style(python): format permutation pickle tests

feat(python): support pickling permutations
Track permutation reopen metadata
2026-04-09 09:20:40 +00:00 · 2026-04-09 14:47:06 +08:00 · 2026-04-09 00:32:48 +08:00 · 2026-04-08 17:34:05 +08:00 · 2026-04-06 11:20:10 -07:00 · 2026-04-05 02:51:18 +00:00
39 changed files with 864 additions and 99 deletions
--- a/.bumpversion.toml
+++ b/.bumpversion.toml
@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.27.2"
+current_version = "0.28.0-beta.1"
 parse = """(?x)
    (?P<major>0|[1-9]\\d*)\\.
    (?P<minor>0|[1-9]\\d*)\\.
--- a/Cargo.lock
+++ b/Cargo.lock
@@ -3072,8 +3072,8 @@ checksum = "42703706b716c37f96a77aea830392ad231f44c9e9a67872fa5548707e11b11c"

 [[package]]
 name = "fsst"
-version = "5.0.0-beta.4"
-source = "git+https://github.com/lance-format/lance.git?tag=v5.0.0-beta.4#d9068e76a301df9e21d7282419f24f61a11375ac"
+version = "5.0.0-beta.5"
+source = "git+https://github.com/lance-format/lance.git?tag=v5.0.0-beta.5#d630106da5a238b3adfb8c5dea3b3921f3519945"
 dependencies = [
 "arrow-array",
 "rand 0.9.2",
@@ -4134,8 +4134,8 @@ dependencies = [

 [[package]]
 name = "lance"
-version = "5.0.0-beta.4"
-source = "git+https://github.com/lance-format/lance.git?tag=v5.0.0-beta.4#d9068e76a301df9e21d7282419f24f61a11375ac"
+version = "5.0.0-beta.5"
+source = "git+https://github.com/lance-format/lance.git?tag=v5.0.0-beta.5#d630106da5a238b3adfb8c5dea3b3921f3519945"
 dependencies = [
 "arrow",
 "arrow-arith",
@@ -4201,8 +4201,8 @@ dependencies = [

 [[package]]
 name = "lance-arrow"
-version = "5.0.0-beta.4"
-source = "git+https://github.com/lance-format/lance.git?tag=v5.0.0-beta.4#d9068e76a301df9e21d7282419f24f61a11375ac"
+version = "5.0.0-beta.5"
+source = "git+https://github.com/lance-format/lance.git?tag=v5.0.0-beta.5#d630106da5a238b3adfb8c5dea3b3921f3519945"
 dependencies = [
 "arrow-array",
 "arrow-buffer",
@@ -4222,8 +4222,8 @@ dependencies = [

 [[package]]
 name = "lance-bitpacking"
-version = "5.0.0-beta.4"
-source = "git+https://github.com/lance-format/lance.git?tag=v5.0.0-beta.4#d9068e76a301df9e21d7282419f24f61a11375ac"
+version = "5.0.0-beta.5"
+source = "git+https://github.com/lance-format/lance.git?tag=v5.0.0-beta.5#d630106da5a238b3adfb8c5dea3b3921f3519945"
 dependencies = [
 "arrayref",
 "paste",
@@ -4232,8 +4232,8 @@ dependencies = [

 [[package]]
 name = "lance-core"
-version = "5.0.0-beta.4"
-source = "git+https://github.com/lance-format/lance.git?tag=v5.0.0-beta.4#d9068e76a301df9e21d7282419f24f61a11375ac"
+version = "5.0.0-beta.5"
+source = "git+https://github.com/lance-format/lance.git?tag=v5.0.0-beta.5#d630106da5a238b3adfb8c5dea3b3921f3519945"
 dependencies = [
 "arrow-array",
 "arrow-buffer",
@@ -4270,8 +4270,8 @@ dependencies = [

 [[package]]
 name = "lance-datafusion"
-version = "5.0.0-beta.4"
-source = "git+https://github.com/lance-format/lance.git?tag=v5.0.0-beta.4#d9068e76a301df9e21d7282419f24f61a11375ac"
+version = "5.0.0-beta.5"
+source = "git+https://github.com/lance-format/lance.git?tag=v5.0.0-beta.5#d630106da5a238b3adfb8c5dea3b3921f3519945"
 dependencies = [
 "arrow",
 "arrow-array",
@@ -4301,8 +4301,8 @@ dependencies = [

 [[package]]
 name = "lance-datagen"
-version = "5.0.0-beta.4"
-source = "git+https://github.com/lance-format/lance.git?tag=v5.0.0-beta.4#d9068e76a301df9e21d7282419f24f61a11375ac"
+version = "5.0.0-beta.5"
+source = "git+https://github.com/lance-format/lance.git?tag=v5.0.0-beta.5#d630106da5a238b3adfb8c5dea3b3921f3519945"
 dependencies = [
 "arrow",
 "arrow-array",
@@ -4320,8 +4320,8 @@ dependencies = [

 [[package]]
 name = "lance-encoding"
-version = "5.0.0-beta.4"
-source = "git+https://github.com/lance-format/lance.git?tag=v5.0.0-beta.4#d9068e76a301df9e21d7282419f24f61a11375ac"
+version = "5.0.0-beta.5"
+source = "git+https://github.com/lance-format/lance.git?tag=v5.0.0-beta.5#d630106da5a238b3adfb8c5dea3b3921f3519945"
 dependencies = [
 "arrow-arith",
 "arrow-array",
@@ -4358,8 +4358,8 @@ dependencies = [

 [[package]]
 name = "lance-file"
-version = "5.0.0-beta.4"
-source = "git+https://github.com/lance-format/lance.git?tag=v5.0.0-beta.4#d9068e76a301df9e21d7282419f24f61a11375ac"
+version = "5.0.0-beta.5"
+source = "git+https://github.com/lance-format/lance.git?tag=v5.0.0-beta.5#d630106da5a238b3adfb8c5dea3b3921f3519945"
 dependencies = [
 "arrow-arith",
 "arrow-array",
@@ -4391,8 +4391,8 @@ dependencies = [

 [[package]]
 name = "lance-index"
-version = "5.0.0-beta.4"
-source = "git+https://github.com/lance-format/lance.git?tag=v5.0.0-beta.4#d9068e76a301df9e21d7282419f24f61a11375ac"
+version = "5.0.0-beta.5"
+source = "git+https://github.com/lance-format/lance.git?tag=v5.0.0-beta.5#d630106da5a238b3adfb8c5dea3b3921f3519945"
 dependencies = [
 "arrow",
 "arrow-arith",
@@ -4456,8 +4456,8 @@ dependencies = [

 [[package]]
 name = "lance-io"
-version = "5.0.0-beta.4"
-source = "git+https://github.com/lance-format/lance.git?tag=v5.0.0-beta.4#d9068e76a301df9e21d7282419f24f61a11375ac"
+version = "5.0.0-beta.5"
+source = "git+https://github.com/lance-format/lance.git?tag=v5.0.0-beta.5#d630106da5a238b3adfb8c5dea3b3921f3519945"
 dependencies = [
 "arrow",
 "arrow-arith",
@@ -4501,8 +4501,8 @@ dependencies = [

 [[package]]
 name = "lance-linalg"
-version = "5.0.0-beta.4"
-source = "git+https://github.com/lance-format/lance.git?tag=v5.0.0-beta.4#d9068e76a301df9e21d7282419f24f61a11375ac"
+version = "5.0.0-beta.5"
+source = "git+https://github.com/lance-format/lance.git?tag=v5.0.0-beta.5#d630106da5a238b3adfb8c5dea3b3921f3519945"
 dependencies = [
 "arrow-array",
 "arrow-buffer",
@@ -4518,8 +4518,8 @@ dependencies = [

 [[package]]
 name = "lance-namespace"
-version = "5.0.0-beta.4"
-source = "git+https://github.com/lance-format/lance.git?tag=v5.0.0-beta.4#d9068e76a301df9e21d7282419f24f61a11375ac"
+version = "5.0.0-beta.5"
+source = "git+https://github.com/lance-format/lance.git?tag=v5.0.0-beta.5#d630106da5a238b3adfb8c5dea3b3921f3519945"
 dependencies = [
 "arrow",
 "async-trait",
@@ -4532,8 +4532,8 @@ dependencies = [

