feat(python): add permutation index snapshots

.bumpversion.toml

@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.28.0-beta.4"
+current_version = "0.28.0-beta.1"
 parse = """(?x)
     (?P<major>0|[1-9]\\d*)\\.
     (?P<minor>0|[1-9]\\d*)\\.

.github/workflows/nodejs.yml

@@ -8,7 +8,6 @@ on:
     paths:
       - Cargo.toml
       - Cargo.lock
-      - rust-toolchain.toml
       - nodejs/**
       - rust/**
       - docs/src/js/**

.github/workflows/python.yml

@@ -8,7 +8,6 @@ on:
     paths:
       - Cargo.toml
       - Cargo.lock
-      - rust-toolchain.toml
       - python/**
       - rust/**
       - .github/workflows/python.yml

.github/workflows/rust.yml

@@ -8,7 +8,6 @@ on:
     paths:
       - Cargo.toml
       - Cargo.lock
-      - rust-toolchain.toml
       - rust/**
       - .github/workflows/rust.yml
 

Cargo.lock

@@ -3072,8 +3072,8 @@ checksum = "42703706b716c37f96a77aea830392ad231f44c9e9a67872fa5548707e11b11c"
 
 [[package]]
 name = "fsst"
-version = "5.1.0-beta.3"
-source = "git+https://github.com/lance-format/lance.git?tag=v5.1.0-beta.3#0a0d53b5ef4b0f65bb775ce63bdcabc79d1d14b8"
+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",
@@ -4134,14 +4134,13 @@ dependencies = [
 
 [[package]]
 name = "lance"
-version = "5.1.0-beta.3"
-source = "git+https://github.com/lance-format/lance.git?tag=v5.1.0-beta.3#0a0d53b5ef4b0f65bb775ce63bdcabc79d1d14b8"
+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",
  "arrow-array",
  "arrow-buffer",
- "arrow-cast",
  "arrow-ipc",
  "arrow-ord",
  "arrow-row",
@@ -4202,14 +4201,13 @@ dependencies = [
 
 [[package]]
 name = "lance-arrow"
-version = "5.1.0-beta.3"
-source = "git+https://github.com/lance-format/lance.git?tag=v5.1.0-beta.3#0a0d53b5ef4b0f65bb775ce63bdcabc79d1d14b8"
+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",
  "arrow-cast",
  "arrow-data",
- "arrow-ipc",
  "arrow-ord",
  "arrow-schema",
  "arrow-select",
@@ -4224,8 +4222,8 @@ dependencies = [
 
 [[package]]
 name = "lance-bitpacking"
-version = "5.1.0-beta.3"
-source = "git+https://github.com/lance-format/lance.git?tag=v5.1.0-beta.3#0a0d53b5ef4b0f65bb775ce63bdcabc79d1d14b8"
+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",
@@ -4234,8 +4232,8 @@ dependencies = [
 
 [[package]]
 name = "lance-core"
-version = "5.1.0-beta.3"
-source = "git+https://github.com/lance-format/lance.git?tag=v5.1.0-beta.3#0a0d53b5ef4b0f65bb775ce63bdcabc79d1d14b8"
+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",
@@ -4272,13 +4270,12 @@ dependencies = [
 
 [[package]]
 name = "lance-datafusion"
-version = "5.1.0-beta.3"
-source = "git+https://github.com/lance-format/lance.git?tag=v5.1.0-beta.3#0a0d53b5ef4b0f65bb775ce63bdcabc79d1d14b8"
+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",
  "arrow-buffer",
- "arrow-cast",
  "arrow-ord",
  "arrow-schema",
  "arrow-select",
@@ -4304,8 +4301,8 @@ dependencies = [
 
 [[package]]
 name = "lance-datagen"
-version = "5.1.0-beta.3"
-source = "git+https://github.com/lance-format/lance.git?tag=v5.1.0-beta.3#0a0d53b5ef4b0f65bb775ce63bdcabc79d1d14b8"
+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",
@@ -4323,8 +4320,8 @@ dependencies = [
 
 [[package]]
 name = "lance-encoding"
-version = "5.1.0-beta.3"
-source = "git+https://github.com/lance-format/lance.git?tag=v5.1.0-beta.3#0a0d53b5ef4b0f65bb775ce63bdcabc79d1d14b8"
+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",
@@ -4361,8 +4358,8 @@ dependencies = [
 
 [[package]]
 name = "lance-file"
-version = "5.1.0-beta.3"
-source = "git+https://github.com/lance-format/lance.git?tag=v5.1.0-beta.3#0a0d53b5ef4b0f65bb775ce63bdcabc79d1d14b8"
+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",
@@ -4394,8 +4391,8 @@ dependencies = [
 
 [[package]]
 name = "lance-index"
-version = "5.1.0-beta.3"
-source = "git+https://github.com/lance-format/lance.git?tag=v5.1.0-beta.3#0a0d53b5ef4b0f65bb775ce63bdcabc79d1d14b8"
+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",
@@ -4459,8 +4456,8 @@ dependencies = [
 
 [[package]]
 name = "lance-io"
-version = "5.1.0-beta.3"
-source = "git+https://github.com/lance-format/lance.git?tag=v5.1.0-beta.3#0a0d53b5ef4b0f65bb775ce63bdcabc79d1d14b8"
+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",
@@ -4504,8 +4501,8 @@ dependencies = [
 
