mirror of
https://github.com/infiniflow/ragflow.git
synced 2026-05-21 00:36:43 +08:00
2d05475693
### What problem does this PR solve? Before consolidation Web API: POST /v1/document/infos Http API - GET /api/v1/datasets/<dataset_id>/documents After consolidation, Restful API -- GET /api/v1/datasets/<dataset_id>/documents?ids=id1&ids=id2 ### Type of change - [ ] Refactoring
122 lines
3.6 KiB
Python
122 lines
3.6 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, page_size=30):
|
|
authorization = {"Authorization": auth}
|
|
url = f"{HOST_ADDRESS}/v1/kb/list?page={page_number}&page_size={page_size}"
|
|
json = {}
|
|
res = requests.post(url=url, headers=authorization, json=json)
|
|
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?id={dataset_id}"
|
|
json = {}
|
|
res = requests.post(url=url, headers=authorization, json=json)
|
|
return res.json()
|
|
|
|
|
|
def get_docs_info(auth, dataset_id, doc_ids=None, doc_id=None):
|
|
"""
|
|
Get document information by IDs.
|
|
|
|
Args:
|
|
auth: Authorization header
|
|
dataset_id: Dataset ID
|
|
doc_ids: List of document IDs (use for multiple) - exclusive with doc_id
|
|
doc_id: Single document ID (use for one) - exclusive with doc_ids
|
|
|
|
Raises:
|
|
ValueError: If both doc_id and doc_ids are provided
|
|
"""
|
|
# Validate that id and ids are not used together
|
|
if doc_id and doc_ids:
|
|
raise ValueError("Cannot use both 'id' and 'ids' parameters at the same time.")
|
|
|
|
authorization = {"Authorization": auth}
|
|
params = {}
|
|
if doc_ids:
|
|
# Multiple IDs
|
|
for id in doc_ids:
|
|
params.append(("ids", id))
|
|
elif doc_id:
|
|
# Single ID
|
|
params["id"] = doc_id
|
|
|
|
# Use /api/v1 prefix for dataset API
|
|
url = f"{HOST_ADDRESS}/api/v1/datasets/{dataset_id}/documents"
|
|
res = requests.get(url=url, headers=authorization, params=params)
|
|
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
|
|
|