Optimizing Search Speed for Vector Similarity in a Filtered Collection Schema

[JaeHyeonSoon]

Hello,
My collection schema is as follows:

fields = [
    FieldSchema(name="id", dtype=DataType.INT64, is_primary=True),
    FieldSchema(name="text", dtype=DataType.VARCHAR, max_length=512),
    FieldSchema(name="word", dtype=DataType.VARCHAR, max_length=512),
    FieldSchema(name="tag", dtype=DataType.VARCHAR, max_length=16),
    FieldSchema(name="vector", dtype=DataType.FLOAT_VECTOR, dim=768)
]

schema = CollectionSchema(fields)

I want to filter by word == "apple" and calculate the vector similarity among the filtered data to retrieve the tag values of the top 10 most similar data points. How can I optimize the search speed for this task?

Thanks.

[yhmo]

Set "word" to be partition key: https://milvus.io/docs/use-partition-key.md#Use-Partition-Key