 [[package]]
 name = "lance-namespace-impls"
-version = "5.0.0-beta.4"
-source = "git+https://github.com/lance-format/lance.git?tag=v5.0.0-beta.4#d9068e76a301df9e21d7282419f24f61a11375ac"
+version = "5.0.0-beta.5"
+source = "git+https://github.com/lance-format/lance.git?tag=v5.0.0-beta.5#d630106da5a238b3adfb8c5dea3b3921f3519945"
 dependencies = [
 "arrow",
 "arrow-ipc",
@@ -4578,8 +4578,8 @@ dependencies = [

 [[package]]
 name = "lance-table"
-version = "5.0.0-beta.4"
-source = "git+https://github.com/lance-format/lance.git?tag=v5.0.0-beta.4#d9068e76a301df9e21d7282419f24f61a11375ac"
+version = "5.0.0-beta.5"
+source = "git+https://github.com/lance-format/lance.git?tag=v5.0.0-beta.5#d630106da5a238b3adfb8c5dea3b3921f3519945"
 dependencies = [
 "arrow",
 "arrow-array",
@@ -4618,8 +4618,8 @@ dependencies = [

 [[package]]
 name = "lance-testing"
-version = "5.0.0-beta.4"
-source = "git+https://github.com/lance-format/lance.git?tag=v5.0.0-beta.4#d9068e76a301df9e21d7282419f24f61a11375ac"
+version = "5.0.0-beta.5"
+source = "git+https://github.com/lance-format/lance.git?tag=v5.0.0-beta.5#d630106da5a238b3adfb8c5dea3b3921f3519945"
 dependencies = [
 "arrow-array",
 "arrow-schema",
@@ -4630,7 +4630,7 @@ dependencies = [

 [[package]]
 name = "lancedb"
-version = "0.27.2"
+version = "0.28.0-beta.1"
 dependencies = [
 "ahash",
 "anyhow",
@@ -4712,7 +4712,7 @@ dependencies = [

 [[package]]
 name = "lancedb-nodejs"
-version = "0.27.2"
+version = "0.28.0-beta.1"
 dependencies = [
 "arrow-array",
 "arrow-buffer",
@@ -4734,7 +4734,7 @@ dependencies = [

 [[package]]
 name = "lancedb-python"
-version = "0.30.2"
+version = "0.31.0-beta.1"
 dependencies = [
 "arrow",
 "async-trait",
--- a/Cargo.toml
+++ b/Cargo.toml
@@ -15,20 +15,20 @@ categories = ["database-implementations"]
 rust-version = "1.91.0"

