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(search.py):remove hard page_size (#8242)

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

Fix the restriction of forcing similarity_threshold=0 and page_size=30
when doc_ids is not empty

#8228

---------

Co-authored-by: shiqing.wusq <shiqing.wusq@dtzhejiang.com>
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
This commit is contained in:
Wesley
2025-06-13 14:56:25 +08:00
committed by GitHub
parent 800e263f64
commit 3d0b440e9f
1 changed files with 2 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
rag/nlp/search.py
View File

@ -380,15 +380,12 @@ class Dealer:
rank_feature=rank_feature) rank_feature=rank_feature)
# Already paginated in search function # Already paginated in search function
idx = np.argsort(sim * -1)[(page - 1) * page_size:page * page_size] idx = np.argsort(sim * -1)[(page - 1) * page_size:page * page_size]
dim = len(sres.query_vector) dim = len(sres.query_vector)
vector_column = f"q_{dim}_vec" vector_column = f"q_{dim}_vec"
zero_vector = [0.0] * dim zero_vector = [0.0] * dim
if doc_ids:
similarity_threshold = 0
page_size = 30
sim_np = np.array(sim) sim_np = np.array(sim)
if doc_ids:
similarity_threshold = 0
filtered_count = (sim_np >= similarity_threshold).sum() filtered_count = (sim_np >= similarity_threshold).sum()
ranks["total"] = int(filtered_count) # Convert from np.int64 to Python int otherwise JSON serializable error ranks["total"] = int(filtered_count) # Convert from np.int64 to Python int otherwise JSON serializable error
for i in idx: for i in idx: