external knowledge api

This commit is contained in:
jyong
2024-09-18 14:36:51 +08:00
parent 89e81873c4
commit 9f894bb3b3
12 changed files with 330 additions and 274 deletions

View File

@ -37,7 +37,7 @@ from .auth import activate, data_source_bearer_auth, data_source_oauth, forgot_p
from .billing import billing
# Import datasets controllers
from .datasets import data_source, datasets, datasets_document, datasets_segments, file, hit_testing, website
from .datasets import data_source, datasets, datasets_document, datasets_segments, external, file, hit_testing, website
# Import explore controllers
from .explore import (

View File

@ -110,6 +110,26 @@ class DatasetListApi(Resource):
nullable=True,
help="Invalid indexing technique.",
)
parser.add_argument(
"external_api_template_id",
type=str,
nullable=True,
required=False,
)
parser.add_argument(
"provider",
type=str,
nullable=True,
choices=Dataset.PROVIDER_LIST,
required=False,
default="vendor",
)
parser.add_argument(
"external_knowledge_id",
type=str,
nullable=True,
required=False,
)
args = parser.parse_args()
# The role of the current user in the ta table must be admin, owner, or editor, or dataset_operator
@ -123,6 +143,9 @@ class DatasetListApi(Resource):
indexing_technique=args["indexing_technique"],
account=current_user,
permission=DatasetPermissionEnum.ONLY_ME,
provider=args["provider"],
external_api_template_id=args["external_api_template_id"],
external_knowledge_id=args["external_knowledge_id"],
)
except services.errors.dataset.DatasetNameDuplicateError:
raise DatasetNameDuplicateError()

