Merge remote-tracking branch 'origin/main' into gatekeeper/fix-2107-1

# Conflicts:
#	python/python/tests/test_table.py

.github/workflows/rust.yml

@@ -296,18 +296,16 @@ jobs:
           cargo update -p aws-types --precise 1.3.9
           cargo update -p aws-sigv4 --precise 1.3.5
           cargo update -p aws-credential-types --precise 1.2.8
-          # aws-smithy-checksums must stay at or above 0.63.13: OpenDAL's S3
-          # service needs crc-fast ~1.9, and older releases pin it to ~1.3.
-          cargo update -p aws-smithy-checksums --precise 0.63.13
+          cargo update -p aws-smithy-checksums --precise 0.63.9
           cargo update -p aws-smithy-runtime --precise 1.9.3
-          cargo update -p aws-smithy-http --precise 0.62.6
-          cargo update -p aws-smithy-eventstream --precise 0.60.14
+          cargo update -p aws-smithy-http --precise 0.62.4
+          cargo update -p aws-smithy-eventstream --precise 0.60.12
           cargo update -p aws-smithy-http-client --precise 1.1.3
           cargo update -p aws-smithy-observability --precise 0.1.4
           cargo update -p aws-smithy-query --precise 0.60.8
-          cargo update -p aws-smithy-runtime-api --precise 1.9.3
-          cargo update -p aws-smithy-async --precise 1.2.7
-          cargo update -p aws-smithy-types --precise 1.3.6
+          cargo update -p aws-smithy-runtime-api --precise 1.9.1
+          cargo update -p aws-smithy-async --precise 1.2.6
+          cargo update -p aws-smithy-types --precise 1.3.5
           cargo update -p aws-smithy-xml --precise 0.60.11
           cargo update -p home --precise 0.5.9
       - name: cargo +${{ matrix.msrv }} check

AGENTS.md

@@ -152,54 +152,3 @@ Please consider the following when reviewing code contributions.
 ### Documentation
 * New features must include updates to the rust documentation comments. Link to
   relevant structs and methods to increase the value of documentation.
-
-## Cursor Cloud specific instructions
-
-The VM snapshot already has the Rust `1.97.0` toolchain (auto-selected by
-`rust-toolchain.toml`), `protoc`, `uv` (on `PATH` via `~/.bashrc`), the Rust
-debug build artifacts, the Python editable extension, and `nodejs/node_modules`.
-The startup update script only refreshes dependencies (`uv sync` for Python and
-`pnpm install` for Node); it deliberately does NOT rebuild the native
-extensions. After changing Rust or PyO3/napi binding code you must rebuild the
-affected binding yourself (see per-binding rebuild commands below).
-
-Non-obvious caveats discovered during setup:
-
-* The documented Python bootstrap `uv run --extra tests --extra dev maturin
-  develop --extras tests,dev` does not work as-is here: `maturin` is not
-  installed as a CLI in the uv environment, and `maturin develop --extras`
-  runs its own dependency resolution that cannot find the prerelease
-  `pylance==9.0.0rc1` (it lacks the extra package index that `uv` uses via
-  `uv.lock`). Because `uv run --extra tests --extra dev` already installs those
-  extras, the working command is:
-  `cd python && uv run --extra tests --extra dev --with maturin maturin develop`
-  (note: `--with maturin`, and no `--extras`). This is the Python binding
-  rebuild command.
-* Rust core, the Python extension (maturin), and the Node addon (napi) all
-  compile into the SHARED `/workspace/target`. Cargo feature unification differs
-  between `maturin develop` and `pnpm build`, so alternating between building
-  the Python and Node bindings forces a full recompile of shared crates
-  (`lancedb`, `datafusion`, `lance-*`) — roughly 6-7 min each way on this
-  4-core VM. Build one binding at a time to avoid the churn.
-* The `_lancedb` release build (triggered when `uv run`/`uv sync` installs the
-  `lancedb` project itself) uses `lto = "fat"` + `opt-level = 3`, needs ~11 GB
-  RAM, and takes ~20 min cold on this VM. To avoid it, the update script uses
-  `uv sync --no-install-project --inexact` (the `--inexact` flag is required so
-  the sync does not uninstall the editable extension). Prefer the debug
-  `maturin develop` (~6 min cold, seconds when warm) for iteration.
-* `cargo check` only produces metadata, so the first `cargo run --example ...`
-  or `cargo test` after a check triggers a large codegen/link compile.
-* Node binding rebuild: `cd nodejs && pnpm build` (napi debug build + `tsc`).
-  The native addon lands at `nodejs/dist/lancedb.linux-x64-gnu.node`.
-
-Verified working (local backend, no cloud credentials needed):
-
-* Rust: `cargo check/clippy --features remote --tests --examples`,
-  `cargo test --features remote -p lancedb --lib`, `cargo run --features remote
-  --example simple`.
-* Python: `cd python && uv run --extra tests pytest python/tests/test_table.py`,
-  `uv run --directory python --extra dev ruff check python`.
-* Node: `cd nodejs && pnpm lint`, `pnpm test __test__/connection.test.ts`.
-
-Java (`java/`) is optional; its integration tests need LanceDB Cloud
-credentials (`LANCEDB_DB`, `LANCEDB_API_KEY`) and were not set up here.

