chore: update lance dependency to v2.0.0-beta.2

feat: infer vector type to float32 if integers are out of uint8 range (#2856 )
## Summary - infer integer vector columns as float32 when any value exceeds uint8 range or is negative - keep uint8 for integer vectors within range and nulls only - add sync/async tests covering large integer vector inference ## Testing - ./.venv/bin/pytest python/python/tests/test_table.py -k "large_int_vectors"
2025-12-26 06:39:57 +00:00 · 2025-12-12 06:32:28 +00:00 · 2025-12-08 17:10:25 +08:00 · 2025-12-05 00:36:39 +00:00
23 changed files with 162 additions and 86 deletions
--- a/.bumpversion.toml
+++ b/.bumpversion.toml
@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.23.0-beta.0"
+current_version = "0.23.0-beta.1"
 parse = """(?x)
    (?P<major>0|[1-9]\\d*)\\.
    (?P<minor>0|[1-9]\\d*)\\.
--- a/Cargo.lock
+++ b/Cargo.lock
@@ -3086,8 +3086,8 @@ checksum = "42703706b716c37f96a77aea830392ad231f44c9e9a67872fa5548707e11b11c"

 [[package]]
 name = "fsst"
-version = "1.1.0-beta.1"
-source = "git+https://github.com/lance-format/lance.git?tag=v1.1.0-beta.1#ddea38f049e64df8b893e1c8ecca7878ea373d1e"
+version = "2.0.0-beta.2"
+source = "git+https://github.com/lance-format/lance.git?tag=v2.0.0-beta.2#92aa361099f42a40e9aa9f9915d041fe1dd30671"
 dependencies = [
 "arrow-array",
 "rand 0.9.2",
@@ -4422,8 +4422,8 @@ dependencies = [

 [[package]]
 name = "lance"
-version = "1.1.0-beta.1"
-source = "git+https://github.com/lance-format/lance.git?tag=v1.1.0-beta.1#ddea38f049e64df8b893e1c8ecca7878ea373d1e"
+version = "2.0.0-beta.2"
+source = "git+https://github.com/lance-format/lance.git?tag=v2.0.0-beta.2#92aa361099f42a40e9aa9f9915d041fe1dd30671"
 dependencies = [
 "arrow",
 "arrow-arith",
@@ -4488,13 +4488,14 @@ dependencies = [

 [[package]]
 name = "lance-arrow"
-version = "1.1.0-beta.1"
-source = "git+https://github.com/lance-format/lance.git?tag=v1.1.0-beta.1#ddea38f049e64df8b893e1c8ecca7878ea373d1e"
+version = "2.0.0-beta.2"
+source = "git+https://github.com/lance-format/lance.git?tag=v2.0.0-beta.2#92aa361099f42a40e9aa9f9915d041fe1dd30671"
 dependencies = [
 "arrow-array",
 "arrow-buffer",
 "arrow-cast",
 "arrow-data",
+ "arrow-ord",
 "arrow-schema",
 "arrow-select",
 "bytes",
@@ -4507,8 +4508,8 @@ dependencies = [

 [[package]]
 name = "lance-bitpacking"
-version = "1.1.0-beta.1"
-source = "git+https://github.com/lance-format/lance.git?tag=v1.1.0-beta.1#ddea38f049e64df8b893e1c8ecca7878ea373d1e"
+version = "2.0.0-beta.2"
+source = "git+https://github.com/lance-format/lance.git?tag=v2.0.0-beta.2#92aa361099f42a40e9aa9f9915d041fe1dd30671"
 dependencies = [
 "arrayref",
 "paste",
@@ -4517,8 +4518,8 @@ dependencies = [

 [[package]]
 name = "lance-core"
-version = "1.1.0-beta.1"
-source = "git+https://github.com/lance-format/lance.git?tag=v1.1.0-beta.1#ddea38f049e64df8b893e1c8ecca7878ea373d1e"
+version = "2.0.0-beta.2"
+source = "git+https://github.com/lance-format/lance.git?tag=v2.0.0-beta.2#92aa361099f42a40e9aa9f9915d041fe1dd30671"
 dependencies = [
 "arrow-array",
 "arrow-buffer",
@@ -4531,6 +4532,7 @@ dependencies = [
 "datafusion-sql",
 "deepsize",
 "futures",
+ "itertools 0.13.0",
 "lance-arrow",
 "libc",
 "log",
@@ -4554,8 +4556,8 @@ dependencies = [

