mirror of
https://git.mirrors.martin98.com/https://github.com/infiniflow/ragflow.git
synced 2025-04-22 06:00:00 +08:00

### What problem does this PR solve? Fixes #5923 Fixes the readonly variables from payload at /datasets/<dataset_id> _Briefly describe what this PR aims to solve. Include background context that will help reviewers understand the purpose of the PR._ Now if user tries to modify readonly values then it will show " The input parameters are invalid. " invalid_keys = {"id", "embd_id", "chunk_num", "doc_num", "parser_id", "create_date", "create_time", "created_by", "status","token_num","update_date","update_time"} if any(key in req for key in invalid_keys): return get_error_data_result(message="The input parameters are invalid.") i have include those readonly keys in invalid_keys ### Type of change - [ ] Bug Fix (non-breaking change which fixes an issue) --------- Co-authored-by: Raghav <2020csb1115@iitrpr.ac.in>
95 lines
2.8 KiB
Python
95 lines
2.8 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.
|
|
#
|
|
|
|
import os
|
|
import requests
|
|
|
|
HOST_ADDRESS = os.getenv('HOST_ADDRESS', 'http://127.0.0.1:9380')
|
|
|
|
DATASET_NAME_LIMIT = 128
|
|
|
|
|
|
def create_dataset(auth, dataset_name):
|
|
authorization = {"Authorization": auth}
|
|
url = f"{HOST_ADDRESS}/v1/kb/create"
|
|
json = {"name": dataset_name}
|
|
res = requests.post(url=url, headers=authorization, json=json)
|
|
return res.json()
|
|
|
|
|
|
def list_dataset(auth, page_number):
|
|
authorization = {"Authorization": auth}
|
|
url = f"{HOST_ADDRESS}/v1/kb/list?page={page_number}"
|
|
res = requests.get(url=url, headers=authorization)
|
|
return res.json()
|
|
|
|
|
|
def rm_dataset(auth, dataset_id):
|
|
authorization = {"Authorization": auth}
|
|
url = f"{HOST_ADDRESS}/v1/kb/rm"
|
|
json = {"kb_id": dataset_id}
|
|
res = requests.post(url=url, headers=authorization, json=json)
|
|
return res.json()
|
|
|
|
|
|
def update_dataset(auth, json_req):
|
|
authorization = {"Authorization": auth}
|
|
url = f"{HOST_ADDRESS}/v1/kb/update"
|
|
res = requests.post(url=url, headers=authorization, json=json_req)
|
|
return res.json()
|
|
|
|
|
|
def upload_file(auth, dataset_id, path):
|
|
authorization = {"Authorization": auth}
|
|
url = f"{HOST_ADDRESS}/v1/document/upload"
|
|
json_req = {
|
|
"kb_id": dataset_id,
|
|
}
|
|
|
|
file = {
|
|
'file': open(f'{path}', 'rb')
|
|
}
|
|
|
|
res = requests.post(url=url, headers=authorization, files=file, data=json_req)
|
|
return res.json()
|
|
|
|
def list_document(auth, dataset_id):
|
|
authorization = {"Authorization": auth}
|
|
url = f"{HOST_ADDRESS}/v1/document/list?kb_id={dataset_id}"
|
|
res = requests.get(url=url, headers=authorization)
|
|
return res.json()
|
|
|
|
def get_docs_info(auth, doc_ids):
|
|
authorization = {"Authorization": auth}
|
|
json_req = {
|
|
"doc_ids": doc_ids
|
|
}
|
|
url = f"{HOST_ADDRESS}/v1/document/infos"
|
|
res = requests.post(url=url, headers=authorization, json=json_req)
|
|
return res.json()
|
|
|
|
def parse_docs(auth, doc_ids):
|
|
authorization = {"Authorization": auth}
|
|
json_req = {
|
|
"doc_ids": doc_ids,
|
|
"run": 1
|
|
}
|
|
url = f"{HOST_ADDRESS}/v1/document/run"
|
|
res = requests.post(url=url, headers=authorization, json=json_req)
|
|
return res.json()
|
|
|
|
def parse_file(auth, document_id):
|
|
pass |