 [[package]]
 name = "lance-linalg"
-version = "5.1.0-beta.3"
-source = "git+https://github.com/lance-format/lance.git?tag=v5.1.0-beta.3#0a0d53b5ef4b0f65bb775ce63bdcabc79d1d14b8"
+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",
@@ -4521,8 +4518,8 @@ dependencies = [
 
 [[package]]
 name = "lance-namespace"
-version = "5.1.0-beta.3"
-source = "git+https://github.com/lance-format/lance.git?tag=v5.1.0-beta.3#0a0d53b5ef4b0f65bb775ce63bdcabc79d1d14b8"
+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",
@@ -4535,8 +4532,8 @@ dependencies = [
 
 [[package]]
 name = "lance-namespace-impls"
-version = "5.1.0-beta.3"
-source = "git+https://github.com/lance-format/lance.git?tag=v5.1.0-beta.3#0a0d53b5ef4b0f65bb775ce63bdcabc79d1d14b8"
+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",
@@ -4581,8 +4578,8 @@ dependencies = [
 
 [[package]]
 name = "lance-table"
-version = "5.1.0-beta.3"
-source = "git+https://github.com/lance-format/lance.git?tag=v5.1.0-beta.3#0a0d53b5ef4b0f65bb775ce63bdcabc79d1d14b8"
+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",
@@ -4621,8 +4618,8 @@ dependencies = [
 
 [[package]]
 name = "lance-testing"
-version = "5.1.0-beta.3"
-source = "git+https://github.com/lance-format/lance.git?tag=v5.1.0-beta.3#0a0d53b5ef4b0f65bb775ce63bdcabc79d1d14b8"
+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",
@@ -4633,7 +4630,7 @@ dependencies = [
 
 [[package]]
 name = "lancedb"
-version = "0.28.0-beta.4"
+version = "0.28.0-beta.1"
 dependencies = [
  "ahash",
  "anyhow",
@@ -4715,7 +4712,7 @@ dependencies = [
 
 [[package]]
 name = "lancedb-nodejs"
-version = "0.28.0-beta.4"
+version = "0.28.0-beta.1"
 dependencies = [
  "arrow-array",
  "arrow-buffer",
@@ -4737,7 +4734,7 @@ dependencies = [
 
 [[package]]
 name = "lancedb-python"
-version = "0.31.0-beta.4"
+version = "0.31.0-beta.1"
 dependencies = [
  "arrow",
  "async-trait",

Cargo.toml

@@ -15,20 +15,20 @@ categories = ["database-implementations"]
 rust-version = "1.91.0"
 
 [workspace.dependencies]
-lance = { "version" = "=5.1.0-beta.3", default-features = false, "tag" = "v5.1.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
-lance-core = { "version" = "=5.1.0-beta.3", "tag" = "v5.1.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
-lance-datagen = { "version" = "=5.1.0-beta.3", "tag" = "v5.1.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
-lance-file = { "version" = "=5.1.0-beta.3", "tag" = "v5.1.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
-lance-io = { "version" = "=5.1.0-beta.3", default-features = false, "tag" = "v5.1.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
-lance-index = { "version" = "=5.1.0-beta.3", "tag" = "v5.1.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
-lance-linalg = { "version" = "=5.1.0-beta.3", "tag" = "v5.1.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
-lance-namespace = { "version" = "=5.1.0-beta.3", "tag" = "v5.1.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
-lance-namespace-impls = { "version" = "=5.1.0-beta.3", default-features = false, "tag" = "v5.1.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
-lance-table = { "version" = "=5.1.0-beta.3", "tag" = "v5.1.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
-lance-testing = { "version" = "=5.1.0-beta.3", "tag" = "v5.1.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
-lance-datafusion = { "version" = "=5.1.0-beta.3", "tag" = "v5.1.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
-lance-encoding = { "version" = "=5.1.0-beta.3", "tag" = "v5.1.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
-lance-arrow = { "version" = "=5.1.0-beta.3", "tag" = "v5.1.0-beta.3", "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 }