 [[package]]
 name = "lance-datafusion"
-version = "1.1.0-beta.1"
-source = "git+https://github.com/lance-format/lance.git?tag=v1.1.0-beta.1#ddea38f049e64df8b893e1c8ecca7878ea373d1e"
+version = "2.0.0-beta.2"
+source = "git+https://github.com/lance-format/lance.git?tag=v2.0.0-beta.2#92aa361099f42a40e9aa9f9915d041fe1dd30671"
 dependencies = [
 "arrow",
 "arrow-array",
@@ -4585,8 +4587,8 @@ dependencies = [

 [[package]]
 name = "lance-datagen"
-version = "1.1.0-beta.1"
-source = "git+https://github.com/lance-format/lance.git?tag=v1.1.0-beta.1#ddea38f049e64df8b893e1c8ecca7878ea373d1e"
+version = "2.0.0-beta.2"
+source = "git+https://github.com/lance-format/lance.git?tag=v2.0.0-beta.2#92aa361099f42a40e9aa9f9915d041fe1dd30671"
 dependencies = [
 "arrow",
 "arrow-array",
@@ -4603,8 +4605,8 @@ dependencies = [

 [[package]]
 name = "lance-encoding"
-version = "1.1.0-beta.1"
-source = "git+https://github.com/lance-format/lance.git?tag=v1.1.0-beta.1#ddea38f049e64df8b893e1c8ecca7878ea373d1e"
+version = "2.0.0-beta.2"
+source = "git+https://github.com/lance-format/lance.git?tag=v2.0.0-beta.2#92aa361099f42a40e9aa9f9915d041fe1dd30671"
 dependencies = [
 "arrow-arith",
 "arrow-array",
@@ -4641,8 +4643,8 @@ dependencies = [

 [[package]]
 name = "lance-file"
-version = "1.1.0-beta.1"
-source = "git+https://github.com/lance-format/lance.git?tag=v1.1.0-beta.1#ddea38f049e64df8b893e1c8ecca7878ea373d1e"
+version = "2.0.0-beta.2"
+source = "git+https://github.com/lance-format/lance.git?tag=v2.0.0-beta.2#92aa361099f42a40e9aa9f9915d041fe1dd30671"
 dependencies = [
 "arrow-arith",
 "arrow-array",
@@ -4674,8 +4676,8 @@ dependencies = [

 [[package]]
 name = "lance-geo"
-version = "1.1.0-beta.1"
-source = "git+https://github.com/lance-format/lance.git?tag=v1.1.0-beta.1#ddea38f049e64df8b893e1c8ecca7878ea373d1e"
+version = "2.0.0-beta.2"
+source = "git+https://github.com/lance-format/lance.git?tag=v2.0.0-beta.2#92aa361099f42a40e9aa9f9915d041fe1dd30671"
 dependencies = [
 "datafusion",
 "geo-types",
@@ -4686,8 +4688,8 @@ dependencies = [

 [[package]]
 name = "lance-index"
-version = "1.1.0-beta.1"
-source = "git+https://github.com/lance-format/lance.git?tag=v1.1.0-beta.1#ddea38f049e64df8b893e1c8ecca7878ea373d1e"
+version = "2.0.0-beta.2"
+source = "git+https://github.com/lance-format/lance.git?tag=v2.0.0-beta.2#92aa361099f42a40e9aa9f9915d041fe1dd30671"
 dependencies = [
 "arrow",
 "arrow-arith",
@@ -4733,6 +4735,7 @@ dependencies = [
 "prost-types",
 "rand 0.9.2",
 "rand_distr 0.5.1",
+ "rangemap",
 "rayon",
 "roaring",
 "serde",
@@ -4748,8 +4751,8 @@ dependencies = [

 [[package]]
 name = "lance-io"
-version = "1.1.0-beta.1"
-source = "git+https://github.com/lance-format/lance.git?tag=v1.1.0-beta.1#ddea38f049e64df8b893e1c8ecca7878ea373d1e"
+version = "2.0.0-beta.2"
+source = "git+https://github.com/lance-format/lance.git?tag=v2.0.0-beta.2#92aa361099f42a40e9aa9f9915d041fe1dd30671"
 dependencies = [
 "arrow",
 "arrow-arith",
@@ -4789,8 +4792,8 @@ dependencies = [

