Plugin/merge main to plugin/beta 20250122 (#12962)

Signed-off-by: yihong0618 <zouzou0208@gmail.com>
Signed-off-by: -LAN- <laipz8200@outlook.com>
Co-authored-by: kurokobo <kuro664@gmail.com>
Co-authored-by: Hiroshi Fujita <fujita-h@users.noreply.github.com>
Co-authored-by: NFish <douxc512@gmail.com>
Co-authored-by: Gen Sato <52241300+halogen22@users.noreply.github.com>
Co-authored-by: eux <euxuuu@gmail.com>
Co-authored-by: huangzhuo1949 <167434202+huangzhuo1949@users.noreply.github.com>
Co-authored-by: huangzhuo <huangzhuo1@xiaomi.com>
Co-authored-by: lotsik <lotsik@mail.ru>
Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>
Co-authored-by: Wu Tianwei <30284043+WTW0313@users.noreply.github.com>
Co-authored-by: nite-knite <nkCoding@gmail.com>
Co-authored-by: Jyong <76649700+JohnJyong@users.noreply.github.com>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: gakkiyomi <gakkiyomi@aliyun.com>
Co-authored-by: CN-P5 <heibai2006@gmail.com>
Co-authored-by: CN-P5 <heibai2006@qq.com>
Co-authored-by: Chuehnone <1897025+chuehnone@users.noreply.github.com>
Co-authored-by: yihong <zouzou0208@gmail.com>
Co-authored-by: Kevin9703 <51311316+Kevin9703@users.noreply.github.com>
Co-authored-by: -LAN- <laipz8200@outlook.com>
Co-authored-by: Boris Feld <lothiraldan@gmail.com>
Co-authored-by: mbo <himabo@gmail.com>
Co-authored-by: mabo <mabo@aeyes.ai>
Co-authored-by: Warren Chen <warren.chen830@gmail.com>
Co-authored-by: KVOJJJin <jzongcode@gmail.com>
Co-authored-by: JzoNgKVO <27049666+JzoNgKVO@users.noreply.github.com>
Co-authored-by: jiandanfeng <chenjh3@wangsu.com>
Co-authored-by: zhu-an <70234959+xhdd123321@users.noreply.github.com>
Co-authored-by: zhaoqingyu.1075 <zhaoqingyu.1075@bytedance.com>
Co-authored-by: 海狸大師 <86974027+yenslife@users.noreply.github.com>
Co-authored-by: Xu Song <xusong.vip@gmail.com>
Co-authored-by: rayshaw001 <396301947@163.com>
Co-authored-by: Ding Jiatong <dingjiatong@gmail.com>
Co-authored-by: Bowen Liang <liangbowen@gf.com.cn>
Co-authored-by: JasonVV <jasonwangiii@outlook.com>
Co-authored-by: le0zh <newlight@qq.com>
Co-authored-by: zhuxinliang <zhuxinliang@didiglobal.com>
Co-authored-by: k-zaku <zaku99@outlook.jp>
Co-authored-by: Joel <iamjoel007@gmail.com>
Co-authored-by: luckylhb90 <luckylhb90@gmail.com>
Co-authored-by: hobo.l <hobo.l@binance.com>
Co-authored-by: jiangbo721 <365065261@qq.com>
Co-authored-by: 刘江波 <jiangbo721@163.com>
Co-authored-by: Shun Miyazawa <34241526+miya@users.noreply.github.com>
Co-authored-by: EricPan <30651140+Egfly@users.noreply.github.com>
Co-authored-by: crazywoola <427733928@qq.com>
Co-authored-by: zxhlyh <jasonapring2015@outlook.com>
Co-authored-by: sino <sino2322@gmail.com>
Co-authored-by: Jhvcc <37662342+Jhvcc@users.noreply.github.com>
Co-authored-by: lowell <lowell.hu@zkteco.in>
This commit is contained in:
Yeuoly
2025-01-23 14:48:16 +08:00
committed by GitHub
parent 8d8d3e3f2f
commit 899df30bf6
238 changed files with 4121 additions and 890 deletions

View File

@ -7,4 +7,4 @@ api = ExternalApi(bp)
from . import index
from .app import app, audio, completion, conversation, file, message, workflow
from .dataset import dataset, document, hit_testing, segment
from .dataset import dataset, document, hit_testing, segment, upload_file