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>0.28.0-beta.4</version>
+    <version>0.28.0-beta.1</version>
 </dependency>
 ```
 

java/lancedb-core/pom.xml

@@ -8,7 +8,7 @@
     <parent>
       <groupId>com.lancedb</groupId>
       <artifactId>lancedb-parent</artifactId>
-      <version>0.28.0-beta.4</version>
+      <version>0.28.0-beta.1</version>
       <relativePath>../pom.xml</relativePath>
     </parent>
 

java/pom.xml

@@ -6,7 +6,7 @@
 
     <groupId>com.lancedb</groupId>
     <artifactId>lancedb-parent</artifactId>
-    <version>0.28.0-beta.4</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>5.1.0-beta.3</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>

nodejs/Cargo.toml

@@ -1,7 +1,7 @@
 [package]
 name = "lancedb-nodejs"
 edition.workspace = true
-version = "0.28.0-beta.4"
+version = "0.28.0-beta.1"
 license.workspace = true
 description.workspace = true
 repository.workspace = true

nodejs/npm/darwin-arm64/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-darwin-arm64",
-	"version": "0.28.0-beta.4",
+	"version": "0.28.0-beta.1",
 	"os": ["darwin"],
 	"cpu": ["arm64"],
 	"main": "lancedb.darwin-arm64.node",

nodejs/npm/linux-arm64-gnu/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-arm64-gnu",
-	"version": "0.28.0-beta.4",
+	"version": "0.28.0-beta.1",
 	"os": ["linux"],
 	"cpu": ["arm64"],
 	"main": "lancedb.linux-arm64-gnu.node",

nodejs/npm/linux-arm64-musl/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-arm64-musl",
-	"version": "0.28.0-beta.4",
+	"version": "0.28.0-beta.1",
 	"os": ["linux"],
 	"cpu": ["arm64"],
 	"main": "lancedb.linux-arm64-musl.node",

nodejs/npm/linux-x64-gnu/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-x64-gnu",
-	"version": "0.28.0-beta.4",
+	"version": "0.28.0-beta.1",
 	"os": ["linux"],
 	"cpu": ["x64"],
 	"main": "lancedb.linux-x64-gnu.node",

nodejs/npm/linux-x64-musl/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-x64-musl",
-	"version": "0.28.0-beta.4",
+	"version": "0.28.0-beta.1",
 	"os": ["linux"],
 	"cpu": ["x64"],
 	"main": "lancedb.linux-x64-musl.node",

nodejs/npm/win32-arm64-msvc/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@lancedb/lancedb-win32-arm64-msvc",
-  "version": "0.28.0-beta.4",
+  "version": "0.28.0-beta.1",
   "os": [
     "win32"
   ],

nodejs/npm/win32-x64-msvc/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-win32-x64-msvc",
-	"version": "0.28.0-beta.4",
+	"version": "0.28.0-beta.1",
 	"os": ["win32"],
 	"cpu": ["x64"],
 	"main": "lancedb.win32-x64-msvc.node",

nodejs/package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "@lancedb/lancedb",
-  "version": "0.28.0-beta.4",
+  "version": "0.28.0-beta.1",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "@lancedb/lancedb",
-      "version": "0.28.0-beta.4",
+      "version": "0.28.0-beta.1",
       "cpu": [
         "x64",
         "arm64"

nodejs/package.json

@@ -11,7 +11,7 @@
     "ann"
   ],
   "private": false,
-  "version": "0.28.0-beta.4",
+  "version": "0.28.0-beta.1",
   "main": "dist/index.js",
   "exports": {
     ".": "./dist/index.js",

python/.bumpversion.toml

@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.31.0-beta.5"
+current_version = "0.31.0-beta.1"
 parse = """(?x)
     (?P<major>0|[1-9]\\d*)\\.
     (?P<minor>0|[1-9]\\d*)\\.

python/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "lancedb-python"
-version = "0.31.0-beta.5"
+version = "0.31.0-beta.1"
 edition.workspace = true
 description = "Python bindings for LanceDB"
 license.workspace = true

python/python/lancedb/__init__.py

@@ -215,85 +215,6 @@ def connect(
     )
 
 
-WORKER_PROPERTY_PREFIX = "_lancedb_worker_"
-
-
-def _apply_worker_overrides(props: dict[str, str]) -> dict[str, str]:
-    """Apply worker property overrides.
-
-    Any key starting with ``_lancedb_worker_`` is extracted, the prefix
-    is stripped, and the resulting key-value pair is put back into the
-    map (overriding the existing value if present).  The original
-    prefixed key is removed.
-    """
-    worker_keys = [k for k in props if k.startswith(WORKER_PROPERTY_PREFIX)]
-    if not worker_keys:
-        return props
-    result = dict(props)
-    for key in worker_keys:
-        value = result.pop(key)
-        real_key = key[len(WORKER_PROPERTY_PREFIX) :]
-        result[real_key] = value
-    return result
-
-
-def deserialize_conn(
-    data: str,
-    *,
-    for_worker: bool = False,
-) -> DBConnection:
-    """Reconstruct a DBConnection from a serialized string.
-
-    The string must have been produced by
-    :meth:`DBConnection.serialize`.
-
-    Parameters
-    ----------
-    data : str
-        String produced by ``serialize()``.
-    for_worker : bool, default False
-        When ``True``, any namespace client property whose key starts
-        with ``_lancedb_worker_`` has that prefix stripped and the
-        value overrides the corresponding property.  For example,
-        ``_lancedb_worker_uri`` replaces ``uri``.
-
-    Returns
-    -------
-    DBConnection
-        A new connection matching the serialized state.
-    """
-    import json
-
-    parsed = json.loads(data)
-    connection_type = parsed.get("connection_type")
-
-    rci_secs = parsed.get("read_consistency_interval_seconds")
-    rci = timedelta(seconds=rci_secs) if rci_secs is not None else None
-    storage_options = parsed.get("storage_options")
-
-    if connection_type == "namespace":
-        props = dict(parsed.get("namespace_client_properties") or {})
-        if for_worker:
-            props = _apply_worker_overrides(props)
-        return connect_namespace(
-            namespace_client_impl=parsed["namespace_client_impl"],
-            namespace_client_properties=props,
-            read_consistency_interval=rci,
