mirror of
https://github.com/lancedb/lancedb.git
synced 2026-03-26 18:40:42 +00:00
Compare commits
1 Commits
python-v0.
...
v0.24.0
| Author | SHA1 | Date | |
|---|---|---|---|
|
ce5a8907cf |
6
.github/workflows/rust.yml
vendored
6
.github/workflows/rust.yml
vendored
@@ -48,8 +48,6 @@ jobs:
|
||||
run: cargo fmt --all -- --check
|
||||
- name: Run clippy
|
||||
run: cargo clippy --profile ci --workspace --tests --all-features -- -D warnings
|
||||
- name: Run clippy (without remote feature)
|
||||
run: cargo clippy --profile ci --workspace --tests -- -D warnings
|
||||
|
||||
build-no-lock:
|
||||
runs-on: ubuntu-24.04
|
||||
@@ -183,7 +181,7 @@ jobs:
|
||||
runs-on: ubuntu-24.04
|
||||
strategy:
|
||||
matrix:
|
||||
msrv: ["1.88.0"] # This should match up with rust-version in Cargo.toml
|
||||
msrv: ["1.78.0"] # This should match up with rust-version in Cargo.toml
|
||||
env:
|
||||
# Need up-to-date compilers for kernels
|
||||
CC: clang-18
|
||||
@@ -214,6 +212,4 @@ jobs:
|
||||
cargo update -p aws-sdk-sts --precise 1.51.0
|
||||
cargo update -p home --precise 0.5.9
|
||||
- name: cargo +${{ matrix.msrv }} check
|
||||
env:
|
||||
RUSTUP_TOOLCHAIN: ${{ matrix.msrv }}
|
||||
run: cargo check --profile ci --workspace --tests --benches --all-features
|
||||
|
||||
76
Cargo.lock
generated
76
Cargo.lock
generated
@@ -1,6 +1,6 @@
|
||||
# This file is automatically @generated by Cargo.
|
||||
# It is not intended for manual editing.
|
||||
version = 4
|
||||
version = 3
|
||||
|
||||
[[package]]
|
||||
name = "adler2"
|
||||
@@ -3141,8 +3141,8 @@ checksum = "42703706b716c37f96a77aea830392ad231f44c9e9a67872fa5548707e11b11c"
|
||||
|
||||
[[package]]
|
||||
name = "fsst"
|
||||
version = "1.0.4"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v1.0.4#a93eaad1f6909a843cf8aa00d5530359012a7aaa"
|
||||
version = "1.0.3"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v1.0.3#dd66ca47101ccd51e59677f5385158f05cabd6f9"
|
||||
dependencies = [
|
||||
"arrow-array",
|
||||
"rand 0.9.2",
|
||||
@@ -4478,8 +4478,8 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "lance"
|
||||
version = "1.0.4"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v1.0.4#a93eaad1f6909a843cf8aa00d5530359012a7aaa"
|
||||
version = "1.0.3"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v1.0.3#dd66ca47101ccd51e59677f5385158f05cabd6f9"
|
||||
dependencies = [
|
||||
"arrow",
|
||||
"arrow-arith",
|
||||
@@ -4544,8 +4544,8 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "lance-arrow"
|
||||
version = "1.0.4"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v1.0.4#a93eaad1f6909a843cf8aa00d5530359012a7aaa"
|
||||
version = "1.0.3"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v1.0.3#dd66ca47101ccd51e59677f5385158f05cabd6f9"
|
||||
dependencies = [
|
||||
"arrow-array",
|
||||
"arrow-buffer",
|
||||
@@ -4563,8 +4563,8 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "lance-bitpacking"
|
||||
version = "1.0.4"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v1.0.4#a93eaad1f6909a843cf8aa00d5530359012a7aaa"
|
||||
version = "1.0.3"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v1.0.3#dd66ca47101ccd51e59677f5385158f05cabd6f9"
|
||||
dependencies = [
|
||||
"arrayref",
|
||||
"paste",
|
||||
@@ -4573,8 +4573,8 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "lance-core"
|
||||
version = "1.0.4"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v1.0.4#a93eaad1f6909a843cf8aa00d5530359012a7aaa"
|
||||
version = "1.0.3"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v1.0.3#dd66ca47101ccd51e59677f5385158f05cabd6f9"
|
||||
dependencies = [
