Bump version: 0.4.2 → 0.4.3

We use `ruff` in CI and dev workflow now.

.bumpversion.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 0.4.1
+current_version = 0.4.3
 commit = True
 message = Bump version: {current_version} → {new_version}
 tag = True

.github/workflows/docs_test.yml

@@ -88,6 +88,9 @@ jobs:
         cd docs/test
         node md_testing.js
     - name: Test
+      env:
+        LANCEDB_URI: ${{ secrets.LANCEDB_URI }}
+        LANCEDB_DEV_API_KEY: ${{ secrets.LANCEDB_DEV_API_KEY }}
       run: |
         cd docs/test/node
         for d in *; do cd "$d"; echo "$d".js; node "$d".js; cd ..; done

.github/workflows/python.yml

@@ -49,7 +49,7 @@ jobs:
     timeout-minutes: 30
     strategy:
       matrix:
-        config: 
+        config:
           - name: x86 Mac
             runner: macos-13
           - name: Arm Mac
@@ -74,7 +74,7 @@ jobs:
       run: |
         pip install -e .[tests]
         pip install tantivy@git+https://github.com/quickwit-oss/tantivy-py#164adc87e1a033117001cf70e38c82a53014d985
-        pip install pytest pytest-mock black
+        pip install pytest pytest-mock
     - name: Run tests
       run: pytest -m "not slow" -x -v --durations=30 tests
   pydantic1x:

Cargo.toml

@@ -5,10 +5,10 @@ exclude = ["python"]
 resolver = "2"
 
 [workspace.dependencies]
-lance = { "version" = "=0.9.1", "features" = ["dynamodb"] }
-lance-index = { "version" = "=0.9.1" }
-lance-linalg = { "version" = "=0.9.1" }
-lance-testing = { "version" = "=0.9.1" }
+lance = { "version" = "=0.9.6", "features" = ["dynamodb"] }
+lance-index = { "version" = "=0.9.6" }
+lance-linalg = { "version" = "=0.9.6" }
+lance-testing = { "version" = "=0.9.6" }
 # Note that this one does not include pyarrow
 arrow = { version = "49.0.0", optional = false }
 arrow-array = "49.0"

docs/mkdocs.yml

@@ -149,6 +149,7 @@ nav:
   - OSS Python API: python/python.md
   - SaaS Python API: python/saas-python.md
   - Javascript API: javascript/modules.md
+  - SaaS Javascript API: javascript/saas-modules.md
 - LanceDB Cloud↗: https://noteforms.com/forms/lancedb-mailing-list-cloud-kty1o5?notionforms=1&utm_source=notionforms
 
 extra_css:

docs/src/ann_indexes.md

@@ -164,6 +164,7 @@ You can further filter the elements returned by a search using a where clause.
      const results_2 = await table
          .search(Array(1536).fill(1.2))
          .where("id != '1141'")
+         .limit(2)
          .execute()
      ```
 
@@ -187,6 +188,7 @@ You can select the columns returned by the query using a select clause.
      const results_3 = await table
          .search(Array(1536).fill(1.2))
          .select(["id"])
+         .limit(2)
          .execute()
      ```
 

docs/src/embeddings/embedding_functions.md

@@ -1,13 +1,14 @@
-Representing multi-modal data as vector embeddings is becoming a standard practice. Embedding functions themselves be thought of as a part of the processing pipeline that each request(input) has to be passed through. After initial setup these components are not expected to change for a particular project. 
-
-This is main motivation behind our new embedding functions API, that allow you simply set it up once and the table remembers it, effectively making the **embedding functions disappear in the background** so you don't have to worry about modelling and simply focus on the DB aspects of VectorDB.
+Representing multi-modal data as vector embeddings is becoming a standard practice. Embedding functions themselves can be thought of as a part of the processing pipeline that each request(input) has to be passed through. After initial setup these components are not expected to change for a particular project. 
 
+Our new embedding functions API allow you simply set it up once and the table remembers it, effectively making the **embedding functions disappear in the background** so you don't have to worry about modelling and can simply focus on the DB aspects of VectorDB.
 
 You can simply follow these steps and forget about the details of your embedding functions as long as you don't intend to change it.
 
 ### Step 1 - Define the embedding function
 We have some pre-defined embedding functions in the global registry with more coming soon. Here's let's an implementation of CLIP as example.
 ```
+from lancedb.embeddings import EmbeddingFunctionRegistry
+
 registry = EmbeddingFunctionRegistry.get_instance()
 clip = registry.get("open-clip").create()
 
@@ -15,9 +16,11 @@ clip = registry.get("open-clip").create()
 You can also define your own embedding function by implementing the `EmbeddingFunction` abstract base interface. It subclasses PyDantic Model which can be utilized to write complex schemas simply as we'll see next!
 
 ### Step 2 - Define the Data Model or Schema
-Our embedding function from the previous section abstracts away all the details about the models and dimensions required to define the schema. You can simply set a feild as **source** or **vector** column. Here's how
+Our embedding function from the previous section abstracts away all the details about the models and dimensions required to define the schema. You can simply set a field as **source** or **vector** column. Here's how
 
 ```python
+from lancedb.pydantic import LanceModel, Vector
+
 class Pets(LanceModel):
     vector: Vector(clip.ndims) = clip.VectorField()
     image_uri: str = clip.SourceField()
@@ -30,11 +33,13 @@ class Pets(LanceModel):
 Now that we have chosen/defined our embedding function and the schema, we can create the table
 
 ```python
+import lancedb
+
 db = lancedb.connect("~/lancedb")
 table = db.create_table("pets", schema=Pets)
-
 ```
-That's it! We have ingested all the information needed to embed source and query inputs. We can now forget about the model and dimension details and start to build or VectorDB
+
+That's it! We have ingested all the information needed to embed source and query inputs. We can now forget about the model and dimension details and start to build our VectorDB.
 
 ### Step 4 - Ingest lots of data and run vector search!
 Now you can just add the data and it'll be vectorized automatically
@@ -52,29 +57,32 @@ result = table.search("dog")
 Let's query an image
 
 ```python
+from pathlib import Path
+
 p = Path("path/to/images/samoyed_100.jpg")
 query_image = Image.open(p)
 table.search(query_image)
-
 ```
+
 ### Rate limit Handling
-`EmbeddingFunction` class wraps the calls for source and query embedding generation inside a rate limit handler that retries the requests with exponential backoff after successive failures. By default the maximum retires is set to 7. You can tune it by setting it to a different number or disable it by setting it to 0.
-Example
-----
+`EmbeddingFunction` class wraps the calls for source and query embedding generation inside a rate limit handler that retries the requests with exponential backoff after successive failures. By default the maximum retires is set to 7. You can tune it by setting it to a different number or disable it by setting it to 0. Example:
 
 ```python
 clip = registry.get("open-clip").create() # Defaults to 7 max retries
 clip = registry.get("open-clip").create(max_retries=10) # Increase max retries to 10
 clip = registry.get("open-clip").create(max_retries=0) # Retries disabled
-````
+```
 
 NOTE:
-Embedding functions can also fail due to other errors that have nothing to do with rate limits. This is why the error is also logged.
+Embedding functions can also fail due to other errors that have nothing to do with rate limits. This is why the errors are also logged.
 
 ### A little fun with PyDantic
-LanceDB is integrated with PyDantic. Infact we've used the integration in the above example to define the schema. It is also being used behing the scene by the embdding function API to ingest useful information as table metadata.
-You can also use it for adding utility operations in the schema. For example, in our multi-modal example, you can search images using text or another image. Let us define a utility function to plot the image.
+LanceDB is integrated with PyDantic. In fact, we've used the integration in the above example to define the schema. It is also being used behind the scene by the embedding function API to ingest useful information as table metadata.
+You can also use it for adding utility operations in the schema. For example, in our multi-modal example, you can search images using text or another image. Let's define a utility function to plot the image.
+
 ```python
+from lancedb.pydantic import LanceModel, Vector
+
 class Pets(LanceModel):
     vector: Vector(clip.ndims) = clip.VectorField()
     image_uri: str = clip.SourceField()
@@ -83,7 +91,8 @@ class Pets(LanceModel):
     def image(self):
         return Image.open(self.image_uri)
 ```
-Now, you can covert your search results to pydantic model and use this property.
+
+Now, you can covert your search results to PyDantic model and use its property.
 
 ```python
 rs = table.search(query_image).limit(3).to_pydantic(Pets)
@@ -92,4 +101,4 @@ rs[2].image
 
 ![](../assets/dog_clip_output.png)
 
-Now that you've the basic idea about LanceDB embedding function, let us now dive deeper into the API that you can use to implement your own embedding functions!
+Now that you have the basic idea about LanceDB embedding function, let us dive deeper into the API that you can use to implement your own embedding functions!

docs/src/fts.md

@@ -29,8 +29,9 @@ uri = "data/sample-lancedb"
 db = lancedb.connect(uri)
 