-            storage_options=storage_options,
-            namespace_client_pushdown_operations=parsed.get(
-                "namespace_client_pushdown_operations"
-            ),
-        )
-    elif connection_type == "local":
-        return LanceDBConnection(
-            parsed["uri"],
-            read_consistency_interval=rci,
-            storage_options=storage_options,
-        )
-    else:
-        raise ValueError(f"Unknown connection_type: {connection_type}")
-
-
 async def connect_async(
     uri: URI,
     *,

python/python/lancedb/_lancedb.pyi

@@ -446,3 +446,4 @@ def fts_query_to_json(query: Any) -> str: ...
 
 class PermutationReader:
     def __init__(self, base_table: Table, permutation_table: Table): ...
+    async def snapshot_indices(self) -> pa.RecordBatch: ...

python/python/lancedb/db.py

@@ -529,19 +529,6 @@ class DBConnection(EnforceOverrides):
             "namespace_client is not supported for this connection type"
         )
 
-    def serialize(self) -> str:
-        """Serialize this connection for reconstruction.
-
-        The returned string can be passed to :func:`lancedb.deserialize_conn`
-        to recreate an equivalent connection, e.g. in a remote worker.
-
-        Returns
-        -------
-        str
-            Serialized representation of this connection.
-        """
-        raise NotImplementedError("serialize is not supported for this connection type")
-
 
 class LanceDBConnection(DBConnection):
     """
@@ -594,7 +581,6 @@ class LanceDBConnection(DBConnection):
     ):
         if _inner is not None:
             self._conn = _inner
-            self._cached_namespace_client = None
             return
 
         if not isinstance(uri, Path):
@@ -642,7 +628,6 @@ class LanceDBConnection(DBConnection):
         # beyond _conn.
         self.storage_options = storage_options
         self._conn = AsyncConnection(LOOP.run(do_connect()))
-        self._cached_namespace_client: Optional[LanceNamespace] = None
 
     @property
     def read_consistency_interval(self) -> Optional[timedelta]:
@@ -667,22 +652,6 @@ class LanceDBConnection(DBConnection):
         val += ")"
         return val
 
-    @override
-    def serialize(self) -> str:
-        import json
-
-        rci = self.read_consistency_interval
-        return json.dumps(
-            {
-                "connection_type": "local",
-                "uri": self.uri,
-                "storage_options": self.storage_options,
-                "read_consistency_interval_seconds": (
-                    rci.total_seconds() if rci else None
-                ),
-            }
-        )
-
     async def _async_get_table_names(self, start_after: Optional[str], limit: int):
         conn = AsyncConnection(await lancedb_connect(self.uri))
         return await conn.table_names(start_after=start_after, limit=limit)
@@ -718,10 +687,10 @@ class LanceDBConnection(DBConnection):
         """
         if namespace_path is None:
             namespace_path = []
-        return self._namespace_conn().list_namespaces(
-            namespace_path=namespace_path,
-            page_token=page_token,
-            limit=limit,
+        return LOOP.run(
+            self._conn.list_namespaces(
+                namespace_path=namespace_path, page_token=page_token, limit=limit
+            )
         )
 
     @override
@@ -731,10 +700,27 @@ class LanceDBConnection(DBConnection):
         mode: Optional[str] = None,
         properties: Optional[Dict[str, str]] = None,
     ) -> CreateNamespaceResponse:
-        return self._namespace_conn().create_namespace(
-            namespace_path=namespace_path,
-            mode=mode,
-            properties=properties,
+        """Create a new namespace.
+
+        Parameters
+        ----------
+        namespace_path: List[str]
+            The namespace identifier to create.
+        mode: str, optional
+            Creation mode - "create" (fail if exists), "exist_ok" (skip if exists),
+            or "overwrite" (replace if exists). Case insensitive.
+        properties: Dict[str, str], optional
+            Properties to set on the namespace.
+
+        Returns
+        -------
+        CreateNamespaceResponse
+            Response containing the properties of the created namespace.
+        """
+        return LOOP.run(
+            self._conn.create_namespace(
+                namespace_path=namespace_path, mode=mode, properties=properties
+            )
         )
 
     @override
@@ -744,19 +730,46 @@ class LanceDBConnection(DBConnection):
         mode: Optional[str] = None,
         behavior: Optional[str] = None,
     ) -> DropNamespaceResponse:
-        return self._namespace_conn().drop_namespace(
-            namespace_path=namespace_path,
-            mode=mode,
-            behavior=behavior,
+        """Drop a namespace.
+
+        Parameters
+        ----------
+        namespace_path: List[str]
+            The namespace identifier to drop.
+        mode: str, optional
+            Whether to skip if not exists ("SKIP") or fail ("FAIL"). Case insensitive.
+        behavior: str, optional
+            Whether to restrict drop if not empty ("RESTRICT") or cascade ("CASCADE").
+            Case insensitive.
+
+        Returns
+        -------
+        DropNamespaceResponse
+            Response containing properties and transaction_id if applicable.
+        """
+        return LOOP.run(
+            self._conn.drop_namespace(
+                namespace_path=namespace_path, mode=mode, behavior=behavior
+            )
         )
 
     @override
     def describe_namespace(
         self, namespace_path: List[str]
     ) -> DescribeNamespaceResponse:
-        return self._namespace_conn().describe_namespace(
