Feat: add splitter (#10161)

### What problem does this PR solve?


### Type of change
- [x] New Feature (non-breaking change which adds functionality)

---------

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: Lynn <lynn_inf@hotmail.com>
Co-authored-by: chanx <1243304602@qq.com>
Co-authored-by: balibabu <cike8899@users.noreply.github.com>
Co-authored-by: 纷繁下的无奈 <zhileihuang@126.com>
Co-authored-by: huangzl <huangzl@shinemo.com>
Co-authored-by: writinwaters <93570324+writinwaters@users.noreply.github.com>
Co-authored-by: Wilmer <33392318@qq.com>
Co-authored-by: Adrian Weidig <adrianweidig@gmx.net>
Co-authored-by: Zhichang Yu <yuzhichang@gmail.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Yongteng Lei <yongtengrey@outlook.com>
Co-authored-by: Liu An <asiro@qq.com>
Co-authored-by: buua436 <66937541+buua436@users.noreply.github.com>
Co-authored-by: BadwomanCraZY <511528396@qq.com>
Co-authored-by: cucusenok <31804608+cucusenok@users.noreply.github.com>
Co-authored-by: Russell Valentine <russ@coldstonelabs.org>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Billy Bao <newyorkupperbay@gmail.com>
Co-authored-by: Zhedong Cen <cenzhedong2@126.com>
Co-authored-by: TensorNull <129579691+TensorNull@users.noreply.github.com>
Co-authored-by: TensorNull <tensor.null@gmail.com>
This commit is contained in:
Kevin Hu
2025-09-19 10:15:19 +08:00
committed by GitHub
parent f9c7404bee
commit a1b947ffd6
81 changed files with 3083 additions and 799 deletions

View File

@ -24,7 +24,7 @@ from io import BytesIO
import trio
import xxhash
from peewee import fn
from peewee import fn, Case
from api import settings
from api.constants import IMG_BASE64_PREFIX, FILE_NAME_LEN_LIMIT
@ -674,6 +674,53 @@ class DocumentService(CommonService):
return False
@classmethod
@DB.connection_context()
def knowledgebase_basic_info(cls, kb_id: str) -> dict[str, int]:
# cancelled: run == "2" but progress can vary
cancelled = (
cls.model.select(fn.COUNT(1))
.where((cls.model.kb_id == kb_id) & (cls.model.run == TaskStatus.CANCEL))
.scalar()
)
row = (
cls.model.select(
# finished: progress == 1
fn.COALESCE(fn.SUM(Case(None, [(cls.model.progress == 1, 1)], 0)), 0).alias("finished"),
# failed: progress == -1
fn.COALESCE(fn.SUM(Case(None, [(cls.model.progress == -1, 1)], 0)), 0).alias("failed"),
# processing: 0 <= progress < 1
fn.COALESCE(
fn.SUM(
Case(
None,
[
(((cls.model.progress == 0) | ((cls.model.progress > 0) & (cls.model.progress < 1))), 1),
],
0,
)
),
0,
).alias("processing"),
)
.where(
(cls.model.kb_id == kb_id)
& ((cls.model.run.is_null(True)) | (cls.model.run != TaskStatus.CANCEL))
)
.dicts()
.get()
)
return {
"processing": int(row["processing"]),
"finished": int(row["finished"]),
"failed": int(row["failed"]),
"cancelled": int(cancelled),
}
def queue_raptor_o_graphrag_tasks(doc, ty, priority):
chunking_config = DocumentService.get_chunking_config(doc["id"])
hasher = xxhash.xxh64()
@ -702,6 +749,8 @@ def queue_raptor_o_graphrag_tasks(doc, ty, priority):
def get_queue_length(priority):
group_info = REDIS_CONN.queue_info(get_svr_queue_name(priority), SVR_CONSUMER_GROUP_NAME)
if not group_info:
return 0
return int(group_info.get("lag", 0) or 0)
@ -847,3 +896,4 @@ def doc_upload_and_parse(conversation_id, file_objs, user_id):
doc_id, kb.id, token_counts[doc_id], chunk_counts[doc_id], 0)
return [d["id"] for d, _ in files]