Cargo.toml

@@ -13,20 +13,20 @@ categories = ["database-implementations"]
 rust-version = "1.91.0"
 
 [workspace.dependencies]
-lance = { "version" = "=11.0.0-beta.2", default-features = false, "tag" = "v11.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-core = { "version" = "=11.0.0-beta.2", "tag" = "v11.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-datagen = { "version" = "=11.0.0-beta.2", "tag" = "v11.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-file = { "version" = "=11.0.0-beta.2", "tag" = "v11.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-io = { "version" = "=11.0.0-beta.2", default-features = false, "tag" = "v11.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-index = { "version" = "=11.0.0-beta.2", "tag" = "v11.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-linalg = { "version" = "=11.0.0-beta.2", "tag" = "v11.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-namespace = { "version" = "=11.0.0-beta.2", "tag" = "v11.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-namespace-impls = { "version" = "=11.0.0-beta.2", default-features = false, "tag" = "v11.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-table = { "version" = "=11.0.0-beta.2", "tag" = "v11.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-testing = { "version" = "=11.0.0-beta.2", "tag" = "v11.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-datafusion = { "version" = "=11.0.0-beta.2", "tag" = "v11.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-encoding = { "version" = "=11.0.0-beta.2", "tag" = "v11.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-arrow = { "version" = "=11.0.0-beta.2", "tag" = "v11.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance = { "version" = "=10.1.0-beta.1", default-features = false, "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
+lance-core = { "version" = "=10.1.0-beta.1", "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
+lance-datagen = { "version" = "=10.1.0-beta.1", "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
+lance-file = { "version" = "=10.1.0-beta.1", "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
+lance-io = { "version" = "=10.1.0-beta.1", default-features = false, "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
+lance-index = { "version" = "=10.1.0-beta.1", "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
+lance-linalg = { "version" = "=10.1.0-beta.1", "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
+lance-namespace = { "version" = "=10.1.0-beta.1", "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
+lance-namespace-impls = { "version" = "=10.1.0-beta.1", default-features = false, "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
+lance-table = { "version" = "=10.1.0-beta.1", "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
+lance-testing = { "version" = "=10.1.0-beta.1", "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
+lance-datafusion = { "version" = "=10.1.0-beta.1", "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
+lance-encoding = { "version" = "=10.1.0-beta.1", "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
+lance-arrow = { "version" = "=10.1.0-beta.1", "tag" = "v10.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
 ahash = "0.8"
 # Note that this one does not include pyarrow
 arrow = { version = "58.0.0", optional = false }

java/pom.xml

@@ -28,7 +28,7 @@
     <properties>
         <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
         <arrow.version>15.0.0</arrow.version>
-        <lance-core.version>11.0.0-beta.2</lance-core.version>
+        <lance-core.version>10.1.0-beta.1</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>

python/python/lancedb/db.py

@@ -5,6 +5,7 @@
 from __future__ import annotations
 
 from abc import abstractmethod
+import asyncio
 from datetime import timedelta
 from pathlib import Path
 import sys
@@ -1735,8 +1736,16 @@ class AsyncConnection(object):
         if fill_value is None:
             fill_value = 0.0
 