-            namespace_path=namespace_path,
-        )
+        """Describe a namespace.
+
+        Parameters
+        ----------
+        namespace_path: List[str]
+            The namespace identifier to describe.
+
+        Returns
+        -------
+        DescribeNamespaceResponse
+            Response containing the namespace properties.
+        """
+        return LOOP.run(self._conn.describe_namespace(namespace_path=namespace_path))
 
     @override
     def list_tables(
@@ -785,12 +798,6 @@ class LanceDBConnection(DBConnection):
         """
         if namespace_path is None:
             namespace_path = []
-        if namespace_path:
-            return self._namespace_conn().list_tables(
-                namespace_path=namespace_path,
-                page_token=page_token,
-                limit=limit,
-            )
         return LOOP.run(
             self._conn.list_tables(
                 namespace_path=namespace_path, page_token=page_token, limit=limit
@@ -879,22 +886,6 @@ class LanceDBConnection(DBConnection):
             raise ValueError("mode must be either 'create' or 'overwrite'")
         validate_table_name(name)
 
-        if namespace_path:
-            return self._namespace_conn().create_table(
-                name,
-                data=data,
-                schema=schema,
-                mode=mode,
-                exist_ok=exist_ok,
-                on_bad_vectors=on_bad_vectors,
-                fill_value=fill_value,
-                embedding_functions=embedding_functions,
-                namespace_path=namespace_path,
-                storage_options=storage_options,
-                data_storage_version=data_storage_version,
-                enable_v2_manifest_paths=enable_v2_manifest_paths,
-            )
-
         tbl = LanceTable.create(
             self,
             name,
@@ -910,19 +901,6 @@ class LanceDBConnection(DBConnection):
         )
         return tbl
 
-    def _namespace_conn(self) -> DBConnection:
-        """Return a LanceNamespaceDBConnection backed by this connection's
-        directory namespace.  Used to delegate child-namespace operations."""
-        from lancedb.namespace import LanceNamespaceDBConnection
-
-        return LanceNamespaceDBConnection(
-            self.namespace_client(),
-            read_consistency_interval=self.read_consistency_interval,
-            storage_options=self.storage_options,
-            namespace_client_impl=None,
-            namespace_client_properties=None,
-        )
-
     @override
     def open_table(
         self,
@@ -939,8 +917,7 @@ class LanceDBConnection(DBConnection):
         name: str
             The name of the table.
         namespace_path: List[str], optional
-            The namespace to open the table from.  When non-empty, the
-            table is resolved through the directory namespace client.
+            The namespace to open the table from.
 
         Returns
         -------
@@ -959,14 +936,6 @@ class LanceDBConnection(DBConnection):
                 stacklevel=2,
             )
 
-        if namespace_path:
-            return self._namespace_conn().open_table(
-                name,
-                namespace_path=namespace_path,
-                storage_options=storage_options,
-                index_cache_size=index_cache_size,
-            )
-
         return LanceTable.open(
             self,
             name,
@@ -1051,9 +1020,6 @@ class LanceDBConnection(DBConnection):
         """
         if namespace_path is None:
             namespace_path = []
-        if namespace_path:
-            self._namespace_conn().drop_table(name, namespace_path=namespace_path)
-            return
         LOOP.run(
             self._conn.drop_table(
                 name, namespace_path=namespace_path, ignore_missing=ignore_missing
@@ -1105,17 +1071,14 @@ class LanceDBConnection(DBConnection):
         """Get the equivalent namespace client for this connection.
 
         Returns a DirectoryNamespace pointing to the same root with the
-        same storage options.  The result is cached for the lifetime of
-        this connection.
+        same storage options.
 
         Returns
         -------
         LanceNamespace
             The namespace client for this connection.
         """
-        if self._cached_namespace_client is None:
-            self._cached_namespace_client = LOOP.run(self._conn.namespace_client())
-        return self._cached_namespace_client
+        return LOOP.run(self._conn.namespace_client())
 
     @deprecation.deprecated(
         deprecated_in="0.15.1",

python/python/lancedb/namespace.py

@@ -381,8 +381,6 @@ class LanceNamespaceDBConnection(DBConnection):
         storage_options: Optional[Dict[str, str]] = None,
         session: Optional[Session] = None,
         namespace_client_pushdown_operations: Optional[List[str]] = None,
-        namespace_client_impl: Optional[str] = None,
-        namespace_client_properties: Optional[Dict[str, str]] = None,
     ):
         """
         Initialize a namespace-based LanceDB connection.
@@ -408,43 +406,12 @@ class LanceNamespaceDBConnection(DBConnection):
               namespace.create_table() instead of using declare_table + local write.
 
             Default is None (no pushdown, all operations run locally).
-        namespace_client_impl : Optional[str]
-            The namespace implementation name used to create this connection.
-            Stored for serialization purposes.
-        namespace_client_properties : Optional[Dict[str, str]]
-            The namespace properties used to create this connection.
-            Stored for serialization purposes.
         """
         self._namespace_client = namespace_client
         self.read_consistency_interval = read_consistency_interval
