youngkingdom/dify
1
0
Fork 0
mirror of https://github.com/langgenius/dify.git synced 2026-04-23 20:36:14 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge remote-tracking branch 'origin/main' into feat/trigger

Browse Source
This commit is contained in:
lyzno1
2025-09-30 08:00:16 +08:00
parent 8106df1d7d f79d8baf63
commit 4a6903fdb4
122 changed files with 1962 additions and 451 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
api/controllers/console/datasets/datasets.py
View File

@ -1,4 +1,5 @@
import flask_restx
from typing import Any, cast
from flask import request
from flask_login import current_user
from flask_restx import Resource, fields, marshal, marshal_with, reqparse
@ -31,12 +32,13 @@ from fields.dataset_fields import dataset_detail_fields, dataset_query_detail_fi
from fields.document_fields import document_status_fields
from libs.login import login_required
from models import ApiToken, Dataset, Document, DocumentSegment, UploadFile
from models.account import Account
from models.dataset import DatasetPermissionEnum
from models.provider_ids import ModelProviderID
from services.dataset_service import DatasetPermissionService, DatasetService, DocumentService
def _validate_name(name):
def _validate_name(name: str) -> str:
if not name or len(name) < 1 or len(name) > 40:
raise ValueError("Name must be between 1 to 40 characters.")
return name
@ -92,7 +94,7 @@ class DatasetListApi(Resource):
for embedding_model in embedding_models:
model_names.append(f"{embedding_model.model}:{embedding_model.provider.provider}")
data = marshal(datasets, dataset_detail_fields)
data = cast(list[dict[str, Any]], marshal(datasets, dataset_detail_fields))
for item in data:
# convert embedding_model_provider to plugin standard format
if item["indexing_technique"] == "high_quality" and item["embedding_model_provider"]:
@ -192,7 +194,7 @@ class DatasetListApi(Resource):
name=args["name"],
description=args["description"],
indexing_technique=args["indexing_technique"],
account=current_user,
account=cast(Account, current_user),
permission=DatasetPermissionEnum.ONLY_ME,
provider=args["provider"],
external_knowledge_api_id=args["external_knowledge_api_id"],
@ -224,7 +226,7 @@ class DatasetApi(Resource):
DatasetService.check_dataset_permission(dataset, current_user)
except services.errors.account.NoPermissionError as e:
raise Forbidden(str(e))
data = marshal(dataset, dataset_detail_fields)
data = cast(dict[str, Any], marshal(dataset, dataset_detail_fields))
if dataset.indexing_technique == "high_quality":
if dataset.embedding_model_provider:
provider_id = ModelProviderID(dataset.embedding_model_provider)
@ -369,7 +371,7 @@ class DatasetApi(Resource):
if dataset is None:
raise NotFound("Dataset not found.")
result_data = marshal(dataset, dataset_detail_fields)
result_data = cast(dict[str, Any], marshal(dataset, dataset_detail_fields))
tenant_id = current_user.current_tenant_id
if data.get("partial_member_list") and data.get("permission") == "partial_members":
@ -688,7 +690,7 @@ class DatasetApiKeyApi(Resource):
)
if current_key_count >= self.max_keys:
flask_restx.abort(
api.abort(
400,
message=f"Cannot create more than {self.max_keys} API keys for this resource type.",
code="max_keys_exceeded",
@ -733,7 +735,7 @@ class DatasetApiDeleteApi(Resource):
)
if key is None:
flask_restx.abort(404, message="API key not found")
api.abort(404, message="API key not found")
db.session.query(ApiToken).where(ApiToken.id == api_key_id).delete()
db.session.commit()