-        data, schema = sanitize_create_table(
-            data, schema, metadata, on_bad_vectors, fill_value
+        # Input preparation may advance a user-provided iterator.  Keep that work
+        # off the background event loop so an iterator can use the synchronous
+        # LanceDB API without blocking the loop that API needs to make progress.
+        data, schema = await asyncio.to_thread(
+            sanitize_create_table,
+            data,
+            schema,
+            metadata,
+            on_bad_vectors,
+            fill_value,
         )
         validate_schema(schema)
 

python/python/lancedb/table.py

@@ -5143,13 +5143,18 @@ class AsyncTable:
         if mode == "overwrite":
             # For overwrite, apply the same preprocessing as create_table
             # so vector columns are inferred as FixedSizeList.
-            data, _ = sanitize_create_table(
-                data, None, on_bad_vectors=on_bad_vectors, fill_value=fill_value
+            data, _ = await asyncio.to_thread(
+                sanitize_create_table,
+                data,
+                None,
+                on_bad_vectors=on_bad_vectors,
+                fill_value=fill_value,
             )
         elif on_bad_vectors != "error" or (
             schema.metadata is not None and b"embedding_functions" in schema.metadata
         ):
-            data = _sanitize_data(
+            data = await asyncio.to_thread(
+                _sanitize_data,
                 data,
                 schema,
                 metadata=schema.metadata,
@@ -5158,7 +5163,10 @@ class AsyncTable:
                 allow_subschema=True,
             )
         _register_optional_converters()
-        data = to_scannable(data)
+        # Converting an iterator peeks at its first item.  A synchronous query in
+        # that iterator schedules work on LOOP, so peeking on LOOP's own thread
+        # would deadlock waiting for itself.
+        data = await asyncio.to_thread(to_scannable, data)
         progress, owns = _normalize_progress(progress)
         try:
             return await self._inner.add(

python/python/tests/test_table.py

@@ -462,6 +462,30 @@ def test_add(mem_db: DBConnection):
     _add(table, schema)
 
 
+def test_add_from_iterator_that_queries_table(mem_db: DBConnection):
+    source = mem_db.create_table("source", data=pa.table({"id": range(16)}))
+    target = mem_db.create_table("target", schema=source.schema)
+
+    def batches():
+        for _ in range(5):
+            yield source.search().limit(10).to_arrow()
+
+    target.add(batches())
+
+    assert target.count_rows() == 50
+
+
+def test_create_table_from_iterator_that_queries_table(mem_db: DBConnection):
+    source = mem_db.create_table("source", data=pa.table({"id": range(16)}))
+
+    def batches():
+        yield source.search().limit(10).to_arrow()
+
+    target = mem_db.create_table("target", data=batches())
+
+    assert target.count_rows() == 10
+
+
 def test_add_releases_arrow_buffers_without_gc(mem_db: DBConnection):
     """Regression test for https://github.com/lancedb/lancedb/issues/2512."""
     schema = pa.schema([pa.field("x", pa.int64())])

rust/lancedb/Cargo.toml

@@ -49,8 +49,8 @@ lance-namespace = { workspace = true }
 lance-namespace-impls = { workspace = true }
 metrics = { workspace = true, optional = true }
 metrics-util = { workspace = true, optional = true }
-# Pin the GooseFS SDK to the version required by Lance's OpenDAL dependency.
-goosefs-sdk = { version = "=0.1.9", optional = true }
+# Pin the transitive GooseFS SDK until the 0.1.6 compile break is fixed upstream.
+goosefs-sdk = { version = "=0.1.5", optional = true }
 moka = { workspace = true }
 pin-project = { workspace = true }
 tokio = { version = "1.23", features = ["rt-multi-thread", "sync"] }

rust/lancedb/src/blob.rs

@@ -17,7 +17,7 @@ use arrow_array::builder::LargeBinaryBuilder;
 use arrow_schema::{DataType, Field, Schema};
 use lance::dataset::{BlobRangeRequest as LanceBlobRangeRequest, Dataset, WriteParams};
 use lance_arrow::FieldExt;
-use lance_file::version::LanceFileVersion;
+use lance_encoding::version::LanceFileVersion;
 use lance_io::object_store::ObjectStore;
 use object_store::path::Path;
 

rust/lancedb/src/connection.rs

@@ -34,7 +34,7 @@ use crate::remote::{
     db::{OPT_REMOTE_API_KEY, OPT_REMOTE_HOST_OVERRIDE, OPT_REMOTE_REGION},
 };
 use lance::io::ObjectStoreParams;
-pub use lance_file::version::LanceFileVersion;
+pub use lance_encoding::version::LanceFileVersion;
 #[cfg(feature = "remote")]
 use lance_io::object_store::StorageOptions;
 use lance_io::object_store::{StorageOptionsAccessor, StorageOptionsProvider};