|
||||
"arrow-array",
|
||||
"arrow-buffer",
|
||||
@@ -4610,8 +4610,8 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "lance-datafusion"
|
||||
version = "1.0.4"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v1.0.4#a93eaad1f6909a843cf8aa00d5530359012a7aaa"
|
||||
version = "1.0.3"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v1.0.3#dd66ca47101ccd51e59677f5385158f05cabd6f9"
|
||||
dependencies = [
|
||||
"arrow",
|
||||
"arrow-array",
|
||||
@@ -4641,8 +4641,8 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "lance-datagen"
|
||||
version = "1.0.4"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v1.0.4#a93eaad1f6909a843cf8aa00d5530359012a7aaa"
|
||||
version = "1.0.3"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v1.0.3#dd66ca47101ccd51e59677f5385158f05cabd6f9"
|
||||
dependencies = [
|
||||
"arrow",
|
||||
"arrow-array",
|
||||
@@ -4659,8 +4659,8 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "lance-encoding"
|
||||
version = "1.0.4"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v1.0.4#a93eaad1f6909a843cf8aa00d5530359012a7aaa"
|
||||
version = "1.0.3"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v1.0.3#dd66ca47101ccd51e59677f5385158f05cabd6f9"
|
||||
dependencies = [
|
||||
"arrow-arith",
|
||||
"arrow-array",
|
||||
@@ -4697,8 +4697,8 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "lance-file"
|
||||
version = "1.0.4"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v1.0.4#a93eaad1f6909a843cf8aa00d5530359012a7aaa"
|
||||
version = "1.0.3"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v1.0.3#dd66ca47101ccd51e59677f5385158f05cabd6f9"
|
||||
dependencies = [
|
||||
"arrow-arith",
|
||||
"arrow-array",
|
||||
@@ -4730,8 +4730,8 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "lance-geo"
|
||||
version = "1.0.4"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v1.0.4#a93eaad1f6909a843cf8aa00d5530359012a7aaa"
|
||||
version = "1.0.3"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v1.0.3#dd66ca47101ccd51e59677f5385158f05cabd6f9"
|
||||
dependencies = [
|
||||
"datafusion",
|
||||
"geo-types",
|
||||
@@ -4742,8 +4742,8 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "lance-index"
|
||||
version = "1.0.4"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v1.0.4#a93eaad1f6909a843cf8aa00d5530359012a7aaa"
|
||||
version = "1.0.3"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v1.0.3#dd66ca47101ccd51e59677f5385158f05cabd6f9"
|
||||
dependencies = [
|
||||
"arrow",
|
||||
"arrow-arith",
|
||||
@@ -4804,8 +4804,8 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "lance-io"
|
||||
version = "1.0.4"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v1.0.4#a93eaad1f6909a843cf8aa00d5530359012a7aaa"
|
||||
version = "1.0.3"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v1.0.3#dd66ca47101ccd51e59677f5385158f05cabd6f9"
|
||||
dependencies = [
|
||||
"arrow",
|
||||
"arrow-arith",
|
||||
@@ -4845,8 +4845,8 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "lance-linalg"
|
||||
version = "1.0.4"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v1.0.4#a93eaad1f6909a843cf8aa00d5530359012a7aaa"
|
||||
version = "1.0.3"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v1.0.3#dd66ca47101ccd51e59677f5385158f05cabd6f9"
|
||||
dependencies = [
|
||||
"arrow-array",
|
||||
"arrow-buffer",
|
||||
@@ -4862,8 +4862,8 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "lance-namespace"
|
||||
version = "1.0.4"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v1.0.4#a93eaad1f6909a843cf8aa00d5530359012a7aaa"
|
||||