 [[package]]
 name = "lance-linalg"
-version = "1.1.0-beta.1"
-source = "git+https://github.com/lance-format/lance.git?tag=v1.1.0-beta.1#ddea38f049e64df8b893e1c8ecca7878ea373d1e"
+version = "2.0.0-beta.2"
+source = "git+https://github.com/lance-format/lance.git?tag=v2.0.0-beta.2#92aa361099f42a40e9aa9f9915d041fe1dd30671"
 dependencies = [
 "arrow-array",
 "arrow-buffer",
@@ -4806,8 +4809,8 @@ dependencies = [

 [[package]]
 name = "lance-namespace"
-version = "1.1.0-beta.1"
-source = "git+https://github.com/lance-format/lance.git?tag=v1.1.0-beta.1#ddea38f049e64df8b893e1c8ecca7878ea373d1e"
+version = "2.0.0-beta.2"
+source = "git+https://github.com/lance-format/lance.git?tag=v2.0.0-beta.2#92aa361099f42a40e9aa9f9915d041fe1dd30671"
 dependencies = [
 "arrow",
 "async-trait",
@@ -4819,8 +4822,8 @@ dependencies = [

 [[package]]
 name = "lance-namespace-impls"
-version = "1.1.0-beta.1"
-source = "git+https://github.com/lance-format/lance.git?tag=v1.1.0-beta.1#ddea38f049e64df8b893e1c8ecca7878ea373d1e"
+version = "2.0.0-beta.2"
+source = "git+https://github.com/lance-format/lance.git?tag=v2.0.0-beta.2#92aa361099f42a40e9aa9f9915d041fe1dd30671"
 dependencies = [
 "arrow",
 "arrow-ipc",
@@ -4845,9 +4848,9 @@ dependencies = [

 [[package]]
 name = "lance-namespace-reqwest-client"
-version = "0.0.18"
+version = "0.3.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "3ea349999bcda4eea53fc05d334b3775ec314761e6a706555c777d7a29b18d19"
+checksum = "b748e89a3a0e5d9fb1b51e4382f783f8aa6b620d755012d4856180968014e619"
 dependencies = [
 "reqwest",
 "serde",
@@ -4858,8 +4861,8 @@ dependencies = [

 [[package]]
 name = "lance-table"
-version = "1.1.0-beta.1"
-source = "git+https://github.com/lance-format/lance.git?tag=v1.1.0-beta.1#ddea38f049e64df8b893e1c8ecca7878ea373d1e"
+version = "2.0.0-beta.2"
+source = "git+https://github.com/lance-format/lance.git?tag=v2.0.0-beta.2#92aa361099f42a40e9aa9f9915d041fe1dd30671"
 dependencies = [
 "arrow",
 "arrow-array",
@@ -4898,8 +4901,8 @@ dependencies = [

 [[package]]
 name = "lance-testing"
-version = "1.1.0-beta.1"
-source = "git+https://github.com/lance-format/lance.git?tag=v1.1.0-beta.1#ddea38f049e64df8b893e1c8ecca7878ea373d1e"
+version = "2.0.0-beta.2"
+source = "git+https://github.com/lance-format/lance.git?tag=v2.0.0-beta.2#92aa361099f42a40e9aa9f9915d041fe1dd30671"
 dependencies = [
 "arrow-array",
 "arrow-schema",
@@ -4910,7 +4913,7 @@ dependencies = [

 [[package]]
 name = "lancedb"
-version = "0.23.0-beta.0"
+version = "0.23.0-beta.1"
 dependencies = [
 "ahash",
 "anyhow",
@@ -4989,7 +4992,7 @@ dependencies = [

 [[package]]
 name = "lancedb-nodejs"
-version = "0.23.0-beta.0"
+version = "0.23.0-beta.1"
 dependencies = [
 "arrow-array",
 "arrow-ipc",
@@ -5009,7 +5012,7 @@ dependencies = [

 [[package]]
 name = "lancedb-python"
-version = "0.26.0-beta.0"
+version = "0.26.0-beta.1"
 dependencies = [
 "arrow",
 "async-trait",
--- a/Cargo.toml
+++ b/Cargo.toml
@@ -15,20 +15,20 @@ categories = ["database-implementations"]
 rust-version = "1.78.0"

