Format python

Signed-off-by: Xuanwo <github@xuanwo.io>
docs: Add examples for where in when_matched_update_all
2025-12-27 23:12:58 +00:00 · 2025-07-10 19:11:02 +08:00 · 2025-07-10 19:08:45 +08:00 · 2025-07-09 14:27:08 -07:00 · 2025-07-09 05:54:20 +00:00 · 2025-07-09 05:53:28 +00:00
27 changed files with 232 additions and 150 deletions
--- a/.bumpversion.toml
+++ b/.bumpversion.toml
@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.21.0"
+current_version = "0.21.1-beta.1"
 parse = """(?x)
    (?P<major>0|[1-9]\\d*)\\.
    (?P<minor>0|[1-9]\\d*)\\.
--- a/Cargo.lock
+++ b/Cargo.lock
@@ -4314,7 +4314,7 @@ dependencies = [

 [[package]]
 name = "lancedb"
-version = "0.21.0"
+version = "0.21.1-beta.1"
 dependencies = [
 "arrow",
 "arrow-array",
@@ -4401,7 +4401,7 @@ dependencies = [

 [[package]]
 name = "lancedb-node"
-version = "0.21.0"
+version = "0.21.1-beta.1"
 dependencies = [
 "arrow-array",
 "arrow-ipc",
@@ -4426,7 +4426,7 @@ dependencies = [

 [[package]]
 name = "lancedb-nodejs"
-version = "0.21.0"
+version = "0.21.1-beta.1"
 dependencies = [
 "arrow-array",
 "arrow-ipc",
@@ -4446,7 +4446,7 @@ dependencies = [

 [[package]]
 name = "lancedb-python"
-version = "0.24.0"
+version = "0.24.1-beta.1"
 dependencies = [
 "arrow",
 "env_logger",
--- a/Cargo.toml
+++ b/Cargo.toml
@@ -46,7 +46,7 @@ datafusion-execution = "48.0"
 datafusion-expr = "48.0"
 datafusion-physical-plan = "48.0"
 env_logger = "0.11"
-half = { "version" = "=2.6.0", default-features = false, features = [
+half = { "version" = "2.6.0", default-features = false, features = [
    "num-traits",
 ] }
 futures = "0"
--- a/docs/src/guides/tables/merge_insert.md
+++ b/docs/src/guides/tables/merge_insert.md
@@ -71,6 +71,45 @@ with merge insert, enable both `when_matched_update_all()` and
    If a column is nullable, it can be omitted from input data and it will be
    considered `null`. Columns can also be provided in any order.

+### Conditional Updates
+
+You can add a `where` clause to `when_matched_update_all()` to only update rows 
+that meet certain conditions. When using the `where` parameter, you must prefix 
+column names with either `source.` (for the new data) or `target.` (for the 
+existing data) to specify which table you're referencing.
+
+=== "Python"
+
+    ```python
+    # Only update rows where the target's status is 'active'
+    table.merge_insert("id")
+        .when_matched_update_all(where="target.status = 'active'")
+        .when_not_matched_insert_all()
+        .execute(new_data)
+
+    # Only update if the new price is higher than the existing price
+    table.merge_insert("product_id")
+        .when_matched_update_all(where="source.price > target.price")
+        .when_not_matched_insert_all()
+        .execute(new_data)
+    ```
+
+=== "Typescript"
+
+    ```typescript
+    // Only update rows where the target's status is 'active'
+    await table.mergeInsert("id")
+        .whenMatchedUpdateAll({ where: "target.status = 'active'" })
+        .whenNotMatchedInsertAll()
+        .execute(newData);
+
+    // Only update if the new price is higher than the existing price
+    await table.mergeInsert("product_id")
+        .whenMatchedUpdateAll({ where: "source.price > target.price" })
+        .whenNotMatchedInsertAll()
+        .execute(newData);
+    ```
+
 ## Insert-if-not-exists

 To avoid inserting duplicate rows, you can use the insert-if-not-exists command.
--- a/java/core/pom.xml
+++ b/java/core/pom.xml
@@ -8,7 +8,7 @@
    <parent>
        <groupId>com.lancedb</groupId>
        <artifactId>lancedb-parent</artifactId>
-        <version>0.21.0-final.0</version>
+        <version>0.21.1-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>0.21.0-final.0</version>
+    <version>0.21.1-beta.1</version>
    <packaging>pom</packaging>