 table = db.create_table("my_table",
-            data=[{"vector": [3.1, 4.1], "text": "Frodo was a happy puppy"},
-                  {"vector": [5.9, 26.5], "text": "There are several kittens playing"}])
+            data=[{"vector": [3.1, 4.1], "text": "Frodo was a happy puppy", "meta": "foo"},
+                  {"vector": [5.9, 26.5], "text": "Sam was a loyal puppy", "meta": "bar"},
+                  {"vector": [15.9, 6.5], "text": "There are several kittens playing"}])
 
 ```
 
@@ -64,10 +65,51 @@ table.create_fts_index(["text1", "text2"])
 
 Note that the search API call does not change - you can search over all indexed columns at once.
 
+## Filtering
+
+Currently the LanceDB full text search feature supports *post-filtering*, meaning filters are
+applied on top of the full text search results. This can be invoked via the familiar
+`where` syntax:
+
+```python
+table.search("puppy").limit(10).where("meta='foo'").to_list()
+```
+
+## Syntax
+
+For full-text search you can perform either a phrase query like "the old man and the sea", 
+or a structured search query like "(Old AND Man) AND Sea".
+Double quotes are used to disambiguate.
+
+For example: 
+
+If you intended "they could have been dogs OR cats" as a phrase query, this actually
+raises a syntax error since `OR` is a recognized operator. If you make `or` lower case,
+this avoids the syntax error. However, it is cumbersome to have to remember what will
+conflict with the query syntax. Instead, if you search using 
+`table.search('"they could have been dogs OR cats"')`, then the syntax checker avoids
+checking inside the quotes.
+
+
+## Configurations
+
+By default, LanceDB configures a 1GB heap size limit for creating the index. You can 
+reduce this if running on a smaller node, or increase this for faster performance while
+indexing a larger corpus.
+
+```python
+# configure a 512MB heap size
+heap = 1024 * 1024 * 512
+table.create_fts_index(["text1", "text2"], writer_heap_size=heap, replace=True)
+```
+
 ## Current limitations
 
 1. Currently we do not yet support incremental writes.
-If you add data after fts index creation, it won't be reflected
-in search results until you do a full reindex.
+   If you add data after fts index creation, it won't be reflected
+   in search results until you do a full reindex.
+
+2. We currently only support local filesystem paths for the fts index. 
+   This is a tantivy limitation. We've implemented an object store plugin
+   but there's no way in tantivy-py to specify to use it.
 
-2. We currently only support local filesystem paths for the fts index.

docs/src/guides/tables.md

@@ -118,6 +118,84 @@ This guide will show how to create tables, insert data into them, and update the
     table = db.create_table(table_name, schema=Content)
     ```
 
+    #### Nested schemas
+
+    Sometimes your data model may contain nested objects.
+    For example, you may want to store the document string
+    and the document soure name as a nested Document object:
+
+    ```python
+    class Document(BaseModel):
+        content: str
+        source: str
+    ```
+
+    This can be used as the type of a LanceDB table column:
+
+    ```python
+    class NestedSchema(LanceModel):
+        id: str
+        vector: Vector(1536)
+        document: Document
+
+    tbl = db.create_table("nested_table", schema=NestedSchema, mode="overwrite")
+    ```
+
+    This creates a struct column called "document" that has two subfields 
+    called "content" and "source":
+
+    ```
+    In [28]: tbl.schema
+    Out[28]:
+    id: string not null
+    vector: fixed_size_list<item: float>[1536] not null
+        child 0, item: float
+    document: struct<content: string not null, source: string not null> not null
+        child 0, content: string not null
+        child 1, source: string not null    
+    ```
+
+    #### Validators
+
+    Note that neither pydantic nor pyarrow automatically validates that input data
+    is of the *correct* timezone, but this is easy to add as a custom field validator:
+
+    ```python
+    from datetime import datetime
+    from zoneinfo import ZoneInfo
+
+    from lancedb.pydantic import LanceModel
+    from pydantic import Field, field_validator, ValidationError, ValidationInfo
+
+    tzname = "America/New_York"
+    tz = ZoneInfo(tzname)
+
+    class TestModel(LanceModel):
+        dt_with_tz: datetime = Field(json_schema_extra={"tz": tzname})
+
+        @field_validator('dt_with_tz')
+        @classmethod
+        def tz_must_match(cls, dt: datetime) -> datetime:
+            assert dt.tzinfo == tz
+            return dt        
+
+    ok = TestModel(dt_with_tz=datetime.now(tz))
+
+    try:
+        TestModel(dt_with_tz=datetime.now(ZoneInfo("Asia/Shanghai")))
+        assert 0 == 1, "this should raise ValidationError"
+    except ValidationError:
+        print("A ValidationError was raised.")
+        pass
+    ```
+
+    When you run this code it should print "A ValidationError was raised."
+
+    #### Pydantic custom types
+
+    LanceDB does NOT yet support converting pydantic custom types. If this is something you need,
+    please file a feature request on the [LanceDB Github repo](https://github.com/lancedb/lancedb/issues/new).
+
     ### Using Iterators / Writing Large Datasets
 
     It is recommended to use itertators to add large datasets in batches when creating your table in one go. This does not create multiple versions of your dataset unlike manually adding batches using `table.add()`
@@ -153,7 +231,7 @@ This guide will show how to create tables, insert data into them, and update the
     You can also use iterators of other types like Pandas dataframe or Pylists directly in the above example.
 
     ## Creating Empty Table
-    You can also create empty tables in python. Initialize it with schema and later ingest data into it.
+    You can create empty tables in python. Initialize it with schema and later ingest data into it.
 
     ```python
     import lancedb

docs/src/javascript/classes/RemoteConnection.md

@@ -0,0 +1,226 @@
+[vectordb](../README.md) / [Exports](../saas-modules.md) / RemoteConnection
+
+# Class: RemoteConnection
+
+A connection to a remote LanceDB database. The class RemoteConnection implements interface Connection
+
+## Implements
+
+- [`Connection`](../interfaces/Connection.md)
+
+## Table of contents
+
+### Constructors
+
+- [constructor](RemoteConnection.md#constructor)
+
+### Methods
+
+- [createTable](RemoteConnection.md#createtable)
+- [tableNames](RemoteConnection.md#tablenames)
+- [openTable](RemoteConnection.md#opentable)
+- [dropTable](RemoteConnection.md#droptable)
+
+
+## Constructors
+
+### constructor
+
+• **new RemoteConnection**(`client`, `dbName`)
+
+#### Parameters
+
+| Name | Type |
+| :------ | :------ |
+| `client` | `HttpLancedbClient` |
+| `dbName` | `string` |
+
+#### Defined in
+
+[remote/index.ts:37](https://github.com/lancedb/lancedb/blob/main/node/src/remote/index.ts#L37)
+
+## Methods
+
+### createTable
+
+▸ **createTable**(`name`, `data`, `mode?`): `Promise`<[`Table`](../interfaces/Table.md)<`number`[]\>\>
+
+Creates a new Table and initialize it with new data.
+
+#### Parameters
+
+| Name | Type | Description |
+| :------ | :------ | :------ |
+| `name` | `string` | The name of the table. |
+| `data` | `Record`<`string`, `unknown`\>[] | Non-empty Array of Records to be inserted into the Table |
+| `mode?` | [`WriteMode`](../enums/WriteMode.md) | The write mode to use when creating the table. |
+
+#### Returns
+
+`Promise`<[`Table`](../interfaces/Table.md)<`number`[]\>\>
+
+#### Implementation of
+
+[Connection](../interfaces/Connection.md).[createTable](../interfaces/Connection.md#createtable)
+
+#### Defined in
+
+[remote/index.ts:75](https://github.com/lancedb/lancedb/blob/main/node/src/remote/index.ts#L75)
+
+▸ **createTable**(`name`, `data`, `mode`): `Promise`<[`Table`](../interfaces/Table.md)<`number`[]\>\>
+
+#### Parameters
+
+| Name | Type |
+| :------ | :------ |
+| `name` | `string` |
+| `data` | `Record`<`string`, `unknown`\>[] |
+| `mode` | [`WriteMode`](../enums/WriteMode.md) |
+| `embeddings` | [`EmbeddingFunction`](../interfaces/EmbeddingFunction.md)<`T`\> | An embedding function to use on this Table |
+
+#### Returns
+
+`Promise`<[`Table`](../interfaces/Table.md)<`number`[]\>\>
+
+#### Implementation of
+
+Connection.createTable
+
+#### Defined in
+
+[remote/index.ts:231](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L231)
+
+___
+
+### dropTable
+
+▸ **dropTable**(`name`): `Promise`<`void`\>
+
+Drop an existing table.
+
+#### Parameters
+
+| Name | Type | Description |
+| :------ | :------ | :------ |
+| `name` | `string` | The name of the table to drop. |
+
+#### Returns
+
+`Promise`<`void`\>
+
+#### Implementation of
+
+[Connection](../interfaces/Connection.md).[dropTable](../interfaces/Connection.md#droptable)
+
+#### Defined in
+
+[remote/index.ts:131](https://github.com/lancedb/lancedb/blob/main/node/src/remote/index.ts#L131)
+
+___
+
+### openTable
+
+▸ **openTable**(`name`): `Promise`<[`Table`](../interfaces/Table.md)<`number`[]\>\>
+
+Open a table in the database.
+
+#### Parameters
+
+| Name | Type | Description |
+| :------ | :------ | :------ |
+| `name` | `string` | The name of the table. |
+
+#### Returns
+
+`Promise`<[`Table`](../interfaces/Table.md)<`number`[]\>\>
+
+#### Implementation of
+
+[Connection](../interfaces/Connection.md).[openTable](../interfaces/Connection.md#opentable)
+
+#### Defined in
+
+[remote/index.ts:65](https://github.com/lancedb/lancedb/blob/main/node/src/remote/index.ts#L65)
+
+▸ **openTable**<`T`\>(`name`, `embeddings`): `Promise`<[`Table`](../interfaces/Table.md)<`T`\>\>
+
+Open a table in the database.
+
+#### Type parameters
+
+| Name |
+| :------ |
+| `T` |
+
+#### Parameters
+
+| Name | Type | Description |
+| :------ | :------ | :------ |
+| `name` | `string` | The name of the table. |
+| `embeddings` | [`EmbeddingFunction`](../interfaces/EmbeddingFunction.md)<`T`\> | An embedding function to use on this Table |
+
+#### Returns
+
+`Promise`<[`Table`](../interfaces/Table.md)<`T`\>\>
+
+#### Implementation of
+
+Connection.openTable
+
+#### Defined in
+
+[remote/index.ts:66](https://github.com/lancedb/lancedb/blob/main/node/src/remote/index.ts#L66)
+
+▸ **openTable**<`T`\>(`name`, `embeddings?`): `Promise`<[`Table`](../interfaces/Table.md)<`T`\>\>
