feat: allow Python and Typescript users to create Sessions (#2530)

## Summary
- Exposes `Session` in Python and Typescript so users can set the
`index_cache_size_bytes` and `metadata_cache_size_bytes`
* The `Session` is attached to the `Connection`, and thus shared across
all tables in that connection.
- Adds deprecation warnings for table-level cache configuration


🤖 Generated with [Claude Code](https://claude.ai/code)

---------

Co-authored-by: Claude <noreply@anthropic.com>
This commit is contained in:
Will Jones
2025-07-24 12:06:29 -07:00
committed by GitHub
parent 81afd8a42f
commit 3d1f102087
21 changed files with 514 additions and 13 deletions

View File

@@ -74,6 +74,10 @@ impl Connection {
builder = builder.host_override(&host_override);
}
if let Some(session) = options.session {
builder = builder.session(session.inner.clone());
}
Ok(Self::inner_new(builder.execute().await.default_error()?))
}

View File

@@ -14,6 +14,7 @@ pub mod merge;
mod query;
pub mod remote;
mod rerankers;
mod session;
mod table;
mod util;
@@ -34,6 +35,9 @@ pub struct ConnectionOptions {
///
/// The available options are described at https://lancedb.github.io/lancedb/guides/storage/
pub storage_options: Option<HashMap<String, String>>,
/// (For LanceDB OSS only): the session to use for this connection. Holds
/// shared caches and other session-specific state.
pub session: Option<session::Session>,
/// (For LanceDB cloud only): configuration for the remote HTTP client.
pub client_config: Option<remote::ClientConfig>,

102
nodejs/src/session.rs Normal file
View File

@@ -0,0 +1,102 @@
// SPDX-License-Identifier: Apache-2.0
// SPDX-FileCopyrightText: Copyright The LanceDB Authors
use std::sync::Arc;
use lancedb::{ObjectStoreRegistry, Session as LanceSession};
use napi::bindgen_prelude::*;
use napi_derive::*;
/// A session for managing caches and object stores across LanceDB operations.
///
/// Sessions allow you to configure cache sizes for index and metadata caches,
/// which can significantly impact memory use and performance. They can
/// also be re-used across multiple connections to share the same cache state.
#[napi]
#[derive(Clone)]
pub struct Session {
pub(crate) inner: Arc<LanceSession>,
}
impl std::fmt::Debug for Session {
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
f.debug_struct("Session")
.field("size_bytes", &self.inner.size_bytes())
.field("approx_num_items", &self.inner.approx_num_items())
.finish()
}
}
#[napi]
impl Session {
/// Create a new session with custom cache sizes.
///
/// # Parameters
///
/// - `index_cache_size_bytes`: The size of the index cache in bytes.
/// Index data is stored in memory in this cache to speed up queries.
/// Defaults to 6GB if not specified.
/// - `metadata_cache_size_bytes`: The size of the metadata cache in bytes.
/// The metadata cache stores file metadata and schema information in memory.
/// This cache improves scan and write performance.
/// Defaults to 1GB if not specified.
#[napi(constructor)]
pub fn new(
index_cache_size_bytes: Option<BigInt>,
metadata_cache_size_bytes: Option<BigInt>,
) -> napi::Result<Self> {
let index_cache_size = index_cache_size_bytes
.map(|size| size.get_u64().1 as usize)
.unwrap_or(6 * 1024 * 1024 * 1024); // 6GB default
let metadata_cache_size = metadata_cache_size_bytes
.map(|size| size.get_u64().1 as usize)
.unwrap_or(1024 * 1024 * 1024); // 1GB default
let session = LanceSession::new(
index_cache_size,
metadata_cache_size,
Arc::new(ObjectStoreRegistry::default()),
);
Ok(Self {
inner: Arc::new(session),
})
}
/// Create a session with default cache sizes.
///
/// This is equivalent to creating a session with 6GB index cache
/// and 1GB metadata cache.
#[napi(factory)]
pub fn default() -> Self {
Self {
inner: Arc::new(LanceSession::default()),
}
}
/// Get the current size of the session caches in bytes.
#[napi]
pub fn size_bytes(&self) -> BigInt {
BigInt::from(self.inner.size_bytes())
}
/// Get the approximate number of items cached in the session.
#[napi]
pub fn approx_num_items(&self) -> u32 {
self.inner.approx_num_items() as u32
}
}
// Implement FromNapiValue for Session to work with napi(object)
impl napi::bindgen_prelude::FromNapiValue for Session {
unsafe fn from_napi_value(
env: napi::sys::napi_env,
napi_val: napi::sys::napi_value,
) -> napi::Result<Self> {
let object: napi::bindgen_prelude::ClassInstance<Session> =
napi::bindgen_prelude::ClassInstance::from_napi_value(env, napi_val)?;
let copy = object.clone();
Ok(copy)
}
}