version = "1.0.3"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v1.0.3#dd66ca47101ccd51e59677f5385158f05cabd6f9"
|
||||
dependencies = [
|
||||
"arrow",
|
||||
"async-trait",
|
||||
@@ -4875,8 +4875,8 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "lance-namespace-impls"
|
||||
version = "1.0.4"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v1.0.4#a93eaad1f6909a843cf8aa00d5530359012a7aaa"
|
||||
version = "1.0.3"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v1.0.3#dd66ca47101ccd51e59677f5385158f05cabd6f9"
|
||||
dependencies = [
|
||||
"arrow",
|
||||
"arrow-ipc",
|
||||
@@ -4919,8 +4919,8 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "lance-table"
|
||||
version = "1.0.4"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v1.0.4#a93eaad1f6909a843cf8aa00d5530359012a7aaa"
|
||||
version = "1.0.3"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v1.0.3#dd66ca47101ccd51e59677f5385158f05cabd6f9"
|
||||
dependencies = [
|
||||
"arrow",
|
||||
"arrow-array",
|
||||
@@ -4959,8 +4959,8 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "lance-testing"
|
||||
version = "1.0.4"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v1.0.4#a93eaad1f6909a843cf8aa00d5530359012a7aaa"
|
||||
version = "1.0.3"
|
||||
source = "git+https://github.com/lance-format/lance.git?tag=v1.0.3#dd66ca47101ccd51e59677f5385158f05cabd6f9"
|
||||
dependencies = [
|
||||
"arrow-array",
|
||||
"arrow-schema",
|
||||
@@ -4971,7 +4971,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "lancedb"
|
||||
version = "0.24.0"
|
||||
version = "0.24.0-beta.0"
|
||||
dependencies = [
|
||||
"ahash",
|
||||
"anyhow",
|
||||
@@ -5050,7 +5050,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "lancedb-nodejs"
|
||||
version = "0.24.0"
|
||||
version = "0.24.0-beta.0"
|
||||
dependencies = [
|
||||
"arrow-array",
|
||||
"arrow-ipc",
|
||||
@@ -5070,7 +5070,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "lancedb-python"
|
||||
version = "0.27.0"
|
||||
version = "0.27.0-beta.0"
|
||||
dependencies = [
|
||||
"arrow",
|
||||
"async-trait",
|
||||
|
||||
30
Cargo.toml
30
Cargo.toml
@@ -12,23 +12,23 @@ repository = "https://github.com/lancedb/lancedb"
|
||||
description = "Serverless, low-latency vector database for AI applications"
|
||||
keywords = ["lancedb", "lance", "database", "vector", "search"]
|
||||
categories = ["database-implementations"]
|
||||
rust-version = "1.88.0"
|
||||
rust-version = "1.78.0"
|
||||
|
||||
[workspace.dependencies]
|
||||
lance = { "version" = "=1.0.4", default-features = false, "tag" = "v1.0.4", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-core = { "version" = "=1.0.4", "tag" = "v1.0.4", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-datagen = { "version" = "=1.0.4", "tag" = "v1.0.4", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-file = { "version" = "=1.0.4", "tag" = "v1.0.4", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-io = { "version" = "=1.0.4", default-features = false, "tag" = "v1.0.4", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-index = { "version" = "=1.0.4", "tag" = "v1.0.4", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-linalg = { "version" = "=1.0.4", "tag" = "v1.0.4", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-namespace = { "version" = "=1.0.4", "tag" = "v1.0.4", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-namespace-impls = { "version" = "=1.0.4", default-features = false, "tag" = "v1.0.4", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-table = { "version" = "=1.0.4", "tag" = "v1.0.4", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-testing = { "version" = "=1.0.4", "tag" = "v1.0.4", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-datafusion = { "version" = "=1.0.4", "tag" = "v1.0.4", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-encoding = { "version" = "=1.0.4", "tag" = "v1.0.4", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-arrow = { "version" = "=1.0.4", "tag" = "v1.0.4", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance = { "version" = "=1.0.3", default-features = false, "tag" = "v1.0.3", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-core = { "version" = "=1.0.3", "tag" = "v1.0.3", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-datagen = { "version" = "=1.0.3", "tag" = "v1.0.3", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-file = { "version" = "=1.0.3", "tag" = "v1.0.3", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-io = { "version" = "=1.0.3", default-features = false, "tag" = "v1.0.3", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-index = { "version" = "=1.0.3", "tag" = "v1.0.3", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-linalg = { "version" = "=1.0.3", "tag" = "v1.0.3", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-namespace = { "version" = "=1.0.3", "tag" = "v1.0.3", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-namespace-impls = { "version" = "=1.0.3", default-features = false, "tag" = "v1.0.3", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-table = { "version" = "=1.0.3", "tag" = "v1.0.3", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-testing = { "version" = "=1.0.3", "tag" = "v1.0.3", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-datafusion = { "version" = "=1.0.3", "tag" = "v1.0.3", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-encoding = { "version" = "=1.0.3", "tag" = "v1.0.3", "git" = "https://github.com/lance-format/lance.git" }
|
||||
lance-arrow = { "version" = "=1.0.3", "tag" = "v1.0.3", "git" = "https://github.com/lance-format/lance.git" }
|
||||
ahash = "0.8"
|
||||
# Note that this one does not include pyarrow
|
||||
arrow = { version = "56.2", optional = false }
|
||||
|
||||
4
nodejs/package-lock.json
generated
4
nodejs/package-lock.json
generated
@@ -1,12 +1,12 @@
|
||||
{
|
||||
"name": "@lancedb/lancedb",
|
||||
"version": "0.24.0",
|
||||
"version": "0.24.0-beta.0",
|
||||
"lockfileVersion": 3,
|
||||
"requires": true,
|
||||
"packages": {
|
||||
"": {
|
||||
"name": "@lancedb/lancedb",
|
||||
"version": "0.24.0",
|
||||
"version": "0.24.0-beta.0",
|
||||
"cpu": [
|
||||
"x64",
|
||||
"arm64"
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
[tool.bumpversion]
|
||||
current_version = "0.27.1"
|
||||
current_version = "0.27.0"
|
||||
parse = """(?x)
|
||||
(?P<major>0|[1-9]\\d*)\\.
|
||||
(?P<minor>0|[1-9]\\d*)\\.
|
||||
|
||||
@@ -1,13 +1,13 @@
|
||||
[package]
|
||||
name = "lancedb-python"
|
||||
version = "0.27.1"
|
||||
version = "0.27.0"
|
||||
edition.workspace = true
|
||||
description = "Python bindings for LanceDB"
|
||||
license.workspace = true
|
||||
repository.workspace = true
|
||||
keywords.workspace = true
|
||||
categories.workspace = true
|
||||
rust-version = "1.88.0"
|
||||
rust-version = "1.75.0"
|
||||
|
||||
[lib]
|
||||
name = "_lancedb"
|
||||
|
||||
@@ -892,10 +892,6 @@ pub struct ConnectBuilder {
|
||||
embedding_registry: Option<Arc<dyn EmbeddingRegistry>>,
|
||||
}
|
||||
|
||||
#[cfg(feature = "remote")]
|
||||
const ENV_VARS_TO_STORAGE_OPTS: [(&str, &str); 1] =
|
||||
[("AZURE_STORAGE_ACCOUNT_NAME", "azure_storage_account_name")];
|
||||
|
||||
impl ConnectBuilder {
|
||||
/// Create a new [`ConnectOptions`] with the given database URI.