 [workspace.dependencies]
-lance = { "version" = "=5.0.0-beta.4", default-features = false, "tag" = "v5.0.0-beta.4", "git" = "https://github.com/lance-format/lance.git" }
-lance-core = { "version" = "=5.0.0-beta.4", "tag" = "v5.0.0-beta.4", "git" = "https://github.com/lance-format/lance.git" }
-lance-datagen = { "version" = "=5.0.0-beta.4", "tag" = "v5.0.0-beta.4", "git" = "https://github.com/lance-format/lance.git" }
-lance-file = { "version" = "=5.0.0-beta.4", "tag" = "v5.0.0-beta.4", "git" = "https://github.com/lance-format/lance.git" }
-lance-io = { "version" = "=5.0.0-beta.4", default-features = false, "tag" = "v5.0.0-beta.4", "git" = "https://github.com/lance-format/lance.git" }
-lance-index = { "version" = "=5.0.0-beta.4", "tag" = "v5.0.0-beta.4", "git" = "https://github.com/lance-format/lance.git" }
-lance-linalg = { "version" = "=5.0.0-beta.4", "tag" = "v5.0.0-beta.4", "git" = "https://github.com/lance-format/lance.git" }
-lance-namespace = { "version" = "=5.0.0-beta.4", "tag" = "v5.0.0-beta.4", "git" = "https://github.com/lance-format/lance.git" }
-lance-namespace-impls = { "version" = "=5.0.0-beta.4", default-features = false, "tag" = "v5.0.0-beta.4", "git" = "https://github.com/lance-format/lance.git" }
-lance-table = { "version" = "=5.0.0-beta.4", "tag" = "v5.0.0-beta.4", "git" = "https://github.com/lance-format/lance.git" }
-lance-testing = { "version" = "=5.0.0-beta.4", "tag" = "v5.0.0-beta.4", "git" = "https://github.com/lance-format/lance.git" }
-lance-datafusion = { "version" = "=5.0.0-beta.4", "tag" = "v5.0.0-beta.4", "git" = "https://github.com/lance-format/lance.git" }
-lance-encoding = { "version" = "=5.0.0-beta.4", "tag" = "v5.0.0-beta.4", "git" = "https://github.com/lance-format/lance.git" }
-lance-arrow = { "version" = "=5.0.0-beta.4", "tag" = "v5.0.0-beta.4", "git" = "https://github.com/lance-format/lance.git" }
+lance = { "version" = "=5.0.0-beta.5", default-features = false, "tag" = "v5.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
+lance-core = { "version" = "=5.0.0-beta.5", "tag" = "v5.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
+lance-datagen = { "version" = "=5.0.0-beta.5", "tag" = "v5.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
+lance-file = { "version" = "=5.0.0-beta.5", "tag" = "v5.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
+lance-io = { "version" = "=5.0.0-beta.5", default-features = false, "tag" = "v5.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
+lance-index = { "version" = "=5.0.0-beta.5", "tag" = "v5.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
+lance-linalg = { "version" = "=5.0.0-beta.5", "tag" = "v5.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
+lance-namespace = { "version" = "=5.0.0-beta.5", "tag" = "v5.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
+lance-namespace-impls = { "version" = "=5.0.0-beta.5", default-features = false, "tag" = "v5.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
+lance-table = { "version" = "=5.0.0-beta.5", "tag" = "v5.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
+lance-testing = { "version" = "=5.0.0-beta.5", "tag" = "v5.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
+lance-datafusion = { "version" = "=5.0.0-beta.5", "tag" = "v5.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
+lance-encoding = { "version" = "=5.0.0-beta.5", "tag" = "v5.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
+lance-arrow = { "version" = "=5.0.0-beta.5", "tag" = "v5.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
 ahash = "0.8"
 # Note that this one does not include pyarrow
 arrow = { version = "57.2", 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>0.27.2</version>
+    <version>0.28.0-beta.1</version>
 </dependency>
 ```

--- a/docs/src/js/interfaces/ClientConfig.md
+++ b/docs/src/js/interfaces/ClientConfig.md
@@ -53,3 +53,18 @@ optional tlsConfig: TlsConfig;
 ```ts
 optional userAgent: string;
 ```
+
+***
+
+### userId?
+
+```ts
+optional userId: string;
+```
+
+User identifier for tracking purposes.
+
+This is sent as the `x-lancedb-user-id` header in requests to LanceDB Cloud/Enterprise.
+It can be set directly, or via the `LANCEDB_USER_ID` environment variable.
+Alternatively, set `LANCEDB_USER_ID_ENV_KEY` to specify another environment
+variable that contains the user ID value.
--- 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>0.27.2-final.0</version>
+      <version>0.28.0-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>0.27.2-final.0</version>
+    <version>0.28.0-beta.1</version>
    <packaging>pom</packaging>
    <name>${project.artifactId}</name>
    <description>LanceDB Java SDK Parent POM</description>
@@ -28,7 +28,7 @@
    <properties>
        <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
        <arrow.version>15.0.0</arrow.version>
-        <lance-core.version>5.0.0-beta.4</lance-core.version>
+        <lance-core.version>5.0.0-beta.5</lance-core.version>
        <spotless.skip>false</spotless.skip>
        <spotless.version>2.30.0</spotless.version>
        <spotless.java.googlejavaformat.version>1.7</spotless.java.googlejavaformat.version>
--- a/nodejs/Cargo.toml
+++ b/nodejs/Cargo.toml
@@ -1,7 +1,7 @@
 [package]
 name = "lancedb-nodejs"
 edition.workspace = true
-version = "0.27.2"
+version = "0.28.0-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": "0.27.2",
+	"version": "0.28.0-beta.1",
 	"os": ["darwin"],
 	"cpu": ["arm64"],
 	"main": "lancedb.darwin-arm64.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": "0.27.2",
+	"version": "0.28.0-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": "0.27.2",
+	"version": "0.28.0-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": "0.27.2",
+	"version": "0.28.0-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": "0.27.2",
+	"version": "0.28.0-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": "0.27.2",
+  "version": "0.28.0-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": "0.27.2",
+	"version": "0.28.0-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": "0.27.2",
+  "version": "0.28.0-beta.1",
  "lockfileVersion": 3,
  "requires": true,
  "packages": {
    "": {
      "name": "@lancedb/lancedb",
-      "version": "0.27.2",
+      "version": "0.28.0-beta.1",
      "cpu": [
        "x64",
        "arm64"
--- a/nodejs/package.json
+++ b/nodejs/package.json
@@ -11,7 +11,7 @@
    "ann"
  ],
  "private": false,
-  "version": "0.27.2",
+  "version": "0.28.0-beta.1",
  "main": "dist/index.js",
  "exports": {
    ".": "./dist/index.js",
--- a/nodejs/src/remote.rs
+++ b/nodejs/src/remote.rs
@@ -92,6 +92,13 @@ pub struct ClientConfig {
    pub extra_headers: Option<HashMap<String, String>>,
    pub id_delimiter: Option<String>,
    pub tls_config: Option<TlsConfig>,
+    /// User identifier for tracking purposes.
+    ///
+    /// This is sent as the `x-lancedb-user-id` header in requests to LanceDB Cloud/Enterprise.
+    /// It can be set directly, or via the `LANCEDB_USER_ID` environment variable.
+    /// Alternatively, set `LANCEDB_USER_ID_ENV_KEY` to specify another environment
+    /// variable that contains the user ID value.
+    pub user_id: Option<String>,
 }

 impl From<TimeoutConfig> for lancedb::remote::TimeoutConfig {
@@ -145,6 +152,7 @@ impl From<ClientConfig> for lancedb::remote::ClientConfig {
            id_delimiter: config.id_delimiter,
            tls_config: config.tls_config.map(Into::into),
            header_provider: None, // the header provider is set separately later
+            user_id: config.user_id,
        }
    }
 }
--- a/python/.bumpversion.toml
+++ b/python/.bumpversion.toml
@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.31.0-beta.0"
+current_version = "0.31.0-beta.1"
 parse = """(?x)
    (?P<major>0|[1-9]\\d*)\\.
    (?P<minor>0|[1-9]\\d*)\\.
--- a/python/Cargo.toml
+++ b/python/Cargo.toml
@@ -1,6 +1,6 @@
 [package]
 name = "lancedb-python"
-version = "0.31.0-beta.0"
+version = "0.31.0-beta.1"
 edition.workspace = true
 description = "Python bindings for LanceDB"
 license.workspace = true
--- a/python/pyproject.toml
+++ b/python/pyproject.toml
@@ -45,7 +45,7 @@ repository = "https://github.com/lancedb/lancedb"

 [project.optional-dependencies]
 pylance = [
-    "pylance>=5.0.0b3",
+    "pylance>=5.0.0b5",
 ]
 tests = [
    "aiohttp>=3.9.0",
@@ -59,7 +59,7 @@ tests = [
    "polars>=0.19, <=1.3.0",
    "tantivy>=0.20.0",
    "pyarrow-stubs>=16.0",
-    "pylance>=5.0.0b3",
+    "pylance>=5.0.0b5",
    "requests>=2.31.0",
    "datafusion>=52,<53",
 ]
--- a/python/python/lancedb/_lancedb.pyi
+++ b/python/python/lancedb/_lancedb.pyi
@@ -151,6 +151,9 @@ class Connection(object):
    async def drop_all_tables(
        self, namespace_path: Optional[List[str]] = None
    ) -> None: ...
+    async def namespace_client_config(
