|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
import json |
|
import os |
|
import re |
|
from datetime import datetime, timedelta |
|
from flask import request, Response |
|
from flask_login import login_required, current_user |
|
|
|
from api.db import FileType, ParserType, FileSource, StatusEnum |
|
from api.db.db_models import APIToken, API4Conversation, Task, File |
|
from api.db.services import duplicate_name |
|
from api.db.services.api_service import APITokenService, API4ConversationService |
|
from api.db.services.dialog_service import DialogService, chat |
|
from api.db.services.document_service import DocumentService |
|
from api.db.services.file2document_service import File2DocumentService |
|
from api.db.services.file_service import FileService |
|
from api.db.services.knowledgebase_service import KnowledgebaseService |
|
from api.db.services.task_service import queue_tasks, TaskService |
|
from api.db.services.user_service import UserTenantService, TenantService |
|
from api.settings import RetCode, retrievaler |
|
from api.utils import get_uuid, current_timestamp, datetime_format |
|
|
|
from itsdangerous import URLSafeTimedSerializer |
|
|
|
from api.utils.file_utils import filename_type, thumbnail |
|
from rag.utils.minio_conn import MINIO |
|
|
|
|
|
from api.utils.api_utils import construct_json_result, construct_result, construct_error_response, validate_request |
|
from api.contants import NAME_LENGTH_LIMIT |
|
|
|
|
|
@manager.route('/', methods=['POST']) |
|
@login_required |
|
@validate_request("name") |
|
def create_dataset(): |
|
|
|
authorization_token = request.headers.get('Authorization') |
|
if not authorization_token: |
|
return construct_json_result(code=RetCode.AUTHENTICATION_ERROR, message="Authorization header is missing.") |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
tenant_id = current_user.id |
|
request_body = request.json |
|
|
|
|
|
if "name" not in request_body: |
|
return construct_json_result(code=RetCode.DATA_ERROR, message="Expected 'name' field in request body") |
|
|
|
dataset_name = request_body["name"] |
|
|
|
|
|
if not dataset_name: |
|
return construct_json_result(code=RetCode.DATA_ERROR, message="Empty dataset name") |
|
|
|
|
|
dataset_name = dataset_name.strip() |
|
|
|
|
|
dataset_name_length = len(dataset_name) |
|
if dataset_name_length > NAME_LENGTH_LIMIT: |
|
return construct_json_result(code=RetCode.DATA_ERROR, |
|
message=f"Dataset name: {dataset_name} with length {dataset_name_length} exceeds {NAME_LENGTH_LIMIT}!") |
|
|
|
|
|
if len(request_body.keys()) > 1: |
|
name_list = [] |
|
for key_name in request_body.keys(): |
|
if key_name != 'name': |
|
name_list.append(key_name) |
|
return construct_json_result(code=RetCode.DATA_ERROR, |
|
message=f"fields: {name_list}, are not allowed in request body.") |
|
|
|
|
|
request_body["name"] = duplicate_name( |
|
KnowledgebaseService.query, |
|
name=dataset_name, |
|
tenant_id=tenant_id, |
|
status=StatusEnum.VALID.value) |
|
try: |
|
request_body["id"] = get_uuid() |
|
request_body["tenant_id"] = tenant_id |
|
request_body["created_by"] = tenant_id |
|
e, t = TenantService.get_by_id(tenant_id) |
|
if not e: |
|
return construct_result(code=RetCode.AUTHENTICATION_ERROR, message="Tenant not found.") |
|
request_body["embd_id"] = t.embd_id |
|
if not KnowledgebaseService.save(**request_body): |
|
|
|
return construct_result() |
|
return construct_json_result(data={"dataset_name": request_body["name"]}) |
|
except Exception as e: |
|
return construct_error_response(e) |
|
|
|
|
|
@manager.route('/', methods=['GET']) |
|
@login_required |
|
def list_datasets(): |
|
offset = request.args.get("offset", 0) |
|
count = request.args.get("count", -1) |
|
orderby = request.args.get("orderby", "create_time") |
|
desc = request.args.get("desc", True) |
|
try: |
|
tenants = TenantService.get_joined_tenants_by_user_id(current_user.id) |
|
kbs = KnowledgebaseService.get_by_tenant_ids( |
|
[m["tenant_id"] for m in tenants], current_user.id, int(offset), int(count), orderby, desc) |
|
return construct_json_result(data=kbs, code=RetCode.DATA_ERROR, message=f"attempt to list datasets") |
|
except Exception as e: |
|
return construct_error_response(e) |
|
|
|
|
|
|
|
@manager.route('/<dataset_id>', methods=['DELETE']) |
|
@login_required |
|
@validate_request("dataset_id") |
|
def remove_dataset(dataset_id): |
|
req = request.json |
|
try: |
|
kbs = KnowledgebaseService.query( |
|
created_by=current_user.id, id=req["dataset_id"]) |
|
if not kbs: |
|
return construct_json_result( |
|
data=False, message=f'Only owner of knowledgebase authorized for this operation.', |
|
code=RetCode.OPERATING_ERROR) |
|
|
|
for doc in DocumentService.query(kb_id=req["dataset_id"]): |
|
if not DocumentService.remove_document(doc, kbs[0].tenant_id): |
|
return construct_json_result( |
|
message="Database error (Document removal)!") |
|
f2d = File2DocumentService.get_by_document_id(doc.id) |
|
FileService.filter_delete([File.source_type == FileSource.KNOWLEDGEBASE, File.id == f2d[0].file_id]) |
|
File2DocumentService.delete_by_document_id(doc.id) |
|
|
|
if not KnowledgebaseService.delete_by_id(req["dataset_id"]): |
|
return construct_json_result( |
|
message="Database error (Knowledgebase removal)!") |
|
return construct_json_result(code=RetCode.DATA_ERROR, message=f"attempt to remove dataset: {dataset_id}") |
|
except Exception as e: |
|
return construct_error_response(e) |
|
|
|
|
|
@manager.route('/<dataset_id>', methods=['GET']) |
|
@login_required |
|
@validate_request("dataset_id") |
|
def get_dataset(): |
|
dataset_id = request.args["dataset_id"] |
|
try: |
|
dataset = KnowledgebaseService.get_detail(dataset_id) |
|
if not dataset: |
|
return construct_json_result( |
|
message="Can't find this knowledgebase!") |
|
return construct_json_result(code=RetCode.DATA_ERROR, message=f"attempt to get detail of dataset: {dataset_id}") |
|
except Exception as e: |
|
return construct_json_result(e) |
|
|
|
|
|
@manager.route('/<dataset_id>', methods=['PUT']) |
|
@login_required |
|
@validate_request("name") |
|
def update_dataset(dataset_id): |
|
return construct_json_result(code=RetCode.DATA_ERROR, message=f"attempt to update dataset: {dataset_id}") |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|