15
api/controllers/console/datasets/datasets_document.py
View File

@ -55,6 +55,7 @@ from fields.document_fields import (
from libs.datetime_utils import naive_utc_now
from libs.login import login_required
from models import Dataset, DatasetProcessRule, Document, DocumentSegment, UploadFile
from models.account import Account
from models.dataset import DocumentPipelineExecutionLog
from services.dataset_service import DatasetService, DocumentService
from services.entities.knowledge_entities.knowledge_entities import KnowledgeConfig
@ -418,7 +419,9 @@ class DatasetInitApi(Resource):
try:
dataset, documents, batch = DocumentService.save_document_without_dataset_id(
tenant_id=current_user.current_tenant_id, knowledge_config=knowledge_config, account=current_user
tenant_id=current_user.current_tenant_id,
knowledge_config=knowledge_config,
account=cast(Account, current_user),
)
except ProviderTokenNotInitError as ex:
raise ProviderNotInitializeError(ex.description)
@ -452,7 +455,7 @@ class DocumentIndexingEstimateApi(DocumentResource):
raise DocumentAlreadyFinishedError()
data_process_rule = document.dataset_process_rule
data_process_rule_dict = data_process_rule.to_dict()
data_process_rule_dict = data_process_rule.to_dict() if data_process_rule else {}
response = {"tokens": 0, "total_price": 0, "currency": "USD", "total_segments": 0, "preview": []}
@ -514,7 +517,7 @@ class DocumentBatchIndexingEstimateApi(DocumentResource):
if not documents:
return {"tokens": 0, "total_price": 0, "currency": "USD", "total_segments": 0, "preview": []}, 200
data_process_rule = documents[0].dataset_process_rule
data_process_rule_dict = data_process_rule.to_dict()
data_process_rule_dict = data_process_rule.to_dict() if data_process_rule else {}
extract_settings = []
for document in documents:
if document.indexing_status in {"completed", "error"}:
@ -753,7 +756,7 @@ class DocumentApi(DocumentResource):
}
else:
dataset_process_rules = DatasetService.get_process_rules(dataset_id)
document_process_rules = document.dataset_process_rule.to_dict()
document_process_rules = document.dataset_process_rule.to_dict() if document.dataset_process_rule else {}
data_source_info = document.data_source_detail_dict
response = {
"id": document.id,
@ -1073,7 +1076,9 @@ class DocumentRenameApi(DocumentResource):
if not current_user.is_dataset_editor:
raise Forbidden()
dataset = DatasetService.get_dataset(dataset_id)
DatasetService.check_dataset_operator_permission(current_user, dataset)
if not dataset:
raise NotFound("Dataset not found.")
DatasetService.check_dataset_operator_permission(cast(Account, current_user), dataset)
parser = reqparse.RequestParser()
parser.add_argument("name", type=str, required=True, nullable=False, location="json")
args = parser.parse_args()

18
api/controllers/console/datasets/datasets_segments.py
View File

@ -392,7 +392,12 @@ class DatasetDocumentSegmentBatchImportApi(Resource):
# send batch add segments task
redis_client.setnx(indexing_cache_key, "waiting")
batch_create_segment_to_index_task.delay(
str(job_id), upload_file_id, dataset_id, document_id, current_user.current_tenant_id, current_user.id
str(job_id),
upload_file_id,
dataset_id,
document_id,
current_user.current_tenant_id,
current_user.id,
)
except Exception as e:
return {"error": str(e)}, 500
@ -468,7 +473,8 @@ class ChildChunkAddApi(Resource):
parser.add_argument("content", type=str, required=True, nullable=False, location="json")
args = parser.parse_args()
try:
child_chunk = SegmentService.create_child_chunk(args.get("content"), segment, document, dataset)
content = args["content"]
child_chunk = SegmentService.create_child_chunk(content, segment, document, dataset)
except ChildChunkIndexingServiceError as e:
raise ChildChunkIndexingError(str(e))
return {"data": marshal(child_chunk, child_chunk_fields)}, 200
@ -557,7 +563,8 @@ class ChildChunkAddApi(Resource):
parser.add_argument("chunks", type=list, required=True, nullable=False, location="json")
args = parser.parse_args()
try:
chunks = [ChildChunkUpdateArgs(**chunk) for chunk in args.get("chunks")]
chunks_data = args["chunks"]
chunks = [ChildChunkUpdateArgs(**chunk) for chunk in chunks_data]
child_chunks = SegmentService.update_child_chunks(chunks, segment, document, dataset)
except ChildChunkIndexingServiceError as e:
raise ChildChunkIndexingError(str(e))
@ -674,9 +681,8 @@ class ChildChunkUpdateApi(Resource):
parser.add_argument("content", type=str, required=True, nullable=False, location="json")
args = parser.parse_args()
try:
child_chunk = SegmentService.update_child_chunk(
args.get("content"), child_chunk, segment, document, dataset
)
content = args["content"]
child_chunk = SegmentService.update_child_chunk(content, child_chunk, segment, document, dataset)
except ChildChunkIndexingServiceError as e:
raise ChildChunkIndexingError(str(e))
return {"data": marshal(child_chunk, child_chunk_fields)}, 200