    <name>LanceDB Parent</name>
--- a/node/package-lock.json
+++ b/node/package-lock.json
@@ -1,12 +1,12 @@
 {
  "name": "vectordb",
-  "version": "0.21.0",
+  "version": "0.21.1-beta.1",
  "lockfileVersion": 3,
  "requires": true,
  "packages": {
    "": {
      "name": "vectordb",
-      "version": "0.21.0",
+      "version": "0.21.1-beta.1",
      "cpu": [
        "x64",
        "arm64"
@@ -52,11 +52,11 @@
        "uuid": "^9.0.0"
      },
      "optionalDependencies": {
-        "@lancedb/vectordb-darwin-arm64": "0.21.0",
-        "@lancedb/vectordb-darwin-x64": "0.21.0",
-        "@lancedb/vectordb-linux-arm64-gnu": "0.21.0",
-        "@lancedb/vectordb-linux-x64-gnu": "0.21.0",
-        "@lancedb/vectordb-win32-x64-msvc": "0.21.0"
+        "@lancedb/vectordb-darwin-arm64": "0.21.1-beta.1",
+        "@lancedb/vectordb-darwin-x64": "0.21.1-beta.1",
+        "@lancedb/vectordb-linux-arm64-gnu": "0.21.1-beta.1",
+        "@lancedb/vectordb-linux-x64-gnu": "0.21.1-beta.1",
+        "@lancedb/vectordb-win32-x64-msvc": "0.21.1-beta.1"
      },
      "peerDependencies": {
        "@apache-arrow/ts": "^14.0.2",
@@ -326,66 +326,6 @@
        "@jridgewell/sourcemap-codec": "^1.4.10"
      }
    },
-    "node_modules/@lancedb/vectordb-darwin-arm64": {
-      "version": "0.21.0",
-      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-darwin-arm64/-/vectordb-darwin-arm64-0.21.0.tgz",
-      "integrity": "sha512-FTKbdYG36mvQ75tId+esyRfRjIBzryRhAp/6h51tiXy8gsq/TButuiPdqIXeonNModEjhu8wkzsGFwgjCcePow==",
-      "cpu": [
-        "arm64"
-      ],
-      "optional": true,
-      "os": [
-        "darwin"
-      ]
-    },
-    "node_modules/@lancedb/vectordb-darwin-x64": {
-      "version": "0.21.0",
-      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-darwin-x64/-/vectordb-darwin-x64-0.21.0.tgz",
-      "integrity": "sha512-vGaFBr2sQZWE0mudg3LGTHiRE7p2Qce2ogiE2VAf1DLAJ4MrIhgVmEttf966ausIwNCgml+5AzUntw6zC0Oyuw==",
-      "cpu": [
-        "x64"
-      ],
-      "optional": true,
-      "os": [
-        "darwin"
-      ]
-    },
-    "node_modules/@lancedb/vectordb-linux-arm64-gnu": {
-      "version": "0.21.0",
-      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-linux-arm64-gnu/-/vectordb-linux-arm64-gnu-0.21.0.tgz",
-      "integrity": "sha512-KlxqhnX4eBN6rDqrPgf/x/vLpnHK2UcIzNLpiOZzSAhooCmKmnNpfs/EXt+KRFloEQMy25AHpMpqkSPv1Q2oDA==",
-      "cpu": [
-        "arm64"
-      ],
-      "optional": true,
-      "os": [
-        "linux"
-      ]
-    },
-    "node_modules/@lancedb/vectordb-linux-x64-gnu": {
-      "version": "0.21.0",
-      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-linux-x64-gnu/-/vectordb-linux-x64-gnu-0.21.0.tgz",
-      "integrity": "sha512-t7dkFV6kga3rqXR1rH460GdpSVuY0tw7CIc0KqsIIkBcXzUPA1n0QDoazdwPQ1MXzG/+F5WWCTp3dYWx2vP0Lw==",
-      "cpu": [
-        "x64"
-      ],
-      "optional": true,
-      "os": [
-        "linux"
-      ]
-    },
-    "node_modules/@lancedb/vectordb-win32-x64-msvc": {
-      "version": "0.21.0",
-      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-win32-x64-msvc/-/vectordb-win32-x64-msvc-0.21.0.tgz",
-      "integrity": "sha512-yovkW61RECBTsu0S527BX1uW0jCAZK9MAsJTknXmDjp78figx4/AyI5ajT63u/Uo4EKoheeNiiLdyU4v+A9YVw==",
-      "cpu": [
-        "x64"
-      ],
-      "optional": true,
-      "os": [
-        "win32"
-      ]
-    },
    "node_modules/@neon-rs/cli": {
      "version": "0.0.160",
      "resolved": "https://registry.npmjs.org/@neon-rs/cli/-/cli-0.0.160.tgz",
--- a/node/package.json
+++ b/node/package.json
@@ -1,6 +1,6 @@
 {
  "name": "vectordb",
-  "version": "0.21.0",
+  "version": "0.21.1-beta.1",
  "description": " Serverless, low-latency vector database for AI applications",
  "private": false,
  "main": "dist/index.js",
@@ -89,10 +89,10 @@
    }
  },
  "optionalDependencies": {
-    "@lancedb/vectordb-darwin-x64": "0.21.0",
-    "@lancedb/vectordb-darwin-arm64": "0.21.0",
