knowledge_config.data_source.info_list.data_source_type == "notion_import": # type: ignore
notion_info_list = knowledge_config.data_source.info_list.notion_info_list # type: ignore
elif knowledge_config.data_source.info_list.data_source_type == "notion_import":
notion_info_list = knowledge_config.data_source.info_list.notion_info_list
if notion_info_list:
for notion_info in notion_info_list:
count = count + len(notion_info.pages)
elif knowledge_config.data_source.info_list.data_source_type == "website_crawl": # type: ignore
website_info = knowledge_config.data_source.info_list.website_info_list # type: ignore
elif knowledge_config.data_source.info_list.data_source_type == "website_crawl":
website_info = knowledge_config.data_source.info_list.website_info_list
if website_info:
count = len(website_info.urls)
if features.billing.subscription.plan == "sandbox" and count > 1:
@@ -2196,9 +2201,11 @@ class DocumentService:
dataset_collection_binding_id = None
retrieval_model = None
if knowledge_config.indexing_technique == "high_quality":
assert knowledge_config.embedding_model_provider
assert knowledge_config.embedding_model
dataset_collection_binding = DatasetCollectionBindingService.get_dataset_collection_binding(
knowledge_config.embedding_model_provider, # type: ignore
knowledge_config.embedding_model, # type: ignore
knowledge_config.embedding_model_provider,
knowledge_config.embedding_model,
)
dataset_collection_binding_id = dataset_collection_binding.id
if knowledge_config.retrieval_model:
@@ -2215,7 +2222,7 @@ class DocumentService:
dataset = Dataset(
tenant_id=tenant_id,
name="",
data_source_type=knowledge_config.data_source.info_list.data_source_type, # type: ignore
data_source_type=knowledge_config.data_source.info_list.data_source_type,
indexing_technique=knowledge_config.indexing_technique,
created_by=account.id,
embedding_model=knowledge_config.embedding_model,
@@ -2224,7 +2231,7 @@ class DocumentService:
retrieval_model=retrieval_model.model_dump() if retrieval_model else None,
)
db.session.add(dataset) # type: ignore
db.session.add(dataset)
db.session.flush()
documents, batch = DocumentService.save_document_with_dataset_id(dataset, knowledge_config, account)

2
api/services/hit_testing_service.py
View File

@@ -88,7 +88,7 @@ class HitTestingService:
db.session.add(dataset_query)
db.session.commit()
return cls.compact_retrieve_response(query, all_documents) # type: ignore
return cls.compact_retrieve_response(query, all_documents)
@classmethod
def external_retrieve(

2
api/services/knowledge_service.py
View File

@@ -1,4 +1,4 @@
import boto3 # type: ignore
import boto3
from configs import dify_config

2
api/services/metadata_service.py
View File

@@ -89,7 +89,7 @@ class MetadataService:
document.doc_metadata = doc_metadata
db.session.add(document)
db.session.commit()
return metadata # type: ignore
return metadata
except Exception:
logger.exception("Update metadata name failed")
finally:

4
api/services/model_provider_service.py
View File

@@ -137,7 +137,7 @@ class ModelProviderService:
:return:
"""
provider_configuration = self._get_provider_configuration(tenant_id, provider)
return provider_configuration.get_provider_credential(credential_id=credential_id) # type: ignore
return provider_configuration.get_provider_credential(credential_id=credential_id)
def validate_provider_credentials(self, tenant_id: str, provider: str, credentials: dict):
"""
@@ -225,7 +225,7 @@ class ModelProviderService:
:return:
"""
provider_configuration = self._get_provider_configuration(tenant_id, provider)
return provider_configuration.get_custom_model_credential( # type: ignore
return provider_configuration.get_custom_model_credential(
model_type=ModelType.value_of(model_type), model=model, credential_id=credential_id
)

2
api/services/plugin/plugin_migration.py
View File

@@ -146,7 +146,7 @@ class PluginMigration:
futures.append(
thread_pool.submit(
process_tenant,
current_app._get_current_object(), # type: ignore[attr-defined]
current_app._get_current_object(), # type: ignore
tenant_id,
)
)

4
api/services/tools/builtin_tools_manage_service.py
View File

@@ -544,8 +544,8 @@ class BuiltinToolManageService:
try:
# handle include, exclude
if is_filtered(
include_set=dify_config.POSITION_TOOL_INCLUDES_SET, # type: ignore
exclude_set=dify_config.POSITION_TOOL_EXCLUDES_SET, # type: ignore
include_set=dify_config.POSITION_TOOL_INCLUDES_SET,
exclude_set=dify_config.POSITION_TOOL_EXCLUDES_SET,
data=provider_controller,
name_func=lambda x: x.entity.identity.name,
):

2
api/services/tools/mcp_tools_manage_service.py
View File

@@ -308,7 +308,7 @@ class MCPToolManageService:
provider_controller = MCPToolProviderController.from_db(mcp_provider)
tool_configuration = ProviderConfigEncrypter(
tenant_id=mcp_provider.tenant_id,
config=list(provider_controller.get_credentials_schema()), # ty: ignore [invalid-argument-type]
config=list(provider_controller.get_credentials_schema()),
provider_config_cache=NoOpProviderCredentialCache(),
)
credentials = tool_configuration.encrypt(credentials)