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

@ -1,3 +1,5 @@
from typing import cast
from flask import request
from flask_login import current_user
from flask_restx import Resource, fields, marshal, reqparse
@ -9,13 +11,14 @@ from controllers.console.datasets.error import DatasetNameDuplicateError
from controllers.console.wraps import account_initialization_required, setup_required
from fields.dataset_fields import dataset_detail_fields
from libs.login import login_required
from models.account import Account
from services.dataset_service import DatasetService
from services.external_knowledge_service import ExternalDatasetService
from services.hit_testing_service import HitTestingService
from services.knowledge_service import ExternalDatasetTestService
def _validate_name(name):
def _validate_name(name: str) -> str:
if not name or len(name) < 1 or len(name) > 100:
raise ValueError("Name must be between 1 to 100 characters.")
return name
@ -274,7 +277,7 @@ class ExternalKnowledgeHitTestingApi(Resource):
response = HitTestingService.external_retrieve(
dataset=dataset,
query=args["query"],
account=current_user,
account=cast(Account, current_user),
external_retrieval_model=args["external_retrieval_model"],
metadata_filtering_conditions=args["metadata_filtering_conditions"],
)

6
api/controllers/console/datasets/hit_testing_base.py
View File

@ -1,10 +1,11 @@
import logging
from typing import cast
from flask_login import current_user
from flask_restx import marshal, reqparse
from werkzeug.exceptions import Forbidden, InternalServerError, NotFound
import services.dataset_service
import services
from controllers.console.app.error import (
CompletionRequestError,
ProviderModelCurrentlyNotSupportError,
@ -20,6 +21,7 @@ from core.errors.error import (
)
from core.model_runtime.errors.invoke import InvokeError
from fields.hit_testing_fields import hit_testing_record_fields
from models.account import Account
from services.dataset_service import DatasetService
from services.hit_testing_service import HitTestingService
@ -59,7 +61,7 @@ class DatasetsHitTestingBase:
response = HitTestingService.retrieve(
dataset=dataset,
query=args["query"],
account=current_user,
account=cast(Account, current_user),
retrieval_model=args["retrieval_model"],
external_retrieval_model=args["external_retrieval_model"],
limit=10,

3
api/controllers/console/datasets/metadata.py
View File

@ -62,6 +62,7 @@ class DatasetMetadataApi(Resource):
parser = reqparse.RequestParser()
parser.add_argument("name", type=str, required=True, nullable=False, location="json")
args = parser.parse_args()
name = args["name"]
dataset_id_str = str(dataset_id)
metadata_id_str = str(metadata_id)
@ -70,7 +71,7 @@ class DatasetMetadataApi(Resource):
raise NotFound("Dataset not found.")
DatasetService.check_dataset_permission(dataset, current_user)
metadata = MetadataService.update_metadata_name(dataset_id_str, metadata_id_str, args.get("name"))
metadata = MetadataService.update_metadata_name(dataset_id_str, metadata_id_str, name)
return metadata, 200
@setup_required

