pengjunjie/ragflow
1
0
Fork 1
mirror of https://github.com/infiniflow/ragflow.git synced 2025-12-08 20:42:30 +08:00
Code Issues Packages Projects Releases Wiki Activity

Move api.settings to common.settings (#11036)

Browse Source 
### What problem does this PR solve?

As title

### Type of change

- [x] Refactoring

---------

Signed-off-by: Jin Hai <haijin.chn@gmail.com>
This commit is contained in:
Jin Hai
2025-11-06 09:36:38 +08:00
committed by GitHub
parent 87c9a054d3
commit f98b24c9bf
68 changed files with 675 additions and 718 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
api/db/services/task_service.py
View File

@ -31,10 +31,8 @@ from common.misc_utils import get_uuid
from common.time_utils import current_timestamp
from common.constants import StatusEnum, TaskStatus
from deepdoc.parser.excel_parser import RAGFlowExcelParser
from rag.settings import get_svr_queue_name
from rag.utils.storage_factory import STORAGE_IMPL
from rag.utils.redis_conn import REDIS_CONN
from common import globals
from common import settings
from rag.nlp import search
CANVAS_DEBUG_DOC_ID = "dataflow_x"
@ -359,7 +357,7 @@ def queue_tasks(doc: dict, bucket: str, name: str, priority: int):
parse_task_array = []
if doc["type"] == FileType.PDF.value:
file_bin = STORAGE_IMPL.get(bucket, name)
file_bin = settings.STORAGE_IMPL.get(bucket, name)
do_layout = doc["parser_config"].get("layout_recognize", "DeepDOC")
pages = PdfParser.total_page_number(doc["name"], file_bin)
if pages is None:
@ -381,7 +379,7 @@ def queue_tasks(doc: dict, bucket: str, name: str, priority: int):
parse_task_array.append(task)
elif doc["parser_id"] == "table":
file_bin = STORAGE_IMPL.get(bucket, name)
file_bin = settings.STORAGE_IMPL.get(bucket, name)
rn = RAGFlowExcelParser.row_number(doc["name"], file_bin)
for i in range(0, rn, 3000):
task = new_task()
@ -418,7 +416,7 @@ def queue_tasks(doc: dict, bucket: str, name: str, priority: int):
if pre_task["chunk_ids"]:
pre_chunk_ids.extend(pre_task["chunk_ids"].split())
if pre_chunk_ids:
globals.docStoreConn.delete({"id": pre_chunk_ids}, search.index_name(chunking_config["tenant_id"]),
settings.docStoreConn.delete({"id": pre_chunk_ids}, search.index_name(chunking_config["tenant_id"]),
chunking_config["kb_id"])
DocumentService.update_by_id(doc["id"], {"chunk_num": ck_num})
@ -428,7 +426,7 @@ def queue_tasks(doc: dict, bucket: str, name: str, priority: int):
unfinished_task_array = [task for task in parse_task_array if task["progress"] < 1.0]
for unfinished_task in unfinished_task_array:
assert REDIS_CONN.queue_product(
get_svr_queue_name(priority), message=unfinished_task
settings.get_svr_queue_name(priority), message=unfinished_task
), "Can't access Redis. Please check the Redis' status."
@ -518,7 +516,7 @@ def queue_dataflow(tenant_id:str, flow_id:str, task_id:str, doc_id:str=CANVAS_DE
task["file"] = file
if not REDIS_CONN.queue_product(
get_svr_queue_name(priority), message=task
settings.get_svr_queue_name(priority), message=task
):
return False, "Can't access Redis. Please check the Redis' status."