chore: update lance dependency to v1.0.0-rc.3

.github/workflows/nodejs.yml

@@ -88,7 +88,7 @@ jobs:
         npm install -g @napi-rs/cli
     - name: Build
       run: |
-        npm ci --include=optional
+        npm ci
         npm run build:debug -- --profile ci
         npm run tsc
     - name: Setup localstack
@@ -146,7 +146,7 @@ jobs:
         npm install -g @napi-rs/cli
     - name: Build
       run: |
-        npm ci --include=optional
+        npm ci
         npm run build:debug -- --profile ci
         npm run tsc
     - name: Test

.github/workflows/python.yml

@@ -49,8 +49,8 @@ jobs:
 
   type-check:
     name: "Type Check"
-    timeout-minutes: 60
+    timeout-minutes: 30
-    runs-on: ubuntu-2404-8x-x64
+    runs-on: "ubuntu-22.04"
     defaults:
       run:
         shell: bash
@@ -78,7 +78,7 @@ jobs:
 
   doctest:
     name: "Doctest"
-    timeout-minutes: 60
+    timeout-minutes: 30
     runs-on: ubuntu-2404-8x-x64
     defaults:
       run:

Cargo.lock

@@ -3086,8 +3086,8 @@ checksum = "42703706b716c37f96a77aea830392ad231f44c9e9a67872fa5548707e11b11c"
 
 [[package]]
 name = "fsst"
-version = "1.0.0"
+version = "1.0.0-rc.3"
-source = "git+https://github.com/lance-format/lance.git?tag=v1.0.0#a0979691926f57afd5d3ac90bf6e5bb11188c0c3"
+source = "git+https://github.com/lance-format/lance.git?tag=v1.0.0-rc.3#2808908de4b5d367d3a8fabe20734ddd566dbf54"
 dependencies = [
  "arrow-array",
  "rand 0.9.2",
@@ -4422,8 +4422,8 @@ dependencies = [
 
 [[package]]
 name = "lance"
-version = "1.0.0"
+version = "1.0.0-rc.3"
-source = "git+https://github.com/lance-format/lance.git?tag=v1.0.0#a0979691926f57afd5d3ac90bf6e5bb11188c0c3"
+source = "git+https://github.com/lance-format/lance.git?tag=v1.0.0-rc.3#2808908de4b5d367d3a8fabe20734ddd566dbf54"
 dependencies = [
  "arrow",
  "arrow-arith",
@@ -4488,8 +4488,8 @@ dependencies = [
 
 [[package]]
 name = "lance-arrow"
-version = "1.0.0"
+version = "1.0.0-rc.3"
-source = "git+https://github.com/lance-format/lance.git?tag=v1.0.0#a0979691926f57afd5d3ac90bf6e5bb11188c0c3"
+source = "git+https://github.com/lance-format/lance.git?tag=v1.0.0-rc.3#2808908de4b5d367d3a8fabe20734ddd566dbf54"
 dependencies = [
  "arrow-array",
  "arrow-buffer",
@@ -4507,8 +4507,8 @@ dependencies = [
 
 [[package]]
 name = "lance-bitpacking"
-version = "1.0.0"
+version = "1.0.0-rc.3"
-source = "git+https://github.com/lance-format/lance.git?tag=v1.0.0#a0979691926f57afd5d3ac90bf6e5bb11188c0c3"
+source = "git+https://github.com/lance-format/lance.git?tag=v1.0.0-rc.3#2808908de4b5d367d3a8fabe20734ddd566dbf54"
 dependencies = [
  "arrayref",
  "paste",
@@ -4517,8 +4517,8 @@ dependencies = [
 
 [[package]]
 name = "lance-core"
-version = "1.0.0"
+version = "1.0.0-rc.3"
-source = "git+https://github.com/lance-format/lance.git?tag=v1.0.0#a0979691926f57afd5d3ac90bf6e5bb11188c0c3"
+source = "git+https://github.com/lance-format/lance.git?tag=v1.0.0-rc.3#2808908de4b5d367d3a8fabe20734ddd566dbf54"
 dependencies = [
  "arrow-array",
  "arrow-buffer",
@@ -4554,8 +4554,8 @@ dependencies = [
 
