mirror of https://github.com/milvus-io/milvus.git
1ce609834a
Add the following methods for convenient fp32 vector <-> fp16/bf16
vector conversion
fp32 <-> fp16/bf16 vector conversion:
- `func (fv FloatVector) ToFloat16Vector() Float16Vector`
- `func (fv FloatVector) ToBFloat16Vector() BFloat16Vector`
- `func (fv Float16Vector) ToFloat32Vector() FloatVector`
- `func (fv BFloat16Vector) ToFloat32Vector() FloatVector`
`columnBasedDataOption`:
- `func (opt *columnBasedDataOption) WithFloat16VectorColumn(colName
string, dim int, data [][]float32) *columnBasedDataOption`
- `func (opt *columnBasedDataOption) WithBFloat16VectorColumn(colName
string, dim int, data [][]float32) *columnBasedDataOption`
`ColumnFloat16Vector`/`ColumnBFloat16Vector`:
- `func NewColumnFloat16VectorFromFp32Vector(fieldName string, dim int,
data [][]float32) *ColumnFloat16Vector`
- `func NewColumnBFloat16VectorFromFp32Vector(fieldName string, dim int,
data [][]float32) *ColumnBFloat16Vector`
- support []float32 or `entity.FloatVector` in
- `func (c *ColumnFloat16Vector) AppendValue(i interface{}) error`
- `func (c *ColumnFloat16Vector) AppendValue(i interface{}) error`
issue: #37448
Signed-off-by: Yinzuo Jiang <yinzuo.jiang@zilliz.com>
Signed-off-by: Yinzuo Jiang <jiangyinzuo@foxmail.com>
|
||
|---|---|---|
| .. | ||
| array.go | ||
| array_test.go | ||
| columns.go | ||
| columns_test.go | ||
| conversion.go | ||
| dynamic.go | ||
| dynamic_test.go | ||
| generic_base.go | ||
| generic_base_test.go | ||
| json.go | ||
| json_test.go | ||
| scalar.go | ||
| scalar_test.go | ||
| sparse.go | ||
| sparse_test.go | ||
| vector.go | ||
| vector_test.go | ||