8
api/controllers/console/datasets/rag_pipeline/rag_pipeline.py
View File

@ -20,13 +20,13 @@ from services.rag_pipeline.rag_pipeline import RagPipelineService
logger = logging.getLogger(__name__)
def _validate_name(name):
def _validate_name(name: str) -> str:
if not name or len(name) < 1 or len(name) > 40:
raise ValueError("Name must be between 1 to 40 characters.")
return name
def _validate_description_length(description):
def _validate_description_length(description: str) -> str:
if len(description) > 400:
raise ValueError("Description cannot exceed 400 characters.")
return description
@ -76,7 +76,7 @@ class CustomizedPipelineTemplateApi(Resource):
)
parser.add_argument(
"description",
type=str,
type=_validate_description_length,
nullable=True,
required=False,
default="",
@ -133,7 +133,7 @@ class PublishCustomizedPipelineTemplateApi(Resource):
)
parser.add_argument(
"description",
type=str,
type=_validate_description_length,
nullable=True,
required=False,
default="",

16
api/controllers/console/datasets/rag_pipeline/rag_pipeline_datasets.py
View File

@ -1,5 +1,5 @@
from flask_login import current_user # type: ignore # type: ignore
from flask_restx import Resource, marshal, reqparse # type: ignore
from flask_login import current_user
from flask_restx import Resource, marshal, reqparse
from sqlalchemy.orm import Session
from werkzeug.exceptions import Forbidden
@ -20,18 +20,6 @@ from services.entities.knowledge_entities.rag_pipeline_entities import IconInfo,
from services.rag_pipeline.rag_pipeline_dsl_service import RagPipelineDslService
def _validate_name(name):
if not name or len(name) < 1 or len(name) > 40:
raise ValueError("Name must be between 1 to 40 characters.")
return name
def _validate_description_length(description):
if len(description) > 400:
raise ValueError("Description cannot exceed 400 characters.")
return description
@console_ns.route("/rag/pipeline/dataset")
class CreateRagPipelineDatasetApi(Resource):
@setup_required

36
api/controllers/console/datasets/rag_pipeline/rag_pipeline_draft_variable.py
View File

@ -1,5 +1,5 @@
import logging
from typing import Any, NoReturn
from typing import NoReturn
from flask import Response
from flask_restx import Resource, fields, inputs, marshal, marshal_with, reqparse
@ -11,14 +11,12 @@ from controllers.console.app.error import (
DraftWorkflowNotExist,
)
from controllers.console.app.workflow_draft_variable import (
_WORKFLOW_DRAFT_VARIABLE_FIELDS,
_WORKFLOW_DRAFT_VARIABLE_WITHOUT_VALUE_FIELDS,
_WORKFLOW_DRAFT_VARIABLE_FIELDS, # type: ignore[private-usage]
_WORKFLOW_DRAFT_VARIABLE_WITHOUT_VALUE_FIELDS, # type: ignore[private-usage]
)
from controllers.console.datasets.wraps import get_rag_pipeline
from controllers.console.wraps import account_initialization_required, setup_required
from controllers.web.error import InvalidArgumentError, NotFoundError
from core.variables.segment_group import SegmentGroup
from core.variables.segments import ArrayFileSegment, FileSegment, Segment
from core.variables.types import SegmentType
from core.workflow.constants import CONVERSATION_VARIABLE_NODE_ID, SYSTEM_VARIABLE_NODE_ID
from extensions.ext_database import db
@ -34,32 +32,6 @@ from services.workflow_draft_variable_service import WorkflowDraftVariableList,
logger = logging.getLogger(__name__)
def _convert_values_to_json_serializable_object(value: Segment) -> Any:
if isinstance(value, FileSegment):
return value.value.model_dump()
elif isinstance(value, ArrayFileSegment):
return [i.model_dump() for i in value.value]
elif isinstance(value, SegmentGroup):
return [_convert_values_to_json_serializable_object(i) for i in value.value]
else:
return value.value
def _serialize_var_value(variable: WorkflowDraftVariable) -> Any:
value = variable.get_value()
# create a copy of the value to avoid affecting the model cache.
value = value.model_copy(deep=True)
# Refresh the url signature before returning it to client.
if isinstance(value, FileSegment):
file = value.value
file.remote_url = file.generate_url()
elif isinstance(value, ArrayFileSegment):
files = value.value
for file in files:
file.remote_url = file.generate_url()
return _convert_values_to_json_serializable_object(value)
def _create_pagination_parser():
parser = reqparse.RequestParser()
parser.add_argument(
@ -104,7 +76,7 @@ def _api_prerequisite(f):
@account_initialization_required
@get_rag_pipeline
def wrapper(*args, **kwargs):
if not isinstance(current_user, Account) or not current_user.is_editor:
if not isinstance(current_user, Account) or not current_user.has_edit_permission:
raise Forbidden()
return f(*args, **kwargs)