 [[package]]
 name = "lance-datafusion"
-version = "1.0.0"
+version = "1.0.0-rc.3"
-source = "git+https://github.com/lance-format/lance.git?tag=v1.0.0#a0979691926f57afd5d3ac90bf6e5bb11188c0c3"
+source = "git+https://github.com/lance-format/lance.git?tag=v1.0.0-rc.3#2808908de4b5d367d3a8fabe20734ddd566dbf54"
 dependencies = [
  "arrow",
  "arrow-array",
@@ -4585,8 +4585,8 @@ dependencies = [
 
 [[package]]
 name = "lance-datagen"
-version = "1.0.0"
+version = "1.0.0-rc.3"
-source = "git+https://github.com/lance-format/lance.git?tag=v1.0.0#a0979691926f57afd5d3ac90bf6e5bb11188c0c3"
+source = "git+https://github.com/lance-format/lance.git?tag=v1.0.0-rc.3#2808908de4b5d367d3a8fabe20734ddd566dbf54"
 dependencies = [
  "arrow",
  "arrow-array",
@@ -4603,8 +4603,8 @@ dependencies = [
 
 [[package]]
 name = "lance-encoding"
-version = "1.0.0"
+version = "1.0.0-rc.3"
-source = "git+https://github.com/lance-format/lance.git?tag=v1.0.0#a0979691926f57afd5d3ac90bf6e5bb11188c0c3"
+source = "git+https://github.com/lance-format/lance.git?tag=v1.0.0-rc.3#2808908de4b5d367d3a8fabe20734ddd566dbf54"
 dependencies = [
  "arrow-arith",
  "arrow-array",
@@ -4641,8 +4641,8 @@ dependencies = [
 
 [[package]]
 name = "lance-file"
-version = "1.0.0"
+version = "1.0.0-rc.3"
-source = "git+https://github.com/lance-format/lance.git?tag=v1.0.0#a0979691926f57afd5d3ac90bf6e5bb11188c0c3"
+source = "git+https://github.com/lance-format/lance.git?tag=v1.0.0-rc.3#2808908de4b5d367d3a8fabe20734ddd566dbf54"
 dependencies = [
  "arrow-arith",
  "arrow-array",
@@ -4674,8 +4674,8 @@ dependencies = [
 
 [[package]]
 name = "lance-geo"
-version = "1.0.0"
+version = "1.0.0-rc.3"
-source = "git+https://github.com/lance-format/lance.git?tag=v1.0.0#a0979691926f57afd5d3ac90bf6e5bb11188c0c3"
+source = "git+https://github.com/lance-format/lance.git?tag=v1.0.0-rc.3#2808908de4b5d367d3a8fabe20734ddd566dbf54"
 dependencies = [
  "datafusion",
  "geo-types",
@@ -4686,8 +4686,8 @@ dependencies = [
 
 [[package]]
 name = "lance-index"
-version = "1.0.0"
+version = "1.0.0-rc.3"
-source = "git+https://github.com/lance-format/lance.git?tag=v1.0.0#a0979691926f57afd5d3ac90bf6e5bb11188c0c3"
+source = "git+https://github.com/lance-format/lance.git?tag=v1.0.0-rc.3#2808908de4b5d367d3a8fabe20734ddd566dbf54"
 dependencies = [
  "arrow",
  "arrow-arith",
@@ -4748,8 +4748,8 @@ dependencies = [
 
 [[package]]
 name = "lance-io"
-version = "1.0.0"
+version = "1.0.0-rc.3"
-source = "git+https://github.com/lance-format/lance.git?tag=v1.0.0#a0979691926f57afd5d3ac90bf6e5bb11188c0c3"
+source = "git+https://github.com/lance-format/lance.git?tag=v1.0.0-rc.3#2808908de4b5d367d3a8fabe20734ddd566dbf54"
 dependencies = [
  "arrow",
  "arrow-arith",
@@ -4789,8 +4789,8 @@ dependencies = [
 