-    "@lancedb/vectordb-linux-x64-gnu": "0.21.0",
-    "@lancedb/vectordb-linux-arm64-gnu": "0.21.0",
-    "@lancedb/vectordb-win32-x64-msvc": "0.21.0"
+    "@lancedb/vectordb-darwin-x64": "0.21.1-beta.1",
+    "@lancedb/vectordb-darwin-arm64": "0.21.1-beta.1",
+    "@lancedb/vectordb-linux-x64-gnu": "0.21.1-beta.1",
+    "@lancedb/vectordb-linux-arm64-gnu": "0.21.1-beta.1",
+    "@lancedb/vectordb-win32-x64-msvc": "0.21.1-beta.1"
  }
 }
--- a/nodejs/Cargo.toml
+++ b/nodejs/Cargo.toml
@@ -1,7 +1,7 @@
 [package]
 name = "lancedb-nodejs"
 edition.workspace = true
-version = "0.21.0"
+version = "0.21.1-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": "0.21.0",
+	"version": "0.21.1-beta.1",
 	"os": ["darwin"],
 	"cpu": ["arm64"],
 	"main": "lancedb.darwin-arm64.node",
--- a/nodejs/npm/darwin-x64/package.json
+++ b/nodejs/npm/darwin-x64/package.json
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-darwin-x64",
-	"version": "0.21.0",
+	"version": "0.21.1-beta.1",
 	"os": ["darwin"],
 	"cpu": ["x64"],
 	"main": "lancedb.darwin-x64.node",
--- a/nodejs/npm/linux-arm64-gnu/package.json
+++ b/nodejs/npm/linux-arm64-gnu/package.json
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-arm64-gnu",
-	"version": "0.21.0",
+	"version": "0.21.1-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": "0.21.0",
+	"version": "0.21.1-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": "0.21.0",
+	"version": "0.21.1-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": "0.21.0",
+	"version": "0.21.1-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": "0.21.0",
+  "version": "0.21.1-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": "0.21.0",
+	"version": "0.21.1-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": "0.21.0",
+  "version": "0.21.1-beta.1",
  "lockfileVersion": 3,
  "requires": true,
  "packages": {
    "": {
      "name": "@lancedb/lancedb",
-      "version": "0.21.0",
+      "version": "0.21.1-beta.1",
      "cpu": [
        "x64",
        "arm64"
--- a/nodejs/package.json
+++ b/nodejs/package.json
@@ -11,7 +11,7 @@
    "ann"
  ],
  "private": false,
-  "version": "0.21.0",
+  "version": "0.21.1-beta.1",
  "main": "dist/index.js",
  "exports": {
    ".": "./dist/index.js",
--- a/python/.bumpversion.toml
+++ b/python/.bumpversion.toml
@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.24.1-beta.0"
+current_version = "0.24.1-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 = "0.24.1-beta.0"
+version = "0.24.1-beta.1"
 edition.workspace = true
 description = "Python bindings for LanceDB"
 license.workspace = true
--- a/python/python/lancedb/merge.py
+++ b/python/python/lancedb/merge.py
@@ -45,6 +45,16 @@ class LanceMergeInsertBuilder(object):
        If there are multiple matches then the behavior is undefined.
        Currently this causes multiple copies of the row to be created
        but that behavior is subject to change.
+
+        Parameters
+        ----------
+        where : Optional[str], default None
+            A SQL filter expression to apply to matched rows. The filter must
+            specify whether you are referencing the source table (new data) or
+            the target table (existing data) by prefixing column names with
+            "source." or "target." respectively.
+
+            Example: "target.status = 'active'" or "source.price > target.price"
        """
        self._when_matched_update_all = True
        self._when_matched_update_all_condition = where
--- a/python/python/lancedb/remote/table.py
+++ b/python/python/lancedb/remote/table.py
@@ -18,7 +18,7 @@ from lancedb._lancedb import (
    UpdateResult,
 )
 from lancedb.embeddings.base import EmbeddingFunctionConfig
-from lancedb.index import FTS, BTree, Bitmap, HnswPq, HnswSq, IvfFlat, IvfPq, LabelList
+from lancedb.index import FTS, BTree, Bitmap, HnswSq, IvfFlat, IvfPq, LabelList
 from lancedb.remote.db import LOOP
 import pyarrow as pa