 [workspace.dependencies]
-lance = { "version" = "=1.1.0-beta.1", default-features = false, "tag" = "v1.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-core = { "version" = "=1.1.0-beta.1", "tag" = "v1.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-datagen = { "version" = "=1.1.0-beta.1", "tag" = "v1.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-file = { "version" = "=1.1.0-beta.1", "tag" = "v1.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-io = { "version" = "=1.1.0-beta.1", default-features = false, "tag" = "v1.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-index = { "version" = "=1.1.0-beta.1", "tag" = "v1.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-linalg = { "version" = "=1.1.0-beta.1", "tag" = "v1.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-namespace = { "version" = "=1.1.0-beta.1", "tag" = "v1.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-namespace-impls = { "version" = "=1.1.0-beta.1", default-features = false, "tag" = "v1.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-table = { "version" = "=1.1.0-beta.1", "tag" = "v1.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-testing = { "version" = "=1.1.0-beta.1", "tag" = "v1.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-datafusion = { "version" = "=1.1.0-beta.1", "tag" = "v1.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-encoding = { "version" = "=1.1.0-beta.1", "tag" = "v1.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-arrow = { "version" = "=1.1.0-beta.1", "tag" = "v1.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
+lance = { "version" = "=2.0.0-beta.2", default-features = false, "tag" = "v2.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-core = { "version" = "=2.0.0-beta.2", "tag" = "v2.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-datagen = { "version" = "=2.0.0-beta.2", "tag" = "v2.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-file = { "version" = "=2.0.0-beta.2", "tag" = "v2.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-io = { "version" = "=2.0.0-beta.2", default-features = false, "tag" = "v2.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-index = { "version" = "=2.0.0-beta.2", "tag" = "v2.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-linalg = { "version" = "=2.0.0-beta.2", "tag" = "v2.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-namespace = { "version" = "=2.0.0-beta.2", "tag" = "v2.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-namespace-impls = { "version" = "=2.0.0-beta.2", default-features = false, "tag" = "v2.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-table = { "version" = "=2.0.0-beta.2", "tag" = "v2.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-testing = { "version" = "=2.0.0-beta.2", "tag" = "v2.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-datafusion = { "version" = "=2.0.0-beta.2", "tag" = "v2.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-encoding = { "version" = "=2.0.0-beta.2", "tag" = "v2.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-arrow = { "version" = "=2.0.0-beta.2", "tag" = "v2.0.0-beta.2", "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 }
--- a/docs/src/java/java.md
+++ b/docs/src/java/java.md
@@ -14,7 +14,7 @@ Add the following dependency to your `pom.xml`:
 <dependency>
    <groupId>com.lancedb</groupId>
    <artifactId>lancedb-core</artifactId>
-    <version>0.23.0-beta.0</version>
+    <version>0.23.0-beta.1</version>
 </dependency>
 ```

--- a/java/lancedb-core/pom.xml
+++ b/java/lancedb-core/pom.xml
@@ -8,7 +8,7 @@
    <parent>
      <groupId>com.lancedb</groupId>
      <artifactId>lancedb-parent</artifactId>
-      <version>0.23.0-beta.0</version>
+      <version>0.23.0-beta.1</version>
      <relativePath>../pom.xml</relativePath>
    </parent>

--- a/java/pom.xml
+++ b/java/pom.xml
@@ -6,7 +6,7 @@

    <groupId>com.lancedb</groupId>
    <artifactId>lancedb-parent</artifactId>
-    <version>0.23.0-beta.0</version>
+    <version>0.23.0-beta.1</version>
    <packaging>pom</packaging>
    <name>${project.artifactId}</name>
    <description>LanceDB Java SDK Parent POM</description>
--- a/nodejs/Cargo.toml
+++ b/nodejs/Cargo.toml
@@ -1,7 +1,7 @@
 [package]
 name = "lancedb-nodejs"
