jprdonnelly/dify
1
0
Fork 0
mirror of https://github.com/langgenius/dify.git synced 2026-03-17 04:02:38 -04:00
Code Issues Packages Projects Releases Wiki Activity

feat: knowledge pipeline (#25360)

Browse Source 
Signed-off-by: -LAN- <laipz8200@outlook.com>
Co-authored-by: twwu <twwu@dify.ai>
Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>
Co-authored-by: jyong <718720800@qq.com>
Co-authored-by: Wu Tianwei <30284043+WTW0313@users.noreply.github.com>
Co-authored-by: QuantumGhost <obelisk.reg+git@gmail.com>
Co-authored-by: lyzno1 <yuanyouhuilyz@gmail.com>
Co-authored-by: quicksand <quicksandzn@gmail.com>
Co-authored-by: Jyong <76649700+JohnJyong@users.noreply.github.com>
Co-authored-by: lyzno1 <92089059+lyzno1@users.noreply.github.com>
Co-authored-by: zxhlyh <jasonapring2015@outlook.com>
Co-authored-by: Yongtao Huang <yongtaoh2022@gmail.com>
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
Co-authored-by: Joel <iamjoel007@gmail.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: nite-knite <nkCoding@gmail.com>
Co-authored-by: Hanqing Zhao <sherry9277@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Harry <xh001x@hotmail.com>
This commit is contained in:
-LAN-
2025-09-18 12:49:10 +08:00
committed by GitHub
parent 7dadb33003
commit 85cda47c70
1772 changed files with 102407 additions and 31710 deletions
Download Patch File Download Diff File Expand all files Collapse all files

112
api/core/datasource/datasource_manager.py Normal file
View File

@@ -0,0 +1,112 @@
import logging
from threading import Lock
from typing import Union
import contexts
from core.datasource.__base.datasource_plugin import DatasourcePlugin
from core.datasource.__base.datasource_provider import DatasourcePluginProviderController
from core.datasource.entities.common_entities import I18nObject
from core.datasource.entities.datasource_entities import DatasourceProviderType
from core.datasource.errors import DatasourceProviderNotFoundError
from core.datasource.local_file.local_file_provider import LocalFileDatasourcePluginProviderController
from core.datasource.online_document.online_document_provider import OnlineDocumentDatasourcePluginProviderController
from core.datasource.online_drive.online_drive_provider import OnlineDriveDatasourcePluginProviderController
from core.datasource.website_crawl.website_crawl_provider import WebsiteCrawlDatasourcePluginProviderController
from core.plugin.impl.datasource import PluginDatasourceManager
logger = logging.getLogger(__name__)
class DatasourceManager:
_builtin_provider_lock = Lock()
_hardcoded_providers: dict[str, DatasourcePluginProviderController] = {}
_builtin_providers_loaded = False
_builtin_tools_labels: dict[str, Union[I18nObject, None]] = {}
@classmethod
def get_datasource_plugin_provider(
cls, provider_id: str, tenant_id: str, datasource_type: DatasourceProviderType
) -> DatasourcePluginProviderController:
"""
get the datasource plugin provider
"""
# check if context is set
try:
contexts.datasource_plugin_providers.get()
except LookupError:
contexts.datasource_plugin_providers.set({})
contexts.datasource_plugin_providers_lock.set(Lock())
with contexts.datasource_plugin_providers_lock.get():
datasource_plugin_providers = contexts.datasource_plugin_providers.get()
if provider_id in datasource_plugin_providers:
return datasource_plugin_providers[provider_id]
manager = PluginDatasourceManager()
provider_entity = manager.fetch_datasource_provider(tenant_id, provider_id)
if not provider_entity:
raise DatasourceProviderNotFoundError(f"plugin provider {provider_id} not found")
controller: DatasourcePluginProviderController | None = None
match datasource_type:
case DatasourceProviderType.ONLINE_DOCUMENT:
controller = OnlineDocumentDatasourcePluginProviderController(
entity=provider_entity.declaration,
plugin_id=provider_entity.plugin_id,
plugin_unique_identifier=provider_entity.plugin_unique_identifier,
tenant_id=tenant_id,
)
case DatasourceProviderType.ONLINE_DRIVE:
controller = OnlineDriveDatasourcePluginProviderController(
entity=provider_entity.declaration,
plugin_id=provider_entity.plugin_id,
plugin_unique_identifier=provider_entity.plugin_unique_identifier,
tenant_id=tenant_id,
)
case DatasourceProviderType.WEBSITE_CRAWL:
controller = WebsiteCrawlDatasourcePluginProviderController(
entity=provider_entity.declaration,
plugin_id=provider_entity.plugin_id,
plugin_unique_identifier=provider_entity.plugin_unique_identifier,
tenant_id=tenant_id,
)
case DatasourceProviderType.LOCAL_FILE:
controller = LocalFileDatasourcePluginProviderController(
entity=provider_entity.declaration,
plugin_id=provider_entity.plugin_id,
plugin_unique_identifier=provider_entity.plugin_unique_identifier,
tenant_id=tenant_id,
)
case _:
raise ValueError(f"Unsupported datasource type: {datasource_type}")
if controller:
datasource_plugin_providers[provider_id] = controller
if controller is None:
raise DatasourceProviderNotFoundError(f"Datasource provider {provider_id} not found.")
return controller
@classmethod
def get_datasource_runtime(
cls,
provider_id: str,
datasource_name: str,
tenant_id: str,
datasource_type: DatasourceProviderType,
) -> DatasourcePlugin:
"""
get the datasource runtime
:param provider_type: the type of the provider
:param provider_id: the id of the provider
:param datasource_name: the name of the datasource
:param tenant_id: the tenant id
:return: the datasource plugin
"""
return cls.get_datasource_plugin_provider(
provider_id,
tenant_id,
datasource_type,
).get_datasource(datasource_name)