12
api/controllers/console/tag/tags.py
View File

@ -3,7 +3,7 @@ from flask_login import current_user
from flask_restx import Resource, marshal_with, reqparse
from werkzeug.exceptions import Forbidden
from controllers.console import api
from controllers.console import console_ns
from controllers.console.wraps import account_initialization_required, setup_required
from fields.tag_fields import dataset_tag_fields
from libs.login import login_required
@ -17,6 +17,7 @@ def _validate_name(name):
return name
@console_ns.route("/tags")
class TagListApi(Resource):
@setup_required
@login_required
@ -52,6 +53,7 @@ class TagListApi(Resource):
return response, 200
@console_ns.route("/tags/<uuid:tag_id>")
class TagUpdateDeleteApi(Resource):
@setup_required
@login_required
@ -89,6 +91,7 @@ class TagUpdateDeleteApi(Resource):
return 204
@console_ns.route("/tag-bindings/create")
class TagBindingCreateApi(Resource):
@setup_required
@login_required
@ -114,6 +117,7 @@ class TagBindingCreateApi(Resource):
return {"result": "success"}, 200
@console_ns.route("/tag-bindings/remove")
class TagBindingDeleteApi(Resource):
@setup_required
@login_required
@ -133,9 +137,3 @@ class TagBindingDeleteApi(Resource):
TagService.delete_tag_binding(args)
return {"result": "success"}, 200
api.add_resource(TagListApi, "/tags")
api.add_resource(TagUpdateDeleteApi, "/tags/<uuid:tag_id>")
api.add_resource(TagBindingCreateApi, "/tag-bindings/create")
api.add_resource(TagBindingDeleteApi, "/tag-bindings/remove")