 edition.workspace = true
-version = "0.23.0-beta.0"
+version = "0.23.0-beta.1"
 license.workspace = true
 description.workspace = true
 repository.workspace = true
--- a/nodejs/npm/darwin-arm64/package.json
+++ b/nodejs/npm/darwin-arm64/package.json
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-darwin-arm64",
-	"version": "0.23.0-beta.0",
+	"version": "0.23.0-beta.1",
 	"os": ["darwin"],
 	"cpu": ["arm64"],
 	"main": "lancedb.darwin-arm64.node",
--- a/nodejs/npm/darwin-x64/package.json
+++ b/nodejs/npm/darwin-x64/package.json
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-darwin-x64",
-	"version": "0.23.0-beta.0",
+	"version": "0.23.0-beta.1",
 	"os": ["darwin"],
 	"cpu": ["x64"],
 	"main": "lancedb.darwin-x64.node",
--- a/nodejs/npm/linux-arm64-gnu/package.json
+++ b/nodejs/npm/linux-arm64-gnu/package.json
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-arm64-gnu",
-	"version": "0.23.0-beta.0",
+	"version": "0.23.0-beta.1",
 	"os": ["linux"],
 	"cpu": ["arm64"],
 	"main": "lancedb.linux-arm64-gnu.node",
--- a/nodejs/npm/linux-arm64-musl/package.json
+++ b/nodejs/npm/linux-arm64-musl/package.json
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-arm64-musl",
-	"version": "0.23.0-beta.0",
+	"version": "0.23.0-beta.1",
 	"os": ["linux"],
 	"cpu": ["arm64"],
 	"main": "lancedb.linux-arm64-musl.node",
--- a/nodejs/npm/linux-x64-gnu/package.json
+++ b/nodejs/npm/linux-x64-gnu/package.json
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-x64-gnu",
-	"version": "0.23.0-beta.0",
+	"version": "0.23.0-beta.1",
 	"os": ["linux"],
 	"cpu": ["x64"],
 	"main": "lancedb.linux-x64-gnu.node",
--- a/nodejs/npm/linux-x64-musl/package.json
+++ b/nodejs/npm/linux-x64-musl/package.json
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-x64-musl",
-	"version": "0.23.0-beta.0",
+	"version": "0.23.0-beta.1",
 	"os": ["linux"],
 	"cpu": ["x64"],
 	"main": "lancedb.linux-x64-musl.node",
--- a/nodejs/npm/win32-arm64-msvc/package.json
+++ b/nodejs/npm/win32-arm64-msvc/package.json
@@ -1,6 +1,6 @@
 {
  "name": "@lancedb/lancedb-win32-arm64-msvc",
-  "version": "0.23.0-beta.0",
+  "version": "0.23.0-beta.1",
  "os": [
    "win32"
  ],
--- a/nodejs/npm/win32-x64-msvc/package.json
+++ b/nodejs/npm/win32-x64-msvc/package.json
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-win32-x64-msvc",
-	"version": "0.23.0-beta.0",
+	"version": "0.23.0-beta.1",
 	"os": ["win32"],
 	"cpu": ["x64"],
 	"main": "lancedb.win32-x64-msvc.node",
--- a/nodejs/package-lock.json
+++ b/nodejs/package-lock.json
@@ -1,12 +1,12 @@
 {
  "name": "@lancedb/lancedb",
-  "version": "0.23.0-beta.0",
+  "version": "0.23.0-beta.1",
  "lockfileVersion": 3,
  "requires": true,
  "packages": {
    "": {
      "name": "@lancedb/lancedb",
-      "version": "0.23.0-beta.0",
+      "version": "0.23.0-beta.1",
      "cpu": [
        "x64",
        "arm64"
--- a/nodejs/package.json
+++ b/nodejs/package.json
@@ -11,7 +11,7 @@
    "ann"
  ],
  "private": false,
-  "version": "0.23.0-beta.0",
+  "version": "0.23.0-beta.1",
  "main": "dist/index.js",
  "exports": {
    ".": "./dist/index.js",
--- a/python/python/lancedb/table.py
+++ b/python/python/lancedb/table.py
@@ -3208,7 +3208,27 @@ def _infer_target_schema(
            if pa.types.is_floating(field.type.value_type):
                target_type = pa.list_(pa.float32(), dim)
            elif pa.types.is_integer(field.type.value_type):
-                target_type = pa.list_(pa.uint8(), dim)
+                values = peeked.column(i)
+
+                if isinstance(values, pa.ChunkedArray):
+                    values = values.combine_chunks()
+
+                flattened = values.flatten()
+                valid_count = pc.count(flattened, mode="only_valid").as_py()
+
+                if valid_count == 0:
+                    target_type = pa.list_(pa.uint8(), dim)
+                else:
+                    min_max = pc.min_max(flattened)
+                    min_value = min_max["min"].as_py()
+                    max_value = min_max["max"].as_py()
+
+                    if (min_value is not None and min_value < 0) or (
+                        max_value is not None and max_value > 255
+                    ):
+                        target_type = pa.list_(pa.float32(), dim)