View File

@ -31,8 +31,11 @@ class DatasetListApi(DatasetApiResource):
# provider = request.args.get("provider", default="vendor")
search = request.args.get("keyword", default=None, type=str)
tag_ids = request.args.getlist("tag_ids")
include_all = request.args.get("include_all", default="false").lower() == "true"
datasets, total = DatasetService.get_datasets(page, limit, tenant_id, current_user, search, tag_ids)
datasets, total = DatasetService.get_datasets(
page, limit, tenant_id, current_user, search, tag_ids, include_all
)
# check embedding setting
provider_manager = ProviderManager()
configurations = provider_manager.get_configurations(tenant_id=current_user.current_tenant_id)

View File

@ -53,8 +53,7 @@ class SegmentApi(DatasetApiResource):
)
except LLMBadRequestError:
raise ProviderNotInitializeError(
"No Embedding Model available. Please configure a valid provider "
"in the Settings -> Model Provider."
"No Embedding Model available. Please configure a valid provider in the Settings -> Model Provider."
)
except ProviderTokenNotInitError as ex:
raise ProviderNotInitializeError(ex.description)
@ -95,8 +94,7 @@ class SegmentApi(DatasetApiResource):
)
except LLMBadRequestError:
raise ProviderNotInitializeError(
"No Embedding Model available. Please configure a valid provider "
"in the Settings -> Model Provider."
"No Embedding Model available. Please configure a valid provider in the Settings -> Model Provider."
)
except ProviderTokenNotInitError as ex:
raise ProviderNotInitializeError(ex.description)
@ -175,8 +173,7 @@ class DatasetSegmentApi(DatasetApiResource):
)
except LLMBadRequestError:
raise ProviderNotInitializeError(
"No Embedding Model available. Please configure a valid provider "
"in the Settings -> Model Provider."
"No Embedding Model available. Please configure a valid provider in the Settings -> Model Provider."
)
except ProviderTokenNotInitError as ex:
raise ProviderNotInitializeError(ex.description)

View File

@ -0,0 +1,54 @@
from werkzeug.exceptions import NotFound
from controllers.service_api import api
from controllers.service_api.wraps import (
DatasetApiResource,
)
from core.file import helpers as file_helpers
from extensions.ext_database import db
from models.dataset import Dataset
from models.model import UploadFile
from services.dataset_service import DocumentService
class UploadFileApi(DatasetApiResource):
def get(self, tenant_id, dataset_id, document_id):
"""Get upload file."""
# check dataset
dataset_id = str(dataset_id)
tenant_id = str(tenant_id)
dataset = db.session.query(Dataset).filter(Dataset.tenant_id == tenant_id, Dataset.id == dataset_id).first()
if not dataset:
raise NotFound("Dataset not found.")
# check document
document_id = str(document_id)
document = DocumentService.get_document(dataset.id, document_id)
if not document:
raise NotFound("Document not found.")
# check upload file
if document.data_source_type != "upload_file":
raise ValueError(f"Document data source type ({document.data_source_type}) is not upload_file.")
data_source_info = document.data_source_info_dict
if data_source_info and "upload_file_id" in data_source_info:
file_id = data_source_info["upload_file_id"]
upload_file = db.session.query(UploadFile).filter(UploadFile.id == file_id).first()
if not upload_file:
raise NotFound("UploadFile not found.")
else:
raise ValueError("Upload file id not found in document data source info.")
url = file_helpers.get_signed_file_url(upload_file_id=upload_file.id)
return {
"id": upload_file.id,
"name": upload_file.name,
"size": upload_file.size,
"extension": upload_file.extension,
"url": url,
"download_url": f"{url}&as_attachment=true",
"mime_type": upload_file.mime_type,
"created_by": upload_file.created_by,
"created_at": upload_file.created_at.timestamp(),
}, 200
api.add_resource(UploadFileApi, "/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/upload-file")

View File

@ -195,7 +195,11 @@ def validate_and_get_api_token(scope: str | None = None):
with Session(db.engine, expire_on_commit=False) as session:
update_stmt = (
update(ApiToken)
.where(ApiToken.token == auth_token, ApiToken.last_used_at < cutoff_time, ApiToken.type == scope)
.where(
ApiToken.token == auth_token,
(ApiToken.last_used_at.is_(None) | (ApiToken.last_used_at < cutoff_time)),
ApiToken.type == scope,
)
.values(last_used_at=current_time)
.returning(ApiToken)
)
@ -236,7 +240,7 @@ def create_or_update_end_user_for_user_id(app_model: App, user_id: Optional[str]
tenant_id=app_model.tenant_id,
app_id=app_model.id,
type="service_api",
is_anonymous=True if user_id == "DEFAULT-USER" else False,
is_anonymous=user_id == "DEFAULT-USER",
session_id=user_id,
)
db.session.add(end_user)