Facebook AI Similarity Search (Faiss): The Missing Manual

Search, No Filter
1

Facebook AI Similarity Search (Faiss) is one of the most popular implementations of efficient similarity search, but what is it — and how can we use it?

What is it that makes Faiss special? How do we make the best use of this incredible tool?

This is a companion discussion topic for the original entry at https://www.pinecone.io/learn/faiss-tutorial/
2

Now, because we’re searching a larger scope by increasing the nprobe value, we will see the search speed increase too.

Do we see the search speed increase too, or the search time?

3

If you encounter the error like:

TypeError: read_csv() got an unexpected keyword argument ‘error_bad_lines’

change it from

data = pd.read_csv(StringIO(res.text), sep='\t', header=None, error_bad_lines=False)

to

data = pd.read_csv(StringIO(res.text), sep='\t', header=None, on_bad_lines='skip')