         self.storage_options = storage_options or {}
         self.session = session
-        self._namespace_client_pushdown_operations = set(
-            namespace_client_pushdown_operations or []
-        )
-        self._namespace_client_impl = namespace_client_impl
-        self._namespace_client_properties = namespace_client_properties
-
-    @override
-    def serialize(self) -> str:
-        import json
-
-        return json.dumps(
-            {
-                "connection_type": "namespace",
-                "namespace_client_impl": self._namespace_client_impl,
-                "namespace_client_properties": self._namespace_client_properties,
-                "namespace_client_pushdown_operations": sorted(
-                    self._namespace_client_pushdown_operations
-                ),
-                "storage_options": self.storage_options or None,
-                "read_consistency_interval_seconds": (
-                    self.read_consistency_interval.total_seconds()
-                    if self.read_consistency_interval
-                    else None
-                ),
-            }
-        )
+        self._pushdown_operations = set(namespace_client_pushdown_operations or [])
 
     @override
     def table_names(
@@ -500,7 +467,7 @@ class LanceNamespaceDBConnection(DBConnection):
 
         table_id = namespace_path + [name]
 
-        if "CreateTable" in self._namespace_client_pushdown_operations:
+        if "CreateTable" in self._pushdown_operations:
             return self._create_table_server_side(
                 name=name,
                 data=data,
@@ -582,7 +549,7 @@ class LanceNamespaceDBConnection(DBConnection):
             storage_options=merged_storage_options,
             location=location,
             namespace_client=self._namespace_client,
-            pushdown_operations=self._namespace_client_pushdown_operations,
+            pushdown_operations=self._pushdown_operations,
         )
 
         return tbl
@@ -613,13 +580,10 @@ class LanceNamespaceDBConnection(DBConnection):
             fill_value=fill_value,
         )
 
-        merged = dict(self.storage_options or {})
-        if storage_options:
-            merged.update(storage_options)
         request = CreateTableRequest(
             id=table_id,
             mode=_normalize_create_table_mode(mode),
-            properties=merged or None,
+            properties=self.storage_options if self.storage_options else None,
         )
 
         try:
@@ -923,7 +887,7 @@ class LanceNamespaceDBConnection(DBConnection):
             location=table_uri,
             namespace_client=namespace_client,
             managed_versioning=managed_versioning,
-            pushdown_operations=self._namespace_client_pushdown_operations,
+            pushdown_operations=self._pushdown_operations,
         )
 
     @override
@@ -987,9 +951,7 @@ class AsyncLanceNamespaceDBConnection:
         self.read_consistency_interval = read_consistency_interval
         self.storage_options = storage_options or {}
         self.session = session
-        self._namespace_client_pushdown_operations = set(
-            namespace_client_pushdown_operations or []
-        )
+        self._pushdown_operations = set(namespace_client_pushdown_operations or [])
 
     async def table_names(
         self,
@@ -1044,7 +1006,7 @@ class AsyncLanceNamespaceDBConnection:
 
         table_id = namespace_path + [name]
 
-        if "CreateTable" in self._namespace_client_pushdown_operations:
+        if "CreateTable" in self._pushdown_operations:
             return await self._create_table_server_side(
                 name=name,
                 data=data,
@@ -1124,7 +1086,7 @@ class AsyncLanceNamespaceDBConnection:
                 storage_options=merged_storage_options,
                 location=location,
                 namespace_client=self._namespace_client,
-                pushdown_operations=self._namespace_client_pushdown_operations,
+                pushdown_operations=self._pushdown_operations,
             )
 
         lance_table = await asyncio.to_thread(_create_table)
@@ -1158,13 +1120,10 @@ class AsyncLanceNamespaceDBConnection:
                 fill_value=fill_value,
             )
 
-            merged = dict(self.storage_options or {})
-            if storage_options:
-                merged.update(storage_options)
             request = CreateTableRequest(
                 id=table_id,
                 mode=_normalize_create_table_mode(mode),
-                properties=merged or None,
+                properties=self.storage_options if self.storage_options else None,
             )
 
             self._namespace_client.create_table(request, arrow_ipc_bytes)
@@ -1231,7 +1190,7 @@ class AsyncLanceNamespaceDBConnection:
                 location=response.location,
                 namespace_client=self._namespace_client,
                 managed_versioning=managed_versioning,
-                pushdown_operations=self._namespace_client_pushdown_operations,
+                pushdown_operations=self._pushdown_operations,
             )
 
         lance_table = await asyncio.to_thread(_open_table)
@@ -1513,8 +1472,6 @@ def connect_namespace(
         storage_options=storage_options,
         session=session,
         namespace_client_pushdown_operations=namespace_client_pushdown_operations,
-        namespace_client_impl=namespace_client_impl,
-        namespace_client_properties=namespace_client_properties,
     )
 
 

python/python/lancedb/permutation.py

@@ -779,6 +779,19 @@ class Permutation:
         batch = LOOP.run(do_getitems())
         return self.transform_fn(batch)
 
+    def _snapshot_indices(self) -> pa.RecordBatch:
+        """
