Zhong Yuedong

version conflict： the doc of experiments-nfcorpus.md

3

It says that ``` python -m pyserini.encode \ input --corpus collections/nfcorpus/corpus.jsonl \ --fields title text \ output --embeddings indexes/nfcorpus.bge-base-en-v1.5 \ --to-faiss \ encoder --encoder BAAI/bge-base-en-v1.5 **--l2-norm** \ --device cpu \...

the faiss index method change: replace the IndexFlatIP with IndexIVFFlat

2

IndexFlatIP is brute searching method. IndexIVFFlat use aggregation to lower the dimension. So it will be faster, but lower the precision.