+        self,
+    ) -> Dict[str, Any]: ...

 class Table:
    def name(self) -> str: ...
--- a/python/python/lancedb/db.py
+++ b/python/python/lancedb/db.py
@@ -23,11 +23,13 @@ from lancedb.embeddings.registry import EmbeddingFunctionRegistry
 from lancedb.common import data_to_reader, sanitize_uri, validate_schema
 from lancedb.background_loop import LOOP
 from lance_namespace import (
+    LanceNamespace,
    ListNamespacesResponse,
    CreateNamespaceResponse,
    DropNamespaceResponse,
    DescribeNamespaceResponse,
    ListTablesResponse,
+    connect as namespace_connect,
 )

 from . import __version__
@@ -507,6 +509,26 @@ class DBConnection(EnforceOverrides):
    def uri(self) -> str:
        return self._uri

+    def namespace_client(self) -> LanceNamespace:
+        """Get the equivalent namespace client for this connection.
+
+        For native storage connections, this returns a DirectoryNamespace
+        pointing to the same root with the same storage options.
+
+        For namespace connections, this returns the backing namespace client.
+
+        For enterprise (remote) connections, this returns a RestNamespace
+        with the same URI and authentication headers.
+
+        Returns
+        -------
+        LanceNamespace
+            The namespace client for this connection.
+        """
+        raise NotImplementedError(
+            "namespace_client is not supported for this connection type"
+        )
+

 class LanceDBConnection(DBConnection):
    """
@@ -1044,6 +1066,20 @@ class LanceDBConnection(DBConnection):
            )
        )

+    @override
+    def namespace_client(self) -> LanceNamespace:
+        """Get the equivalent namespace client for this connection.
+
+        Returns a DirectoryNamespace pointing to the same root with the
+        same storage options.
+
+        Returns
+        -------
+        LanceNamespace
+            The namespace client for this connection.
+        """
+        return LOOP.run(self._conn.namespace_client())
+
    @deprecation.deprecated(
        deprecated_in="0.15.1",
        removed_in="0.17",
@@ -1716,6 +1752,25 @@ class AsyncConnection(object):
            namespace_path = []
        await self._inner.drop_all_tables(namespace_path=namespace_path)

+    async def namespace_client(self) -> LanceNamespace:
+        """Get the equivalent namespace client for this connection.
+
+        For native storage connections, this returns a DirectoryNamespace
+        pointing to the same root with the same storage options.
+
+        For namespace connections, this returns the backing namespace client.
+
+        For enterprise (remote) connections, this returns a RestNamespace
+        with the same URI and authentication headers.
+
+        Returns
+        -------
+        LanceNamespace
+            The namespace client for this connection.
+        """
+        config = await self._inner.namespace_client_config()
+        return namespace_connect(config["impl"], config["properties"])
+
    @deprecation.deprecated(
        deprecated_in="0.15.1",
        removed_in="0.17",
--- a/python/python/lancedb/namespace.py
+++ b/python/python/lancedb/namespace.py
@@ -890,6 +890,20 @@ class LanceNamespaceDBConnection(DBConnection):
            pushdown_operations=self._pushdown_operations,
        )

+    @override
+    def namespace_client(self) -> LanceNamespace:
+        """Get the namespace client for this connection.
+
+        For namespace connections, this returns the backing namespace client
+        that was provided during construction.
+
+        Returns
+        -------
+        LanceNamespace
+            The namespace client for this connection.
+        """
+        return self._namespace_client
+

 class AsyncLanceNamespaceDBConnection:
    """
@@ -1387,6 +1401,19 @@ class AsyncLanceNamespaceDBConnection:
            page_token=response.page_token,
        )

+    async def namespace_client(self) -> LanceNamespace:
+        """Get the namespace client for this connection.
+
+        For namespace connections, this returns the backing namespace client
+        that was provided during construction.
+
+        Returns
+        -------
+        LanceNamespace
+            The namespace client for this connection.
+        """
+        return self._namespace_client
+

 def connect_namespace(
    namespace_client_impl: str,
--- a/python/python/lancedb/permutation.py
+++ b/python/python/lancedb/permutation.py
@@ -1,21 +1,98 @@
 # SPDX-License-Identifier: Apache-2.0
 # SPDX-FileCopyrightText: Copyright The LanceDB Authors

+import json
+import pickle
+from datetime import timedelta
+from typing import Any, Callable, Iterator, Literal, Optional, TYPE_CHECKING, Union
+
+import pyarrow as pa
 from deprecation import deprecated
 from lancedb import AsyncConnection, DBConnection
-import pyarrow as pa
-import json

 from ._lancedb import async_permutation_builder, PermutationReader
-from .table import LanceTable
 from .background_loop import LOOP
+from .table import LanceTable
 from .util import batch_to_tensor, batch_to_tensor_rows
-from typing import Any, Callable, Iterator, Literal, Optional, TYPE_CHECKING, Union

 if TYPE_CHECKING:
    from lancedb.dependencies import pandas as pd, numpy as np, polars as pl


+def _builtin_transform(format: str) -> Callable[[pa.RecordBatch], Any]:
+    if format == "python":
+        return Transforms.arrow2python
+    if format == "python_col":
+        return Transforms.arrow2pythoncol
+    if format == "numpy":
+        return Transforms.arrow2numpy
+    if format == "pandas":
+        return Transforms.arrow2pandas
+    if format == "arrow":
+        return Transforms.arrow2arrow
+    if format == "torch":
+        return batch_to_tensor_rows
+    if format == "torch_col":
+        return batch_to_tensor
+    if format == "polars":
+        return Transforms.arrow2polars()
+    raise ValueError(f"Invalid format: {format}")
+
+
+def _table_to_state(
+    table: Union[LanceTable, dict[str, Any]],
+) -> dict[str, Any]:
+    if isinstance(table, dict):
+        return table
+    if not isinstance(table, LanceTable):
+        raise pickle.PicklingError(
+            "Permutation pickling only supports LanceTable-backed permutations"
+        )
+    if table._namespace_client is not None:
+        raise pickle.PicklingError(
+            "Permutation pickling does not yet support namespace-backed tables"
+        )
+    if table._conn.uri.startswith("memory://"):
+        raise pickle.PicklingError(
+            "Permutation pickling does not support in-memory databases"
+        )
+
+    try:
+        read_consistency_interval = table._conn.read_consistency_interval
+    except Exception:
+        read_consistency_interval = None
+    return {
+        "uri": table._conn.uri,
+        "name": table.name,
+        "version": table.version,
+        "storage_options": table.initial_storage_options(),
+        "read_consistency_interval_secs": (
+            read_consistency_interval.total_seconds()
+            if read_consistency_interval is not None
+            else None
+        ),
+        "namespace_path": list(table.namespace),
+    }
+
+
+def _table_from_state(state: dict[str, Any]) -> LanceTable:
+    from . import connect
+
+    read_consistency_interval = (
+        timedelta(seconds=state["read_consistency_interval_secs"])
+        if state["read_consistency_interval_secs"] is not None
+        else None
+    )
+    db = connect(
+        state["uri"],
+        read_consistency_interval=read_consistency_interval,
+        storage_options=state["storage_options"],
+    )
+    table = db.open_table(state["name"], namespace_path=state["namespace_path"])
+    table.checkout(state["version"])
+    return table
+
+
 class PermutationBuilder:
    """
    A utility for creating a "permutation table" which is a table that defines an
@@ -385,6 +462,13 @@ class Permutation:
        selection: dict[str, str],
        batch_size: int,
        transform_fn: Callable[pa.RecordBatch, Any],
+        *,
+        base_table: Union[LanceTable, dict[str, Any]],
+        permutation_table: Optional[Union[LanceTable, dict[str, Any]]],
+        split: int,
+        offset: Optional[int] = None,
+        limit: Optional[int] = None,
+        transform_spec: Optional[str] = None,
    ):
        """
        Internal constructor.  Use [from_tables](#from_tables) instead.
@@ -395,6 +479,93 @@ class Permutation:
        self.selection = selection
        self.transform_fn = transform_fn
        self.batch_size = batch_size
+        self._transform_spec = transform_spec
+        # These fields are used to reconstruct the permutation in a new process.
+        self._base_table = base_table
+        self._permutation_table = permutation_table
