Generic usage of sync Python client.
VectorParams
which are indicating our
vector configuration for our collection.
ANODE
index, our new invention.size
indicates the vector size, and index_type
is
one of the possible indexes that we have documented at Index Types.
Let’s start with HNSW
for now.
As a next step let’s create a collection. Collections are like tables for us.
They allow us to organize vectors and their indexes into same location for data locality.
You can learn more with storage system doc.
SIFT1M
dataset to our system as an example:
xq
and xb
both query and base vectors.
Now let’s prepare our vector data for insertion
client.search_multi
method too.limit
will give most similar top-K (in our case top 100) vectors for us.
AsyncPulsejetClient
. You can head to Quickstart - Async Client to reduce your time to insert vectors.