hz/ebiz-dify-ai
1
0
Fork 0
mirror of http://112.124.100.131/huang.ze/ebiz-dify-ai.git synced 2025-12-09 19:06:51 +08:00
Code Issues Packages Projects Releases Wiki Activity

Model Runtime (#1858)

Browse Source 
Co-authored-by: StyleZhang <jasonapring2015@outlook.com>
Co-authored-by: Garfield Dai <dai.hai@foxmail.com>
Co-authored-by: chenhe <guchenhe@gmail.com>
Co-authored-by: jyong <jyong@dify.ai>
Co-authored-by: Joel <iamjoel007@gmail.com>
Co-authored-by: Yeuoly <admin@srmxy.cn>
This commit is contained in:
takatost
2024-01-02 23:42:00 +08:00
committed by GitHub
parent e91dd28a76
commit d069c668f8
807 changed files with 171310 additions and 23806 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
api/controllers/service_api/dataset/dataset.py
View File

@@ -4,11 +4,11 @@ import services.dataset_service
from controllers.service_api import api
from controllers.service_api.dataset.error import DatasetNameDuplicateError
from controllers.service_api.wraps import DatasetApiResource
from core.model_runtime.entities.model_entities import ModelType
from core.provider_manager import ProviderManager
from libs.login import current_user
from core.model_providers.models.entity.model_params import ModelType
from fields.dataset_fields import dataset_detail_fields
from services.dataset_service import DatasetService
from services.provider_service import ProviderService
def _validate_name(name):
@@ -27,12 +27,20 @@ class DatasetApi(DatasetApiResource):
datasets, total = DatasetService.get_datasets(page, limit, provider,
tenant_id, current_user)
# check embedding setting
provider_service = ProviderService()
valid_model_list = provider_service.get_valid_model_list(current_user.current_tenant_id,
ModelType.EMBEDDINGS.value)
provider_manager = ProviderManager()
configurations = provider_manager.get_configurations(
tenant_id=current_user.current_tenant_id
)
embedding_models = configurations.get_models(
model_type=ModelType.TEXT_EMBEDDING,
only_active=True
)
model_names = []
for valid_model in valid_model_list:
model_names.append(f"{valid_model['model_name']}:{valid_model['model_provider']['provider_name']}")
for embedding_model in embedding_models:
model_names.append(f"{embedding_model.model}:{embedding_model.provider.provider}")
data = marshal(datasets, dataset_detail_fields)
for item in data:
if item['indexing_technique'] == 'high_quality':

2
api/controllers/service_api/dataset/document.py
View File

@@ -13,7 +13,7 @@ from controllers.service_api.dataset.error import ArchivedDocumentImmutableError
NoFileUploadedError, TooManyFilesError
from controllers.service_api.wraps import DatasetApiResource, cloud_edition_billing_resource_check
from libs.login import current_user
from core.model_providers.error import ProviderTokenNotInitError
from core.errors.error import ProviderTokenNotInitError
from extensions.ext_database import db
from fields.document_fields import document_fields, document_status_fields
from models.dataset import Dataset, Document, DocumentSegment

29
api/controllers/service_api/dataset/segment.py
View File

@@ -4,8 +4,9 @@ from werkzeug.exceptions import NotFound
from controllers.service_api import api
from controllers.service_api.app.error import ProviderNotInitializeError
from controllers.service_api.wraps import DatasetApiResource, cloud_edition_billing_resource_check
from core.model_providers.error import ProviderTokenNotInitError, LLMBadRequestError
from core.model_providers.model_factory import ModelFactory
from core.errors.error import ProviderTokenNotInitError, LLMBadRequestError
from core.model_manager import ModelManager
from core.model_runtime.entities.model_entities import ModelType
from extensions.ext_database import db
from fields.segment_fields import segment_fields
from models.dataset import Dataset, DocumentSegment
@@ -35,10 +36,12 @@ class SegmentApi(DatasetApiResource):
# check embedding model setting
if dataset.indexing_technique == 'high_quality':
try:
ModelFactory.get_embedding_model(
model_manager = ModelManager()
model_manager.get_model_instance(
tenant_id=current_user.current_tenant_id,
model_provider_name=dataset.embedding_model_provider,
model_name=dataset.embedding_model
provider=dataset.embedding_model_provider,
model_type=ModelType.TEXT_EMBEDDING,
model=dataset.embedding_model
)
except LLMBadRequestError:
raise ProviderNotInitializeError(
@@ -77,10 +80,12 @@ class SegmentApi(DatasetApiResource):
# check embedding model setting
if dataset.indexing_technique == 'high_quality':
try:
ModelFactory.get_embedding_model(
model_manager = ModelManager()
model_manager.get_model_instance(
tenant_id=current_user.current_tenant_id,
model_provider_name=dataset.embedding_model_provider,
model_name=dataset.embedding_model
provider=dataset.embedding_model_provider,
model_type=ModelType.TEXT_EMBEDDING,
model=dataset.embedding_model
)
except LLMBadRequestError:
raise ProviderNotInitializeError(
@@ -167,10 +172,12 @@ class DatasetSegmentApi(DatasetApiResource):
if dataset.indexing_technique == 'high_quality':
# check embedding model setting
try:
ModelFactory.get_embedding_model(
model_manager = ModelManager()
model_manager.get_model_instance(
tenant_id=current_user.current_tenant_id,
model_provider_name=dataset.embedding_model_provider,
model_name=dataset.embedding_model
provider=dataset.embedding_model_provider,
model_type=ModelType.TEXT_EMBEDDING,
model=dataset.embedding_model
)
except LLMBadRequestError:
raise ProviderNotInitializeError(