|
||||
pub fn new(uri: &str) -> Self {
|
||||
@@ -1079,27 +1075,11 @@ impl ConnectBuilder {
|
||||
self
|
||||
}
|
||||
|
||||
#[cfg(feature = "remote")]
|
||||
fn apply_env_defaults(
|
||||
env_var_to_remote_storage_option: &[(&str, &str)],
|
||||
options: &mut HashMap<String, String>,
|
||||
) {
|
||||
for (env_key, opt_key) in env_var_to_remote_storage_option {
|
||||
if let Ok(env_value) = std::env::var(env_key) {
|
||||
if !options.contains_key(*opt_key) {
|
||||
options.insert((*opt_key).to_string(), env_value);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(feature = "remote")]
|
||||
fn execute_remote(self) -> Result<Connection> {
|
||||
use crate::remote::db::RemoteDatabaseOptions;
|
||||
|
||||
let mut merged_options = self.request.options.clone();
|
||||
Self::apply_env_defaults(&ENV_VARS_TO_STORAGE_OPTS, &mut merged_options);
|
||||
let options = RemoteDatabaseOptions::parse_from_map(&merged_options)?;
|
||||
let options = RemoteDatabaseOptions::parse_from_map(&self.request.options)?;
|
||||
|
||||
let region = options.region.ok_or_else(|| Error::InvalidInput {
|
||||
message: "A region is required when connecting to LanceDb Cloud".to_string(),
|
||||
@@ -1344,23 +1324,6 @@ mod tests {
|
||||
assert_eq!(tc.connection.uri(), tc.uri);
|
||||
}
|
||||
|
||||
#[cfg(feature = "remote")]
|
||||
#[test]
|
||||
fn test_apply_env_defaults() {
|
||||
let env_key = "TEST_APPLY_ENV_DEFAULTS_ENVIRONMENT_VARIABLE_ENV_KEY";
|
||||
let env_val = "TEST_APPLY_ENV_DEFAULTS_ENVIRONMENT_VARIABLE_ENV_VAL";
|
||||
let opts_key = "test_apply_env_defaults_environment_variable_opts_key";
|
||||
std::env::set_var(env_key, env_val);
|
||||
|
||||
let mut options = HashMap::new();
|
||||
ConnectBuilder::apply_env_defaults(&[(env_key, opts_key)], &mut options);
|
||||
assert_eq!(Some(&env_val.to_string()), options.get(opts_key));
|
||||
|
||||
options.insert(opts_key.to_string(), "EXPLICIT-VALUE".to_string());
|
||||
ConnectBuilder::apply_env_defaults(&[(env_key, opts_key)], &mut options);
|
||||
assert_eq!(Some(&"EXPLICIT-VALUE".to_string()), options.get(opts_key));
|
||||
}
|
||||
|
||||
#[cfg(not(windows))]
|
||||
#[tokio::test]
|
||||
async fn test_connect_relative() {
|
||||
|
||||
@@ -171,7 +171,7 @@ impl Shuffler {
|
||||
// This is kind of an annoying limitation but if we allow runt clumps from batches then
|
||||
// clumps will get unaligned and we will mess up the clumps when we do the in-memory
|
||||
// shuffle step. If this is a problem we can probably figure out a better way to do this.
|
||||
if !is_last && !(batch.num_rows() as u64).is_multiple_of(clump_size) {
|
||||
if !is_last && batch.num_rows() as u64 % clump_size != 0 {
|
||||
return Err(Error::Runtime {
|
||||
message: format!(
|
||||
"Expected batch size ({}) to be divisible by clump size ({})",
|
||||
|
||||
@@ -1,9 +1,12 @@
|
||||
// SPDX-License-Identifier: Apache-2.0
|
||||
// SPDX-FileCopyrightText: Copyright The LanceDB Authors
|
||||
|
||||
use std::sync::{
|
||||
atomic::{AtomicBool, AtomicU64, AtomicUsize, Ordering},
|
||||
Arc,
|
||||
use std::{
|
||||
iter,
|
||||
sync::{
|
||||
atomic::{AtomicBool, AtomicU64, AtomicUsize, Ordering},
|
||||
Arc,
|
||||
},
|
||||
};
|
||||
|
||||
use arrow_array::{Array, BooleanArray, RecordBatch, UInt64Array};
|
||||
@@ -155,7 +158,7 @@ impl Splitter {
|
||||
remaining_in_split
|
||||
};
|
||||
|
||||
split_ids.extend(std::iter::repeat_n(split_id as u64, rows_to_add as usize));
|
||||
split_ids.extend(iter::repeat(split_id as u64).take(rows_to_add as usize));
|
||||
if done {
|
||||
// Quit early if we've run out of splits
|
||||
break;
|
||||
@@ -659,7 +662,7 @@ mod tests {
|
||||
assert_eq!(split_batch.num_rows(), total_split_sizes as usize);
|
||||
let mut expected = Vec::with_capacity(total_split_sizes as usize);
|
||||
for (i, size) in expected_split_sizes.iter().enumerate() {
|
||||
expected.extend(std::iter::repeat_n(i as u64, *size as usize));
|
||||
expected.extend(iter::repeat(i as u64).take(*size as usize));
|
||||
}
|
||||
let expected = Arc::new(UInt64Array::from(expected)) as Arc<dyn Array>;
|
||||
|
||||
|
||||
@@ -297,10 +297,10 @@ impl IvfPqIndexBuilder {
|
||||
}
|
||||
|
||||
pub(crate) fn suggested_num_sub_vectors(dim: u32) -> u32 {
|
||||
if dim.is_multiple_of(16) {
|
||||
if dim % 16 == 0 {
|
||||
// Should be more aggressive than this default.