+                    else:
+                        target_type = pa.list_(pa.uint8(), dim)
            else:
                continue  # Skip non-numeric types

--- a/python/python/tests/test_table.py
+++ b/python/python/tests/test_table.py
@@ -46,6 +46,39 @@ def test_basic(mem_db: DBConnection):
    assert table.to_arrow() == expected_data


+def test_create_table_infers_large_int_vectors(mem_db: DBConnection):
+    data = [{"vector": [0, 300]}]
+
+    table = mem_db.create_table(
+        "int_vector_overflow", data=data, mode="overwrite", exist_ok=True
+    )
+
+    vector_field = table.schema.field("vector")
+    assert vector_field.type == pa.list_(pa.float32(), 2)
+
+    vector_column = table.to_arrow().column("vector")
+    assert vector_column.type == pa.list_(pa.float32(), 2)
+    assert vector_column.to_pylist() == [[0.0, 300.0]]
+
+
+@pytest.mark.asyncio
+async def test_create_table_async_infers_large_int_vectors(
+    mem_db_async: AsyncConnection,
+):
+    data = [{"vector": [256, 257]}]
+
+    table = await mem_db_async.create_table(
+        "int_vector_overflow_async", data=data, mode="overwrite", exist_ok=True
+    )
+
+    schema = await table.schema()
+    assert schema.field("vector").type == pa.list_(pa.float32(), 2)
+
+    vector_column = (await table.to_arrow()).column("vector")
+    assert vector_column.type == pa.list_(pa.float32(), 2)
+    assert vector_column.to_pylist() == [[256.0, 257.0]]
+
+
 def test_input_data_type(mem_db: DBConnection, tmp_path):
    schema = pa.schema(
        {
--- a/python/src/connection.rs
+++ b/python/src/connection.rs
@@ -325,11 +325,11 @@ impl Connection {
        let inner = self_.get_inner()?.clone();
        let py = self_.py();
        future_into_py(py, async move {
-            use lance_namespace::models::{create_namespace_request, CreateNamespaceRequest};
+            use lance_namespace::models::CreateNamespaceRequest;
            let mode_enum = mode.and_then(|m| match m.to_lowercase().as_str() {
-                "create" => Some(create_namespace_request::Mode::Create),
-                "exist_ok" => Some(create_namespace_request::Mode::ExistOk),
-                "overwrite" => Some(create_namespace_request::Mode::Overwrite),
+                "create" => Some("Create".to_string()),
+                "exist_ok" => Some("ExistOk".to_string()),
+                "overwrite" => Some("Overwrite".to_string()),
                _ => None,
            });
            let request = CreateNamespaceRequest {
@@ -360,15 +360,15 @@ impl Connection {
        let inner = self_.get_inner()?.clone();
        let py = self_.py();
        future_into_py(py, async move {
-            use lance_namespace::models::{drop_namespace_request, DropNamespaceRequest};
+            use lance_namespace::models::DropNamespaceRequest;
            let mode_enum = mode.and_then(|m| match m.to_uppercase().as_str() {
-                "SKIP" => Some(drop_namespace_request::Mode::Skip),
-                "FAIL" => Some(drop_namespace_request::Mode::Fail),
+                "SKIP" => Some("Skip".to_string()),
+                "FAIL" => Some("Fail".to_string()),
                _ => None,
            });
            let behavior_enum = behavior.and_then(|b| match b.to_uppercase().as_str() {
-                "RESTRICT" => Some(drop_namespace_request::Behavior::Restrict),
-                "CASCADE" => Some(drop_namespace_request::Behavior::Cascade),
+                "RESTRICT" => Some("Restrict".to_string()),
+                "CASCADE" => Some("Cascade".to_string()),
                _ => None,
            });
            let request = DropNamespaceRequest {
--- a/rust/lancedb/Cargo.toml
+++ b/rust/lancedb/Cargo.toml
@@ -1,6 +1,6 @@
 [package]
 name = "lancedb"
-version = "0.23.0-beta.0"
+version = "0.23.0-beta.1"
 edition.workspace = true
 description = "LanceDB: A serverless, low-latency vector database for AI applications"
 license.workspace = true
--- a/rust/lancedb/src/database/namespace.rs
+++ b/rust/lancedb/src/database/namespace.rs
@@ -208,6 +208,7 @@ impl Database for LanceNamespaceDatabase {
        let describe_request = DescribeTableRequest {
            id: Some(table_id.clone()),
            version: None,
+            with_table_uri: Some(true),
        };