+        self._split = split
+        self._offset = offset
+        self._limit = limit
+
+    def _reopen_metadata(self) -> dict[str, Any]:
+        return {
+            "base_table": self._base_table,
+            "permutation_table": self._permutation_table,
+            "split": self._split,
+            "offset": self._offset,
+            "limit": self._limit,
+            "transform_spec": self._transform_spec,
+        }
+
+    def __getstate__(self) -> dict[str, Any]:
+        if self._transform_spec is not None:
+            transform_state = {
+                "kind": "builtin",
+                "format": self._transform_spec,
+            }
+        else:
+            transform_state = {
+                "kind": "callable",
+                "transform_fn": self.transform_fn,
+            }
+
+        return {
+            "selection": self.selection,
+            "batch_size": self.batch_size,
+            "transform": transform_state,
+            "reopen": {
+                **self._reopen_metadata(),
+                # Store reopen state instead of live LanceTable handles.
+                "base_table": _table_to_state(self._base_table),
+                "permutation_table": (
+                    _table_to_state(self._permutation_table)
+                    if self._permutation_table is not None
+                    else None
+                ),
+            },
+        }
+
+    def __setstate__(self, state: dict[str, Any]) -> None:
+        reopen = state["reopen"]
+        base_table = _table_from_state(reopen["base_table"])
+        permutation_table_state = reopen["permutation_table"]
+        permutation_table = (
+            _table_from_state(permutation_table_state)
+            if permutation_table_state is not None
+            else None
+        )
+        split = reopen["split"]
+        offset = reopen["offset"]
+        limit = reopen["limit"]
+
+        async def do_reopen():
+            reader = await PermutationReader.from_tables(
+                base_table, permutation_table, split
+            )
+            if offset is not None:
+                reader = await reader.with_offset(offset)
+            if limit is not None:
+                reader = await reader.with_limit(limit)
+            return reader
+
+        transform = state["transform"]
+        if transform["kind"] == "builtin":
+            transform_spec = transform["format"]
+            transform_fn = _builtin_transform(transform_spec)
+        else:
+            transform_spec = None
+            transform_fn = transform["transform_fn"]
+
+        self.reader = LOOP.run(do_reopen())
+        self.selection = state["selection"]
+        self.batch_size = state["batch_size"]
+        self.transform_fn = transform_fn
+        self._transform_spec = transform_spec
+        self._base_table = reopen["base_table"]
+        self._permutation_table = permutation_table_state
+        self._split = split
+        self._offset = offset
+        self._limit = limit

    def _with_selection(self, selection: dict[str, str]) -> "Permutation":
        """
@@ -403,7 +574,13 @@ class Permutation:
        Does not validation of the selection and it replaces it entirely.  This is not
        intended for public use.
        """
-        return Permutation(self.reader, selection, self.batch_size, self.transform_fn)
+        return Permutation(
+            self.reader,
+            selection,
+            self.batch_size,
+            self.transform_fn,
+            **self._reopen_metadata(),
+        )

    def _with_reader(self, reader: PermutationReader) -> "Permutation":
        """
@@ -411,13 +588,25 @@ class Permutation:

        This is an internal method and should not be used directly.
        """
-        return Permutation(reader, self.selection, self.batch_size, self.transform_fn)
+        return Permutation(
+            reader,
+            self.selection,
+            self.batch_size,
+            self.transform_fn,
+            **self._reopen_metadata(),
+        )

    def with_batch_size(self, batch_size: int) -> "Permutation":
        """
        Creates a new permutation with the given batch size
        """
-        return Permutation(self.reader, self.selection, batch_size, self.transform_fn)
+        return Permutation(
+            self.reader,
+            self.selection,
+            batch_size,
+            self.transform_fn,
+            **self._reopen_metadata(),
+        )

    @classmethod
    def identity(cls, table: LanceTable) -> "Permutation":
@@ -491,7 +680,14 @@ class Permutation:
            schema = await reader.output_schema(None)
            initial_selection = {name: name for name in schema.names}
            return cls(
-                reader, initial_selection, DEFAULT_BATCH_SIZE, Transforms.arrow2python
+                reader,
+                initial_selection,
+                DEFAULT_BATCH_SIZE,
+                Transforms.arrow2python,
+                base_table=base_table,
+                permutation_table=permutation_table,
+                split=split,
+                transform_spec="python",
            )

        return LOOP.run(do_from_tables())
@@ -732,24 +928,16 @@ class Permutation:
        this method.
        """
        assert format is not None, "format is required"
-        if format == "python":
-            return self.with_transform(Transforms.arrow2python)
-        if format == "python_col":
-            return self.with_transform(Transforms.arrow2pythoncol)
-        elif format == "numpy":
-            return self.with_transform(Transforms.arrow2numpy)
-        elif format == "pandas":
-            return self.with_transform(Transforms.arrow2pandas)
-        elif format == "arrow":
-            return self.with_transform(Transforms.arrow2arrow)
-        elif format == "torch":
-            return self.with_transform(batch_to_tensor_rows)
-        elif format == "torch_col":
-            return self.with_transform(batch_to_tensor)
-        elif format == "polars":
-            return self.with_transform(Transforms.arrow2polars())
-        else:
-            raise ValueError(f"Invalid format: {format}")
+        return Permutation(
+            self.reader,
+            self.selection,
+            self.batch_size,
+            _builtin_transform(format),
+            **{
+                **self._reopen_metadata(),
+                "transform_spec": format,
+            },
+        )

    def with_transform(self, transform: Callable[pa.RecordBatch, Any]) -> "Permutation":
        """
@@ -762,7 +950,16 @@ class Permutation:
        for expensive operations such as image decoding.
        """
        assert transform is not None, "transform is required"
-        return Permutation(self.reader, self.selection, self.batch_size, transform)
+        return Permutation(
+            self.reader,
+            self.selection,
+            self.batch_size,
+            transform,
+            **{
+                **self._reopen_metadata(),
+                "transform_spec": None,
+            },
+        )

    def __getitem__(self, index: int) -> Any:
        """
@@ -800,7 +997,16 @@ class Permutation:

        async def do_with_skip():
            reader = await self.reader.with_offset(skip)
-            return self._with_reader(reader)
+            return Permutation(
+                reader,
+                self.selection,
+                self.batch_size,
+                self.transform_fn,
+                **{
+                    **self._reopen_metadata(),
+                    "offset": skip,
+                },
+            )

        return LOOP.run(do_with_skip())

@@ -823,7 +1029,16 @@ class Permutation:

        async def do_with_take():
            reader = await self.reader.with_limit(limit)
-            return self._with_reader(reader)
+            return Permutation(
+                reader,
+                self.selection,
+                self.batch_size,
+                self.transform_fn,
+                **{
+                    **self._reopen_metadata(),
+                    "limit": limit,
+                },
+            )

        return LOOP.run(do_with_take())

--- a/python/python/lancedb/pydantic.py
+++ b/python/python/lancedb/pydantic.py
@@ -10,6 +10,7 @@ import sys
 import types
 from abc import ABC, abstractmethod
 from datetime import date, datetime
+from enum import Enum
 from typing import (
    TYPE_CHECKING,
    Any,
@@ -314,6 +315,19 @@ def _pydantic_type_to_arrow_type(tp: Any, field: FieldInfo) -> pa.DataType:
                return pa.list_(pa.list_(tp.value_arrow_type(), tp.dim()))
            # For regular Vector
            return pa.list_(tp.value_arrow_type(), tp.dim())
+        if _safe_issubclass(tp, Enum):
