In TopK, a vector is represented as a flat array of numbers. To differentiate between various types of vectors, use provided data constructors when inserting or querying vectors: TopK supports the following types of vectors:

• Float32 vectors
• U8 vectors
• Binary vectors
• Sparse f32 vectors
• Sparse u8 vectors

If no helper function is used, the vector is assumed to be a float32 vector.

​

f32_vector()

To pass a float32 vector, use the f32_vector() helper function:

from topk_sdk.data import f32_vector

f32_vector([0.12, 0.67, 0.82, 0.53])

​

u8_vector()

To pass a u8 vector, use the u8_vector() helper function:

from topk_sdk.data import u8_vector

u8_vector([0, 1, 2, 3])

​

binary_vector()

To pass a binary vector, use the binary_vector() helper function:

from topk_sdk.data import binary_vector

binary_vector([0, 1, 1, 0])

​

f32_sparse_vector()

To pass a sparse vector with float32 values, use the f32_sparse_vector() helper function:

from topk_sdk.data import f32_sparse_vector

f32_sparse_vector({0: 0.12, 6: 0.67, 17: 0.82, 97: 0.53})

​

u8_sparse_vector()

To pass a sparse vector with 8-bit unsigned integer values, use the u8_sparse_vector() helper function:

from topk_sdk.data import u8_sparse_vector

u8_sparse_vector({0: 12, 6: 67, 17: 82, 97: 53})

​

bytes()

To pass a byte object, use the bytes() helper function:

from topk_sdk.data import bytes

bytes([0, 1, 1, 0])