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

Feat: add advanced document filter (#8723)

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

Add advanced document filter

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
This commit is contained in:
Yongteng Lei
2025-07-09 09:33:11 +08:00
committed by GitHub
parent f7af0fc71e
commit c1f6e6f00e
6 changed files with 109 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

52
api/db/services/document_service.py
View File

@ -72,7 +72,7 @@ class DocumentService(CommonService):
@classmethod
@DB.connection_context()
def get_by_kb_id(cls, kb_id, page_number, items_per_page,
orderby, desc, keywords, run_status, types):
orderby, desc, keywords, run_status, types, suffix):
if keywords:
docs = cls.model.select().where(
(cls.model.kb_id == kb_id),
@ -85,6 +85,8 @@ class DocumentService(CommonService):
docs = docs.where(cls.model.run.in_(run_status))
if types:
docs = docs.where(cls.model.type.in_(types))
if suffix:
docs = docs.where(cls.model.suffix.in_(suffix))
count = docs.count()
if desc:
@ -98,6 +100,54 @@ class DocumentService(CommonService):
return list(docs.dicts()), count
@classmethod
@DB.connection_context()
def get_filter_by_kb_id(cls, kb_id, keywords, run_status, types, suffix):
"""
returns:
{
"suffix": {
"ppt": 1,
"doxc": 2
},
"run_status": {
"1": 2,
"2": 2
}
}, total
where "1" => RUNNING, "2" => CANCEL
"""
if keywords:
query = cls.model.select().where(
(cls.model.kb_id == kb_id),
(fn.LOWER(cls.model.name).contains(keywords.lower()))
)
else:
query = cls.model.select().where(cls.model.kb_id == kb_id)
if run_status:
query = query.where(cls.model.run.in_(run_status))
if types:
query = query.where(cls.model.type.in_(types))
if suffix:
query = query.where(cls.model.suffix.in_(suffix))
rows = query.select(cls.model.run, cls.model.suffix)
total = rows.count()
suffix_counter = {}
run_status_counter = {}
for row in rows:
suffix_counter[row.suffix] = suffix_counter.get(row.suffix, 0) + 1
run_status_counter[str(row.run)] = run_status_counter.get(str(row.run), 0) + 1
return {
"suffix": suffix_counter,
"run_status": run_status_counter
}, total
@classmethod
@DB.connection_context()
def count_by_kb_id(cls, kb_id, keywords, run_status, types):