@@ -89,7 +89,7 @@ class RemoteTable(Table):

    def to_pandas(self):
        """to_pandas() is not yet supported on LanceDB cloud."""
-        return NotImplementedError("to_pandas() is not yet supported on LanceDB cloud.")
+        raise NotImplementedError("to_pandas() is not yet supported on LanceDB cloud.")

    def checkout(self, version: Union[int, str]):
        return LOOP.run(self._table.checkout(version))
@@ -186,6 +186,8 @@ class RemoteTable(Table):
        accelerator: Optional[str] = None,
        index_type="vector",
        wait_timeout: Optional[timedelta] = None,
+        *,
+        num_bits: int = 8,
    ):
        """Create an index on the table.
        Currently, the only parameters that matter are
@@ -220,11 +222,6 @@ class RemoteTable(Table):
        >>> table.create_index("l2", "vector") # doctest: +SKIP
        """

-        if num_partitions is not None:
-            logging.warning(
-                "num_partitions is not supported on LanceDB cloud."
-                "This parameter will be tuned automatically."
-            )
        if num_sub_vectors is not None:
            logging.warning(
                "num_sub_vectors is not supported on LanceDB cloud."
@@ -244,13 +241,21 @@ class RemoteTable(Table):

        index_type = index_type.upper()
        if index_type == "VECTOR" or index_type == "IVF_PQ":
-            config = IvfPq(distance_type=metric)
+            config = IvfPq(
+                distance_type=metric,
+                num_partitions=num_partitions,
+                num_sub_vectors=num_sub_vectors,
+                num_bits=num_bits,
+            )
        elif index_type == "IVF_HNSW_PQ":
-            config = HnswPq(distance_type=metric)
+            raise ValueError(
+                "IVF_HNSW_PQ is not supported on LanceDB cloud."
+                "Please use IVF_HNSW_SQ instead."
+            )
        elif index_type == "IVF_HNSW_SQ":
-            config = HnswSq(distance_type=metric)
+            config = HnswSq(distance_type=metric, num_partitions=num_partitions)
        elif index_type == "IVF_FLAT":
-            config = IvfFlat(distance_type=metric)
+            config = IvfFlat(distance_type=metric, num_partitions=num_partitions)
        else:
            raise ValueError(
                f"Unknown vector index type: {index_type}. Valid options are"
--- a/python/python/tests/test_remote_db.py
+++ b/python/python/tests/test_remote_db.py
@@ -210,6 +210,25 @@ async def test_retry_error():
        assert cause.status_code == 429