+
+#### Type parameters
+
+| Name |
+| :------ |
+| `T` |
+
+#### Parameters
+
+| Name | Type |
+| :------ | :------ |
+| `name` | `string` |
+| `embeddings?` | [`EmbeddingFunction`](../interfaces/EmbeddingFunction.md)<`T`\> |
+
+#### Returns
+
+`Promise`<[`Table`](../interfaces/Table.md)<`T`\>\>
+
+#### Implementation of
+
+Connection.openTable
+
+#### Defined in
+
+[remote/index.ts:67](https://github.com/lancedb/lancedb/blob/main/node/src/remote/index.ts#L67)
+
+___
+
+### tableNames
+
+▸ **tableNames**(): `Promise`<`string`[]\>
+
+Get the names of all tables in the database, with pagination.
+
+#### Parameters
+
+| Name | Type |
+| :------ | :------ |
+| `pageToken` | `string` |
+| `limit` | `int` |
+
+#### Returns
+
+`Promise`<`string`[]\>
+
+#### Implementation of
+
+[Connection](../interfaces/Connection.md).[tableNames](../interfaces/Connection.md#tablenames)
+
+#### Defined in
+
+[remote/index.ts:60](https://github.com/lancedb/lancedb/blob/main/node/src/remote/index.ts#L60)

docs/src/javascript/classes/RemoteQuery.md

@@ -0,0 +1,76 @@
+[vectordb](../README.md) / [Exports](../saas-modules.md) / RemoteQuery
+
+# Class: Query<T\>
+
+A builder for nearest neighbor queries for LanceDB.
+
+## Type parameters
+
+| Name | Type |
+| :------ | :------ |
+| `T` | `number`[] |
+
+## Table of contents
+
+### Constructors
+
+- [constructor](RemoteQuery.md#constructor)
+
+### Properties
+
+- [\_embeddings](RemoteQuery.md#_embeddings)
+- [\_query](RemoteQuery.md#_query)
+- [\_name](RemoteQuery.md#_name)
+- [\_client](RemoteQuery.md#_client)
+
+### Methods
+
+- [execute](RemoteQuery.md#execute)
+
+
+## Constructors
+
+### constructor
+
+• **new Query**<`T`\>(`name`, `client`, `query`, `embeddings?`)
+
+#### Type parameters
+
+| Name | Type |
+| :------ | :------ |
+| `T` | `number`[] |
+
+#### Parameters
+
+| Name | Type |
+| :------ | :------ |
+| `name` | `string` |
+| `client` | `HttpLancedbClient` |
+| `query` | `T` |
+| `embeddings?` | [`EmbeddingFunction`](../interfaces/EmbeddingFunction.md)<`T`\> |
+
+#### Defined in
+
+[remote/index.ts:137](https://github.com/lancedb/lancedb/blob/main/node/src/remote/index.ts#L137)
+
+## Methods
+
+### execute
+
+▸ **execute**<`T`\>(): `Promise`<`T`[]\>
+
+Execute the query and return the results as an Array of Objects
+
+#### Type parameters
+
+| Name | Type |
+| :------ | :------ |
+| `T` | `Record`<`string`, `unknown`\> |
+
+#### Returns
+
+`Promise`<`T`[]\>
+
+#### Defined in
+
+[remote/index.ts:143](https://github.com/lancedb/lancedb/blob/main/node/src/remote/index.ts#L143)

docs/src/javascript/classes/RemoteTable.md

@@ -0,0 +1,355 @@
+[vectordb](../README.md) / [Exports](../saas-modules.md) / RemoteTable
+
+# Class: RemoteTable<T\>
+
+A LanceDB Table is the collection of Records. Each Record has one or more vector fields.
+
+## Type parameters
+
+| Name | Type |
+| :------ | :------ |
+| `T` | `number`[] |
+
+## Implements
+
+- [`Table`](../interfaces/Table.md)<`T`\>
+
+## Table of contents
+
+### Constructors
+
+- [constructor](RemoteTable.md#constructor)
+
+### Properties
+
+- [\_name](RemoteTable.md#_name)
+- [\_client](RemoteTable.md#_client)
+- [\_embeddings](RemoteTable.md#_embeddings)
+
+### Accessors
+
+- [name](RemoteTable.md#name)
+
+### Methods
+
+- [add](RemoteTable.md#add)
+- [countRows](RemoteTable.md#countrows)
+- [createIndex](RemoteTable.md#createindex)
+- [delete](RemoteTable.md#delete)
+- [listIndices](classes/RemoteTable.md#listindices)
+- [indexStats](classes/RemoteTable.md#liststats)
+- [overwrite](RemoteTable.md#overwrite)
+- [search](RemoteTable.md#search)
+- [schema](classes/RemoteTable.md#schema)
+- [update](RemoteTable.md#update)
+
+## Constructors
+
+### constructor
+
+• **new RemoteTable**<`T`\>(`client`, `name`)
+
+#### Type parameters
+
+| Name | Type |
+| :------ | :------ |
+| `T` | `number`[] |
+
+#### Parameters
+
+| Name | Type |
+| :------ | :------ |
+| `client` | `HttpLancedbClient` |
+| `name` | `string` |
+
+#### Defined in
+
+[remote/index.ts:186](https://github.com/lancedb/lancedb/blob/main/node/src/remote/index.ts#L186)
+
+• **new RemoteTable**<`T`\>(`client`, `name`, `embeddings`)
+
+#### Type parameters
+
+| Name | Type |
+| :------ | :------ |
+| `T` | `number`[] |
+
+#### Parameters
+
+| Name | Type | Description |
+| :------ | :------ | :------ |
+| `client` | `HttpLancedbClient` |  |
+| `name` | `string` |  |
+| `embeddings` | [`EmbeddingFunction`](../interfaces/EmbeddingFunction.md)<`T`\> | An embedding function to use when interacting with this table |
+
+#### Defined in
+
+[remote/index.ts:187](https://github.com/lancedb/lancedb/blob/main/node/src/remote/index.ts#L187)
+
+## Accessors
+
+### name
+
+• `get` **name**(): `string`
+
+#### Returns
+
+`string`
+
+#### Implementation of
+
+[Table](../interfaces/Table.md).[name](../interfaces/Table.md#name)
+
+#### Defined in
+
+[remote/index.ts:194](https://github.com/lancedb/lancedb/blob/main/node/src/remote/index.ts#L194)
+
+## Methods
+
+### add
+
+▸ **add**(`data`): `Promise`<`number`\>
+
+Insert records into this Table.
+
+#### Parameters
+
+| Name | Type | Description |
+| :------ | :------ | :------ |
+| `data` | `Record`<`string`, `unknown`\>[] | Records to be inserted into the Table |
+
+#### Returns
+
+`Promise`<`number`\>
+
+The number of rows added to the table
+
+#### Implementation of
+
+[Table](../interfaces/Table.md).[add](../interfaces/Table.md#add)
+
+#### Defined in
+
+[remote/index.ts:293](https://github.com/lancedb/lancedb/blob/main/node/src/remote/index.ts#L293)
+
+___
+
+### countRows
+
+▸ **countRows**(): `Promise`<`number`\>
+
+Returns the number of rows in this table.
+
+#### Returns
+
+`Promise`<`number`\>
+
+#### Implementation of
+
+[Table](../interfaces/Table.md).[countRows](../interfaces/Table.md#countrows)
+
+#### Defined in
+
+[remote/index.ts:290](https://github.com/lancedb/lancedb/blob/main/node/src/remote/index.ts#L290)
+
+___
+
+### createIndex
+
+▸ **createIndex**(`metric_type`, `column`, `index_cache_size`): `Promise`<`any`\>
+
+Create an ANN index on this Table vector index.
+
+#### Parameters
+
+| Name | Type | Description |
+| :------ | :------ | :------ |
+| `metric_type` | `string` | distance metric type, L2 or cosine or dot |
+| `column` | `string` | the name of the column to be indexed |
+
+#### Returns
+
+`Promise`<`any`\>
+
+#### Implementation of
+
+[Table](../interfaces/Table.md).[createIndex](../interfaces/Table.md#createindex)
+
+#### Defined in
+
+[remote/index.ts:249](https://github.com/lancedb/lancedb/blob/main/node/src/remote/index.ts#L249)
+
+___
+
+### delete
+
+▸ **delete**(`filter`): `Promise`<`void`\>
+
+Delete rows from this table.
+
+#### Parameters
+
+| Name | Type | Description |
+| :------ | :------ | :------ |
+| `filter` | `string` | A filter in the same format used by a sql WHERE clause. |
+
+#### Returns
+
+`Promise`<`void`\>
+
+#### Implementation of
+
+[Table](../interfaces/Table.md).[delete](../interfaces/Table.md#delete)
+
+#### Defined in
+
+[remote/index.ts:295](https://github.com/lancedb/lancedb/blob/main/node/src/remote/index.ts#L295)
+
+___
+
+### overwrite
+
+▸ **overwrite**(`data`): `Promise`<`number`\>
+
+Insert records into this Table, replacing its contents.
+
+#### Parameters
+
+| Name | Type | Description |
+| :------ | :------ | :------ |
+| `data` | `Record`<`string`, `unknown`\>[] | Records to be inserted into the Table |
+
+#### Returns
+
+`Promise`<`number`\>
+
+The number of rows added to the table
+
+#### Implementation of
+
+[Table](../interfaces/Table.md).[overwrite](../interfaces/Table.md#overwrite)
+
+#### Defined in
+
+[remote/index.ts:231](https://github.com/lancedb/lancedb/blob/main/node/src/remote/index.ts#L231)
+
+___
+
+### search
+
+▸ **search**(`query`): [`Query`](Query.md)<`T`\>
+
+Creates a search query to find the nearest neighbors of the given search term
+
+#### Parameters
+
+| Name | Type | Description |
+| :------ | :------ | :------ |
+| `query` | `T` | The query search term |
+
+#### Returns
+
+[`Query`](Query.md)<`T`\>
+
+#### Implementation of
+
+[Table](../interfaces/Table.md).[search](../interfaces/Table.md#search)
+
+#### Defined in
+
+[remote/index.ts:209](https://github.com/lancedb/lancedb/blob/main/node/src/remote/index.ts#L209)
+
+___
+
+### update
+
+▸ **update**(`args`): `Promise`<`void`\>
+
+Update zero to all rows depending on how many rows match the where clause.
+
+#### Parameters
+
+| Name | Type | Description |
+| :------ | :------ | :------ |
+| `args` | `UpdateArgs` or `UpdateSqlArgs` | The query search arguments |
+
+#### Returns
+
+`Promise`<`any`\>
+
+#### Implementation of
+
+[Table](../interfaces/Table.md).[search](../interfaces/Table.md#update)
+
+#### Defined in
+
+[remote/index.ts:299](https://github.com/lancedb/lancedb/blob/main/node/src/remote/index.ts#L299)
+
+___
+
+### schema
+
+▸ **schema**(): `Promise`<`void`\>
+
+Get the schema of the table
+
+
+#### Returns
+
+`Promise`<`any`\>
+
+#### Implementation of
+
+[Table](../interfaces/Table.md).[search](../interfaces/Table.md#schema)
+
+#### Defined in
+
+[remote/index.ts:198](https://github.com/lancedb/lancedb/blob/main/node/src/remote/index.ts#L198)
+
+___
+
+### listIndices
+
+▸ **listIndices**(): `Promise`<`void`\>
+
+List the indices of the table
+
+
+#### Returns
+
+`Promise`<`any`\>
+
+#### Implementation of
+
+[Table](../interfaces/Table.md).[search](../interfaces/Table.md#listIndices)
+
+#### Defined in
+
+[remote/index.ts:319](https://github.com/lancedb/lancedb/blob/main/node/src/remote/index.ts#L319)
+
+___
+
+### indexStats
+
+▸ **indexStats**(`indexUuid`): `Promise`<`void`\>
+
+Get the indexed/unindexed of rows from the table
+
+#### Parameters
+
+| Name | Type | Description |
+| :------ | :------ | :------ |
+| `indexUuid` | `string`  | the uuid of the index |
+
+#### Returns
+
+`Promise`<`numIndexedRows`\>
+`Promise`<`numUnindexedRows`\>
+
+#### Implementation of
+
+[Table](../interfaces/Table.md).[search](../interfaces/Table.md#indexStats)
+
+#### Defined in
+
+[remote/index.ts:328](https://github.com/lancedb/lancedb/blob/main/node/src/remote/index.ts#L328)

docs/src/javascript/saas-modules.md

@@ -0,0 +1,92 @@
+# Table of contents
+
+## Installation
+
+```bash
+npm install vectordb
+```
+
+This will download the appropriate native library for your platform. We currently