66
api/controllers/service_api/dataset/dataset.py
View File

@ -1,10 +1,10 @@
from typing import Literal
from typing import Any, Literal, cast
from flask import request
from flask_restx import marshal, reqparse
from werkzeug.exceptions import Forbidden, NotFound
import services.dataset_service
import services
from controllers.service_api import service_api_ns
from controllers.service_api.dataset.error import DatasetInUseError, DatasetNameDuplicateError, InvalidActionError
from controllers.service_api.wraps import (
@ -254,19 +254,21 @@ class DatasetListApi(DatasetApiResource):
"""Resource for creating datasets."""
args = dataset_create_parser.parse_args()
if args.get("embedding_model_provider"):
DatasetService.check_embedding_model_setting(
tenant_id, args.get("embedding_model_provider"), args.get("embedding_model")
)
embedding_model_provider = args.get("embedding_model_provider")
embedding_model = args.get("embedding_model")
if embedding_model_provider and embedding_model:
DatasetService.check_embedding_model_setting(tenant_id, embedding_model_provider, embedding_model)
retrieval_model = args.get("retrieval_model")
if (
args.get("retrieval_model")
and args.get("retrieval_model").get("reranking_model")
and args.get("retrieval_model").get("reranking_model").get("reranking_provider_name")
retrieval_model
and retrieval_model.get("reranking_model")
and retrieval_model.get("reranking_model").get("reranking_provider_name")
):
DatasetService.check_reranking_model_setting(
tenant_id,
args.get("retrieval_model").get("reranking_model").get("reranking_provider_name"),
args.get("retrieval_model").get("reranking_model").get("reranking_model_name"),
retrieval_model.get("reranking_model").get("reranking_provider_name"),
retrieval_model.get("reranking_model").get("reranking_model_name"),
)
try:
@ -317,7 +319,7 @@ class DatasetApi(DatasetApiResource):
DatasetService.check_dataset_permission(dataset, current_user)
except services.errors.account.NoPermissionError as e:
raise Forbidden(str(e))
data = marshal(dataset, dataset_detail_fields)
data = cast(dict[str, Any], marshal(dataset, dataset_detail_fields))
# check embedding setting
provider_manager = ProviderManager()
assert isinstance(current_user, Account)
@ -331,8 +333,8 @@ class DatasetApi(DatasetApiResource):
for embedding_model in embedding_models:
model_names.append(f"{embedding_model.model}:{embedding_model.provider.provider}")
if data["indexing_technique"] == "high_quality":
item_model = f"{data['embedding_model']}:{data['embedding_model_provider']}"
if data.get("indexing_technique") == "high_quality":
item_model = f"{data.get('embedding_model')}:{data.get('embedding_model_provider')}"
if item_model in model_names:
data["embedding_available"] = True
else:
@ -341,7 +343,9 @@ class DatasetApi(DatasetApiResource):
data["embedding_available"] = True
# force update search method to keyword_search if indexing_technique is economic
data["retrieval_model_dict"]["search_method"] = "keyword_search"
retrieval_model_dict = data.get("retrieval_model_dict")
if retrieval_model_dict:
retrieval_model_dict["search_method"] = "keyword_search"
if data.get("permission") == "partial_members":
part_users_list = DatasetPermissionService.get_dataset_partial_member_list(dataset_id_str)
@ -372,19 +376,24 @@ class DatasetApi(DatasetApiResource):
data = request.get_json()
# check embedding model setting
if data.get("indexing_technique") == "high_quality" or data.get("embedding_model_provider"):
DatasetService.check_embedding_model_setting(
dataset.tenant_id, data.get("embedding_model_provider"), data.get("embedding_model")
)
embedding_model_provider = data.get("embedding_model_provider")
embedding_model = data.get("embedding_model")
if data.get("indexing_technique") == "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
)
retrieval_model = data.get("retrieval_model")
if (
data.get("retrieval_model")
and data.get("retrieval_model").get("reranking_model")
and data.get("retrieval_model").get("reranking_model").get("reranking_provider_name")
retrieval_model
and retrieval_model.get("reranking_model")
and retrieval_model.get("reranking_model").get("reranking_provider_name")
):
DatasetService.check_reranking_model_setting(
dataset.tenant_id,
data.get("retrieval_model").get("reranking_model").get("reranking_provider_name"),
data.get("retrieval_model").get("reranking_model").get("reranking_model_name"),
retrieval_model.get("reranking_model").get("reranking_provider_name"),
retrieval_model.get("reranking_model").get("reranking_model_name"),
)
# The role of the current user in the ta table must be admin, owner, editor, or dataset_operator
@ -397,7 +406,7 @@ class DatasetApi(DatasetApiResource):
if dataset is None:
raise NotFound("Dataset not found.")
result_data = marshal(dataset, dataset_detail_fields)
result_data = cast(dict[str, Any], marshal(dataset, dataset_detail_fields))
assert isinstance(current_user, Account)
tenant_id = current_user.current_tenant_id
@ -591,9 +600,10 @@ class DatasetTagsApi(DatasetApiResource):
args = tag_update_parser.parse_args()
args["type"] = "knowledge"
tag = TagService.update_tags(args, args.get("tag_id"))
tag_id = args["tag_id"]
tag = TagService.update_tags(args, tag_id)
binding_count = TagService.get_tag_binding_count(args.get("tag_id"))
binding_count = TagService.get_tag_binding_count(tag_id)
response = {"id": tag.id, "name": tag.name, "type": tag.type, "binding_count": binding_count}
@ -616,7 +626,7 @@ class DatasetTagsApi(DatasetApiResource):
if not current_user.has_edit_permission:
raise Forbidden()
args = tag_delete_parser.parse_args()
TagService.delete_tag(args.get("tag_id"))
TagService.delete_tag(args["tag_id"])
return 204

