### 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>
Fix: incorrect total chunks count in retrieval function after similarity filtering (#6741) (#6932)
### Related Issue:
https://github.com/infiniflow/ragflow/issues/6741
### Environment:
Using nightly version
Commit version:
[[6051abb](6051abb4a3)]
### Bug Description:
The retrieval function in rag/nlp/search.py returns the original total
chunks number
even after chunks are filtered by similarity_threshold. This creates
inconsistency
between the actual returned chunks and the reported total.
### Changes Made:
Added code to count how many search results actually meet or exceed the
configured similarity threshold
Positioned the calculation after the doc_ids conditional logic to ensure
special cases are handled correctly
Updated the ranks["total"] value to store this filtered count instead of
using the raw search result count
Using NumPy leverages optimized C-level batch operations to optimize
speed
Fix infinite recursion in RagTokenizer when processing repetitive characters (#6109)
### What problem does this PR solve?
fix #6085
RagTokenizer's dfs_() function falls into infinite recursion when
processing text with repetitive Chinese characters (e.g.,
"一一一一一十一十一十一..." or "一一一一一一十十十十十十十二十二十二..."), causing memory leaks.
### Type of change
Implemented three optimizations to the dfs_() function:
1.Added memoization with _memo dictionary to cache computed results
2.Added recursion depth limiting with _depth parameter (max 10 levels)
3.Implemented special handling for repetitive character sequences
- [x] Bug Fix (non-breaking change which fixes an issue)
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
Fix: Use self.dataStore.indexExist in all_tags method of Dealer (#5108)
### What problem does this PR solve?
This PR fixes an AttributeError in the all_tags method of the Dealer
class. Previously, the method incorrectly called
self.docStoreConn.indexExist instead of self.dataStore.indexExist. Since
self.docStoreConn was never set (and self.dataStore is already
initialized in init), this resulted in an error when attempting to check
if the index exists. This change ensures that the proper connector is
used for the index existence check, thereby resolving the issue._
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
Use `json.loads()` instead.
### What problem does this PR solve?
Using `eval()` can lead to code injections. I think this loads a JSON
field, right? If yes, why is this done via `eval()` and not
`json.loads()`?
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
fix: stop rerank by model when search result is empty (#4203)
### What problem does this PR solve?
stop rerank by model when search result is empty, otherwise rerank may
raise an error (qwen).
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
Co-authored-by: 刘博 <liubo@ynby.cn>
### What problem does this PR solve?
1. Fix initial build and load trie
2. Update comment
### Type of change
- [x] Refactoring
Signed-off-by: jinhai <haijin.chn@gmail.com>
### What problem does this PR solve?
Fix hierarchical_merge function. From idx vs. actual value to actual
value vs. actual value.
Related issue #4003
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
Co-authored-by: luopan <luopan@example.com>
### What problem does this PR solve?
Rename page_num_list, top_list, position_list to page_num_int, top_int,
position_int
### Type of change
- [x] Refactoring
Yongteng Lei
alulala
kaiyuan Zhang
Kevin Hu
ubbg
Mathias Panzenböck
Bo Liu
Jin Hai
Luo Pan
Zhichang Yu