merge main

This commit is contained in:
zxhlyh
2025-07-28 16:00:38 +08:00
344 changed files with 2476 additions and 1275 deletions

View File

@ -77,10 +77,10 @@ from .billing import billing, compliance
# Import datasets controllers
from .datasets import (
data_source,
datasets,
datasets_document,
datasets_segments,
data_source,
external,
hit_testing,
metadata,

View File

@ -86,7 +86,7 @@ class AnnotationReplyActionStatusApi(Resource):
raise Forbidden()
job_id = str(job_id)
app_annotation_job_key = "{}_app_annotation_job_{}".format(action, str(job_id))
app_annotation_job_key = f"{action}_app_annotation_job_{str(job_id)}"
cache_result = redis_client.get(app_annotation_job_key)
if cache_result is None:
raise ValueError("The job does not exist.")
@ -94,7 +94,7 @@ class AnnotationReplyActionStatusApi(Resource):
job_status = cache_result.decode()
error_msg = ""
if job_status == "error":
app_annotation_error_key = "{}_app_annotation_error_{}".format(action, str(job_id))
app_annotation_error_key = f"{action}_app_annotation_error_{str(job_id)}"
error_msg = redis_client.get(app_annotation_error_key).decode()
return {"job_id": job_id, "job_status": job_status, "error_msg": error_msg}, 200
@ -123,6 +123,17 @@ class AnnotationListApi(Resource):
}
return response, 200
@setup_required
@login_required
@account_initialization_required
def delete(self, app_id):
if not current_user.is_editor:
raise Forbidden()
app_id = str(app_id)
AppAnnotationService.clear_all_annotations(app_id)
return {"result": "success"}, 204
class AnnotationExportApi(Resource):
@setup_required
@ -223,14 +234,14 @@ class AnnotationBatchImportStatusApi(Resource):
raise Forbidden()
job_id = str(job_id)
indexing_cache_key = "app_annotation_batch_import_{}".format(str(job_id))
indexing_cache_key = f"app_annotation_batch_import_{str(job_id)}"
cache_result = redis_client.get(indexing_cache_key)
if cache_result is None:
raise ValueError("The job does not exist.")
job_status = cache_result.decode()
error_msg = ""
if job_status == "error":
indexing_error_msg_key = "app_annotation_batch_import_error_msg_{}".format(str(job_id))
indexing_error_msg_key = f"app_annotation_batch_import_error_msg_{str(job_id)}"
error_msg = redis_client.get(indexing_error_msg_key).decode()
return {"job_id": job_id, "job_status": job_status, "error_msg": error_msg}, 200

View File

@ -51,8 +51,8 @@ class CompletionConversationApi(Resource):
if args["keyword"]:
query = query.join(Message, Message.conversation_id == Conversation.id).where(
or_(
Message.query.ilike("%{}%".format(args["keyword"])),
Message.answer.ilike("%{}%".format(args["keyword"])),
Message.query.ilike(f"%{args['keyword']}%"),
Message.answer.ilike(f"%{args['keyword']}%"),
)
)
@ -174,7 +174,7 @@ class ChatConversationApi(Resource):
query = db.select(Conversation).where(Conversation.app_id == app_model.id)
if args["keyword"]:
keyword_filter = "%{}%".format(args["keyword"])
keyword_filter = f"%{args['keyword']}%"
query = (
query.join(
Message,

View File

@ -1,5 +1,3 @@
import os
from flask_login import current_user
from flask_restful import Resource, reqparse
@ -29,15 +27,12 @@ class RuleGenerateApi(Resource):
args = parser.parse_args()
account = current_user
PROMPT_GENERATION_MAX_TOKENS = int(os.getenv("PROMPT_GENERATION_MAX_TOKENS", "512"))
try:
rules = LLMGenerator.generate_rule_config(
tenant_id=account.current_tenant_id,
instruction=args["instruction"],
model_config=args["model_config"],
no_variable=args["no_variable"],
rule_config_max_tokens=PROMPT_GENERATION_MAX_TOKENS,
)
except ProviderTokenNotInitError as ex:
raise ProviderNotInitializeError(ex.description)
@ -64,14 +59,12 @@ class RuleCodeGenerateApi(Resource):
args = parser.parse_args()
account = current_user
CODE_GENERATION_MAX_TOKENS = int(os.getenv("CODE_GENERATION_MAX_TOKENS", "1024"))
try:
code_result = LLMGenerator.generate_code(
tenant_id=account.current_tenant_id,
instruction=args["instruction"],
model_config=args["model_config"],
code_language=args["code_language"],
max_tokens=CODE_GENERATION_MAX_TOKENS,
)
except ProviderTokenNotInitError as ex:
raise ProviderNotInitializeError(ex.description)

