### 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