+support x86_64 Linux, aarch64 Linux, Intel MacOS, and ARM (M1/M2) MacOS. We do not
+yet support Windows or musl-based Linux (such as Alpine Linux).
+
+
+## Classes 
+- [RemoteConnection](classes/RemoteConnection.md)
+- [RemoteTable](classes/RemoteTable.md)
+- [RemoteQuery](classes/RemoteQuery.md)
+
+
+## Methods
+
+- [add](classes/RemoteTable.md#add)
+- [countRows](classes/RemoteTable.md#countrows)
+- [createIndex](classes/RemoteTable.md#createindex)
+- [createTable](classes/RemoteConnection.md#createtable)
+- [delete](classes/RemoteTable.md#delete)
+- [dropTable](classes/RemoteConnection.md#droptable)
+- [listIndices](classes/RemoteTable.md#listindices)
+- [indexStats](classes/RemoteTable.md#liststats)
+- [openTable](classes/RemoteConnection.md#opentable)
+- [overwrite](classes/RemoteTable.md#overwrite)
+- [schema](classes/RemoteTable.md#schema)
+- [search](classes/RemoteTable.md#search)
+- [tableNames](classes/RemoteConnection.md#tablenames)
+- [update](classes/RemoteTable.md#update)
+
+
+## Example code 
+```javascript
+
+const lancedb = require('vectordb');
+const { Schema, Field, Int32, Float32, Utf8, FixedSizeList } = require ("apache-arrow/Arrow.node")
+
+// connect to a remote DB
+const devApiKey = process.env.LANCEDB_DEV_API_KEY
+const dbURI = process.env.LANCEDB_URI
+const db = await lancedb.connect({
+  uri: dbURI, // replace dbURI with your project, e.g. "db://your-project-name"
+  apiKey: devApiKey,  // replace dbURI with your api key
+  region: "us-east-1-dev"
+});
+// create a new table
+const tableName = "my_table_000"
+const data = [
+    { id: 1, vector: [0.1, 1.0], item: "foo", price: 10.0 },
+    { id: 2, vector: [3.9, 0.5], item: "bar", price: 20.0 }
+]
+const schema = new Schema(
+    [
+        new Field('id', new Int32()), 
+        new Field('vector', new FixedSizeList(2, new Field('float32', new Float32()))),
+        new Field('item', new Utf8()),
+        new Field('price', new Float32())
+    ]
+)
+const table = await db.createTable({
+    name: tableName,
+    schema,
+}, data)
+
+// list the table
+const tableNames_1 = await db.tableNames('')
+// add some data and search should be okay
+const newData = [
+      { id: 3, vector: [10.3, 1.9], item: "test1", price: 30.0 }, 
+      { id: 4, vector: [6.2, 9.2], item: "test2", price: 40.0 }
+]
+await table.add(newData)
+// create the index for the table
+await table.createIndex({
+      metric_type: "L2", 
+      column: "vector"
+})
+let result = await table.search([2.8, 4.3]).select(["vector", "price"]).limit(1).execute()
+// update the data
+await table.update({ 
+      where: "id == 1", 
+      values: { item: "foo1" } 
+})
+//drop the table
+await db.dropTable(tableName)
+```

docs/src/notebooks/code_qa_bot.ipynb

@@ -44,15 +44,14 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "import openai\n",
+    "from openai import OpenAI\n",
     "import os\n",
     "\n",
     "# Configuring the environment variable OPENAI_API_KEY\n",
     "if \"OPENAI_API_KEY\" not in os.environ:\n",
-    "    # OR set the key here as a variable\n",
-    "    openai.api_key = \"sk-...\"\n",
-    "    \n",
-    "assert len(openai.Model.list()[\"data\"]) > 0"
+    "    os.environ[\"OPENAI_API_KEY\"] = \"sk-...\"\n",
+    "client = OpenAI()\n",
+    "assert len(client.models.list().data) > 0"
    ]
   },
   {

docs/src/notebooks/youtube_transcript_search.ipynb

@@ -27,11 +27,11 @@
      "output_type": "stream",
      "text": [
       "\n",
-      "\u001B[1m[\u001B[0m\u001B[34;49mnotice\u001B[0m\u001B[1;39;49m]\u001B[0m\u001B[39;49m A new release of pip is available: \u001B[0m\u001B[31;49m23.0\u001B[0m\u001B[39;49m -> \u001B[0m\u001B[32;49m23.1.1\u001B[0m\n",
-      "\u001B[1m[\u001B[0m\u001B[34;49mnotice\u001B[0m\u001B[1;39;49m]\u001B[0m\u001B[39;49m To update, run: \u001B[0m\u001B[32;49mpip install --upgrade pip\u001B[0m\n",
+      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m A new release of pip is available: \u001b[0m\u001b[31;49m23.0\u001b[0m\u001b[39;49m -> \u001b[0m\u001b[32;49m23.1.1\u001b[0m\n",
+      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m To update, run: \u001b[0m\u001b[32;49mpip install --upgrade pip\u001b[0m\n",
       "\n",
-      "\u001B[1m[\u001B[0m\u001B[34;49mnotice\u001B[0m\u001B[1;39;49m]\u001B[0m\u001B[39;49m A new release of pip is available: \u001B[0m\u001B[31;49m23.0\u001B[0m\u001B[39;49m -> \u001B[0m\u001B[32;49m23.1.1\u001B[0m\n",
-      "\u001B[1m[\u001B[0m\u001B[34;49mnotice\u001B[0m\u001B[1;39;49m]\u001B[0m\u001B[39;49m To update, run: \u001B[0m\u001B[32;49mpip install --upgrade pip\u001B[0m\n"
+      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m A new release of pip is available: \u001b[0m\u001b[31;49m23.0\u001b[0m\u001b[39;49m -> \u001b[0m\u001b[32;49m23.1.1\u001b[0m\n",
+      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m To update, run: \u001b[0m\u001b[32;49mpip install --upgrade pip\u001b[0m\n"
      ]
     }
    ],
@@ -206,15 +206,16 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "import openai\n",
+    "from openai import OpenAI\n",
     "import os\n",
     "\n",
     "# Configuring the environment variable OPENAI_API_KEY\n",
     "if \"OPENAI_API_KEY\" not in os.environ:\n",
     "    # OR set the key here as a variable\n",
-    "    openai.api_key = \"sk-...\"\n",
+    "    os.environ[\"OPENAI_API_KEY\"] = \"sk-...\"\n",
     "    \n",
-    "assert len(openai.Model.list()[\"data\"]) > 0"
+    "client = OpenAI()\n",
+    "assert len(client.models.list().data) > 0"
    ]
   },
   {
@@ -234,8 +235,8 @@
    "outputs": [],
    "source": [
     "def embed_func(c):    \n",
-    "    rs = openai.Embedding.create(input=c, engine=\"text-embedding-ada-002\")\n",
-    "    return [record[\"embedding\"] for record in rs[\"data\"]]"
+    "    rs = client.embeddings.create(input=c, model=\"text-embedding-ada-002\")\n",
+    "    return [rs.data[0].embedding]"
    ]
   },
   {
@@ -536,9 +537,8 @@
    ],
    "source": [
     "def complete(prompt):\n",
-    "    # query text-davinci-003\n",
-    "    res = openai.Completion.create(\n",
-    "        engine='text-davinci-003',\n",
+    "    res = client.completions.create(\n",
+    "        model='text-davinci-003',\n",
     "        prompt=prompt,\n",
     "        temperature=0,\n",
     "        max_tokens=400,\n",
@@ -547,7 +547,7 @@
     "        presence_penalty=0,\n",
     "        stop=None\n",
     "    )\n",
-    "    return res['choices'][0]['text'].strip()\n",
+    "    return res.choices[0].text\n",
     "\n",
     "# check that it works\n",
     "query = \"who was the 12th person on the moon and when did they land?\"\n",

docs/src/python/pydantic.md

@@ -7,7 +7,7 @@ LanceDB integrates with Pydantic for schema inference, data ingestion, and query
 
 LanceDB supports to create Apache Arrow Schema from a
 [Pydantic BaseModel](https://docs.pydantic.dev/latest/api/main/#pydantic.main.BaseModel)
-via [pydantic_to_schema()](python.md##lancedb.pydantic.pydantic_to_schema) method.
+via [pydantic_to_schema()](python.md#lancedb.pydantic.pydantic_to_schema) method.
 
 ::: lancedb.pydantic.pydantic_to_schema
 

node/package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "vectordb",
-  "version": "0.4.0",
+  "version": "0.4.2",
   "lockfileVersion": 2,
   "requires": true,
   "packages": {
     "": {
       "name": "vectordb",
-      "version": "0.4.0",
+      "version": "0.4.2",
       "cpu": [
         "x64",
         "arm64"
@@ -18,9 +18,9 @@
         "win32"
       ],
       "dependencies": {
-        "@apache-arrow/ts": "^12.0.0",
+        "@apache-arrow/ts": "^14.0.2",
         "@neon-rs/load": "^0.0.74",
-        "apache-arrow": "^12.0.0",
+        "apache-arrow": "^14.0.2",
         "axios": "^1.4.0"
       },
       "devDependencies": {
@@ -53,39 +53,59 @@
         "uuid": "^9.0.0"
       },
       "optionalDependencies": {
-        "@lancedb/vectordb-darwin-arm64": "0.4.0",
-        "@lancedb/vectordb-darwin-x64": "0.4.0",
-        "@lancedb/vectordb-linux-arm64-gnu": "0.4.0",
-        "@lancedb/vectordb-linux-x64-gnu": "0.4.0",
-        "@lancedb/vectordb-win32-x64-msvc": "0.4.0"
+        "@lancedb/vectordb-darwin-arm64": "0.4.2",
+        "@lancedb/vectordb-darwin-x64": "0.4.2",
+        "@lancedb/vectordb-linux-arm64-gnu": "0.4.2",
+        "@lancedb/vectordb-linux-x64-gnu": "0.4.2",
+        "@lancedb/vectordb-win32-x64-msvc": "0.4.2"
+      }
+    },
+    "node_modules/@75lb/deep-merge": {
+      "version": "1.1.1",
+      "resolved": "https://registry.npmjs.org/@75lb/deep-merge/-/deep-merge-1.1.1.tgz",
+      "integrity": "sha512-xvgv6pkMGBA6GwdyJbNAnDmfAIR/DfWhrj9jgWh3TY7gRm3KO46x/GPjRg6wJ0nOepwqrNxFfojebh0Df4h4Tw==",
+      "dependencies": {
+        "lodash.assignwith": "^4.2.0",
+        "typical": "^7.1.1"
+      },
+      "engines": {
+        "node": ">=12.17"
+      }
+    },
+    "node_modules/@75lb/deep-merge/node_modules/typical": {
+      "version": "7.1.1",
+      "resolved": "https://registry.npmjs.org/typical/-/typical-7.1.1.tgz",
+      "integrity": "sha512-T+tKVNs6Wu7IWiAce5BgMd7OZfNYUndHwc5MknN+UHOudi7sGZzuHdCadllRuqJ3fPtgFtIH9+lt9qRv6lmpfA==",
+      "engines": {
+        "node": ">=12.17"
       }
     },
     "node_modules/@apache-arrow/ts": {
-      "version": "12.0.0",
-      "resolved": "https://registry.npmjs.org/@apache-arrow/ts/-/ts-12.0.0.tgz",
-      "integrity": "sha512-ArJ3Fw5W9RAeNWuyCU2CdjL/nEAZSVDG1p3jz/ZtLo/q3NTz2w7HUCOJeszejH/5alGX+QirYrJ5c6BW++/P7g==",
+      "version": "14.0.2",
+      "resolved": "https://registry.npmjs.org/@apache-arrow/ts/-/ts-14.0.2.tgz",
+      "integrity": "sha512-CtwAvLkK0CZv7xsYeCo91ml6PvlfzAmAJZkRYuz2GNBwfYufj5SVi0iuSMwIMkcU/szVwvLdzORSLa5PlF/2ug==",
       "dependencies": {
         "@types/command-line-args": "5.2.0",
         "@types/command-line-usage": "5.0.2",
-        "@types/node": "18.14.5",
+        "@types/node": "20.3.0",
         "@types/pad-left": "2.1.1",
         "command-line-args": "5.2.1",
-        "command-line-usage": "6.1.3",
-        "flatbuffers": "23.3.3",
+        "command-line-usage": "7.0.1",
+        "flatbuffers": "23.5.26",
         "json-bignum": "^0.0.3",
         "pad-left": "^2.1.0",
-        "tslib": "^2.5.0"
+        "tslib": "^2.5.3"
       }
     },
     "node_modules/@apache-arrow/ts/node_modules/@types/node": {
-      "version": "18.14.5",