View File

@ -81,7 +81,7 @@ class OAuthDataSourceBinding(Resource):
oauth_provider.get_access_token(code)
except requests.exceptions.HTTPError as e:
logging.exception(
f"An error occurred during the OAuthCallback process with {provider}: {e.response.text}"
"An error occurred during the OAuthCallback process with %s: %s", provider, e.response.text
)
return {"error": "OAuth data source process failed"}, 400
@ -103,7 +103,9 @@ class OAuthDataSourceSync(Resource):
try:
oauth_provider.sync_data_source(binding_id)
except requests.exceptions.HTTPError as e:
logging.exception(f"An error occurred during the OAuthCallback process with {provider}: {e.response.text}")
logging.exception(
"An error occurred during the OAuthCallback process with %s: %s", provider, e.response.text
)
return {"error": "OAuth data source process failed"}, 400
return {"result": "success"}, 200

View File

@ -80,7 +80,7 @@ class OAuthCallback(Resource):
user_info = oauth_provider.get_user_info(token)
except requests.exceptions.RequestException as e:
error_text = e.response.text if e.response else str(e)
logging.exception(f"An error occurred during the OAuth process with {provider}: {error_text}")
logging.exception("An error occurred during the OAuth process with %s: %s", provider, error_text)
return {"error": "OAuth process failed"}, 400
if invite_token and RegisterService.is_valid_invite_token(invite_token):

View File

@ -972,7 +972,7 @@ class DocumentRetryApi(DocumentResource):
raise DocumentAlreadyFinishedError()
retry_documents.append(document)
except Exception:
logging.exception(f"Failed to retry document, document id: {document_id}")
logging.exception("Failed to retry document, document id: %s", document_id)
continue
# retry document
DocumentService.retry_document(dataset_id, retry_documents)

View File

@ -1,6 +1,5 @@
import uuid
import pandas as pd
from flask import request
from flask_login import current_user
from flask_restful import Resource, marshal, reqparse
@ -14,8 +13,6 @@ from controllers.console.datasets.error import (
ChildChunkDeleteIndexError,
ChildChunkIndexingError,
InvalidActionError,
NoFileUploadedError,
TooManyFilesError,
)
from controllers.console.wraps import (
account_initialization_required,
@ -32,6 +29,7 @@ from extensions.ext_redis import redis_client
from fields.segment_fields import child_chunk_fields, segment_fields
from libs.login import login_required
from models.dataset import ChildChunk, DocumentSegment
from models.model import UploadFile
from services.dataset_service import DatasetService, DocumentService, SegmentService
from services.entities.knowledge_entities.knowledge_entities import ChildChunkUpdateArgs, SegmentUpdateArgs
from services.errors.chunk import ChildChunkDeleteIndexError as ChildChunkDeleteIndexServiceError
@ -184,7 +182,7 @@ class DatasetDocumentSegmentApi(Resource):
raise ProviderNotInitializeError(ex.description)
segment_ids = request.args.getlist("segment_id")
document_indexing_cache_key = "document_{}_indexing".format(document.id)
document_indexing_cache_key = f"document_{document.id}_indexing"
cache_result = redis_client.get(document_indexing_cache_key)
if cache_result is not None:
raise InvalidActionError("Document is being indexed, please try again later")
@ -365,37 +363,28 @@ class DatasetDocumentSegmentBatchImportApi(Resource):
document = DocumentService.get_document(dataset_id, document_id)
if not document:
raise NotFound("Document not found.")
# get file from request
file = request.files["file"]
# check file
if "file" not in request.files:
raise NoFileUploadedError()
if len(request.files) > 1:
raise TooManyFilesError()
parser = reqparse.RequestParser()
parser.add_argument("upload_file_id", type=str, required=True, nullable=False, location="json")
args = parser.parse_args()
upload_file_id = args["upload_file_id"]
upload_file = db.session.query(UploadFile).where(UploadFile.id == upload_file_id).first()
if not upload_file:
raise NotFound("UploadFile not found.")
# check file type
if not file.filename or not file.filename.lower().endswith(".csv"):
if not upload_file.name or not upload_file.name.lower().endswith(".csv"):
raise ValueError("Invalid file type. Only CSV files are allowed")
try:
# Skip the first row
df = pd.read_csv(file)
result = []
for index, row in df.iterrows():
if document.doc_form == "qa_model":
data = {"content": row.iloc[0], "answer": row.iloc[1]}
else:
data = {"content": row.iloc[0]}
result.append(data)
if len(result) == 0:
raise ValueError("The CSV file is empty.")
# async job
job_id = str(uuid.uuid4())
indexing_cache_key = "segment_batch_import_{}".format(str(job_id))
indexing_cache_key = f"segment_batch_import_{str(job_id)}"
# send batch add segments task
redis_client.setnx(indexing_cache_key, "waiting")
batch_create_segment_to_index_task.delay(
str(job_id), result, dataset_id, document_id, current_user.current_tenant_id, current_user.id
str(job_id), upload_file_id, dataset_id, document_id, current_user.current_tenant_id, current_user.id
)
except Exception as e:
return {"error": str(e)}, 500
@ -406,7 +395,7 @@ class DatasetDocumentSegmentBatchImportApi(Resource):
@account_initialization_required
def get(self, job_id):
job_id = str(job_id)
indexing_cache_key = "segment_batch_import_{}".format(job_id)
indexing_cache_key = f"segment_batch_import_{job_id}"
cache_result = redis_client.get(indexing_cache_key)
if cache_result is None:
raise ValueError("The job does not exist.")