View File

@ -1,69 +1,49 @@
import flask_restful
from flask import request
from flask_login import current_user
from flask_restful import Resource, marshal, marshal_with, reqparse
from flask_restful import Resource, marshal, reqparse
from werkzeug.exceptions import Forbidden, NotFound
import services
from configs import dify_config
from controllers.console import api
from controllers.console.apikey import api_key_fields, api_key_list
from controllers.console.app.error import ProviderNotInitializeError
from controllers.console.datasets.error import DatasetInUseError, DatasetNameDuplicateError, IndexingEstimateError
from controllers.console.datasets.error import DatasetNameDuplicateError
from controllers.console.setup import setup_required
from controllers.console.wraps import account_initialization_required
from core.errors.error import LLMBadRequestError, ProviderTokenNotInitError
from core.indexing_runner import IndexingRunner
from core.model_runtime.entities.model_entities import ModelType
from core.provider_manager import ProviderManager
from core.rag.datasource.vdb.vector_type import VectorType
from core.rag.extractor.entity.extract_setting import ExtractSetting
from core.rag.retrieval.retrival_methods import RetrievalMethod
from extensions.ext_database import db
from fields.app_fields import related_app_list
from fields.dataset_fields import dataset_detail_fields, dataset_query_detail_fields
from fields.document_fields import document_status_fields
from fields.dataset_fields import dataset_detail_fields
from libs.login import login_required
from models.dataset import Dataset, Document, DocumentSegment
from models.model import ApiToken, UploadFile
from services.dataset_service import DatasetPermissionService, DatasetService, DocumentService
from services.external_knowledge_service import ExternalDatasetService
def _validate_name(name):
if not name or len(name) < 1 or len(name) > 100:
raise ValueError('Name must be between 1 to 100 characters.')
raise ValueError("Name must be between 1 to 100 characters.")
return name
def _validate_description_length(description):
if len(description) > 400:
raise ValueError('Description cannot exceed 400 characters.')
raise ValueError("Description cannot exceed 400 characters.")
return description
class ExternalApiTemplateListApi(Resource):
@setup_required
@login_required
@account_initialization_required
def get(self):
page = request.args.get('page', default=1, type=int)
limit = request.args.get('limit', default=20, type=int)
search = request.args.get('keyword', default=None, type=str)
page = request.args.get("page", default=1, type=int)
limit = request.args.get("limit", default=20, type=int)
search = request.args.get("keyword", default=None, type=str)
api_templates, total = ExternalDatasetService.get_external_api_templates(
page,
limit,
current_user.current_tenant_id,
search
page, limit, current_user.current_tenant_id, search
)
response = {
'data': [item.to_dict() for item in api_templates],
'has_more': len(api_templates) == limit,
'limit': limit,
'total': total,
'page': page
"data": [item.to_dict() for item in api_templates],
"has_more": len(api_templates) == limit,
"limit": limit,
"total": total,
"page": page,
}
return response, 200
@ -72,18 +52,30 @@ class ExternalApiTemplateListApi(Resource):
@account_initialization_required
def post(self):
parser = reqparse.RequestParser()
parser.add_argument('name', nullable=False, required=True,
help='Name is required. Name must be between 1 to 100 characters.',
type=_validate_name)
parser.add_argument('description', nullable=False, required=True,
help='Description is required. Description must be between 1 to 400 characters.',
type=_validate_description_length)
parser.add_argument('settings', type=list, location='json',
nullable=False,
required=True, )
parser.add_argument(
"name",
nullable=False,
required=True,
help="Name is required. Name must be between 1 to 100 characters.",
type=_validate_name,
)
parser.add_argument(
"description",
nullable=False,
required=True,
help="Description is required. Description must be between 1 to 400 characters.",
type=_validate_description_length,
)
parser.add_argument(
"settings",
type=list,
location="json",
nullable=False,
required=True,
)
args = parser.parse_args()
ExternalDatasetService.validate_api_list(args['settings'])
ExternalDatasetService.validate_api_list(args["settings"])
# The role of the current user in the ta table must be admin, owner, or editor, or dataset_operator
if not current_user.is_dataset_editor:
@ -91,9 +83,7 @@ class ExternalApiTemplateListApi(Resource):
try:
api_template = ExternalDatasetService.create_api_template(
tenant_id=current_user.current_tenant_id,
user_id=current_user.id,
args=args
tenant_id=current_user.current_tenant_id, user_id=current_user.id, args=args
)
except services.errors.dataset.DatasetNameDuplicateError:
raise DatasetNameDuplicateError()
@ -120,23 +110,35 @@ class ExternalApiTemplateApi(Resource):
api_template_id = str(api_template_id)
parser = reqparse.RequestParser()
parser.add_argument('name', nullable=False, required=True,
help='type is required. Name must be between 1 to 100 characters.',
type=_validate_name)
parser.add_argument('description', nullable=False, required=True,
help='description is required. Description must be between 1 to 400 characters.',
type=_validate_description_length)
parser.add_argument('settings', type=list, location='json',
nullable=False,
required=True, )
parser.add_argument(
"name",
nullable=False,
required=True,
help="type is required. Name must be between 1 to 100 characters.",
type=_validate_name,
)
parser.add_argument(
"description",
nullable=False,
required=True,
help="description is required. Description must be between 1 to 400 characters.",
type=_validate_description_length,
)
parser.add_argument(
"settings",
type=list,
location="json",
nullable=False,
required=True,
)
args = parser.parse_args()
ExternalDatasetService.validate_api_list(args['settings'])
ExternalDatasetService.validate_api_list(args["settings"])
api_template = ExternalDatasetService.update_api_template(
tenant_id=current_user.current_tenant_id,
user_id=current_user.id,
api_template_id=api_template_id,
args=args
args=args,
)
return api_template.to_dict(), 200
@ -152,7 +154,7 @@ class ExternalApiTemplateApi(Resource):
raise Forbidden()
ExternalDatasetService.delete_api_template(current_user.current_tenant_id, api_template_id)
return {'result': 'success'}, 204
return {"result": "success"}, 204
class ExternalApiUseCheckApi(Resource):
@ -163,11 +165,10 @@ class ExternalApiUseCheckApi(Resource):
api_template_id = str(api_template_id)
external_api_template_is_using = ExternalDatasetService.external_api_template_use_check(api_template_id)
return {'is_using': external_api_template_is_using}, 200
return {"is_using": external_api_template_is_using}, 200
class ExternalDatasetInitApi(Resource):
@setup_required
@login_required
@account_initialization_required
@ -177,13 +178,13 @@ class ExternalDatasetInitApi(Resource):
raise Forbidden()
parser = reqparse.RequestParser()
parser.add_argument('api_template_id', type=str, required=True, nullable=True, location='json')
parser.add_argument("api_template_id", type=str, required=True, nullable=True, location="json")
# parser.add_argument('name', nullable=False, required=True,
# help='name is required. Name must be between 1 to 100 characters.',
# type=_validate_name)
# parser.add_argument('description', type=str, required=True, nullable=True, location='json')
parser.add_argument('data_source', type=dict, required=True, nullable=True, location='json')
parser.add_argument('process_parameter', type=dict, required=True, nullable=True, location='json')
parser.add_argument("data_source", type=dict, required=True, nullable=True, location="json")
parser.add_argument("process_parameter", type=dict, required=True, nullable=True, location="json")
args = parser.parse_args()
@ -193,9 +194,7 @@ class ExternalDatasetInitApi(Resource):
# validate args
ExternalDatasetService.document_create_args_validate(
current_user.current_tenant_id,
args['api_template_id'],
args['process_parameter']
current_user.current_tenant_id, args["api_template_id"], args["process_parameter"]
)
try:
@ -206,17 +205,12 @@ class ExternalDatasetInitApi(Resource):
)
except Exception as ex:
raise ProviderNotInitializeError(ex.description)
response = {
'dataset': dataset,
'documents': documents,
'batch': batch
}
response = {"dataset": dataset, "documents": documents, "batch": batch}
return response
class ExternalDatasetCreateApi(Resource):
@setup_required
@login_required
@account_initialization_required
@ -226,12 +220,16 @@ class ExternalDatasetCreateApi(Resource):
raise Forbidden()
parser = reqparse.RequestParser()
parser.add_argument('api_template_id', type=str, required=True, nullable=False, location='json')
parser.add_argument('external_knowledge_id', type=str, required=True, nullable=False, location='json')
parser.add_argument('name', nullable=False, required=True,
help='name is required. Name must be between 1 to 100 characters.',
type=_validate_name)
parser.add_argument('description', type=str, required=True, nullable=True, location='json')
parser.add_argument("external_api_template_id", type=str, required=True, nullable=False, location="json")
parser.add_argument("external_knowledge_id", type=str, required=True, nullable=False, location="json")
parser.add_argument(
"name",
nullable=False,
required=True,
help="name is required. Name must be between 1 to 100 characters.",
type=_validate_name,
)
parser.add_argument("description", type=str, required=True, nullable=True, location="json")
args = parser.parse_args()
@ -251,6 +249,6 @@ class ExternalDatasetCreateApi(Resource):
return marshal(dataset, dataset_detail_fields), 201
api.add_resource(ExternalApiTemplateListApi, '/datasets/external-api-template')
api.add_resource(ExternalApiTemplateApi, '/datasets/external-api-template/<uuid:api_template_id>')
api.add_resource(ExternalApiUseCheckApi, '/datasets/external-api-template/<uuid:api_template_id>/use-check')
api.add_resource(ExternalApiTemplateListApi, "/datasets/external-api-template")
api.add_resource(ExternalApiTemplateApi, "/datasets/external-api-template/<uuid:api_template_id>")
api.add_resource(ExternalApiUseCheckApi, "/datasets/external-api-template/<uuid:api_template_id>/use-check")