+def test_table_unimplemented_functions():
+    def handler(request):
+        if request.path == "/v1/table/test/create/?mode=create":
+            request.send_response(200)
+            request.send_header("Content-Type", "application/json")
+            request.end_headers()
+            request.wfile.write(b"{}")
+        else:
+            request.send_response(404)
+            request.end_headers()
+
+    with mock_lancedb_connection(handler) as db:
+        table = db.create_table("test", [{"id": 1}])
+        with pytest.raises(NotImplementedError):
+            table.to_arrow()
+        with pytest.raises(NotImplementedError):
+            table.to_pandas()
+
+
 def test_table_add_in_threadpool():
    def handler(request):
        if request.path == "/v1/table/test/insert/":
--- a/rust/ffi/node/Cargo.toml
+++ b/rust/ffi/node/Cargo.toml
@@ -1,6 +1,6 @@
 [package]
 name = "lancedb-node"
-version = "0.21.0"
+version = "0.21.1-beta.1"
 description = "Serverless, low-latency vector database for AI applications"
 license.workspace = true
 edition.workspace = true
--- a/rust/lancedb/Cargo.toml
+++ b/rust/lancedb/Cargo.toml
@@ -1,6 +1,6 @@
 [package]
 name = "lancedb"
-version = "0.21.0"
+version = "0.21.1-beta.1"
 edition.workspace = true
 description = "LanceDB: A serverless, low-latency vector database for AI applications"
 license.workspace = true
--- a/rust/lancedb/src/remote/table.rs
+++ b/rust/lancedb/src/remote/table.rs
@@ -57,6 +57,8 @@ use crate::{
 };

 const REQUEST_TIMEOUT_HEADER: HeaderName = HeaderName::from_static("x-request-timeout-ms");
+const METRIC_TYPE_KEY: &str = "metric_type";
+const INDEX_TYPE_KEY: &str = "index_type";

 pub struct RemoteTags<'a, S: HttpSend = Sender> {
    inner: &'a RemoteTable<S>,
@@ -997,23 +999,53 @@ impl<S: HttpSend> BaseTable for RemoteTable<S> {
            "column": column
        });

-        let (index_type, distance_type) = match index.index {
+        match index.index {
            // TODO: Should we pass the actual index parameters? SaaS does not
            // yet support them.
-            Index::IvfFlat(index) => ("IVF_FLAT", Some(index.distance_type)),
-            Index::IvfPq(index) => ("IVF_PQ", Some(index.distance_type)),
-            Index::IvfHnswSq(index) => ("IVF_HNSW_SQ", Some(index.distance_type)),
-            Index::BTree(_) => ("BTREE", None),
-            Index::Bitmap(_) => ("BITMAP", None),
-            Index::LabelList(_) => ("LABEL_LIST", None),
+            Index::IvfFlat(index) => {
+                body[INDEX_TYPE_KEY] = serde_json::Value::String("IVF_FLAT".to_string());
+                body[METRIC_TYPE_KEY] =
+                    serde_json::Value::String(index.distance_type.to_string().to_lowercase());
+                if let Some(num_partitions) = index.num_partitions {
+                    body["num_partitions"] = serde_json::Value::Number(num_partitions.into());
+                }
+            }
+            Index::IvfPq(index) => {
+                body[INDEX_TYPE_KEY] = serde_json::Value::String("IVF_PQ".to_string());
+                body[METRIC_TYPE_KEY] =
+                    serde_json::Value::String(index.distance_type.to_string().to_lowercase());
+                if let Some(num_partitions) = index.num_partitions {
+                    body["num_partitions"] = serde_json::Value::Number(num_partitions.into());
+                }
+                if let Some(num_bits) = index.num_bits {
+                    body["num_bits"] = serde_json::Value::Number(num_bits.into());
+                }
+            }
+            Index::IvfHnswSq(index) => {
+                body[INDEX_TYPE_KEY] = serde_json::Value::String("IVF_HNSW_SQ".to_string());
+                body[METRIC_TYPE_KEY] =
+                    serde_json::Value::String(index.distance_type.to_string().to_lowercase());
+                if let Some(num_partitions) = index.num_partitions {
+                    body["num_partitions"] = serde_json::Value::Number(num_partitions.into());
+                }
+            }
+            Index::BTree(_) => {
+                body[INDEX_TYPE_KEY] = serde_json::Value::String("BTREE".to_string());
+            }
+            Index::Bitmap(_) => {
+                body[INDEX_TYPE_KEY] = serde_json::Value::String("BITMAP".to_string());
+            }
+            Index::LabelList(_) => {
+                body[INDEX_TYPE_KEY] = serde_json::Value::String("LABEL_LIST".to_string());
+            }
            Index::FTS(fts) => {
+                body[INDEX_TYPE_KEY] = serde_json::Value::String("FTS".to_string());
                let params = serde_json::to_value(&fts).map_err(|e| Error::InvalidInput {
                    message: format!("failed to serialize FTS index params {:?}", e),
                })?;
                for (key, value) in params.as_object().unwrap() {
                    body[key] = value.clone();
                }
-                ("FTS", None)
            }
            Index::Auto => {
                let schema = self.schema().await?;
@@ -1023,9 +1055,11 @@ impl<S: HttpSend> BaseTable for RemoteTable<S> {
                        message: format!("Column {} not found in schema", column),
                    })?;
                if supported_vector_data_type(field.data_type()) {
-                    ("IVF_PQ", Some(DistanceType::L2))
+                    body[INDEX_TYPE_KEY] = serde_json::Value::String("IVF_PQ".to_string());
+                    body[METRIC_TYPE_KEY] =
+                        serde_json::Value::String(DistanceType::L2.to_string().to_lowercase());
                } else if supported_btree_data_type(field.data_type()) {
-                    ("BTREE", None)
+                    body[INDEX_TYPE_KEY] = serde_json::Value::String("BTREE".to_string());
                } else {
                    return Err(Error::NotSupported {
                        message: format!(
@@ -1042,12 +1076,6 @@ impl<S: HttpSend> BaseTable for RemoteTable<S> {
                })
            }
        };
-        body["index_type"] = serde_json::Value::String(index_type.into());
-        if let Some(distance_type) = distance_type {
-            // Phalanx expects this to be lowercase right now.
-            body["metric_type"] =
-                serde_json::Value::String(distance_type.to_string().to_lowercase());
-        }