|
||||
dim / 16
|
||||
} else if dim.is_multiple_of(8) {
|
||||
} else if dim % 8 == 0 {
|
||||
dim / 8
|
||||
} else {
|
||||
log::warn!(
|
||||
|
||||
@@ -51,15 +51,17 @@
|
||||
//! - `s3://bucket/path/to/database` or `gs://bucket/path/to/database` - database on cloud object store
|
||||
//! - `db://dbname` - Lance Cloud
|
||||
//!
|
||||
//! You can also use [`ConnectBuilder`] to configure the connection to the database.
|
||||
//! You can also use [`ConnectOptions`] to configure the connection to the database.
|
||||
//!
|
||||
//! ```rust
|
||||
//! use object_store::aws::AwsCredential;
|
||||
//! # tokio::runtime::Runtime::new().unwrap().block_on(async {
|
||||
//! let db = lancedb::connect("data/sample-lancedb")
|
||||
//! .storage_options([
|
||||
//! ("aws_access_key_id", "some_key"),
|
||||
//! ("aws_secret_access_key", "some_secret"),
|
||||
//! ])
|
||||
//! .aws_creds(AwsCredential {
|
||||
//! key_id: "some_key".to_string(),
|
||||
//! secret_key: "some_secret".to_string(),
|
||||
//! token: None,
|
||||
//! })
|
||||
//! .execute()
|
||||
//! .await
|
||||
//! .unwrap();
|
||||
|
||||
@@ -2059,7 +2059,7 @@ impl NativeTable {
|
||||
return provided;
|
||||
}
|
||||
let suggested = suggested_num_sub_vectors(dim);
|
||||
if num_bits.is_some_and(|num_bits| num_bits == 4) && !suggested.is_multiple_of(2) {
|
||||
if num_bits.is_some_and(|num_bits| num_bits == 4) && suggested % 2 != 0 {
|
||||
// num_sub_vectors must be even when 4 bits are used
|
||||
suggested + 1
|
||||
} else {
|
||||
@@ -3400,6 +3400,7 @@ pub struct FragmentSummaryStats {
|
||||
#[cfg(test)]
|
||||
#[allow(deprecated)]
|
||||
mod tests {
|
||||
use std::iter;
|
||||
use std::sync::atomic::{AtomicBool, Ordering};
|
||||
use std::sync::Arc;
|
||||
use std::time::Duration;
|
||||
@@ -4016,7 +4017,7 @@ mod tests {
|
||||
schema.clone(),
|
||||
vec![
|
||||
Arc::new(Int32Array::from_iter_values(offset..(offset + 10))),
|
||||
Arc::new(Int32Array::from_iter_values(std::iter::repeat_n(age, 10))),
|
||||
Arc::new(Int32Array::from_iter_values(iter::repeat(age).take(10))),
|
||||
],
|
||||
)],
|
||||
schema,
|
||||
|
||||
@@ -4,6 +4,7 @@
|
||||
use std::{
|
||||
borrow::Cow,
|
||||
collections::{HashMap, HashSet},
|
||||
iter::repeat,
|
||||
sync::Arc,
|
||||
};
|
||||
|
||||
@@ -267,10 +268,9 @@ fn create_some_records() -> Result<impl IntoArrow> {
|
||||
schema.clone(),
|
||||
vec![
|
||||
Arc::new(Int32Array::from_iter_values(0..TOTAL as i32)),
|
||||
Arc::new(StringArray::from_iter(std::iter::repeat_n(
|
||||
Some("hello world".to_string()),
|
||||
TOTAL,
|
||||
))),
|
||||
Arc::new(StringArray::from_iter(
|
||||
repeat(Some("hello world".to_string())).take(TOTAL),
|
||||
)),
|
||||
],
|
||||
)
|
||||
.unwrap()]
|
||||
|
||||
Reference in New Issue
Block a user