mirror of
https://github.com/infiniflow/ragflow.git
synced 2026-03-27 17:29:39 +08:00
Problem The /file2document/convert endpoint ran all file lookups, document deletions, and insertions synchronously inside the request cycle. Linking a large folder (~1.7GB with many files) caused 504 Gateway Timeout because the blocking DB loop held the HTTP connection open for too long. Fix - Extracted the heavy DB work into a plain sync function _convert_files - Inputs are validated and folder file IDs expanded upfront (fast path) - The blocking work is dispatched to a thread pool via get_running_loop().run_in_executor() and the endpoint returns 200 immediately - Frontend only checks data.code === 0 so the response change (file2documents list → True) has no impact Fixes #13781 --------- Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
38 lines
1.5 KiB
Python
38 lines
1.5 KiB
Python
#
|
|
# Copyright 2026 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.
|
|
#
|
|
from common.constants import LLMType
|
|
from api.db.services.tenant_llm_service import TenantLLMService
|
|
|
|
_KEY_TO_MODEL_TYPE = {
|
|
"llm_id": LLMType.CHAT,
|
|
"embd_id": LLMType.EMBEDDING,
|
|
"asr_id": LLMType.SPEECH2TEXT,
|
|
"img2txt_id": LLMType.IMAGE2TEXT,
|
|
"rerank_id": LLMType.RERANK,
|
|
"tts_id": LLMType.TTS,
|
|
}
|
|
|
|
def ensure_tenant_model_id_for_params(tenant_id: str, param_dict: dict) -> dict:
|
|
for key in ["llm_id", "embd_id", "asr_id", "img2txt_id", "rerank_id", "tts_id"]:
|
|
if param_dict.get(key) and not param_dict.get(f"tenant_{key}"):
|
|
model_type = _KEY_TO_MODEL_TYPE.get(key)
|
|
tenant_model = TenantLLMService.get_api_key(tenant_id, param_dict[key], model_type)
|
|
if tenant_model:
|
|
param_dict.update({f"tenant_{key}": tenant_model.id})
|
|
else:
|
|
param_dict.update({f"tenant_{key}": 0})
|
|
return param_dict
|