-      "resolved": "https://registry.npmjs.org/@types/node/-/node-18.14.5.tgz",
-      "integrity": "sha512-CRT4tMK/DHYhw1fcCEBwME9CSaZNclxfzVMe7GsO6ULSwsttbj70wSiX6rZdIjGblu93sTJxLdhNIT85KKI7Qw=="
+      "version": "20.3.0",
+      "resolved": "https://registry.npmjs.org/@types/node/-/node-20.3.0.tgz",
+      "integrity": "sha512-cumHmIAf6On83X7yP+LrsEyUOf/YlociZelmpRYaGFydoaPdxdt80MAbu6vWerQT2COCp2nPvHdsbD7tHn/YlQ=="
     },
     "node_modules/@apache-arrow/ts/node_modules/tslib": {
-      "version": "2.5.0",
-      "resolved": "https://registry.npmjs.org/tslib/-/tslib-2.5.0.tgz",
-      "integrity": "sha512-336iVw3rtn2BUK7ORdIAHTyxHGRIHVReokCR3XjbckJMK7ms8FysBfhLR8IXnAgy7T0PTPNBWKiH514FOW/WSg=="
+      "version": "2.6.2",
+      "resolved": "https://registry.npmjs.org/tslib/-/tslib-2.6.2.tgz",
+      "integrity": "sha512-AEYxH93jGFPn/a2iVAwW87VuUIkR1FVUKB77NwMF7nBTDkDrrT/Hpt/IrCJ0QXhW27jTBDcf5ZY7w6RiqTMw2Q=="
     },
     "node_modules/@cargo-messages/android-arm-eabi": {
       "version": "0.0.160",
@@ -317,9 +337,9 @@
       }
     },
     "node_modules/@lancedb/vectordb-darwin-arm64": {
-      "version": "0.4.0",
-      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-darwin-arm64/-/vectordb-darwin-arm64-0.4.0.tgz",
-      "integrity": "sha512-cP6zGtBWXEcJHCI4uLNIP5ILtRvexvwmL8Uri1dnHG8dT8g12Ykug3BHO6Wt6wp/xASd2jJRIF/VAJsN9IeP1A==",
+      "version": "0.4.2",
+      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-darwin-arm64/-/vectordb-darwin-arm64-0.4.2.tgz",
+      "integrity": "sha512-Ec73W2IHnZK4VC8g/7JyLbgcwcpNb9YI20yEhfTjEEFjJKoElZhDD/ZgghC3QQSRnrXFTxDzPK1V9BDT5QB2Hg==",
       "cpu": [
         "arm64"
       ],
@@ -329,9 +349,9 @@
       ]
     },
     "node_modules/@lancedb/vectordb-darwin-x64": {
-      "version": "0.4.0",
-      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-darwin-x64/-/vectordb-darwin-x64-0.4.0.tgz",
-      "integrity": "sha512-ig0gV5ol1sFe2lb1HOatK0rizyj9I91WbnH79i7OdUl3nAQIcWm70CnxrPLtx0DS2NTGh2kFJbYCWcaUlu6YfA==",
+      "version": "0.4.2",
+      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-darwin-x64/-/vectordb-darwin-x64-0.4.2.tgz",
+      "integrity": "sha512-tj0JJlOfOdeSAfmM7EZhrhFdCFjoq9Bmrjt4741BNjtF+Nv4Otl53lFtUQrexTr4oh/E1yY1qaydJ7K++8u3UA==",
       "cpu": [
         "x64"
       ],
@@ -341,9 +361,9 @@
       ]
     },
     "node_modules/@lancedb/vectordb-linux-arm64-gnu": {
-      "version": "0.4.0",
-      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-linux-arm64-gnu/-/vectordb-linux-arm64-gnu-0.4.0.tgz",
-      "integrity": "sha512-gMXIDT2kriAPDwWIRKXdaTCNdOeFGEok1S9Y30AOruHXddW1vCIo4JNJIYbBqHnwAeI4wI3ae6GRCFaf1UxO3g==",
+      "version": "0.4.2",
+      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-linux-arm64-gnu/-/vectordb-linux-arm64-gnu-0.4.2.tgz",
+      "integrity": "sha512-OQ7ra5Q5RrLLwxIyI338KfQ2sSl8NJfqAHWvwiMtjCYFFYxIJGjX7U0I2MjSEPqJ5/ZoyjV4mjsvs0G1q20u+Q==",
       "cpu": [
         "arm64"
       ],
@@ -353,9 +373,9 @@
       ]
     },
     "node_modules/@lancedb/vectordb-linux-x64-gnu": {
-      "version": "0.4.0",
-      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-linux-x64-gnu/-/vectordb-linux-x64-gnu-0.4.0.tgz",
-      "integrity": "sha512-ZQ3lDrDSz1IKdx/mS9Lz08agFO+OD5oSFrrcFNCoT1+H93eS1mCLdmCoEARu3jKbx0tMs38l5J9yXZ2QmJye3w==",
+      "version": "0.4.2",
+      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-linux-x64-gnu/-/vectordb-linux-x64-gnu-0.4.2.tgz",
+      "integrity": "sha512-9tgIFSOYqNJzonnYsQr7v2gGdJm8aZ62UsVX2SWAIVhypoP4A05tAlbzjBgKO3R5xy5gpcW8tt/Pt8IsYWON7Q==",
       "cpu": [
         "x64"
       ],
@@ -365,9 +385,9 @@
       ]
     },
     "node_modules/@lancedb/vectordb-win32-x64-msvc": {
-      "version": "0.4.0",
-      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-win32-x64-msvc/-/vectordb-win32-x64-msvc-0.4.0.tgz",
-      "integrity": "sha512-toNcNwBRE1sdsSf5hr7W8QiqZ33csc/knVEek4CyvYkZHJGh4Z6WI+DJUIASo5wzUez4TX7qUPpRPL9HuaPMCg==",
+      "version": "0.4.2",
+      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-win32-x64-msvc/-/vectordb-win32-x64-msvc-0.4.2.tgz",
+      "integrity": "sha512-jhG3MqZ3r8BexXANLRNX57RAnCZT9psdSBORG3KTu5qe2xaunRlJNSA2kk8a79tf+gtUT/BAmMiXMzAi/dwq8w==",
       "cpu": [
         "x64"
       ],
@@ -866,7 +886,6 @@
       "version": "4.3.0",
       "resolved": "https://registry.npmjs.org/ansi-styles/-/ansi-styles-4.3.0.tgz",
       "integrity": "sha512-zbB9rCJAT1rbjiVDb2hqKFHNYLxgtk8NURxZ3IZwD3F6NtxbXZQCnnSi1Lkx+IDohdPlFp222wVALIheZJQSEg==",
-      "dev": true,
       "dependencies": {
         "color-convert": "^2.0.1"
       },
@@ -891,34 +910,34 @@
       }
     },
     "node_modules/apache-arrow": {
-      "version": "12.0.0",
-      "resolved": "https://registry.npmjs.org/apache-arrow/-/apache-arrow-12.0.0.tgz",
-      "integrity": "sha512-uI+hnZZsGfNJiR/wG8j5yPQuDjmOHx4hZpkA743G4x3TlFrCpA3MMX7KUkIOIw0e/CwZ8NYuaMzaQsblA47qVA==",
+      "version": "14.0.2",
+      "resolved": "https://registry.npmjs.org/apache-arrow/-/apache-arrow-14.0.2.tgz",
+      "integrity": "sha512-EBO2xJN36/XoY81nhLcwCJgFwkboDZeyNQ+OPsG7bCoQjc2BT0aTyH/MR6SrL+LirSNz+cYqjGRlupMMlP1aEg==",
       "dependencies": {
         "@types/command-line-args": "5.2.0",
         "@types/command-line-usage": "5.0.2",
-        "@types/node": "18.14.5",
+        "@types/node": "20.3.0",
         "@types/pad-left": "2.1.1",
         "command-line-args": "5.2.1",
-        "command-line-usage": "6.1.3",
-        "flatbuffers": "23.3.3",
+        "command-line-usage": "7.0.1",
+        "flatbuffers": "23.5.26",
         "json-bignum": "^0.0.3",
         "pad-left": "^2.1.0",
-        "tslib": "^2.5.0"
+        "tslib": "^2.5.3"
       },
       "bin": {
         "arrow2csv": "bin/arrow2csv.js"
       }
     },
     "node_modules/apache-arrow/node_modules/@types/node": {
-      "version": "18.14.5",
-      "resolved": "https://registry.npmjs.org/@types/node/-/node-18.14.5.tgz",
-      "integrity": "sha512-CRT4tMK/DHYhw1fcCEBwME9CSaZNclxfzVMe7GsO6ULSwsttbj70wSiX6rZdIjGblu93sTJxLdhNIT85KKI7Qw=="
+      "version": "20.3.0",
+      "resolved": "https://registry.npmjs.org/@types/node/-/node-20.3.0.tgz",
+      "integrity": "sha512-cumHmIAf6On83X7yP+LrsEyUOf/YlociZelmpRYaGFydoaPdxdt80MAbu6vWerQT2COCp2nPvHdsbD7tHn/YlQ=="
     },
     "node_modules/apache-arrow/node_modules/tslib": {
-      "version": "2.5.0",
-      "resolved": "https://registry.npmjs.org/tslib/-/tslib-2.5.0.tgz",
-      "integrity": "sha512-336iVw3rtn2BUK7ORdIAHTyxHGRIHVReokCR3XjbckJMK7ms8FysBfhLR8IXnAgy7T0PTPNBWKiH514FOW/WSg=="
+      "version": "2.6.2",
+      "resolved": "https://registry.npmjs.org/tslib/-/tslib-2.6.2.tgz",
+      "integrity": "sha512-AEYxH93jGFPn/a2iVAwW87VuUIkR1FVUKB77NwMF7nBTDkDrrT/Hpt/IrCJ0QXhW27jTBDcf5ZY7w6RiqTMw2Q=="
     },
     "node_modules/arg": {
       "version": "4.1.3",
@@ -1170,7 +1189,6 @@
       "version": "4.1.2",
       "resolved": "https://registry.npmjs.org/chalk/-/chalk-4.1.2.tgz",
       "integrity": "sha512-oKnbhFyRIXpUuez8iBMmyEa4nbj4IOQyuhc/wy9kY7/WVPcwIO9VA668Pu8RkO7+0G76SLROeyw9CpQ061i4mA==",
-      "dev": true,
       "dependencies": {
         "ansi-styles": "^4.1.0",
         "supports-color": "^7.1.0"
@@ -1182,11 +1200,24 @@
         "url": "https://github.com/chalk/chalk?sponsor=1"
       }
     },
+    "node_modules/chalk-template": {
+      "version": "0.4.0",
+      "resolved": "https://registry.npmjs.org/chalk-template/-/chalk-template-0.4.0.tgz",
+      "integrity": "sha512-/ghrgmhfY8RaSdeo43hNXxpoHAtxdbskUHjPpfqUWGttFgycUhYPGx3YZBCnUCvOa7Doivn1IZec3DEGFoMgLg==",
+      "dependencies": {
+        "chalk": "^4.1.2"
+      },
+      "engines": {
+        "node": ">=12"
+      },
+      "funding": {
+        "url": "https://github.com/chalk/chalk-template?sponsor=1"
+      }
+    },
     "node_modules/chalk/node_modules/supports-color": {
       "version": "7.2.0",
       "resolved": "https://registry.npmjs.org/supports-color/-/supports-color-7.2.0.tgz",
       "integrity": "sha512-qpCAvRl9stuOHveKsn7HncJRvv501qIacKzQlO/+Lwxc9+0q2wLyv4Dfvt80/DPn2pqOBsJdDiogXGR9+OvwRw==",
-      "dev": true,
       "dependencies": {
         "has-flag": "^4.0.0"
       },
@@ -1245,7 +1276,6 @@
       "version": "2.0.1",
       "resolved": "https://registry.npmjs.org/color-convert/-/color-convert-2.0.1.tgz",
       "integrity": "sha512-RRECPsj7iu/xb5oKYcsFHSppFNnsj/52OVTRKb4zP5onXwVF3zVmmToNcOfGC+CRDpfK/U584fMg38ZHCaElKQ==",
-      "dev": true,
       "dependencies": {
         "color-name": "~1.1.4"
       },
@@ -1256,8 +1286,7 @@
     "node_modules/color-name": {
       "version": "1.1.4",
       "resolved": "https://registry.npmjs.org/color-name/-/color-name-1.1.4.tgz",
-      "integrity": "sha512-dOy+3AuW3a2wNbZHIuMZpTcgjGuLU/uBL/ubcZF9OXbDo8ff4O8yVp5Bf0efS8uEoYo5q4Fx7dY9OgQGXgAsQA==",
-      "dev": true
+      "integrity": "sha512-dOy+3AuW3a2wNbZHIuMZpTcgjGuLU/uBL/ubcZF9OXbDo8ff4O8yVp5Bf0efS8uEoYo5q4Fx7dY9OgQGXgAsQA=="
     },
     "node_modules/combined-stream": {
       "version": "1.0.8",
@@ -1285,97 +1314,33 @@
       }
     },
     "node_modules/command-line-usage": {
-      "version": "6.1.3",
-      "resolved": "https://registry.npmjs.org/command-line-usage/-/command-line-usage-6.1.3.tgz",
-      "integrity": "sha512-sH5ZSPr+7UStsloltmDh7Ce5fb8XPlHyoPzTpyyMuYCtervL65+ubVZ6Q61cFtFl62UyJlc8/JwERRbAFPUqgw==",
+      "version": "7.0.1",
+      "resolved": "https://registry.npmjs.org/command-line-usage/-/command-line-usage-7.0.1.tgz",
+      "integrity": "sha512-NCyznE//MuTjwi3y84QVUGEOT+P5oto1e1Pk/jFPVdPPfsG03qpTIl3yw6etR+v73d0lXsoojRpvbru2sqePxQ==",
       "dependencies": {
-        "array-back": "^4.0.2",
-        "chalk": "^2.4.2",
-        "table-layout": "^1.0.2",
-        "typical": "^5.2.0"
+        "array-back": "^6.2.2",
+        "chalk-template": "^0.4.0",
+        "table-layout": "^3.0.0",
+        "typical": "^7.1.1"
       },
       "engines": {
-        "node": ">=8.0.0"
-      }
-    },
-    "node_modules/command-line-usage/node_modules/ansi-styles": {
-      "version": "3.2.1",
-      "resolved": "https://registry.npmjs.org/ansi-styles/-/ansi-styles-3.2.1.tgz",
-      "integrity": "sha512-VT0ZI6kZRdTh8YyJw3SMbYm/u+NqfsAxEpWO0Pf9sq8/e94WxxOpPKx9FR1FlyCtOVDNOQ+8ntlqFxiRc+r5qA==",
-      "dependencies": {
-        "color-convert": "^1.9.0"
-      },
-      "engines": {
-        "node": ">=4"