rust/lancedb/src/database/listing.rs

@@ -12,7 +12,7 @@ use lance::dataset::refs::Ref;
 use lance::dataset::{ReadParams, WriteMode, builder::DatasetBuilder};
 use lance::io::{ObjectStore, ObjectStoreParams, WrappingObjectStore};
 use lance_datafusion::utils::StreamingWriteSource;
-use lance_file::version::LanceFileVersion;
+use lance_encoding::version::LanceFileVersion;
 use lance_io::object_store::{StorageOptionsAccessor, StorageOptionsProvider};
 use lance_table::io::commit::commit_handler_from_url;
 use object_store::local::LocalFileSystem;

rust/lancedb/src/database/namespace.rs

@@ -201,7 +201,7 @@ impl LanceNamespaceDatabase {
         &self,
         request: &DbCreateTableRequest,
     ) -> Result<(
-        Option<lance_file::version::LanceFileVersion>,
+        Option<lance_encoding::version::LanceFileVersion>,
         Option<bool>,
         Option<bool>,
     )> {
@@ -214,7 +214,7 @@ impl LanceNamespaceDatabase {
 
         let storage_version_override = storage_options
             .and_then(|opts| opts.get(OPT_NEW_TABLE_STORAGE_VERSION))
-            .map(|s| s.parse::<lance_file::version::LanceFileVersion>())
+            .map(|s| s.parse::<lance_encoding::version::LanceFileVersion>())
             .transpose()?;
 
         let v2_manifest_override = storage_options

rust/lancedb/src/remote/table.rs

@@ -2942,7 +2942,7 @@ impl<S: HttpSend> BaseTable for RemoteTable<S> {
 }
 
 #[derive(Serialize, Clone, Debug)]
-pub struct MergeInsertRequest {
+pub(crate) struct MergeInsertRequest {
     on: String,
     when_matched_update_all: bool,
     when_matched_update_all_filt: Option<String>,
@@ -5907,18 +5907,16 @@ mod tests {
             .await
             .unwrap();
 
-        // Positions are relative to the first retained token, so dropping the
-        // leading "hello" stop word does not shift the remaining tokens.
         assert_eq!(
             tokens,
             vec![
                 FtsToken {
                     text: "こんにちは".to_string(),
-                    position: 0,
+                    position: 1,
                 },
                 FtsToken {
                     text: "世界".to_string(),
-                    position: 1,
+                    position: 2,
                 },
             ]
         );

rust/lancedb/src/remote/table/blobs.rs

@@ -90,7 +90,7 @@ struct RemoteBlobState {
 
 /// Seekable Cloud blob handle over HTTP Range.
 #[derive(Debug)]
-pub struct RemoteBlobFile {
+pub(crate) struct RemoteBlobFile {
     requester: Arc<dyn BlobRangeRequester>,
     state: Mutex<RemoteBlobState>,
     closed: AtomicBool,

rust/lancedb/src/remote/table/insert.rs

@@ -33,7 +33,7 @@ use crate::table::{AddResult, MergeResult};
 /// same Arrow-IPC streaming body and error side-channel; only the target
 /// endpoint, query parameters, and parsed result type differ.
 #[derive(Debug, Clone)]
-pub enum WriteOp {
+pub(crate) enum WriteOp {
     /// `add`: stream to `/v1/table/{id}/insert/`, optionally overwriting.
     Insert { overwrite: bool },
     /// `merge_insert`: stream to `/v1/table/{id}/merge_insert/` with the merge
@@ -49,7 +49,7 @@ pub enum WriteOp {
 /// The parsed server response for a completed write, discriminated by the
 /// operation that produced it.
 #[derive(Debug, Clone)]
-pub enum WriteResult {
+pub(crate) enum WriteResult {
     Add(AddResult),
     Merge(MergeResult),
 }

rust/lancedb/tests/blob_integration.rs

@@ -10,7 +10,7 @@ use arrow_array::{
 use arrow_schema::{DataType, Field, Fields, Schema};
 use futures::TryStreamExt;
 use lance::Dataset;
-use lance_file::version::LanceFileVersion;
+use lance_encoding::version::LanceFileVersion;
 use lancedb::{
     Connection, Error, Result, Table,
     blob::{BlobRangeRequest, blob},