View File

@ -74,7 +74,7 @@ class InstalledAppsListApi(Resource):
):
res.append(installed_app)
installed_app_list = res
logger.debug(f"installed_app_list: {installed_app_list}, user_id: {user_id}")
logger.debug("installed_app_list: %s, user_id: %s", installed_app_list, user_id)
installed_app_list.sort(
key=lambda app: (

View File

@ -34,7 +34,7 @@ class VersionApi(Resource):
try:
response = requests.get(check_update_url, {"current_version": args.get("current_version")})
except Exception as error:
logging.warning("Check update version error: {}.".format(str(error)))
logging.warning("Check update version error: %s.", str(error))
result["version"] = args.get("current_version")
return result
@ -55,7 +55,7 @@ def _has_new_version(*, latest_version: str, current_version: str) -> bool:
# Compare versions
return latest > current
except version.InvalidVersion:
logging.warning(f"Invalid version format: latest={latest_version}, current={current_version}")
logging.warning("Invalid version format: latest=%s, current=%s", latest_version, current_version)
return False

View File

@ -511,6 +511,8 @@ class CheckEmailUnique(Resource):
parser = reqparse.RequestParser()
parser.add_argument("email", type=email, required=True, location="json")
args = parser.parse_args()
if AccountService.is_account_in_freeze(args["email"]):
raise AccountInFreezeError()
if not AccountService.check_email_unique(args["email"]):
raise EmailAlreadyInUseError()
return {"result": "success"}

View File

@ -73,8 +73,9 @@ class DefaultModelApi(Resource):
)
except Exception as ex:
logging.exception(
f"Failed to update default model, model type: {model_setting['model_type']},"
f" model:{model_setting.get('model')}"
"Failed to update default model, model type: %s, model: %s",
model_setting["model_type"],
model_setting.get("model"),
)
raise ex
@ -160,8 +161,10 @@ class ModelProviderModelApi(Resource):
)
except CredentialsValidateFailedError as ex:
logging.exception(
f"Failed to save model credentials, tenant_id: {tenant_id},"
f" model: {args.get('model')}, model_type: {args.get('model_type')}"
"Failed to save model credentials, tenant_id: %s, model: %s, model_type: %s",
tenant_id,
args.get("model"),
args.get("model_type"),
)
raise ValueError(str(ex))

View File

@ -34,7 +34,7 @@ class AnnotationReplyActionStatusApi(Resource):
@validate_app_token
def get(self, app_model: App, job_id, action):
job_id = str(job_id)
app_annotation_job_key = "{}_app_annotation_job_{}".format(action, str(job_id))
app_annotation_job_key = f"{action}_app_annotation_job_{str(job_id)}"
cache_result = redis_client.get(app_annotation_job_key)
if cache_result is None:
raise ValueError("The job does not exist.")
@ -42,7 +42,7 @@ class AnnotationReplyActionStatusApi(Resource):
job_status = cache_result.decode()
error_msg = ""
if job_status == "error":
app_annotation_error_key = "{}_app_annotation_error_{}".format(action, str(job_id))
app_annotation_error_key = f"{action}_app_annotation_error_{str(job_id)}"
error_msg = redis_client.get(app_annotation_error_key).decode()
return {"job_id": job_id, "job_status": job_status, "error_msg": error_msg}, 200