+        Materialize the current permutation view as ordered row ids.
+
+        This is an internal helper for dataset integrations and should not be
+        considered stable public API.
+        """
+
+        async def do_snapshot():
+            return await self.reader.snapshot_indices()
+
+        return LOOP.run(do_snapshot())
+
     @deprecated(details="Use with_skip instead")
     def skip(self, skip: int) -> "Permutation":
         """

python/python/tests/test_db.py

@@ -897,22 +897,42 @@ def test_bypass_vector_index_sync(tmp_db: lancedb.DBConnection):
 
 
 def test_local_namespace_operations(tmp_path):
-    """Test that local mode namespace operations work via directory namespace."""
+    """Test that local mode namespace operations behave as expected."""
+    # Create a local database connection
     db = lancedb.connect(tmp_path)
 
-    # Root namespace starts empty
-    assert db.list_namespaces().namespaces == []
+    # Test list_namespaces returns empty list for root namespace
+    namespaces = db.list_namespaces().namespaces
+    assert namespaces == []
 
-    # Create and list child namespace
-    db.create_namespace(["child"])
-    assert "child" in db.list_namespaces().namespaces
+    # Test list_namespaces with non-empty namespace raises NotImplementedError
+    with pytest.raises(
+        NotImplementedError,
+        match="Namespace operations are not supported for listing database",
+    ):
+        db.list_namespaces(namespace_path=["test"])
 
-    # List namespaces under child
-    assert db.list_namespaces(namespace_path=["child"]).namespaces == []
 
-    # Drop namespace
-    db.drop_namespace(["child"])
-    assert db.list_namespaces().namespaces == []
+def test_local_create_namespace_not_supported(tmp_path):
+    """Test that create_namespace is not supported in local mode."""
+    db = lancedb.connect(tmp_path)
+
+    with pytest.raises(
+        NotImplementedError,
+        match="Namespace operations are not supported for listing database",
+    ):
+        db.create_namespace(["test_namespace"])
+
+
+def test_local_drop_namespace_not_supported(tmp_path):
+    """Test that drop_namespace is not supported in local mode."""
+    db = lancedb.connect(tmp_path)
+
+    with pytest.raises(
+        NotImplementedError,
+        match="Namespace operations are not supported for listing database",
+    ):
+        db.drop_namespace(["test_namespace"])
 
 
 def test_clone_table_latest_version(tmp_path):

python/python/tests/test_namespace.py

@@ -681,7 +681,7 @@ class TestPushdownOperations:
             {"root": self.temp_dir},
             namespace_client_pushdown_operations=["QueryTable"],
         )
-        assert "QueryTable" in db._namespace_client_pushdown_operations
+        assert "QueryTable" in db._pushdown_operations
 
     def test_create_table_pushdown_stored(self):
         """Test that CreateTable pushdown is stored on sync connection."""
@@ -690,7 +690,7 @@ class TestPushdownOperations:
             {"root": self.temp_dir},
             namespace_client_pushdown_operations=["CreateTable"],
         )
-        assert "CreateTable" in db._namespace_client_pushdown_operations
+        assert "CreateTable" in db._pushdown_operations
 
     def test_both_pushdowns_stored(self):
         """Test that both pushdown operations can be set together."""
@@ -699,13 +699,13 @@ class TestPushdownOperations:
             {"root": self.temp_dir},
             namespace_client_pushdown_operations=["QueryTable", "CreateTable"],
         )
-        assert "QueryTable" in db._namespace_client_pushdown_operations
-        assert "CreateTable" in db._namespace_client_pushdown_operations
+        assert "QueryTable" in db._pushdown_operations
+        assert "CreateTable" in db._pushdown_operations
 
     def test_pushdown_defaults_to_empty(self):
         """Test that pushdown operations default to empty."""
         db = lancedb.connect_namespace("dir", {"root": self.temp_dir})
-        assert len(db._namespace_client_pushdown_operations) == 0
+        assert len(db._pushdown_operations) == 0
 
 
 @pytest.mark.asyncio
@@ -727,7 +727,7 @@ class TestAsyncPushdownOperations:
             {"root": self.temp_dir},
             namespace_client_pushdown_operations=["QueryTable"],
         )
-        assert "QueryTable" in db._namespace_client_pushdown_operations
+        assert "QueryTable" in db._pushdown_operations
 
     async def test_async_create_table_pushdown_stored(self):
         """Test that CreateTable pushdown is stored on async connection."""
@@ -736,9 +736,9 @@ class TestAsyncPushdownOperations:
             {"root": self.temp_dir},
             namespace_client_pushdown_operations=["CreateTable"],
         )
-        assert "CreateTable" in db._namespace_client_pushdown_operations
+        assert "CreateTable" in db._pushdown_operations
 
     async def test_async_pushdown_defaults_to_empty(self):
         """Test that pushdown operations default to empty on async connection."""
         db = lancedb.connect_namespace_async("dir", {"root": self.temp_dir})
-        assert len(db._namespace_client_pushdown_operations) == 0
+        assert len(db._pushdown_operations) == 0

python/python/tests/test_permutation.py

@@ -2,6 +2,7 @@
 # SPDX-FileCopyrightText: Copyright The LanceDB Authors
 
 import pyarrow as pa
+import pyarrow.compute as pc
 import math
 import pytest
 
@@ -643,6 +644,60 @@ def test_limit_offset(some_permutation: Permutation):
         some_permutation.with_skip(500).with_take(500).num_rows
 
 
+def test_snapshot_indices_identity(mem_db: DBConnection):
+    table = mem_db.create_table(
+        "identity_snapshot_table",
+        pa.table({"id": range(10), "value": range(10)}),
+    )
+
+    snapshot = Permutation.identity(table)._snapshot_indices()