+            # Map Enum to the Arrow type of its value.
+            # For string-valued enums, use dictionary encoding for efficiency.
+            # For integer enums, use the native type.
+            # Fall back to utf8 for mixed-type or empty enums.
+            value_types = {type(m.value) for m in tp}
+            if len(value_types) == 1:
+                value_type = value_types.pop()
+                if value_type is str:
+                    # Use dictionary encoding for string enums
+                    return pa.dictionary(pa.int32(), pa.utf8())
+                return _py_type_to_arrow_type(value_type, field)
+            return pa.utf8()
    return _py_type_to_arrow_type(tp, field)


--- a/python/python/lancedb/remote/init.py
+++ b/python/python/lancedb/remote/init.py
@@ -145,6 +145,33 @@ class TlsConfig:

@dataclass
 class ClientConfig:
+    """Configuration for the LanceDB Cloud HTTP client.
+
+    Attributes
+    ----------
+    user_agent: str
+        User agent string sent with requests.
+    retry_config: RetryConfig
+        Configuration for retrying failed requests.
+    timeout_config: Optional[TimeoutConfig]
+        Configuration for request timeouts.
+    extra_headers: Optional[dict]
+        Additional headers to include in requests.
+    id_delimiter: Optional[str]
+        The delimiter to use when constructing object identifiers.
+    tls_config: Optional[TlsConfig]
+        TLS/mTLS configuration for secure connections.
+    header_provider: Optional[HeaderProvider]
+        Provider for dynamic headers to be added to each request.
+    user_id: Optional[str]
+        User identifier for tracking purposes. This is sent as the
+        `x-lancedb-user-id` header in requests to LanceDB Cloud/Enterprise.
+
+        This can also be set via the `LANCEDB_USER_ID` environment variable.
+        Alternatively, set `LANCEDB_USER_ID_ENV_KEY` to specify another
+        environment variable that contains the user ID value.
+    """
+
    user_agent: str = f"LanceDB-Python-Client/{__version__}"
    retry_config: RetryConfig = field(default_factory=RetryConfig)
    timeout_config: Optional[TimeoutConfig] = field(default_factory=TimeoutConfig)
@@ -152,6 +179,7 @@ class ClientConfig:
    id_delimiter: Optional[str] = None
    tls_config: Optional[TlsConfig] = None
    header_provider: Optional["HeaderProvider"] = None
+    user_id: Optional[str] = None

    def __post_init__(self):
        if isinstance(self.retry_config, dict):
--- a/python/python/lancedb/remote/db.py
+++ b/python/python/lancedb/remote/db.py
@@ -24,6 +24,7 @@ from ..common import DATA
 from ..db import DBConnection, LOOP
 from ..embeddings import EmbeddingFunctionConfig
 from lance_namespace import (
+    LanceNamespace,
    CreateNamespaceResponse,
    DescribeNamespaceResponse,
    DropNamespaceResponse,
@@ -570,6 +571,19 @@ class RemoteDBConnection(DBConnection):
            )
        )

+    @override
+    def namespace_client(self) -> LanceNamespace:
+        """Get the equivalent namespace client for this connection.
+
+        Returns a RestNamespace with the same URI and authentication headers.
+
+        Returns
+        -------
+        LanceNamespace
+            The namespace client for this connection.
+        """
+        return LOOP.run(self._conn.namespace_client())
+
    async def close(self):
        """Close the connection to the database."""
        self._conn.close()
--- a/python/python/tests/test_db.py
+++ b/python/python/tests/test_db.py
@@ -3,6 +3,7 @@


 import re
+import sys
 from datetime import timedelta
 import os

@@ -1048,3 +1049,59 @@ def test_clone_table_deep_clone_fails(tmp_path):
    source_uri = os.path.join(tmp_path, "source.lance")
    with pytest.raises(Exception, match="Deep clone is not yet implemented"):
        db.clone_table("cloned", source_uri, is_shallow=False)
+
+
+@pytest.mark.skipif(sys.platform == "win32", reason="Namespace client issues")
+def test_namespace_client_native_storage(tmp_path):
+    """Test namespace_client() returns DirectoryNamespace for native storage."""
+    from lance.namespace import DirectoryNamespace
+
+    db = lancedb.connect(tmp_path)
+    ns_client = db.namespace_client()
+
+    assert isinstance(ns_client, DirectoryNamespace)
+    assert str(tmp_path) in ns_client.namespace_id()
+
+
+@pytest.mark.skipif(sys.platform == "win32", reason="Namespace client issues")
+def test_namespace_client_with_storage_options(tmp_path):
+    """Test namespace_client() preserves storage options."""
+    from lance.namespace import DirectoryNamespace
+
+    storage_options = {"timeout": "10s"}
+    db = lancedb.connect(tmp_path, storage_options=storage_options)
+    ns_client = db.namespace_client()
+
+    assert isinstance(ns_client, DirectoryNamespace)
+
+
+@pytest.mark.skipif(sys.platform == "win32", reason="Namespace client issues")
+def test_namespace_client_operations(tmp_path):
+    """Test that namespace_client() returns a functional namespace client."""
+    db = lancedb.connect(tmp_path)
+    ns_client = db.namespace_client()
+
+    # Create a table through the main db connection
+    data = [{"id": 1, "text": "hello", "vector": [1.0, 2.0]}]
+    db.create_table("test_table", data=data)
+
+    # Verify the namespace client can see the table
+    from lance_namespace import ListTablesRequest
+
+    # id=[] means root namespace
+    response = ns_client.list_tables(ListTablesRequest(id=[]))
+    # Tables can be strings or objects with name attribute
+    table_names = [t.name if hasattr(t, "name") else t for t in response.tables]
+    assert "test_table" in table_names
+
+
+@pytest.mark.skipif(sys.platform == "win32", reason="Namespace client issues")
+def test_namespace_client_namespace_connection(tmp_path):
+    """Test namespace_client() returns the backing client for namespace connections."""
+    from lance.namespace import DirectoryNamespace
+
+    db = lancedb.connect_namespace("dir", {"root": str(tmp_path)})
+    ns_client = db.namespace_client()
+
+    assert isinstance(ns_client, DirectoryNamespace)
+    assert str(tmp_path) in ns_client.namespace_id()
--- a/python/python/tests/test_permutation.py
+++ b/python/python/tests/test_permutation.py
@@ -3,6 +3,7 @@

 import pyarrow as pa
 import math
+import pickle
 import pytest

 from lancedb import DBConnection, Table, connect
@@ -599,6 +600,87 @@ def test_limit_offset(some_permutation: Permutation):
        some_permutation.with_skip(500).with_take(500).num_rows


+def test_permutation_pickle_rejects_in_memory_tables(mem_db: DBConnection):
+    table = mem_db.create_table("identity_table", pa.table({"id": range(10)}))
+    permutation = Permutation.identity(table)
+
+    with pytest.raises(
+        pickle.PicklingError,
+        match="in-memory databases",
+    ):
+        pickle.dumps(permutation)
+
+
+def test_identity_permutation_pickle_roundtrip_preserves_table_version(tmp_path):
+    db = connect(tmp_path)
+    table = db.create_table(
+        "identity_table",
+        pa.table({"id": range(10), "value": range(10)}),
+    )
+    permutation = (
+        Permutation.identity(table).with_skip(2).with_take(3).with_format("python_col")
+    )
+
+    payload = pickle.dumps(permutation)
+    table.add(pa.table({"id": [10], "value": [10]}))
+
+    restored = pickle.loads(payload)
+    assert restored.num_rows == 3
+    batches = list(restored.iter(10, skip_last_batch=False))
+    assert batches == [{"id": [2, 3, 4], "value": [2, 3, 4]}]
+
+
+def test_permutation_pickle_roundtrip_with_persisted_permutation_table(tmp_path):
+    db = connect(tmp_path)
+    table = db.create_table(
+        "base_table",
+        pa.table({"id": range(1000), "value": range(1000)}),
+    )
+    permutation_table = (
+        permutation_builder(table)
+        .split_random(ratios=[0.95, 0.05], seed=42, split_names=["train", "test"])
+        .shuffle(seed=42)
+        .persist(db, "persisted_permutation")
+        .execute()
+    )
+    permutation = (
+        Permutation.from_tables(table, permutation_table, "test")
+        .select_columns(["id"])
+        .rename_column("id", "row_id")
+        .with_batch_size(32)
+        .with_skip(5)
+        .with_take(10)
+        .with_format("arrow")
+    )
+
+    restored = pickle.loads(pickle.dumps(permutation))
+
+    assert restored.batch_size == 32
+    assert restored.column_names == ["row_id"]
+    assert restored.num_rows == 10
+    assert (
+        restored.__getitems__([0, 1, 2]).to_pylist()
+        == permutation.__getitems__([0, 1, 2]).to_pylist()
+    )
+
+
+def test_permutation_pickle_roundtrip_preserves_builtin_polars_format(tmp_path):
+    pl = pytest.importorskip("polars")
+
+    db = connect(tmp_path)
+    table = db.create_table(
+        "polars_table",