 [[package]]
 name = "lance-linalg"
-version = "1.0.0"
+version = "1.0.0-rc.3"
-source = "git+https://github.com/lance-format/lance.git?tag=v1.0.0#a0979691926f57afd5d3ac90bf6e5bb11188c0c3"
+source = "git+https://github.com/lance-format/lance.git?tag=v1.0.0-rc.3#2808908de4b5d367d3a8fabe20734ddd566dbf54"
 dependencies = [
  "arrow-array",
  "arrow-buffer",
@@ -4806,8 +4806,8 @@ dependencies = [
 
 [[package]]
 name = "lance-namespace"
-version = "1.0.0"
+version = "1.0.0-rc.3"
-source = "git+https://github.com/lance-format/lance.git?tag=v1.0.0#a0979691926f57afd5d3ac90bf6e5bb11188c0c3"
+source = "git+https://github.com/lance-format/lance.git?tag=v1.0.0-rc.3#2808908de4b5d367d3a8fabe20734ddd566dbf54"
 dependencies = [
  "arrow",
  "async-trait",
@@ -4819,8 +4819,8 @@ dependencies = [
 
 [[package]]
 name = "lance-namespace-impls"
-version = "1.0.0"
+version = "1.0.0-rc.3"
-source = "git+https://github.com/lance-format/lance.git?tag=v1.0.0#a0979691926f57afd5d3ac90bf6e5bb11188c0c3"
+source = "git+https://github.com/lance-format/lance.git?tag=v1.0.0-rc.3#2808908de4b5d367d3a8fabe20734ddd566dbf54"
 dependencies = [
  "arrow",
  "arrow-ipc",
@@ -4858,8 +4858,8 @@ dependencies = [
 
 [[package]]
 name = "lance-table"
-version = "1.0.0"
+version = "1.0.0-rc.3"
-source = "git+https://github.com/lance-format/lance.git?tag=v1.0.0#a0979691926f57afd5d3ac90bf6e5bb11188c0c3"
+source = "git+https://github.com/lance-format/lance.git?tag=v1.0.0-rc.3#2808908de4b5d367d3a8fabe20734ddd566dbf54"
 dependencies = [
  "arrow",
  "arrow-array",
@@ -4898,8 +4898,8 @@ dependencies = [
 
 [[package]]
 name = "lance-testing"
-version = "1.0.0"
+version = "1.0.0-rc.3"
-source = "git+https://github.com/lance-format/lance.git?tag=v1.0.0#a0979691926f57afd5d3ac90bf6e5bb11188c0c3"
+source = "git+https://github.com/lance-format/lance.git?tag=v1.0.0-rc.3#2808908de4b5d367d3a8fabe20734ddd566dbf54"
 dependencies = [
  "arrow-array",
  "arrow-schema",

Cargo.toml

@@ -15,20 +15,20 @@ categories = ["database-implementations"]
 rust-version = "1.78.0"
 