+        "node": ">=12.20.0"
       }
     },
     "node_modules/command-line-usage/node_modules/array-back": {
-      "version": "4.0.2",
-      "resolved": "https://registry.npmjs.org/array-back/-/array-back-4.0.2.tgz",
-      "integrity": "sha512-NbdMezxqf94cnNfWLL7V/im0Ub+Anbb0IoZhvzie8+4HJ4nMQuzHuy49FkGYCJK2yAloZ3meiB6AVMClbrI1vg==",
+      "version": "6.2.2",
+      "resolved": "https://registry.npmjs.org/array-back/-/array-back-6.2.2.tgz",
+      "integrity": "sha512-gUAZ7HPyb4SJczXAMUXMGAvI976JoK3qEx9v1FTmeYuJj0IBiaKttG1ydtGKdkfqWkIkouke7nG8ufGy77+Cvw==",
       "engines": {
-        "node": ">=8"
-      }
-    },
-    "node_modules/command-line-usage/node_modules/chalk": {
-      "version": "2.4.2",
-      "resolved": "https://registry.npmjs.org/chalk/-/chalk-2.4.2.tgz",
-      "integrity": "sha512-Mti+f9lpJNcwF4tWV8/OrTTtF1gZi+f8FqlyAdouralcFWFQWF2+NgCHShjkCb+IFBLq9buZwE1xckQU4peSuQ==",
-      "dependencies": {
-        "ansi-styles": "^3.2.1",
-        "escape-string-regexp": "^1.0.5",
-        "supports-color": "^5.3.0"
-      },
-      "engines": {
-        "node": ">=4"
-      }
-    },
-    "node_modules/command-line-usage/node_modules/color-convert": {
-      "version": "1.9.3",
-      "resolved": "https://registry.npmjs.org/color-convert/-/color-convert-1.9.3.tgz",
-      "integrity": "sha512-QfAUtd+vFdAtFQcC8CCyYt1fYWxSqAiK2cSD6zDB8N3cpsEBAvRxp9zOGg6G/SHHJYAT88/az/IuDGALsNVbGg==",
-      "dependencies": {
-        "color-name": "1.1.3"
-      }
-    },
-    "node_modules/command-line-usage/node_modules/color-name": {
-      "version": "1.1.3",
-      "resolved": "https://registry.npmjs.org/color-name/-/color-name-1.1.3.tgz",
-      "integrity": "sha512-72fSenhMw2HZMTVHeCA9KCmpEIbzWiQsjN+BHcBbS9vr1mtt+vJjPdksIBNUmKAW8TFUDPJK5SUU3QhE9NEXDw=="
-    },
-    "node_modules/command-line-usage/node_modules/escape-string-regexp": {
-      "version": "1.0.5",
-      "resolved": "https://registry.npmjs.org/escape-string-regexp/-/escape-string-regexp-1.0.5.tgz",
-      "integrity": "sha512-vbRorB5FUQWvla16U8R/qgaFIya2qGzwDrNmCZuYKrbdSUMG6I1ZCGQRefkRVhuOkIGVne7BQ35DSfo1qvJqFg==",
-      "engines": {
-        "node": ">=0.8.0"
-      }
-    },
-    "node_modules/command-line-usage/node_modules/has-flag": {
-      "version": "3.0.0",
-      "resolved": "https://registry.npmjs.org/has-flag/-/has-flag-3.0.0.tgz",
-      "integrity": "sha512-sKJf1+ceQBr4SMkvQnBDNDtf4TXpVhVGateu0t918bl30FnbE2m4vNLX+VWe/dpjlb+HugGYzW7uQXH98HPEYw==",
-      "engines": {
-        "node": ">=4"
-      }
-    },
-    "node_modules/command-line-usage/node_modules/supports-color": {
-      "version": "5.5.0",
-      "resolved": "https://registry.npmjs.org/supports-color/-/supports-color-5.5.0.tgz",
-      "integrity": "sha512-QjVjwdXIt408MIiAqCX4oUKsgU2EqAGzs2Ppkm4aQYbjm+ZEWEcW4SfFNTr4uMNZma0ey4f5lgLrkB0aX0QMow==",
-      "dependencies": {
-        "has-flag": "^3.0.0"
-      },
-      "engines": {
-        "node": ">=4"
+        "node": ">=12.17"
       }
     },
     "node_modules/command-line-usage/node_modules/typical": {
-      "version": "5.2.0",
-      "resolved": "https://registry.npmjs.org/typical/-/typical-5.2.0.tgz",
-      "integrity": "sha512-dvdQgNDNJo+8B2uBQoqdb11eUCE1JQXhvjC/CZtgvZseVd5TYMXnq0+vuUemXbd/Se29cTaUuPX3YIc2xgbvIg==",
+      "version": "7.1.1",
+      "resolved": "https://registry.npmjs.org/typical/-/typical-7.1.1.tgz",
+      "integrity": "sha512-T+tKVNs6Wu7IWiAce5BgMd7OZfNYUndHwc5MknN+UHOudi7sGZzuHdCadllRuqJ3fPtgFtIH9+lt9qRv6lmpfA==",
       "engines": {
-        "node": ">=8"
+        "node": ">=12.17"
       }
     },
     "node_modules/concat-map": {
@@ -1451,14 +1416,6 @@
         "node": ">=6"
       }
     },
-    "node_modules/deep-extend": {
-      "version": "0.6.0",
-      "resolved": "https://registry.npmjs.org/deep-extend/-/deep-extend-0.6.0.tgz",
-      "integrity": "sha512-LOHxIOaPYdHlJRtCQfDIVZtfw/ufM8+rVj649RIHzcm/vGwQRXFt6OPqIFWsm2XEMrNIEtWR64sY1LEKD2vAOA==",
-      "engines": {
-        "node": ">=4.0.0"
-      }
-    },
     "node_modules/deep-is": {
       "version": "0.1.4",
       "resolved": "https://registry.npmjs.org/deep-is/-/deep-is-0.1.4.tgz",
@@ -2237,9 +2194,9 @@
       }
     },
     "node_modules/flatbuffers": {
-      "version": "23.3.3",
-      "resolved": "https://registry.npmjs.org/flatbuffers/-/flatbuffers-23.3.3.tgz",
-      "integrity": "sha512-jmreOaAT1t55keaf+Z259Tvh8tR/Srry9K8dgCgvizhKSEr6gLGgaOJI2WFL5fkOpGOGRZwxUrlFn0GCmXUy6g=="
+      "version": "23.5.26",
+      "resolved": "https://registry.npmjs.org/flatbuffers/-/flatbuffers-23.5.26.tgz",
+      "integrity": "sha512-vE+SI9vrJDwi1oETtTIFldC/o9GsVKRM+s6EL0nQgxXlYV1Vc4Tk30hj4xGICftInKQKj1F3up2n8UbIVobISQ=="
     },
     "node_modules/flatted": {
       "version": "3.2.7",
@@ -2535,7 +2492,6 @@
       "version": "4.0.0",
       "resolved": "https://registry.npmjs.org/has-flag/-/has-flag-4.0.0.tgz",
       "integrity": "sha512-EykJT/Q1KjTWctppgIAgfSO0tKVuZUjhgMr17kqTumMl6Afv3EISleU7qZUzoXDFTAHTDC4NOoG/ZxU3EvlMPQ==",
-      "dev": true,
       "engines": {
         "node": ">=8"
       }
@@ -3048,6 +3004,11 @@
         "url": "https://github.com/sponsors/sindresorhus"
       }
     },
+    "node_modules/lodash.assignwith": {
+      "version": "4.2.0",
+      "resolved": "https://registry.npmjs.org/lodash.assignwith/-/lodash.assignwith-4.2.0.tgz",
+      "integrity": "sha512-ZznplvbvtjK2gMvnQ1BR/zqPFZmS6jbK4p+6Up4xcRYA7yMIwxHCfbTcrYxXKzzqLsQ05eJPVznEW3tuwV7k1g=="
+    },
     "node_modules/lodash.camelcase": {
       "version": "4.3.0",
       "resolved": "https://registry.npmjs.org/lodash.camelcase/-/lodash.camelcase-4.3.0.tgz",
@@ -3668,14 +3629,6 @@
         "node": ">=8.10.0"
       }
     },
-    "node_modules/reduce-flatten": {
-      "version": "2.0.0",
-      "resolved": "https://registry.npmjs.org/reduce-flatten/-/reduce-flatten-2.0.0.tgz",
-      "integrity": "sha512-EJ4UNY/U1t2P/2k6oqotuX2Cc3T6nxJwsM0N0asT7dhrtH1ltUxDn4NalSYmPE2rCkVpcf/X6R0wDwcFpzhd4w==",
-      "engines": {
-        "node": ">=6"
-      }
-    },
     "node_modules/regexp.prototype.flags": {
       "version": "1.5.0",
       "resolved": "https://registry.npmjs.org/regexp.prototype.flags/-/regexp.prototype.flags-1.5.0.tgz",
@@ -3965,6 +3918,14 @@
         "source-map": "^0.6.0"
       }
     },
+    "node_modules/stream-read-all": {
+      "version": "3.0.1",
+      "resolved": "https://registry.npmjs.org/stream-read-all/-/stream-read-all-3.0.1.tgz",
+      "integrity": "sha512-EWZT9XOceBPlVJRrYcykW8jyRSZYbkb/0ZK36uLEmoWVO5gxBOnntNTseNzfREsqxqdfEGQrD8SXQ3QWbBmq8A==",
+      "engines": {
+        "node": ">=10"
+      }
+    },
     "node_modules/string-width": {
       "version": "4.2.3",
       "resolved": "https://registry.npmjs.org/string-width/-/string-width-4.2.3.tgz",
@@ -4082,33 +4043,39 @@
       }
     },
     "node_modules/table-layout": {
-      "version": "1.0.2",
-      "resolved": "https://registry.npmjs.org/table-layout/-/table-layout-1.0.2.tgz",
-      "integrity": "sha512-qd/R7n5rQTRFi+Zf2sk5XVVd9UQl6ZkduPFC3S7WEGJAmetDTjY3qPN50eSKzwuzEyQKy5TN2TiZdkIjos2L6A==",
+      "version": "3.0.2",
+      "resolved": "https://registry.npmjs.org/table-layout/-/table-layout-3.0.2.tgz",
+      "integrity": "sha512-rpyNZYRw+/C+dYkcQ3Pr+rLxW4CfHpXjPDnG7lYhdRoUcZTUt+KEsX+94RGp/aVp/MQU35JCITv2T/beY4m+hw==",
       "dependencies": {
-        "array-back": "^4.0.1",
-        "deep-extend": "~0.6.0",
-        "typical": "^5.2.0",
-        "wordwrapjs": "^4.0.0"
+        "@75lb/deep-merge": "^1.1.1",
+        "array-back": "^6.2.2",
+        "command-line-args": "^5.2.1",
+        "command-line-usage": "^7.0.0",
+        "stream-read-all": "^3.0.1",
+        "typical": "^7.1.1",
+        "wordwrapjs": "^5.1.0"
+      },
+      "bin": {
+        "table-layout": "bin/cli.js"
       },
       "engines": {
-        "node": ">=8.0.0"
+        "node": ">=12.17"
       }
     },
     "node_modules/table-layout/node_modules/array-back": {
-      "version": "4.0.2",
-      "resolved": "https://registry.npmjs.org/array-back/-/array-back-4.0.2.tgz",
-      "integrity": "sha512-NbdMezxqf94cnNfWLL7V/im0Ub+Anbb0IoZhvzie8+4HJ4nMQuzHuy49FkGYCJK2yAloZ3meiB6AVMClbrI1vg==",
+      "version": "6.2.2",
+      "resolved": "https://registry.npmjs.org/array-back/-/array-back-6.2.2.tgz",
+      "integrity": "sha512-gUAZ7HPyb4SJczXAMUXMGAvI976JoK3qEx9v1FTmeYuJj0IBiaKttG1ydtGKdkfqWkIkouke7nG8ufGy77+Cvw==",
       "engines": {
-        "node": ">=8"
+        "node": ">=12.17"
       }
     },
     "node_modules/table-layout/node_modules/typical": {
-      "version": "5.2.0",
-      "resolved": "https://registry.npmjs.org/typical/-/typical-5.2.0.tgz",
-      "integrity": "sha512-dvdQgNDNJo+8B2uBQoqdb11eUCE1JQXhvjC/CZtgvZseVd5TYMXnq0+vuUemXbd/Se29cTaUuPX3YIc2xgbvIg==",
+      "version": "7.1.1",
+      "resolved": "https://registry.npmjs.org/typical/-/typical-7.1.1.tgz",
+      "integrity": "sha512-T+tKVNs6Wu7IWiAce5BgMd7OZfNYUndHwc5MknN+UHOudi7sGZzuHdCadllRuqJ3fPtgFtIH9+lt9qRv6lmpfA==",
       "engines": {
-        "node": ">=8"
+        "node": ">=12.17"
       }
     },
     "node_modules/temp": {
@@ -4553,23 +4520,11 @@
       "dev": true
     },
     "node_modules/wordwrapjs": {
-      "version": "4.0.1",
-      "resolved": "https://registry.npmjs.org/wordwrapjs/-/wordwrapjs-4.0.1.tgz",
-      "integrity": "sha512-kKlNACbvHrkpIw6oPeYDSmdCTu2hdMHoyXLTcUKala++lx5Y+wjJ/e474Jqv5abnVmwxw08DiTuHmw69lJGksA==",
-      "dependencies": {
-        "reduce-flatten": "^2.0.0",
-        "typical": "^5.2.0"
-      },
+      "version": "5.1.0",
+      "resolved": "https://registry.npmjs.org/wordwrapjs/-/wordwrapjs-5.1.0.tgz",
+      "integrity": "sha512-JNjcULU2e4KJwUNv6CHgI46UvDGitb6dGryHajXTDiLgg1/RiGoPSDw4kZfYnwGtEXf2ZMeIewDQgFGzkCB2Sg==",
       "engines": {
-        "node": ">=8.0.0"
-      }
-    },
-    "node_modules/wordwrapjs/node_modules/typical": {
-      "version": "5.2.0",
-      "resolved": "https://registry.npmjs.org/typical/-/typical-5.2.0.tgz",
-      "integrity": "sha512-dvdQgNDNJo+8B2uBQoqdb11eUCE1JQXhvjC/CZtgvZseVd5TYMXnq0+vuUemXbd/Se29cTaUuPX3YIc2xgbvIg==",
-      "engines": {
-        "node": ">=8"
+        "node": ">=12.17"
       }
     },
     "node_modules/workerpool": {
@@ -4690,32 +4645,48 @@
     }
   },
   "dependencies": {
+    "@75lb/deep-merge": {
+      "version": "1.1.1",