+        pa.table({"id": range(5), "value": range(5)}),
+    )
+    permutation = Permutation.identity(table).with_take(2).with_format("polars")
+
+    restored = pickle.loads(pickle.dumps(permutation))
+    batch = restored.__getitems__([0, 1])
+
+    assert isinstance(batch, pl.DataFrame)
+    assert batch.to_dict(as_series=False) == {"id": [0, 1], "value": [0, 1]}
+
+
 def test_remove_columns(some_permutation: Permutation):
    assert some_permutation.remove_columns(["value"]).schema == pa.schema(
        [("id", pa.int64())]
--- a/python/python/tests/test_pydantic.py
+++ b/python/python/tests/test_pydantic.py
@@ -3,6 +3,7 @@

 import json
 from datetime import date, datetime
+from enum import Enum
 from typing import List, Optional, Tuple

 import pyarrow as pa
@@ -673,3 +674,29 @@ async def test_aliases_in_lance_model_async(mem_db_async):
    assert hasattr(model, "name")
    assert hasattr(model, "distance")
    assert model.distance < 0.01
+
+
+def test_enum_types():
+    """Enum fields should map to the Arrow type of their value (issue #1846)."""
+
+    class StrStatus(str, Enum):
+        PENDING = "pending"
+        RUNNING = "running"
+        DONE = "done"
+
+    class IntPriority(int, Enum):
+        LOW = 1
+        MEDIUM = 2
+        HIGH = 3
+
+    class TestModel(pydantic.BaseModel):
+        status: StrStatus
+        priority: IntPriority
+        opt_status: Optional[StrStatus] = None
+
+    schema = pydantic_to_schema(TestModel)
+
+    assert schema.field("status").type == pa.dictionary(pa.int32(), pa.utf8())
+    assert schema.field("priority").type == pa.int64()
+    assert schema.field("opt_status").type == pa.dictionary(pa.int32(), pa.utf8())
+    assert schema.field("opt_status").nullable
--- a/python/src/connection.rs
+++ b/python/src/connection.rs
@@ -474,6 +474,25 @@ impl Connection {
            })
        })
    }
+
+    /// Get the configuration for constructing an equivalent namespace client.
+    /// Returns a dict with:
+    /// - "impl": "dir" for DirectoryNamespace, "rest" for RestNamespace
+    /// - "properties": configuration properties for the namespace
+    #[pyo3(signature = ())]
+    pub fn namespace_client_config(self_: PyRef<'_, Self>) -> PyResult<Bound<'_, PyAny>> {
+        let inner = self_.get_inner()?.clone();
+        let py = self_.py();
+        future_into_py(py, async move {
+            let (impl_type, properties) = inner.namespace_client_config().await.infer_error()?;
+            Python::attach(|py| -> PyResult<Py<PyDict>> {
+                let dict = PyDict::new(py);
+                dict.set_item("impl", impl_type)?;
+                dict.set_item("properties", properties)?;
+                Ok(dict.unbind())
+            })
+        })
+    }
 }

 #[pyfunction]
@@ -528,6 +547,7 @@ pub struct PyClientConfig {
    id_delimiter: Option<String>,
    tls_config: Option<PyClientTlsConfig>,
    header_provider: Option<Py<PyAny>>,
+    user_id: Option<String>,
 }

 #[derive(FromPyObject)]
@@ -612,6 +632,7 @@ impl From<PyClientConfig> for lancedb::remote::ClientConfig {
            id_delimiter: value.id_delimiter,
            tls_config: value.tls_config.map(Into::into),
            header_provider,
+            user_id: value.user_id,
        }
    }
 }
--- a/rust/lancedb/Cargo.toml
+++ b/rust/lancedb/Cargo.toml
@@ -1,6 +1,6 @@
 [package]
 name = "lancedb"
-version = "0.27.2"
+version = "0.28.0-beta.1"
 edition.workspace = true
 description = "LanceDB: A serverless, low-latency vector database for AI applications"
 license.workspace = true
--- a/rust/lancedb/src/connection.rs
+++ b/rust/lancedb/src/connection.rs
@@ -541,6 +541,16 @@ impl Connection {
        self.internal.namespace_client().await
    }

+    /// Get the configuration for constructing an equivalent namespace client.
+    /// Returns (impl_type, properties) where:
+    /// - impl_type: "dir" for DirectoryNamespace, "rest" for RestNamespace
+    /// - properties: configuration properties for the namespace
+    pub async fn namespace_client_config(
+        &self,
+    ) -> Result<(String, std::collections::HashMap<String, String>)> {
+        self.internal.namespace_client_config().await
+    }
+
    /// List tables with pagination support
    pub async fn list_tables(&self, request: ListTablesRequest) -> Result<ListTablesResponse> {
        self.internal.list_tables(request).await
--- a/rust/lancedb/src/database.rs
+++ b/rust/lancedb/src/database.rs
@@ -265,4 +265,13 @@ pub trait Database:
    /// For ListingDatabase, it is the equivalent DirectoryNamespace.
    /// For RemoteDatabase, it is the equivalent RestNamespace.
    async fn namespace_client(&self) -> Result<Arc<dyn LanceNamespace>>;
+
+    /// Get the configuration for constructing an equivalent namespace client.
+    /// Returns (impl_type, properties) where:
+    /// - impl_type: "dir" for DirectoryNamespace, "rest" for RestNamespace
+    /// - properties: configuration properties for the namespace
+    ///
+    /// This is useful for Python bindings where we want to return a Python
+    /// namespace object rather than a Rust trait object.
+    async fn namespace_client_config(&self) -> Result<(String, HashMap<String, String>)>;
 }
--- a/rust/lancedb/src/database/listing.rs
+++ b/rust/lancedb/src/database/listing.rs
@@ -1099,6 +1099,15 @@ impl Database for ListingDatabase {
        })?;
        Ok(Arc::new(namespace) as Arc<dyn lance_namespace::LanceNamespace>)
    }
+
+    async fn namespace_client_config(&self) -> Result<(String, HashMap<String, String>)> {
+        let mut properties = HashMap::new();
+        properties.insert("root".to_string(), self.uri.clone());
+        for (key, value) in &self.storage_options {
+            properties.insert(format!("storage.{}", key), value.clone());
+        }
+        Ok(("dir".to_string(), properties))
+    }
 }

 #[cfg(test)]
--- a/rust/lancedb/src/database/namespace.rs
+++ b/rust/lancedb/src/database/namespace.rs
@@ -45,6 +45,10 @@ pub struct LanceNamespaceDatabase {
    uri: String,
    // Operations to push down to the namespace server
    pushdown_operations: HashSet<PushdownOperation>,
+    // Namespace implementation type (e.g., "dir", "rest")
+    ns_impl: String,
+    // Namespace properties used to construct the namespace client
+    ns_properties: HashMap<String, String>,
 }

 impl LanceNamespaceDatabase {
@@ -74,6 +78,8 @@ impl LanceNamespaceDatabase {
            session,
            uri: format!("namespace://{}", ns_impl),
            pushdown_operations,
+            ns_impl: ns_impl.to_string(),
+            ns_properties,
        })
    }
 }
@@ -345,6 +351,10 @@ impl Database for LanceNamespaceDatabase {
    async fn namespace_client(&self) -> Result<Arc<dyn LanceNamespace>> {
        Ok(self.namespace.clone())
    }
+
+    async fn namespace_client_config(&self) -> Result<(String, HashMap<String, String>)> {
+        Ok((self.ns_impl.clone(), self.ns_properties.clone()))
+    }
 }

 #[cfg(test)]
--- a/rust/lancedb/src/remote/client.rs
+++ b/rust/lancedb/src/remote/client.rs
@@ -52,6 +52,13 @@ pub struct ClientConfig {
    pub tls_config: Option<TlsConfig>,
    /// Provider for custom headers to be added to each request
    pub header_provider: Option<Arc<dyn HeaderProvider>>,
+    /// User identifier for tracking purposes.
+    ///
+    /// This is sent as the `x-lancedb-user-id` header in requests to LanceDB Cloud/Enterprise.
+    /// It can be set directly, or via the `LANCEDB_USER_ID` environment variable.
+    /// Alternatively, set `LANCEDB_USER_ID_ENV_KEY` to specify another environment
+    /// variable that contains the user ID value.
+    pub user_id: Option<String>,
 }

 impl std::fmt::Debug for ClientConfig {
@@ -67,6 +74,7 @@ impl std::fmt::Debug for ClientConfig {
                "header_provider",
                &self.header_provider.as_ref().map(|_| "Some(...)"),
            )
+            .field("user_id", &self.user_id)
            .finish()
    }
 }
@@ -81,10 +89,41 @@ impl Default for ClientConfig {
            id_delimiter: None,
            tls_config: None,
            header_provider: None,
+            user_id: None,
        }
    }
 }

+impl ClientConfig {
+    /// Resolve the user ID from the config or environment variables.
+    ///
+    /// Resolution order:
+    /// 1. If `user_id` is set in the config, use that value
+    /// 2. If `LANCEDB_USER_ID` environment variable is set, use that value
+    /// 3. If `LANCEDB_USER_ID_ENV_KEY` is set, read the env var it points to
+    /// 4. Otherwise, return None
+    pub fn resolve_user_id(&self) -> Option<String> {
+        if self.user_id.is_some() {
+            return self.user_id.clone();
+        }
+
+        if let Ok(user_id) = std::env::var("LANCEDB_USER_ID")
+            && !user_id.is_empty()