 [workspace.dependencies]
-lance = { "version" = "=1.0.0", default-features = false, "tag" = "v1.0.0", "git" = "https://github.com/lance-format/lance.git" }
+lance = { "version" = "=1.0.0-rc.3", default-features = false, "tag" = "v1.0.0-rc.3", "git" = "https://github.com/lance-format/lance.git" }
-lance-core = { "version" = "=1.0.0", "tag" = "v1.0.0", "git" = "https://github.com/lance-format/lance.git" }
+lance-core = { "version" = "=1.0.0-rc.3", "tag" = "v1.0.0-rc.3", "git" = "https://github.com/lance-format/lance.git" }
-lance-datagen = { "version" = "=1.0.0", "tag" = "v1.0.0", "git" = "https://github.com/lance-format/lance.git" }
+lance-datagen = { "version" = "=1.0.0-rc.3", "tag" = "v1.0.0-rc.3", "git" = "https://github.com/lance-format/lance.git" }
-lance-file = { "version" = "=1.0.0", "tag" = "v1.0.0", "git" = "https://github.com/lance-format/lance.git" }
+lance-file = { "version" = "=1.0.0-rc.3", "tag" = "v1.0.0-rc.3", "git" = "https://github.com/lance-format/lance.git" }
-lance-io = { "version" = "=1.0.0", default-features = false, "tag" = "v1.0.0", "git" = "https://github.com/lance-format/lance.git" }
+lance-io = { "version" = "=1.0.0-rc.3", default-features = false, "tag" = "v1.0.0-rc.3", "git" = "https://github.com/lance-format/lance.git" }
-lance-index = { "version" = "=1.0.0", "tag" = "v1.0.0", "git" = "https://github.com/lance-format/lance.git" }
+lance-index = { "version" = "=1.0.0-rc.3", "tag" = "v1.0.0-rc.3", "git" = "https://github.com/lance-format/lance.git" }
-lance-linalg = { "version" = "=1.0.0", "tag" = "v1.0.0", "git" = "https://github.com/lance-format/lance.git" }
+lance-linalg = { "version" = "=1.0.0-rc.3", "tag" = "v1.0.0-rc.3", "git" = "https://github.com/lance-format/lance.git" }
-lance-namespace = { "version" = "=1.0.0", "tag" = "v1.0.0", "git" = "https://github.com/lance-format/lance.git" }
+lance-namespace = { "version" = "=1.0.0-rc.3", "tag" = "v1.0.0-rc.3", "git" = "https://github.com/lance-format/lance.git" }
-lance-namespace-impls = { "version" = "=1.0.0", default-features = false, "tag" = "v1.0.0", "git" = "https://github.com/lance-format/lance.git" }
+lance-namespace-impls = { "version" = "=1.0.0-rc.3", default-features = false, "tag" = "v1.0.0-rc.3", "git" = "https://github.com/lance-format/lance.git" }
-lance-table = { "version" = "=1.0.0", "tag" = "v1.0.0", "git" = "https://github.com/lance-format/lance.git" }
+lance-table = { "version" = "=1.0.0-rc.3", "tag" = "v1.0.0-rc.3", "git" = "https://github.com/lance-format/lance.git" }
-lance-testing = { "version" = "=1.0.0", "tag" = "v1.0.0", "git" = "https://github.com/lance-format/lance.git" }
+lance-testing = { "version" = "=1.0.0-rc.3", "tag" = "v1.0.0-rc.3", "git" = "https://github.com/lance-format/lance.git" }
-lance-datafusion = { "version" = "=1.0.0", "tag" = "v1.0.0", "git" = "https://github.com/lance-format/lance.git" }
+lance-datafusion = { "version" = "=1.0.0-rc.3", "tag" = "v1.0.0-rc.3", "git" = "https://github.com/lance-format/lance.git" }
-lance-encoding = { "version" = "=1.0.0", "tag" = "v1.0.0", "git" = "https://github.com/lance-format/lance.git" }
+lance-encoding = { "version" = "=1.0.0-rc.3", "tag" = "v1.0.0-rc.3", "git" = "https://github.com/lance-format/lance.git" }
-lance-arrow = { "version" = "=1.0.0", "tag" = "v1.0.0", "git" = "https://github.com/lance-format/lance.git" }
+lance-arrow = { "version" = "=1.0.0-rc.3", "tag" = "v1.0.0-rc.3", "git" = "https://github.com/lance-format/lance.git" }
 ahash = "0.8"
 # Note that this one does not include pyarrow
 arrow = { version = "56.2", optional = false }

ci/set_lance_version.py

@@ -229,29 +229,6 @@ def set_local_version():
     update_cargo_toml(line_updater)
 
 
-def update_lockfiles(version: str, fallback_to_git: bool = False):
-    """
-    Update Cargo metadata and optionally fall back to using the git tag if the
-    requested crates.io version is unavailable.
-    """
-    try:
-        print("Updating lockfiles...", file=sys.stderr, end="")
-        run_command("cargo metadata > /dev/null")
-        print(" done.", file=sys.stderr)
-    except Exception as e:
-        if fallback_to_git and "failed to select a version" in str(e):
-            print(
-                f" failed for crates.io v{version}, retrying with git tag...",
-                file=sys.stderr,
-            )
-            set_preview_version(version)
-            print("Updating lockfiles...", file=sys.stderr, end="")
-            run_command("cargo metadata > /dev/null")
-            print(" done.", file=sys.stderr)
-        else:
-            raise
-
-
 parser = argparse.ArgumentParser(description="Set the version of the Lance package.")
 parser.add_argument(
     "version",
@@ -267,7 +244,6 @@ if args.version == "stable":
         file=sys.stderr,
     )
     set_stable_version(latest_stable_version)
-    update_lockfiles(latest_stable_version)
 elif args.version == "preview":
     latest_preview_version = get_latest_preview_version()
     print(
@@ -275,10 +251,8 @@ elif args.version == "preview":
         file=sys.stderr,
     )
     set_preview_version(latest_preview_version)
-    update_lockfiles(latest_preview_version)
 elif args.version == "local":
     set_local_version()
-    update_lockfiles("local")
 else:
     # Parse the version number.
     version = args.version
@@ -286,9 +260,11 @@ else:
     if version.startswith("v"):
         version = version[1:]
 
