Fix: Merge main branch (#10377)

### What problem does this PR solve?


### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)

---------

Signed-off-by: dependabot[bot] <support@github.com>
Signed-off-by: jinhai <haijin.chn@gmail.com>
Signed-off-by: Jin Hai <haijin.chn@gmail.com>
Co-authored-by: Lynn <lynn_inf@hotmail.com>
Co-authored-by: chanx <1243304602@qq.com>
Co-authored-by: balibabu <cike8899@users.noreply.github.com>
Co-authored-by: 纷繁下的无奈 <zhileihuang@126.com>
Co-authored-by: huangzl <huangzl@shinemo.com>
Co-authored-by: writinwaters <93570324+writinwaters@users.noreply.github.com>
Co-authored-by: Wilmer <33392318@qq.com>
Co-authored-by: Adrian Weidig <adrianweidig@gmx.net>
Co-authored-by: Zhichang Yu <yuzhichang@gmail.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Yongteng Lei <yongtengrey@outlook.com>
Co-authored-by: Liu An <asiro@qq.com>
Co-authored-by: buua436 <66937541+buua436@users.noreply.github.com>
Co-authored-by: BadwomanCraZY <511528396@qq.com>
Co-authored-by: cucusenok <31804608+cucusenok@users.noreply.github.com>
Co-authored-by: Russell Valentine <russ@coldstonelabs.org>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Billy Bao <newyorkupperbay@gmail.com>
Co-authored-by: Zhedong Cen <cenzhedong2@126.com>
Co-authored-by: TensorNull <129579691+TensorNull@users.noreply.github.com>
Co-authored-by: TensorNull <tensor.null@gmail.com>
Co-authored-by: Ajay <160579663+aybanda@users.noreply.github.com>
Co-authored-by: AB <aj@Ajays-MacBook-Air.local>
Co-authored-by: 天海蒼灆 <huangaoqin@tecpie.com>
Co-authored-by: He Wang <wanghechn@qq.com>
Co-authored-by: Atsushi Hatakeyama <atu729@icloud.com>
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
Co-authored-by: Mohamed Mathari <155896313+melmathari@users.noreply.github.com>
Co-authored-by: Mohamed Mathari <nocodeventure@Mac-mini-van-Mohamed.fritz.box>
Co-authored-by: Stephen Hu <stephenhu@seismic.com>
Co-authored-by: Shaun Zhang <zhangwfjh@users.noreply.github.com>
Co-authored-by: zhimeng123 <60221886+zhimeng123@users.noreply.github.com>
Co-authored-by: mxc <mxc@example.com>
Co-authored-by: Dominik Novotný <50611433+SgtMarmite@users.noreply.github.com>
Co-authored-by: EVGENY M <168018528+rjohny55@users.noreply.github.com>
Co-authored-by: mcoder6425 <mcoder64@gmail.com>
Co-authored-by: TeslaZY <TeslaZY@outlook.com>
Co-authored-by: lemsn <lemsn@msn.com>
Co-authored-by: lemsn <lemsn@126.com>
Co-authored-by: Adrian Gora <47756404+adagora@users.noreply.github.com>
Co-authored-by: Womsxd <45663319+Womsxd@users.noreply.github.com>
Co-authored-by: FatMii <39074672+FatMii@users.noreply.github.com>
This commit is contained in:
Kevin Hu
2025-09-30 13:13:15 +08:00
committed by GitHub
parent 4d6ff672eb
commit 20b577a72c
201 changed files with 7929 additions and 1110 deletions

View File

@ -3,9 +3,11 @@ import re
import flask
from flask import request
from pathlib import Path
from api.db.services.document_service import DocumentService
from api.db.services.file2document_service import File2DocumentService
from api.db.services.knowledgebase_service import KnowledgebaseService
from api.utils.api_utils import server_error_response, token_required
from api.utils import get_uuid
from api.db import FileType
@ -81,16 +83,16 @@ def upload(tenant_id):
return get_json_result(data=False, message="Can't find this folder!", code=404)
for file_obj in file_objs:
# 文件路径处理
# Handle file path
full_path = '/' + file_obj.filename
file_obj_names = full_path.split('/')
file_len = len(file_obj_names)
# 获取文件夹路径ID
# Get folder path ID
file_id_list = FileService.get_id_list_by_id(pf_id, file_obj_names, 1, [pf_id])
len_id_list = len(file_id_list)
# 创建文件夹结构
# Crete file folder
if file_len != len_id_list:
e, file = FileService.get_by_id(file_id_list[len_id_list - 1])
if not e:
@ -666,3 +668,71 @@ def move(tenant_id):
return get_json_result(data=True)
except Exception as e:
return server_error_response(e)
@manager.route('/file/convert', methods=['POST']) # noqa: F821
@token_required
def convert(tenant_id):
req = request.json
kb_ids = req["kb_ids"]
file_ids = req["file_ids"]
file2documents = []
try:
files = FileService.get_by_ids(file_ids)
files_set = dict({file.id: file for file in files})
for file_id in file_ids:
file = files_set[file_id]
if not file:
return get_json_result(message="File not found!", code=404)
file_ids_list = [file_id]
if file.type == FileType.FOLDER.value:
file_ids_list = FileService.get_all_innermost_file_ids(file_id, [])
for id in file_ids_list:
informs = File2DocumentService.get_by_file_id(id)
# delete
for inform in informs:
doc_id = inform.document_id
e, doc = DocumentService.get_by_id(doc_id)
if not e:
return get_json_result(message="Document not found!", code=404)
tenant_id = DocumentService.get_tenant_id(doc_id)
if not tenant_id:
return get_json_result(message="Tenant not found!", code=404)
if not DocumentService.remove_document(doc, tenant_id):
return get_json_result(
message="Database error (Document removal)!", code=404)
File2DocumentService.delete_by_file_id(id)
# insert
for kb_id in kb_ids:
e, kb = KnowledgebaseService.get_by_id(kb_id)
if not e:
return get_json_result(
message="Can't find this knowledgebase!", code=404)
e, file = FileService.get_by_id(id)
if not e:
return get_json_result(
message="Can't find this file!", code=404)
doc = DocumentService.insert({
"id": get_uuid(),
"kb_id": kb.id,
"parser_id": FileService.get_parser(file.type, file.name, kb.parser_id),
"parser_config": kb.parser_config,
"created_by": tenant_id,
"type": file.type,
"name": file.name,
"suffix": Path(file.name).suffix.lstrip("."),
"location": file.location,
"size": file.size
})
file2document = File2DocumentService.insert({
"id": get_uuid(),
"file_id": id,
"document_id": doc.id,
})
file2documents.append(file2document.to_json())
return get_json_result(data=file2documents)
except Exception as e:
return server_error_response(e)