mirror of
https://github.com/infiniflow/ragflow.git
synced 2025-08-01 05:12:01 +00:00
cc1b2c8f09
### What problem does this PR solve? Add sdk document test cases ### Type of change - [x] Add test cases
42 lines
1.4 KiB
Python
42 lines
1.4 KiB
Python
#
|
|
# Copyright 2025 The InfiniFlow Authors. All Rights Reserved.
|
|
#
|
|
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
#
|
|
|
|
from pathlib import Path
|
|
|
|
from ragflow_sdk import DataSet, Document, RAGFlow
|
|
from utils.file_utils import create_txt_file
|
|
|
|
|
|
# DATASET MANAGEMENT
|
|
def batch_create_datasets(client: RAGFlow, num: int) -> list[DataSet]:
|
|
datasets = []
|
|
for i in range(num):
|
|
dataset = client.create_dataset(name=f"dataset_{i}")
|
|
datasets.append(dataset)
|
|
return datasets
|
|
|
|
|
|
# FILE MANAGEMENT WITHIN DATASET
|
|
def bulk_upload_documents(dataset: DataSet, num: int, tmp_path: Path) -> list[Document]:
|
|
document_infos = []
|
|
for i in range(num):
|
|
fp = create_txt_file(tmp_path / f"ragflow_test_upload_{i}.txt")
|
|
with fp.open("rb") as f:
|
|
blob = f.read()
|
|
document_infos.append({"display_name": fp.name, "blob": blob})
|
|
|
|
return dataset.upload_documents(document_infos)
|