        let request = request.json(&body);

@@ -1429,11 +1457,12 @@ mod tests {
    use chrono::{DateTime, Utc};
    use futures::{future::BoxFuture, StreamExt, TryFutureExt};
    use lance_index::scalar::inverted::query::MatchQuery;
-    use lance_index::scalar::FullTextSearchQuery;
+    use lance_index::scalar::{FullTextSearchQuery, InvertedIndexParams};
    use reqwest::Body;
    use rstest::rstest;
+    use serde_json::json;

-    use crate::index::vector::IvfFlatIndexBuilder;
+    use crate::index::vector::{IvfFlatIndexBuilder, IvfHnswSqIndexBuilder};
    use crate::remote::db::DEFAULT_SERVER_VERSION;
    use crate::remote::JSON_CONTENT_TYPE;
    use crate::{
@@ -2433,29 +2462,79 @@ mod tests {
        let cases = [
            (
                "IVF_FLAT",
-                Some("hamming"),
+                json!({
+                    "metric_type": "hamming",
+                }),
                Index::IvfFlat(IvfFlatIndexBuilder::default().distance_type(DistanceType::Hamming)),
            ),
-            ("IVF_PQ", Some("l2"), Index::IvfPq(Default::default())),
+            (
+                "IVF_FLAT",
+                json!({
+                    "metric_type": "hamming",
+                    "num_partitions": 128,
+                }),
+                Index::IvfFlat(
+                    IvfFlatIndexBuilder::default()
+                        .distance_type(DistanceType::Hamming)
+                        .num_partitions(128),
+                ),
+            ),
            (
                "IVF_PQ",
-                Some("cosine"),
-                Index::IvfPq(IvfPqIndexBuilder::default().distance_type(DistanceType::Cosine)),
+                json!({
+                    "metric_type": "l2",
+                }),
+                Index::IvfPq(Default::default()),
+            ),
+            (
+                "IVF_PQ",
+                json!({
+                    "metric_type": "cosine",
+                    "num_partitions": 128,
+                    "num_bits": 4,
+                }),
+                Index::IvfPq(
+                    IvfPqIndexBuilder::default()
+                        .distance_type(DistanceType::Cosine)
+                        .num_partitions(128)
+                        .num_bits(4),
+                ),
            ),
            (
                "IVF_HNSW_SQ",
-                Some("l2"),
+                json!({
+                    "metric_type": "l2",
+                }),
                Index::IvfHnswSq(Default::default()),
            ),
+            (
+                "IVF_HNSW_SQ",
+                json!({
+                    "metric_type": "l2",
+                    "num_partitions": 128,
+                }),
+                Index::IvfHnswSq(
+                    IvfHnswSqIndexBuilder::default()
+                        .distance_type(DistanceType::L2)
+                        .num_partitions(128),
+                ),
+            ),
            // HNSW_PQ isn't yet supported on SaaS
-            ("BTREE", None, Index::BTree(Default::default())),
-            ("BITMAP", None, Index::Bitmap(Default::default())),
-            ("LABEL_LIST", None, Index::LabelList(Default::default())),
-            ("FTS", None, Index::FTS(Default::default())),
+            ("BTREE", json!({}), Index::BTree(Default::default())),
+            ("BITMAP", json!({}), Index::Bitmap(Default::default())),
+            (
+                "LABEL_LIST",
+                json!({}),
+                Index::LabelList(Default::default()),
+            ),
+            (
+                "FTS",
+                serde_json::to_value(InvertedIndexParams::default()).unwrap(),
+                Index::FTS(Default::default()),
+            ),
        ];