+      "resolved": "https://registry.npmjs.org/@75lb/deep-merge/-/deep-merge-1.1.1.tgz",
+      "integrity": "sha512-xvgv6pkMGBA6GwdyJbNAnDmfAIR/DfWhrj9jgWh3TY7gRm3KO46x/GPjRg6wJ0nOepwqrNxFfojebh0Df4h4Tw==",
+      "requires": {
+        "lodash.assignwith": "^4.2.0",
+        "typical": "^7.1.1"
+      },
+      "dependencies": {
+        "typical": {
+          "version": "7.1.1",
+          "resolved": "https://registry.npmjs.org/typical/-/typical-7.1.1.tgz",
+          "integrity": "sha512-T+tKVNs6Wu7IWiAce5BgMd7OZfNYUndHwc5MknN+UHOudi7sGZzuHdCadllRuqJ3fPtgFtIH9+lt9qRv6lmpfA=="
+        }
+      }
+    },
     "@apache-arrow/ts": {
-      "version": "12.0.0",
-      "resolved": "https://registry.npmjs.org/@apache-arrow/ts/-/ts-12.0.0.tgz",
-      "integrity": "sha512-ArJ3Fw5W9RAeNWuyCU2CdjL/nEAZSVDG1p3jz/ZtLo/q3NTz2w7HUCOJeszejH/5alGX+QirYrJ5c6BW++/P7g==",
+      "version": "14.0.2",
+      "resolved": "https://registry.npmjs.org/@apache-arrow/ts/-/ts-14.0.2.tgz",
+      "integrity": "sha512-CtwAvLkK0CZv7xsYeCo91ml6PvlfzAmAJZkRYuz2GNBwfYufj5SVi0iuSMwIMkcU/szVwvLdzORSLa5PlF/2ug==",
       "requires": {
         "@types/command-line-args": "5.2.0",
         "@types/command-line-usage": "5.0.2",
-        "@types/node": "18.14.5",
+        "@types/node": "20.3.0",
         "@types/pad-left": "2.1.1",
         "command-line-args": "5.2.1",
-        "command-line-usage": "6.1.3",
-        "flatbuffers": "23.3.3",
+        "command-line-usage": "7.0.1",
+        "flatbuffers": "23.5.26",
         "json-bignum": "^0.0.3",
         "pad-left": "^2.1.0",
-        "tslib": "^2.5.0"
+        "tslib": "^2.5.3"
       },
       "dependencies": {
         "@types/node": {
-          "version": "18.14.5",
-          "resolved": "https://registry.npmjs.org/@types/node/-/node-18.14.5.tgz",
-          "integrity": "sha512-CRT4tMK/DHYhw1fcCEBwME9CSaZNclxfzVMe7GsO6ULSwsttbj70wSiX6rZdIjGblu93sTJxLdhNIT85KKI7Qw=="
+          "version": "20.3.0",
+          "resolved": "https://registry.npmjs.org/@types/node/-/node-20.3.0.tgz",
+          "integrity": "sha512-cumHmIAf6On83X7yP+LrsEyUOf/YlociZelmpRYaGFydoaPdxdt80MAbu6vWerQT2COCp2nPvHdsbD7tHn/YlQ=="
         },
         "tslib": {
-          "version": "2.5.0",
-          "resolved": "https://registry.npmjs.org/tslib/-/tslib-2.5.0.tgz",
-          "integrity": "sha512-336iVw3rtn2BUK7ORdIAHTyxHGRIHVReokCR3XjbckJMK7ms8FysBfhLR8IXnAgy7T0PTPNBWKiH514FOW/WSg=="
+          "version": "2.6.2",
+          "resolved": "https://registry.npmjs.org/tslib/-/tslib-2.6.2.tgz",
+          "integrity": "sha512-AEYxH93jGFPn/a2iVAwW87VuUIkR1FVUKB77NwMF7nBTDkDrrT/Hpt/IrCJ0QXhW27jTBDcf5ZY7w6RiqTMw2Q=="
         }
       }
     },
@@ -4869,33 +4840,33 @@
       }
     },
     "@lancedb/vectordb-darwin-arm64": {
-      "version": "0.4.0",
-      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-darwin-arm64/-/vectordb-darwin-arm64-0.4.0.tgz",
-      "integrity": "sha512-cP6zGtBWXEcJHCI4uLNIP5ILtRvexvwmL8Uri1dnHG8dT8g12Ykug3BHO6Wt6wp/xASd2jJRIF/VAJsN9IeP1A==",
+      "version": "0.4.2",
+      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-darwin-arm64/-/vectordb-darwin-arm64-0.4.2.tgz",
+      "integrity": "sha512-Ec73W2IHnZK4VC8g/7JyLbgcwcpNb9YI20yEhfTjEEFjJKoElZhDD/ZgghC3QQSRnrXFTxDzPK1V9BDT5QB2Hg==",
       "optional": true
     },
     "@lancedb/vectordb-darwin-x64": {
-      "version": "0.4.0",
-      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-darwin-x64/-/vectordb-darwin-x64-0.4.0.tgz",
-      "integrity": "sha512-ig0gV5ol1sFe2lb1HOatK0rizyj9I91WbnH79i7OdUl3nAQIcWm70CnxrPLtx0DS2NTGh2kFJbYCWcaUlu6YfA==",
+      "version": "0.4.2",
+      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-darwin-x64/-/vectordb-darwin-x64-0.4.2.tgz",
+      "integrity": "sha512-tj0JJlOfOdeSAfmM7EZhrhFdCFjoq9Bmrjt4741BNjtF+Nv4Otl53lFtUQrexTr4oh/E1yY1qaydJ7K++8u3UA==",
       "optional": true
     },
     "@lancedb/vectordb-linux-arm64-gnu": {
-      "version": "0.4.0",
-      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-linux-arm64-gnu/-/vectordb-linux-arm64-gnu-0.4.0.tgz",
-      "integrity": "sha512-gMXIDT2kriAPDwWIRKXdaTCNdOeFGEok1S9Y30AOruHXddW1vCIo4JNJIYbBqHnwAeI4wI3ae6GRCFaf1UxO3g==",
+      "version": "0.4.2",
+      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-linux-arm64-gnu/-/vectordb-linux-arm64-gnu-0.4.2.tgz",
+      "integrity": "sha512-OQ7ra5Q5RrLLwxIyI338KfQ2sSl8NJfqAHWvwiMtjCYFFYxIJGjX7U0I2MjSEPqJ5/ZoyjV4mjsvs0G1q20u+Q==",
       "optional": true
     },
     "@lancedb/vectordb-linux-x64-gnu": {
-      "version": "0.4.0",
-      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-linux-x64-gnu/-/vectordb-linux-x64-gnu-0.4.0.tgz",
-      "integrity": "sha512-ZQ3lDrDSz1IKdx/mS9Lz08agFO+OD5oSFrrcFNCoT1+H93eS1mCLdmCoEARu3jKbx0tMs38l5J9yXZ2QmJye3w==",
+      "version": "0.4.2",
+      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-linux-x64-gnu/-/vectordb-linux-x64-gnu-0.4.2.tgz",
+      "integrity": "sha512-9tgIFSOYqNJzonnYsQr7v2gGdJm8aZ62UsVX2SWAIVhypoP4A05tAlbzjBgKO3R5xy5gpcW8tt/Pt8IsYWON7Q==",
       "optional": true
     },
     "@lancedb/vectordb-win32-x64-msvc": {
-      "version": "0.4.0",
-      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-win32-x64-msvc/-/vectordb-win32-x64-msvc-0.4.0.tgz",
-      "integrity": "sha512-toNcNwBRE1sdsSf5hr7W8QiqZ33csc/knVEek4CyvYkZHJGh4Z6WI+DJUIASo5wzUez4TX7qUPpRPL9HuaPMCg==",
+      "version": "0.4.2",
+      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-win32-x64-msvc/-/vectordb-win32-x64-msvc-0.4.2.tgz",
+      "integrity": "sha512-jhG3MqZ3r8BexXANLRNX57RAnCZT9psdSBORG3KTu5qe2xaunRlJNSA2kk8a79tf+gtUT/BAmMiXMzAi/dwq8w==",
       "optional": true
     },
     "@neon-rs/cli": {
@@ -5268,7 +5239,6 @@
       "version": "4.3.0",
       "resolved": "https://registry.npmjs.org/ansi-styles/-/ansi-styles-4.3.0.tgz",
       "integrity": "sha512-zbB9rCJAT1rbjiVDb2hqKFHNYLxgtk8NURxZ3IZwD3F6NtxbXZQCnnSi1Lkx+IDohdPlFp222wVALIheZJQSEg==",
-      "dev": true,
       "requires": {
         "color-convert": "^2.0.1"
       }
@@ -5284,31 +5254,31 @@
       }
     },
     "apache-arrow": {
-      "version": "12.0.0",
-      "resolved": "https://registry.npmjs.org/apache-arrow/-/apache-arrow-12.0.0.tgz",
-      "integrity": "sha512-uI+hnZZsGfNJiR/wG8j5yPQuDjmOHx4hZpkA743G4x3TlFrCpA3MMX7KUkIOIw0e/CwZ8NYuaMzaQsblA47qVA==",
+      "version": "14.0.2",
+      "resolved": "https://registry.npmjs.org/apache-arrow/-/apache-arrow-14.0.2.tgz",
+      "integrity": "sha512-EBO2xJN36/XoY81nhLcwCJgFwkboDZeyNQ+OPsG7bCoQjc2BT0aTyH/MR6SrL+LirSNz+cYqjGRlupMMlP1aEg==",
       "requires": {
         "@types/command-line-args": "5.2.0",
         "@types/command-line-usage": "5.0.2",
-        "@types/node": "18.14.5",
+        "@types/node": "20.3.0",
         "@types/pad-left": "2.1.1",
         "command-line-args": "5.2.1",
-        "command-line-usage": "6.1.3",
-        "flatbuffers": "23.3.3",
+        "command-line-usage": "7.0.1",
+        "flatbuffers": "23.5.26",
         "json-bignum": "^0.0.3",
         "pad-left": "^2.1.0",
-        "tslib": "^2.5.0"
+        "tslib": "^2.5.3"
       },
       "dependencies": {
         "@types/node": {
-          "version": "18.14.5",
-          "resolved": "https://registry.npmjs.org/@types/node/-/node-18.14.5.tgz",
-          "integrity": "sha512-CRT4tMK/DHYhw1fcCEBwME9CSaZNclxfzVMe7GsO6ULSwsttbj70wSiX6rZdIjGblu93sTJxLdhNIT85KKI7Qw=="
+          "version": "20.3.0",
+          "resolved": "https://registry.npmjs.org/@types/node/-/node-20.3.0.tgz",
+          "integrity": "sha512-cumHmIAf6On83X7yP+LrsEyUOf/YlociZelmpRYaGFydoaPdxdt80MAbu6vWerQT2COCp2nPvHdsbD7tHn/YlQ=="
         },
         "tslib": {
-          "version": "2.5.0",
-          "resolved": "https://registry.npmjs.org/tslib/-/tslib-2.5.0.tgz",
-          "integrity": "sha512-336iVw3rtn2BUK7ORdIAHTyxHGRIHVReokCR3XjbckJMK7ms8FysBfhLR8IXnAgy7T0PTPNBWKiH514FOW/WSg=="
+          "version": "2.6.2",
+          "resolved": "https://registry.npmjs.org/tslib/-/tslib-2.6.2.tgz",
+          "integrity": "sha512-AEYxH93jGFPn/a2iVAwW87VuUIkR1FVUKB77NwMF7nBTDkDrrT/Hpt/IrCJ0QXhW27jTBDcf5ZY7w6RiqTMw2Q=="
         }
       }
     },
@@ -5505,7 +5475,6 @@
       "version": "4.1.2",
       "resolved": "https://registry.npmjs.org/chalk/-/chalk-4.1.2.tgz",
       "integrity": "sha512-oKnbhFyRIXpUuez8iBMmyEa4nbj4IOQyuhc/wy9kY7/WVPcwIO9VA668Pu8RkO7+0G76SLROeyw9CpQ061i4mA==",
-      "dev": true,
       "requires": {
         "ansi-styles": "^4.1.0",
         "supports-color": "^7.1.0"
@@ -5515,13 +5484,20 @@
           "version": "7.2.0",
           "resolved": "https://registry.npmjs.org/supports-color/-/supports-color-7.2.0.tgz",
           "integrity": "sha512-qpCAvRl9stuOHveKsn7HncJRvv501qIacKzQlO/+Lwxc9+0q2wLyv4Dfvt80/DPn2pqOBsJdDiogXGR9+OvwRw==",
-          "dev": true,
           "requires": {
             "has-flag": "^4.0.0"
           }
         }
       }
     },
+    "chalk-template": {
+      "version": "0.4.0",
+      "resolved": "https://registry.npmjs.org/chalk-template/-/chalk-template-0.4.0.tgz",
+      "integrity": "sha512-/ghrgmhfY8RaSdeo43hNXxpoHAtxdbskUHjPpfqUWGttFgycUhYPGx3YZBCnUCvOa7Doivn1IZec3DEGFoMgLg==",
+      "requires": {
+        "chalk": "^4.1.2"
+      }
+    },
     "check-error": {
       "version": "1.0.2",
       "resolved": "https://registry.npmjs.org/check-error/-/check-error-1.0.2.tgz",
@@ -5559,7 +5535,6 @@
       "version": "2.0.1",
       "resolved": "https://registry.npmjs.org/color-convert/-/color-convert-2.0.1.tgz",
       "integrity": "sha512-RRECPsj7iu/xb5oKYcsFHSppFNnsj/52OVTRKb4zP5onXwVF3zVmmToNcOfGC+CRDpfK/U584fMg38ZHCaElKQ==",
-      "dev": true,
       "requires": {
         "color-name": "~1.1.4"
       }
@@ -5567,8 +5542,7 @@
     "color-name": {
       "version": "1.1.4",
       "resolved": "https://registry.npmjs.org/color-name/-/color-name-1.1.4.tgz",
-      "integrity": "sha512-dOy+3AuW3a2wNbZHIuMZpTcgjGuLU/uBL/ubcZF9OXbDo8ff4O8yVp5Bf0efS8uEoYo5q4Fx7dY9OgQGXgAsQA==",
-      "dev": true
+      "integrity": "sha512-dOy+3AuW3a2wNbZHIuMZpTcgjGuLU/uBL/ubcZF9OXbDo8ff4O8yVp5Bf0efS8uEoYo5q4Fx7dY9OgQGXgAsQA=="
     },
     "combined-stream": {
       "version": "1.0.8",
@@ -5590,74 +5564,25 @@
       }
     },
     "command-line-usage": {
-      "version": "6.1.3",
-      "resolved": "https://registry.npmjs.org/command-line-usage/-/command-line-usage-6.1.3.tgz",