+        {
+            return Some(user_id);
+        }
+
+        if let Ok(env_key) = std::env::var("LANCEDB_USER_ID_ENV_KEY")
+            && let Ok(user_id) = std::env::var(&env_key)
+            && !user_id.is_empty()
+        {
+            return Some(user_id);
+        }
+
+        None
+    }
+}
+
 /// How to handle timeouts for HTTP requests.
 #[derive(Clone, Default, Debug)]
 pub struct TimeoutConfig {
@@ -464,6 +503,15 @@ impl<S: HttpSend> RestfulLanceDbClient<S> {
            );
        }

+        if let Some(user_id) = config.resolve_user_id() {
+            headers.insert(
+                HeaderName::from_static("x-lancedb-user-id"),
+                HeaderValue::from_str(&user_id).map_err(|_| Error::InvalidInput {
+                    message: format!("non-ascii user_id '{}' provided", user_id),
+                })?,
+            );
+        }
+
        Ok(headers)
    }

@@ -1072,4 +1120,91 @@ mod tests {
            _ => panic!("Expected Runtime error"),
        }
    }
+
+    #[test]
+    fn test_resolve_user_id_direct_value() {
+        let config = ClientConfig {
+            user_id: Some("direct-user-id".to_string()),
+            ..Default::default()
+        };
+        assert_eq!(config.resolve_user_id(), Some("direct-user-id".to_string()));
+    }
+
+    #[test]
+    fn test_resolve_user_id_none() {
+        let config = ClientConfig::default();
+        // Clear env vars that might be set from other tests
+        // SAFETY: This is only called in tests
+        unsafe {
+            std::env::remove_var("LANCEDB_USER_ID");
+            std::env::remove_var("LANCEDB_USER_ID_ENV_KEY");
+        }
+        assert_eq!(config.resolve_user_id(), None);
+    }
+
+    #[test]
+    fn test_resolve_user_id_from_env() {
+        // SAFETY: This is only called in tests
+        unsafe {
+            std::env::set_var("LANCEDB_USER_ID", "env-user-id");
+        }
+        let config = ClientConfig::default();
+        assert_eq!(config.resolve_user_id(), Some("env-user-id".to_string()));
+        // SAFETY: This is only called in tests
+        unsafe {
+            std::env::remove_var("LANCEDB_USER_ID");
+        }
+    }
+
+    #[test]
+    fn test_resolve_user_id_from_env_key() {
+        // SAFETY: This is only called in tests
+        unsafe {
+            std::env::remove_var("LANCEDB_USER_ID");
+            std::env::set_var("LANCEDB_USER_ID_ENV_KEY", "MY_CUSTOM_USER_ID");
+            std::env::set_var("MY_CUSTOM_USER_ID", "custom-env-user-id");
+        }
+        let config = ClientConfig::default();
+        assert_eq!(
+            config.resolve_user_id(),
+            Some("custom-env-user-id".to_string())
+        );
+        // SAFETY: This is only called in tests
+        unsafe {
+            std::env::remove_var("LANCEDB_USER_ID_ENV_KEY");
+            std::env::remove_var("MY_CUSTOM_USER_ID");
+        }
+    }
+
+    #[test]
+    fn test_resolve_user_id_direct_takes_precedence() {
+        // SAFETY: This is only called in tests
+        unsafe {
+            std::env::set_var("LANCEDB_USER_ID", "env-user-id");
+        }
+        let config = ClientConfig {
+            user_id: Some("direct-user-id".to_string()),
+            ..Default::default()
+        };
+        assert_eq!(config.resolve_user_id(), Some("direct-user-id".to_string()));
+        // SAFETY: This is only called in tests
+        unsafe {
+            std::env::remove_var("LANCEDB_USER_ID");
+        }
+    }
+
+    #[test]
+    fn test_resolve_user_id_empty_env_ignored() {
+        // SAFETY: This is only called in tests
+        unsafe {
+            std::env::set_var("LANCEDB_USER_ID", "");
+            std::env::remove_var("LANCEDB_USER_ID_ENV_KEY");
+        }
+        let config = ClientConfig::default();
+        assert_eq!(config.resolve_user_id(), None);
+        // SAFETY: This is only called in tests
+        unsafe {
+            std::env::remove_var("LANCEDB_USER_ID");
+        }
+    }
 }
--- a/rust/lancedb/src/remote/db.rs
+++ b/rust/lancedb/src/remote/db.rs
@@ -777,6 +777,32 @@ impl<S: HttpSend> Database for RemoteDatabase<S> {
        let namespace = builder.build();
        Ok(Arc::new(namespace) as Arc<dyn lance_namespace::LanceNamespace>)
    }
+
+    async fn namespace_client_config(&self) -> Result<(String, HashMap<String, String>)> {
+        let mut properties = HashMap::new();
+        properties.insert("uri".to_string(), self.client.host().to_string());
+        properties.insert("delimiter".to_string(), self.client.id_delimiter.clone());
+        for (key, value) in &self.namespace_headers {
+            properties.insert(format!("header.{}", key), value.clone());
+        }
+        // Add TLS configuration if present
+        if let Some(tls_config) = &self.tls_config {
+            if let Some(cert_file) = &tls_config.cert_file {
+                properties.insert("tls.cert_file".to_string(), cert_file.clone());
+            }
+            if let Some(key_file) = &tls_config.key_file {
+                properties.insert("tls.key_file".to_string(), key_file.clone());
+            }
+            if let Some(ssl_ca_cert) = &tls_config.ssl_ca_cert {
+                properties.insert("tls.ssl_ca_cert".to_string(), ssl_ca_cert.clone());
+            }
+            properties.insert(
+                "tls.assert_hostname".to_string(),
+                tls_config.assert_hostname.to_string(),
+            );
+        }
+        Ok(("rest".to_string(), properties))
+    }
 }

 /// RemoteOptions contains a subset of StorageOptions that are compatible with Remote LanceDB connections
Author	SHA1	Message	Date
Xuanwo	7c37ba216a	style(python): format permutation pickle tests	2026-04-09 14:47:06 +08:00
Xuanwo	768d84845c	feat(python): support pickling permutations	2026-04-09 00:32:48 +08:00
Xuanwo	2d380d1669	Track permutation reopen metadata	2026-04-08 17:34:05 +08:00
Jack Ye	a898dc81c2	feat: add user_id field to ClientConfig for user identification (#3240 ) ## Summary - Add a `user_id` field to `ClientConfig` that allows users to identify themselves to LanceDB Cloud/Enterprise - The user_id is sent as the `x-lancedb-user-id` HTTP header in all requests - Supports three configuration methods: - Direct assignment via `ClientConfig.user_id` - Environment variable `LANCEDB_USER_ID` - Indirect env var lookup via `LANCEDB_USER_ID_ENV_KEY` Closes #3230 🤖 Generated with [Claude Code](https://claude.com/claude-code) --------- Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>	2026-04-06 11:20:10 -07:00
Lance Release	de3f8097e7	Bump version: 0.28.0-beta.0 → 0.28.0-beta.1	2026-04-05 02:51:18 +00:00
Lance Release	0ac59de5f1	Bump version: 0.31.0-beta.0 → 0.31.0-beta.1	2026-04-05 02:50:52 +00:00
LanceDB Robot	d082c2d2ac	chore: update lance dependency to v5.0.0-beta.5 (#3237 ) ## Summary - update Rust Lance workspace dependencies to `v5.0.0-beta.5` using `ci/set_lance_version.py` - update Java `lance-core` dependency property to `5.0.0-beta.5` - refresh Cargo lockfile to the new Lance tag ## Verification - `cargo clippy --workspace --tests --all-features -- -D warnings` - `cargo fmt --all` ## Upstream Tag - https://github.com/lance-format/lance/releases/tag/v5.0.0-beta.5 --------- Co-authored-by: Jack Ye <yezhaoqin@gmail.com>	2026-04-04 19:49:51 -07:00
Zelys	9d8699f99e	feat(python): support Enum types in Pydantic to Arrow schema conversion (#3232 ) ## Summary Fixes #1846. Python `Enum` fields raised `TypeError: Converting Pydantic type to Arrow Type: unsupported type <enum 'SomethingTypes'>` when converting a Pydantic model to an Arrow schema. The fix adds Enum detection in `_pydantic_type_to_arrow_type`. When an Enum subclass is encountered, the value type of its members is inspected and mapped to the appropriate Arrow type: - `str`-valued enums (e.g. `class Status(str, Enum)`) → `pa.utf8()` - `int`-valued enums (e.g. `class Priority(int, Enum)`) → `pa.int64()` - Other homogeneous value types → the Arrow type for that Python type - Mixed-value or empty enums → `pa.utf8()` (safe fallback) This covers the common `(str, Enum)` and `(int, Enum)` mixin patterns used in practice. ## Changes - `python/python/lancedb/pydantic.py`: add Enum branch in `_pydantic_type_to_arrow_type` - `python/python/tests/test_pydantic.py`: add `test_enum_types` covering `str`, `int`, and `Optional` Enum fields ## Note on #2395 PR #2395 handles `StrEnum` (Python 3.11+) specifically, using a dictionary-encoded type. This PR handles the broader `(str, Enum)` / `(int, Enum)` mixin pattern that works across all Python versions and stores values as their natural Arrow type. AI assistance was used in developing this fix.	2026-04-03 10:40:49 -07:00
Lance Release	aa2c7b3591	Bump version: 0.27.2 → 0.28.0-beta.0	2026-04-03 08:45:56 +00:00