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

fix position extraction bug (#93)

Browse Source 
* fix position extraction bug

* remove delimiter for naive parser
This commit is contained in:
KevinHuSh
2024-03-04 17:08:35 +08:00
committed by GitHub
parent fae00827e6
commit 7bfaf0df29
11 changed files with 34 additions and 22 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
rag/nlp/__init__.py
View File

@ -246,6 +246,8 @@ def naive_merge(sections, chunk_token_num=128, delimiter="\n。；！？"):
tk_nums[-1] += tnum
for sec, pos in sections:
add_chunk(sec, pos)
continue
s, e = 0, 1
while e < len(sec):
if sec[e] in delimiter:

2
rag/nlp/search.py
View File

@ -83,7 +83,7 @@ class Dealer:
else:
s = s.sort(
{"page_num_int": {"order": "asc", "unmapped_type": "float"}},
{"top_int": {"order": "asc", "unmapped_type": "float"}},
{"top_int": {"order": "asc", "unmapped_type": "float", "mode" : "avg"}},
{"create_time": {"order": "desc", "unmapped_type": "date"}},
{"create_timestamp_flt": {"order": "desc", "unmapped_type": "float"}}
)