-        for (index_type, distance_type, index) in cases {
-            let params = index.clone();
+        for (index_type, expected_body, index) in cases {
            let table = Table::new_with_handler("my_table", move |request| {
                assert_eq!(request.method(), "POST");
                assert_eq!(request.url().path(), "/v1/table/my_table/create_index/");
@@ -2465,19 +2544,9 @@ mod tests {
                );
                let body = request.body().unwrap().as_bytes().unwrap();
                let body: serde_json::Value = serde_json::from_slice(body).unwrap();
-                let mut expected_body = serde_json::json!({
-                    "column": "a",
-                    "index_type": index_type,
-                });
-                if let Some(distance_type) = distance_type {
-                    expected_body["metric_type"] = distance_type.to_lowercase().into();
-                }
-                if let Index::FTS(fts) = &params {
-                    let params = serde_json::to_value(fts).unwrap();
-                    for (key, value) in params.as_object().unwrap() {
-                        expected_body[key] = value.clone();
-                    }
-                }
+                let mut expected_body = expected_body.clone();
+                expected_body["column"] = "a".into();
+                expected_body[INDEX_TYPE_KEY] = index_type.into();

                assert_eq!(body, expected_body);
Author	SHA1	Message	Date
Xuanwo	16a7e29639	Format python Signed-off-by: Xuanwo <github@xuanwo.io>	2025-07-10 19:11:02 +08:00
Xuanwo	0e7a218d62	docs: Add examples for where in when_matched_update_all Signed-off-by: Xuanwo <github@xuanwo.io>	2025-07-10 19:08:45 +08:00
CyrusAttoun	167fccc427	fix: change 'return' to 'raise' for unimplemented remote table function (#2484 ) just noticed that we're doing a 'return' instead of a 'raise' while trying to get remote functionality working for my project. I went ahead and implemented tests for both of the unimplemented functions (to_pandas and to_arrow) while I was in there. --------- Co-authored-by: Cyrus Attoun <jattoun1@gmail.com>	2025-07-09 14:27:08 -07:00
Lance Release	2bffbcefa5	Bump version: 0.21.1-beta.0 → 0.21.1-beta.1	2025-07-09 05:54:20 +00:00
Lance Release	905552f993	Bump version: 0.24.1-beta.0 → 0.24.1-beta.1	2025-07-09 05:53:28 +00:00
BubbleCal	e4898c9313	chore: sync node package-lock (#2491 ) Signed-off-by: BubbleCal <bubble-cal@outlook.com>	2025-07-09 12:34:03 +08:00
BubbleCal	cab36d94b2	feat: support to specify num_partitions and num_bits (#2488 )	2025-07-09 11:36:09 +08:00
Weston Pace	b64252d4fd	chore: don't require exact version of half (#2489 ) I can't find any reason for pinning this dependency and the fact that it is pinned can be kind of annoying to use downstream (e.g. datafusion currently requires >= 2.6).	2025-07-08 08:36:04 -07:00
Lance Release	6fc006072c	Bump version: 0.21.0 → 0.21.1-beta.0	2025-07-07 21:01:30 +00:00