feat: add polars dataframe integration (#3584)

This PR is part cleanup, part feature, part example.

It removes `IntoArrow` and `IntoArrowStream`. There was only one
redundant call site between the two. Once we moved everything to
`Scannable` these traits no longer serve any purpose.

It adds a `Scannable` impl for a polars DataFrame. We used to have this
at one point for `IntoArrow` so this is more like a regression fix than
anything.

It adds an example (and unit test) which ensures we can ingest from a
Polars DataFrame and export to one. LazyFrame support would be a
follow-up (though a pretty straightforward one) but we've never had
proper LazyFrame support before.
This commit is contained in:
Weston Pace
2026-06-30 08:28:41 -07:00
committed by GitHub
parent a8f1c5a69f
commit f6c9d31f98
5 changed files with 150 additions and 53 deletions

View File

@@ -3,7 +3,7 @@
use std::time::Duration;
use lancedb::{arrow::IntoArrow, ipc::ipc_file_to_batches, table::merge::MergeInsertBuilder};
use lancedb::{ipc::ipc_file_to_batches, table::merge::MergeInsertBuilder};
use napi::bindgen_prelude::*;
use napi_derive::napi;
@@ -66,11 +66,9 @@ impl NativeMergeInsertBuilder {
#[napi(catch_unwind)]
pub async fn execute(&self, buf: Buffer) -> napi::Result<MergeResult> {
let data = ipc_file_to_batches(buf.to_vec())
.and_then(IntoArrow::into_arrow)
.map_err(|e| {
napi::Error::from_reason(format!("Failed to read IPC file: {}", convert_error(&e)))
})?;
let data = ipc_file_to_batches(buf.to_vec()).map_err(|e| {
napi::Error::from_reason(format!("Failed to read IPC file: {}", convert_error(&e)))
})?;
let this = self.clone();