        let describe_result = self.namespace.describe_table(describe_request).await;
@@ -334,6 +335,7 @@ impl Database for LanceNamespaceDatabase {
        let describe_request = DescribeTableRequest {
            id: Some(table_id.clone()),
            version: None,
+            with_table_uri: Some(true),
        };
        let response = self
            .namespace
--- a/rust/lancedb/src/table.rs
+++ b/rust/lancedb/src/table.rs
@@ -41,8 +41,8 @@ use lance_index::vector::sq::builder::SQBuildParams;
 use lance_index::DatasetIndexExt;
 use lance_index::IndexType;
 use lance_namespace::models::{
-    QueryTableRequest as NsQueryTableRequest, QueryTableRequestFullTextQuery,
-    QueryTableRequestVector, StringFtsQuery,
+    QueryTableRequest as NsQueryTableRequest, QueryTableRequestColumns,
+    QueryTableRequestFullTextQuery, QueryTableRequestVector, StringFtsQuery,
 };
 use lance_namespace::LanceNamespace;
 use lance_table::format::Manifest;
@@ -2152,7 +2152,10 @@ impl NativeTable {
                // Convert select to columns list
                let columns = match &vq.base.select {
                    Select::All => None,
-                    Select::Columns(cols) => Some(cols.clone()),
+                    Select::Columns(cols) => Some(Box::new(QueryTableRequestColumns {
+                        column_names: Some(cols.clone()),
+                        column_aliases: None,
+                    })),
                    Select::Dynamic(_) => {
                        return Err(Error::NotSupported {
                            message:
@@ -2225,7 +2228,10 @@ impl NativeTable {

                let columns = match &q.select {
                    Select::All => None,
-                    Select::Columns(cols) => Some(cols.clone()),
+                    Select::Columns(cols) => Some(Box::new(QueryTableRequestColumns {
+                        column_names: Some(cols.clone()),
+                        column_aliases: None,
+                    })),
                    Select::Dynamic(_) => {
                        return Err(Error::NotSupported {
                            message: "Dynamic columns are not supported for server-side query"
@@ -4950,7 +4956,13 @@ mod tests {
        assert_eq!(ns_request.k, 10);
        assert_eq!(ns_request.offset, Some(5));
        assert_eq!(ns_request.filter, Some("id > 0".to_string()));
-        assert_eq!(ns_request.columns, Some(vec!["id".to_string()]));
+        assert_eq!(
+            ns_request.columns,
+            Some(Box::new(QueryTableRequestColumns {
+                column_names: Some(vec!["id".to_string()]),
+                column_aliases: None,
+            }))
+        );
        assert_eq!(ns_request.vector_column, Some("vector".to_string()));
        assert_eq!(ns_request.distance_type, Some("l2".to_string()));
        assert!(ns_request.vector.single_vector.is_some());
@@ -4991,7 +5003,13 @@ mod tests {
        assert_eq!(ns_request.k, 20);
        assert_eq!(ns_request.offset, Some(5));
        assert_eq!(ns_request.filter, Some("id > 5".to_string()));
-        assert_eq!(ns_request.columns, Some(vec!["id".to_string()]));
+        assert_eq!(
+            ns_request.columns,
+            Some(Box::new(QueryTableRequestColumns {
+                column_names: Some(vec!["id".to_string()]),
+                column_aliases: None,
+            }))
+        );
        assert_eq!(ns_request.with_row_id, Some(true));
        assert_eq!(ns_request.bypass_vector_index, Some(true));
        assert!(ns_request.vector_column.is_none()); // No vector column for plain queries
Author	SHA1	Message	Date
lancedb automation	ed30ad93f6	chore: update lance dependency to v2.0.0-beta.2	2025-12-12 06:32:28 +00:00
BubbleCal	39a18baf59	feat: infer vector type to float32 if integers are out of uint8 range (#2856 ) ## Summary - infer integer vector columns as float32 when any value exceeds uint8 range or is negative - keep uint8 for integer vectors within range and nulls only - add sync/async tests covering large integer vector inference ## Testing - ./.venv/bin/pytest python/python/tests/test_table.py -k "large_int_vectors"	2025-12-08 17:10:25 +08:00
Lance Release	0960e19559	Bump version: 0.23.0-beta.0 → 0.23.0-beta.1	2025-12-05 00:36:39 +00:00