31
api/controllers/service_api/dataset/document.py
View File

@ -108,19 +108,21 @@ class DocumentAddByTextApi(DatasetApiResource):
if text is None or name is None:
raise ValueError("Both 'text' and 'name' must be non-null values.")
if args.get("embedding_model_provider"):
DatasetService.check_embedding_model_setting(
tenant_id, args.get("embedding_model_provider"), args.get("embedding_model")
)
embedding_model_provider = args.get("embedding_model_provider")
embedding_model = args.get("embedding_model")
if embedding_model_provider and embedding_model:
DatasetService.check_embedding_model_setting(tenant_id, embedding_model_provider, embedding_model)
retrieval_model = args.get("retrieval_model")
if (
args.get("retrieval_model")
and args.get("retrieval_model").get("reranking_model")
and args.get("retrieval_model").get("reranking_model").get("reranking_provider_name")
retrieval_model
and retrieval_model.get("reranking_model")
and retrieval_model.get("reranking_model").get("reranking_provider_name")
):
DatasetService.check_reranking_model_setting(
tenant_id,
args.get("retrieval_model").get("reranking_model").get("reranking_provider_name"),
args.get("retrieval_model").get("reranking_model").get("reranking_model_name"),
retrieval_model.get("reranking_model").get("reranking_provider_name"),
retrieval_model.get("reranking_model").get("reranking_model_name"),
)
if not current_user:
@ -187,15 +189,16 @@ class DocumentUpdateByTextApi(DatasetApiResource):
if not dataset:
raise ValueError("Dataset does not exist.")
retrieval_model = args.get("retrieval_model")
if (
args.get("retrieval_model")
and args.get("retrieval_model").get("reranking_model")
and args.get("retrieval_model").get("reranking_model").get("reranking_provider_name")
retrieval_model
and retrieval_model.get("reranking_model")
and retrieval_model.get("reranking_model").get("reranking_provider_name")
):
DatasetService.check_reranking_model_setting(
tenant_id,
args.get("retrieval_model").get("reranking_model").get("reranking_provider_name"),
args.get("retrieval_model").get("reranking_model").get("reranking_model_name"),
retrieval_model.get("reranking_model").get("reranking_provider_name"),
retrieval_model.get("reranking_model").get("reranking_model_name"),
)
# indexing_technique is already set in dataset since this is an update

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

@ -106,7 +106,7 @@ class DatasetMetadataServiceApi(DatasetApiResource):
raise NotFound("Dataset not found.")
DatasetService.check_dataset_permission(dataset, current_user)
metadata = MetadataService.update_metadata_name(dataset_id_str, metadata_id_str, args.get("name"))
metadata = MetadataService.update_metadata_name(dataset_id_str, metadata_id_str, args["name"])
return marshal(metadata, dataset_metadata_fields), 200
@service_api_ns.doc("delete_dataset_metadata")