+
+    assert snapshot.schema == pa.schema(
+        [pa.field("row_id", pa.uint64(), nullable=False)]
+    )
+    assert snapshot.column("row_id").to_pylist() == list(range(10))
+
+
+def test_snapshot_indices_split_respects_permutation_order(
+    some_table: Table, some_perm_table: Table
+):
+    permutation = Permutation.from_tables(some_table, some_perm_table, "test")
+    snapshot = permutation._snapshot_indices()
+    row_ids = snapshot.column("row_id").to_pylist()
+
+    assert snapshot.schema == pa.schema(
+        [pa.field("row_id", pa.uint64(), nullable=False)]
+    )
+    assert len(row_ids) == permutation.num_rows == 50
+
+    permutation_rows = some_perm_table.to_arrow()
+    expected = permutation_rows.filter(pc.equal(permutation_rows["split_id"], 1))[
+        "row_id"
+    ].to_pylist()
+    assert row_ids == expected
+
+
+def test_snapshot_indices_tracks_skip_take(some_permutation: Permutation):
+    full_snapshot = some_permutation._snapshot_indices().column("row_id").to_pylist()
+    sliced = some_permutation.with_skip(100).with_take(25)._snapshot_indices()
+
+    assert sliced.column("row_id").to_pylist() == full_snapshot[100:125]
+
+
+def test_snapshot_indices_ignores_selection_changes(some_permutation: Permutation):
+    snapshot = some_permutation._snapshot_indices()
+    selected = (
+        some_permutation.select_columns(["id"])
+        .rename_column("id", "row_id_alias")
+        .with_batch_size(32)
+        ._snapshot_indices()
+    )
+
+    assert (
+        selected.column("row_id").to_pylist() == snapshot.column("row_id").to_pylist()
+    )
+
+
 def test_remove_columns(some_permutation: Permutation):
     assert some_permutation.remove_columns(["value"]).schema == pa.schema(
         [("id", pa.int64())]

python/src/permutation.rs

@@ -303,6 +303,15 @@ impl PyPermutationReader {
         slf.reader.count_rows()
     }
 
+    #[pyo3(signature = ())]
+    pub fn snapshot_indices<'py>(slf: PyRef<'py, Self>) -> PyResult<Bound<'py, PyAny>> {
+        let reader = slf.reader.clone();
+        future_into_py(slf.py(), async move {
+            let batch = reader.snapshot_indices().await.infer_error()?;
+            Ok(PyArrowType(batch))
+        })
+    }
+
     #[pyo3(signature = (offset))]
     pub fn with_offset<'py>(slf: PyRef<'py, Self>, offset: u64) -> PyResult<Bound<'py, PyAny>> {
         let reader = slf.reader.as_ref().clone();

rust-toolchain.toml

@@ -1,2 +1,2 @@
 [toolchain]
-channel = "1.94.0"
+channel = "1.91.0"

rust/lancedb/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "lancedb"
-version = "0.28.0-beta.4"
+version = "0.28.0-beta.1"
 edition.workspace = true
 description = "LanceDB: A serverless, low-latency vector database for AI applications"
 license.workspace = true

rust/lancedb/src/dataloader/permutation/reader.rs

@@ -20,7 +20,7 @@ use arrow::array::AsArray;
 use arrow::compute::concat_batches;
 use arrow::datatypes::UInt64Type;
 use arrow_array::{RecordBatch, UInt64Array};
-use arrow_schema::SchemaRef;
+use arrow_schema::{DataType, Field, Schema, SchemaRef};
 use futures::{StreamExt, TryStreamExt};
 use lance::dataset::scanner::DatasetRecordBatchStream;
 use lance::io::RecordBatchStream;
@@ -409,6 +409,54 @@ impl PermutationReader {
         Self::row_ids_to_batches(self.base_table.clone(), row_ids, selection).await
     }
 
+    pub async fn snapshot_indices(&self) -> Result<RecordBatch> {
+        let row_ids = if let Some(permutation_table) = &self.permutation_table {
+            permutation_table
+                .query(
+                    &AnyQuery::Query(QueryRequest {
+                        select: Select::Columns(vec![SRC_ROW_ID_COL.to_string()]),
+                        filter: Some(QueryFilter::Sql(format!(
+                            "{} = {}",
+                            SPLIT_ID_COLUMN, self.split
+                        ))),
+                        offset: self.offset.map(|o| o as usize),
+                        limit: self.limit.map(|l| l as usize),
+                        ..Default::default()
+                    }),
+                    QueryExecutionOptions::default(),
+                )
+                .await?
+        } else {
+            self.base_table
+                .query(
+                    &AnyQuery::Query(QueryRequest {
+                        select: Select::Columns(vec![ROW_ID.to_string()]),
+                        offset: self.offset.map(|o| o as usize),
+                        limit: self.limit.map(|l| l as usize),
+                        ..Default::default()
+                    }),
+                    QueryExecutionOptions::default(),
+                )
+                .await?
+        };
+
+        let batches = row_ids.try_collect::<Vec<_>>().await?;
+        let schema = Arc::new(Schema::new(vec![Field::new(
+            SRC_ROW_ID_COL,
+            DataType::UInt64,
+            false,
+        )]));
+        if batches.is_empty() {
+            return Ok(RecordBatch::try_new(
+                schema,
+                vec![Arc::new(UInt64Array::from(Vec::<u64>::new()))],
+            )?);
+        }
+
+        let batch = concat_batches(&batches[0].schema(), &batches)?;
+        Ok(RecordBatch::try_new(schema, vec![batch.column(0).clone()])?)
+    }
+
     /// If we are going to use `take` then we load the offset -> row id map once for the split and cache it
     ///
     /// This method fetches the map with find-or-create semantics.

rust/lancedb/src/embeddings/bedrock.rs

@@ -177,7 +177,6 @@ impl BedrockEmbeddingFunction {
                         ))
                         .send()
                         .await
-                        .map_err(Box::new)
                 })
             })
             .unwrap();