Struct lance::dataset::scanner::Scanner

pub struct Scanner { /* private fields */ }

Dataset Scanner

let dataset = Dataset::open(uri).await.unwrap();
let stream = dataset.scan()
    .project(&["col", "col2.subfield"]).unwrap()
    .limit(10)
    .into_stream();
stream
  .map(|batch| batch.num_rows())
  .buffered(16)
  .sum()

Implementations

impl Scanner

pub fn new(dataset: Arc<Dataset>) -> Self

pub fn project(&mut self, columns: &[&str]) -> Result<&mut Self>

Projection.

Only seelect the specific columns. If not specifid, all columns will be scanned.

pub fn limit(&mut self, limit: i64, offset: Option<i64>) -> Result<&mut Self>

Set limit and offset.

pub fn nearest(
&mut self,
column: &str,
q: &Float32Array,
k: usize
) -> Result<&mut Self>

Find k-nearest neighbour within the vector column.

pub fn nprobs(&mut self, n: usize) -> &mut Self

pub fn refine(&mut self, factor: u32) -> &mut Self

Apply a refine step to the vector search.

A refine step uses the original vector values to re-rank the distances.

pub fn with_row_id(&mut self) -> &mut Self

Instruct the scanner to return the _rowid meta column from the dataset.

pub fn schema(&self) -> Result<SchemaRef>

The schema of the output, a.k.a, projection schema.

pub async fn try_into_stream(&self) -> Result<ScannerStream>

Create a stream of this Scanner.

TODO: implement as IntoStream/IntoIterator.