-    if "beta" in version:
+    if "beta" in version or "rc" in version:
         set_preview_version(version)
-        update_lockfiles(version)
     else:
         set_stable_version(version)
-        update_lockfiles(version, fallback_to_git=True)
+
+print("Updating lockfiles...", file=sys.stderr, end="")
+run_command("cargo metadata > /dev/null")
+print(" done.", file=sys.stderr)

python/.bumpversion.toml

@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.26.0"
+current_version = "0.26.0-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 = "0.26.0"
+version = "0.26.0-beta.1"
 edition.workspace = true
 description = "Python bindings for LanceDB"
 license.workspace = true

python/pyproject.toml

@@ -10,7 +10,7 @@ dependencies = [
     "pyarrow>=16",
     "pydantic>=1.10",
     "tqdm>=4.27.0",
-    "lance-namespace>=0.3.2"
+    "lance-namespace>=0.2.1"
 ]
 description = "lancedb"
 authors = [{ name = "LanceDB Devs", email = "dev@lancedb.com" }]

python/python/lancedb/table.py

@@ -3208,27 +3208,7 @@ def _infer_target_schema(
             if pa.types.is_floating(field.type.value_type):
                 target_type = pa.list_(pa.float32(), dim)
             elif pa.types.is_integer(field.type.value_type):
-                values = peeked.column(i)
+                target_type = pa.list_(pa.uint8(), dim)
-
-                if isinstance(values, pa.ChunkedArray):
-                    values = values.combine_chunks()
-
-                flattened = values.flatten()
-                valid_count = pc.count(flattened, mode="only_valid").as_py()
-
-                if valid_count == 0:
-                    target_type = pa.list_(pa.uint8(), dim)
-                else:
-                    min_max = pc.min_max(flattened)
-                    min_value = min_max["min"].as_py()
-                    max_value = min_max["max"].as_py()
-
-                    if (min_value is not None and min_value < 0) or (
-                        max_value is not None and max_value > 255
-                    ):
-                        target_type = pa.list_(pa.float32(), dim)
-                    else:
-                        target_type = pa.list_(pa.uint8(), dim)
             else:
                 continue  # Skip non-numeric types
 

python/python/tests/test_table.py

@@ -46,39 +46,6 @@ def test_basic(mem_db: DBConnection):
     assert table.to_arrow() == expected_data
 
 
-def test_create_table_infers_large_int_vectors(mem_db: DBConnection):
-    data = [{"vector": [0, 300]}]
-
-    table = mem_db.create_table(
-        "int_vector_overflow", data=data, mode="overwrite", exist_ok=True
-    )
-
-    vector_field = table.schema.field("vector")
-    assert vector_field.type == pa.list_(pa.float32(), 2)
-
-    vector_column = table.to_arrow().column("vector")
-    assert vector_column.type == pa.list_(pa.float32(), 2)
-    assert vector_column.to_pylist() == [[0.0, 300.0]]
-
-
-@pytest.mark.asyncio
-async def test_create_table_async_infers_large_int_vectors(
-    mem_db_async: AsyncConnection,
-):
-    data = [{"vector": [256, 257]}]
-
-    table = await mem_db_async.create_table(
-        "int_vector_overflow_async", data=data, mode="overwrite", exist_ok=True
-    )
-
-    schema = await table.schema()
-    assert schema.field("vector").type == pa.list_(pa.float32(), 2)
-
-    vector_column = (await table.to_arrow()).column("vector")
-    assert vector_column.type == pa.list_(pa.float32(), 2)
-    assert vector_column.to_pylist() == [[256.0, 257.0]]
-
-
 def test_input_data_type(mem_db: DBConnection, tmp_path):
     schema = pa.schema(
         {