AI/ragflow
1
0
Fork 0
mirror of https://git.mirrors.martin98.com/https://github.com/infiniflow/ragflow.git synced 2025-08-14 04:36:01 +08:00
Code Issues Packages Projects Releases Wiki Activity

Fix: fix retrieval tesing wrong pagination (#7174)

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

Fix retrieval testing wrong pagination. #7171 

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)

---------

Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
This commit is contained in:
Yongteng Lei 2025-04-22 15:16:04 +08:00 committed by GitHub
parent bcac195a0c
commit 67dee2d74e
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 7 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
rag/nlp/search.py
View File

@ -15,6 +15,7 @@
# #
import logging import logging
import re import re
import math
from collections import OrderedDict from collections import OrderedDict
from dataclasses import dataclass from dataclasses import dataclass
@ -353,11 +354,13 @@ class Dealer:
return ranks return ranks
RERANK_LIMIT = 64 RERANK_LIMIT = 64
req = {"kb_ids": kb_ids, "doc_ids": doc_ids, "page": page, "size": RERANK_LIMIT, RERANK_LIMIT = int(RERANK_LIMIT//page_size + ((RERANK_LIMIT%page_size)/(page_size*1.) + 0.5)) * page_size if page_size>1 else 1
req = {"kb_ids": kb_ids, "doc_ids": doc_ids, "page": math.ceil(page_size*page/RERANK_LIMIT), "size": RERANK_LIMIT,
"question": question, "vector": True, "topk": top, "question": question, "vector": True, "topk": top,
"similarity": similarity_threshold, "similarity": similarity_threshold,
"available_int": 1} "available_int": 1}
if isinstance(tenant_ids, str): if isinstance(tenant_ids, str):
tenant_ids = tenant_ids.split(",") tenant_ids = tenant_ids.split(",")
@ -373,6 +376,7 @@ class Dealer:
sim, tsim, vsim = self.rerank( sim, tsim, vsim = self.rerank(
sres, question, 1 - vector_similarity_weight, vector_similarity_weight, sres, question, 1 - vector_similarity_weight, vector_similarity_weight,
rank_feature=rank_feature) rank_feature=rank_feature)
# 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]

4
sdk/python/test/test_http_api/test_chunk_management_within_dataset/test_retrieval_chunks.py
View File

@ -120,11 +120,11 @@ class TestChunksRetrieval:
"""TypeError("int() argument must be a string, a bytes-like object or a real number, not \'NoneType\'")""", """TypeError("int() argument must be a string, a bytes-like object or a real number, not \'NoneType\'")""",
marks=pytest.mark.skip, marks=pytest.mark.skip,
), ),
({"page_size": 0}, 0, 0, ""), # ({"page_size": 0}, 0, 0, ""),
({"page_size": 1}, 0, 1, ""), ({"page_size": 1}, 0, 1, ""),
({"page_size": 5}, 0, 4, ""), ({"page_size": 5}, 0, 4, ""),
({"page_size": "1"}, 0, 1, ""), ({"page_size": "1"}, 0, 1, ""),
({"page_size": -1}, 0, 0, ""), # ({"page_size": -1}, 0, 0, ""),
pytest.param( pytest.param(
{"page_size": "a"}, {"page_size": "a"},
100, 100,