-      "integrity": "sha512-sH5ZSPr+7UStsloltmDh7Ce5fb8XPlHyoPzTpyyMuYCtervL65+ubVZ6Q61cFtFl62UyJlc8/JwERRbAFPUqgw==",
+      "version": "7.0.1",
+      "resolved": "https://registry.npmjs.org/command-line-usage/-/command-line-usage-7.0.1.tgz",
+      "integrity": "sha512-NCyznE//MuTjwi3y84QVUGEOT+P5oto1e1Pk/jFPVdPPfsG03qpTIl3yw6etR+v73d0lXsoojRpvbru2sqePxQ==",
       "requires": {
-        "array-back": "^4.0.2",
-        "chalk": "^2.4.2",
-        "table-layout": "^1.0.2",
-        "typical": "^5.2.0"
+        "array-back": "^6.2.2",
+        "chalk-template": "^0.4.0",
+        "table-layout": "^3.0.0",
+        "typical": "^7.1.1"
       },
       "dependencies": {
-        "ansi-styles": {
-          "version": "3.2.1",
-          "resolved": "https://registry.npmjs.org/ansi-styles/-/ansi-styles-3.2.1.tgz",
-          "integrity": "sha512-VT0ZI6kZRdTh8YyJw3SMbYm/u+NqfsAxEpWO0Pf9sq8/e94WxxOpPKx9FR1FlyCtOVDNOQ+8ntlqFxiRc+r5qA==",
-          "requires": {
-            "color-convert": "^1.9.0"
-          }
-        },
         "array-back": {
-          "version": "4.0.2",
-          "resolved": "https://registry.npmjs.org/array-back/-/array-back-4.0.2.tgz",
-          "integrity": "sha512-NbdMezxqf94cnNfWLL7V/im0Ub+Anbb0IoZhvzie8+4HJ4nMQuzHuy49FkGYCJK2yAloZ3meiB6AVMClbrI1vg=="
-        },
-        "chalk": {
-          "version": "2.4.2",
-          "resolved": "https://registry.npmjs.org/chalk/-/chalk-2.4.2.tgz",
-          "integrity": "sha512-Mti+f9lpJNcwF4tWV8/OrTTtF1gZi+f8FqlyAdouralcFWFQWF2+NgCHShjkCb+IFBLq9buZwE1xckQU4peSuQ==",
-          "requires": {
-            "ansi-styles": "^3.2.1",
-            "escape-string-regexp": "^1.0.5",
-            "supports-color": "^5.3.0"
-          }
-        },
-        "color-convert": {
-          "version": "1.9.3",
-          "resolved": "https://registry.npmjs.org/color-convert/-/color-convert-1.9.3.tgz",
-          "integrity": "sha512-QfAUtd+vFdAtFQcC8CCyYt1fYWxSqAiK2cSD6zDB8N3cpsEBAvRxp9zOGg6G/SHHJYAT88/az/IuDGALsNVbGg==",
-          "requires": {
-            "color-name": "1.1.3"
-          }
-        },
-        "color-name": {
-          "version": "1.1.3",
-          "resolved": "https://registry.npmjs.org/color-name/-/color-name-1.1.3.tgz",
-          "integrity": "sha512-72fSenhMw2HZMTVHeCA9KCmpEIbzWiQsjN+BHcBbS9vr1mtt+vJjPdksIBNUmKAW8TFUDPJK5SUU3QhE9NEXDw=="
-        },
-        "escape-string-regexp": {
-          "version": "1.0.5",
-          "resolved": "https://registry.npmjs.org/escape-string-regexp/-/escape-string-regexp-1.0.5.tgz",
-          "integrity": "sha512-vbRorB5FUQWvla16U8R/qgaFIya2qGzwDrNmCZuYKrbdSUMG6I1ZCGQRefkRVhuOkIGVne7BQ35DSfo1qvJqFg=="
-        },
-        "has-flag": {
-          "version": "3.0.0",
-          "resolved": "https://registry.npmjs.org/has-flag/-/has-flag-3.0.0.tgz",
-          "integrity": "sha512-sKJf1+ceQBr4SMkvQnBDNDtf4TXpVhVGateu0t918bl30FnbE2m4vNLX+VWe/dpjlb+HugGYzW7uQXH98HPEYw=="
-        },
-        "supports-color": {
-          "version": "5.5.0",
-          "resolved": "https://registry.npmjs.org/supports-color/-/supports-color-5.5.0.tgz",
-          "integrity": "sha512-QjVjwdXIt408MIiAqCX4oUKsgU2EqAGzs2Ppkm4aQYbjm+ZEWEcW4SfFNTr4uMNZma0ey4f5lgLrkB0aX0QMow==",
-          "requires": {
-            "has-flag": "^3.0.0"
-          }
+          "version": "6.2.2",
+          "resolved": "https://registry.npmjs.org/array-back/-/array-back-6.2.2.tgz",
+          "integrity": "sha512-gUAZ7HPyb4SJczXAMUXMGAvI976JoK3qEx9v1FTmeYuJj0IBiaKttG1ydtGKdkfqWkIkouke7nG8ufGy77+Cvw=="
         },
         "typical": {
-          "version": "5.2.0",
-          "resolved": "https://registry.npmjs.org/typical/-/typical-5.2.0.tgz",
-          "integrity": "sha512-dvdQgNDNJo+8B2uBQoqdb11eUCE1JQXhvjC/CZtgvZseVd5TYMXnq0+vuUemXbd/Se29cTaUuPX3YIc2xgbvIg=="
+          "version": "7.1.1",
+          "resolved": "https://registry.npmjs.org/typical/-/typical-7.1.1.tgz",
+          "integrity": "sha512-T+tKVNs6Wu7IWiAce5BgMd7OZfNYUndHwc5MknN+UHOudi7sGZzuHdCadllRuqJ3fPtgFtIH9+lt9qRv6lmpfA=="
         }
       }
     },
@@ -5716,11 +5641,6 @@
         "type-detect": "^4.0.0"
       }
     },
-    "deep-extend": {
-      "version": "0.6.0",
-      "resolved": "https://registry.npmjs.org/deep-extend/-/deep-extend-0.6.0.tgz",
-      "integrity": "sha512-LOHxIOaPYdHlJRtCQfDIVZtfw/ufM8+rVj649RIHzcm/vGwQRXFt6OPqIFWsm2XEMrNIEtWR64sY1LEKD2vAOA=="
-    },
     "deep-is": {
       "version": "0.1.4",
       "resolved": "https://registry.npmjs.org/deep-is/-/deep-is-0.1.4.tgz",
@@ -6297,9 +6217,9 @@
       }
     },
     "flatbuffers": {
-      "version": "23.3.3",
-      "resolved": "https://registry.npmjs.org/flatbuffers/-/flatbuffers-23.3.3.tgz",
-      "integrity": "sha512-jmreOaAT1t55keaf+Z259Tvh8tR/Srry9K8dgCgvizhKSEr6gLGgaOJI2WFL5fkOpGOGRZwxUrlFn0GCmXUy6g=="
+      "version": "23.5.26",
+      "resolved": "https://registry.npmjs.org/flatbuffers/-/flatbuffers-23.5.26.tgz",
+      "integrity": "sha512-vE+SI9vrJDwi1oETtTIFldC/o9GsVKRM+s6EL0nQgxXlYV1Vc4Tk30hj4xGICftInKQKj1F3up2n8UbIVobISQ=="
     },
     "flatted": {
       "version": "3.2.7",
@@ -6502,8 +6422,7 @@
     "has-flag": {
       "version": "4.0.0",
       "resolved": "https://registry.npmjs.org/has-flag/-/has-flag-4.0.0.tgz",
-      "integrity": "sha512-EykJT/Q1KjTWctppgIAgfSO0tKVuZUjhgMr17kqTumMl6Afv3EISleU7qZUzoXDFTAHTDC4NOoG/ZxU3EvlMPQ==",
-      "dev": true
+      "integrity": "sha512-EykJT/Q1KjTWctppgIAgfSO0tKVuZUjhgMr17kqTumMl6Afv3EISleU7qZUzoXDFTAHTDC4NOoG/ZxU3EvlMPQ=="
     },
     "has-property-descriptors": {
       "version": "1.0.0",
@@ -6856,6 +6775,11 @@
         "p-locate": "^5.0.0"
       }
     },
+    "lodash.assignwith": {
+      "version": "4.2.0",
+      "resolved": "https://registry.npmjs.org/lodash.assignwith/-/lodash.assignwith-4.2.0.tgz",
+      "integrity": "sha512-ZznplvbvtjK2gMvnQ1BR/zqPFZmS6jbK4p+6Up4xcRYA7yMIwxHCfbTcrYxXKzzqLsQ05eJPVznEW3tuwV7k1g=="
+    },
     "lodash.camelcase": {
       "version": "4.3.0",
       "resolved": "https://registry.npmjs.org/lodash.camelcase/-/lodash.camelcase-4.3.0.tgz",
@@ -7323,11 +7247,6 @@
         "picomatch": "^2.2.1"
       }
     },
-    "reduce-flatten": {
-      "version": "2.0.0",
-      "resolved": "https://registry.npmjs.org/reduce-flatten/-/reduce-flatten-2.0.0.tgz",
-      "integrity": "sha512-EJ4UNY/U1t2P/2k6oqotuX2Cc3T6nxJwsM0N0asT7dhrtH1ltUxDn4NalSYmPE2rCkVpcf/X6R0wDwcFpzhd4w=="
-    },
     "regexp.prototype.flags": {
       "version": "1.5.0",
       "resolved": "https://registry.npmjs.org/regexp.prototype.flags/-/regexp.prototype.flags-1.5.0.tgz",
@@ -7523,6 +7442,11 @@
         "source-map": "^0.6.0"
       }
     },
+    "stream-read-all": {
+      "version": "3.0.1",
+      "resolved": "https://registry.npmjs.org/stream-read-all/-/stream-read-all-3.0.1.tgz",
+      "integrity": "sha512-EWZT9XOceBPlVJRrYcykW8jyRSZYbkb/0ZK36uLEmoWVO5gxBOnntNTseNzfREsqxqdfEGQrD8SXQ3QWbBmq8A=="
+    },
     "string-width": {
       "version": "4.2.3",
       "resolved": "https://registry.npmjs.org/string-width/-/string-width-4.2.3.tgz",
@@ -7604,25 +7528,28 @@
       "dev": true
     },
     "table-layout": {
-      "version": "1.0.2",
-      "resolved": "https://registry.npmjs.org/table-layout/-/table-layout-1.0.2.tgz",
-      "integrity": "sha512-qd/R7n5rQTRFi+Zf2sk5XVVd9UQl6ZkduPFC3S7WEGJAmetDTjY3qPN50eSKzwuzEyQKy5TN2TiZdkIjos2L6A==",
+      "version": "3.0.2",
+      "resolved": "https://registry.npmjs.org/table-layout/-/table-layout-3.0.2.tgz",
+      "integrity": "sha512-rpyNZYRw+/C+dYkcQ3Pr+rLxW4CfHpXjPDnG7lYhdRoUcZTUt+KEsX+94RGp/aVp/MQU35JCITv2T/beY4m+hw==",
       "requires": {
-        "array-back": "^4.0.1",
-        "deep-extend": "~0.6.0",
-        "typical": "^5.2.0",
-        "wordwrapjs": "^4.0.0"
+        "@75lb/deep-merge": "^1.1.1",
+        "array-back": "^6.2.2",
+        "command-line-args": "^5.2.1",
+        "command-line-usage": "^7.0.0",
+        "stream-read-all": "^3.0.1",
+        "typical": "^7.1.1",
+        "wordwrapjs": "^5.1.0"
       },
       "dependencies": {
         "array-back": {
-          "version": "4.0.2",
-          "resolved": "https://registry.npmjs.org/array-back/-/array-back-4.0.2.tgz",
-          "integrity": "sha512-NbdMezxqf94cnNfWLL7V/im0Ub+Anbb0IoZhvzie8+4HJ4nMQuzHuy49FkGYCJK2yAloZ3meiB6AVMClbrI1vg=="
+          "version": "6.2.2",
+          "resolved": "https://registry.npmjs.org/array-back/-/array-back-6.2.2.tgz",
+          "integrity": "sha512-gUAZ7HPyb4SJczXAMUXMGAvI976JoK3qEx9v1FTmeYuJj0IBiaKttG1ydtGKdkfqWkIkouke7nG8ufGy77+Cvw=="
         },
         "typical": {
-          "version": "5.2.0",
-          "resolved": "https://registry.npmjs.org/typical/-/typical-5.2.0.tgz",
-          "integrity": "sha512-dvdQgNDNJo+8B2uBQoqdb11eUCE1JQXhvjC/CZtgvZseVd5TYMXnq0+vuUemXbd/Se29cTaUuPX3YIc2xgbvIg=="
+          "version": "7.1.1",
+          "resolved": "https://registry.npmjs.org/typical/-/typical-7.1.1.tgz",
+          "integrity": "sha512-T+tKVNs6Wu7IWiAce5BgMd7OZfNYUndHwc5MknN+UHOudi7sGZzuHdCadllRuqJ3fPtgFtIH9+lt9qRv6lmpfA=="
         }
       }
     },
@@ -7940,20 +7867,9 @@
       "dev": true
     },
     "wordwrapjs": {
-      "version": "4.0.1",
-      "resolved": "https://registry.npmjs.org/wordwrapjs/-/wordwrapjs-4.0.1.tgz",
-      "integrity": "sha512-kKlNACbvHrkpIw6oPeYDSmdCTu2hdMHoyXLTcUKala++lx5Y+wjJ/e474Jqv5abnVmwxw08DiTuHmw69lJGksA==",
-      "requires": {
-        "reduce-flatten": "^2.0.0",
-        "typical": "^5.2.0"
-      },
-      "dependencies": {
-        "typical": {
-          "version": "5.2.0",
-          "resolved": "https://registry.npmjs.org/typical/-/typical-5.2.0.tgz",
-          "integrity": "sha512-dvdQgNDNJo+8B2uBQoqdb11eUCE1JQXhvjC/CZtgvZseVd5TYMXnq0+vuUemXbd/Se29cTaUuPX3YIc2xgbvIg=="
-        }
-      }
+      "version": "5.1.0",
+      "resolved": "https://registry.npmjs.org/wordwrapjs/-/wordwrapjs-5.1.0.tgz",
+      "integrity": "sha512-JNjcULU2e4KJwUNv6CHgI46UvDGitb6dGryHajXTDiLgg1/RiGoPSDw4kZfYnwGtEXf2ZMeIewDQgFGzkCB2Sg=="
     },
     "workerpool": {
       "version": "6.2.1",

node/package.json

@@ -1,6 +1,6 @@
 {
   "name": "vectordb",
-  "version": "0.4.1",
+  "version": "0.4.3",
   "description": " Serverless, low-latency vector database for AI applications",
   "main": "dist/index.js",
   "types": "dist/index.d.ts",
@@ -57,9 +57,9 @@
     "uuid": "^9.0.0"
   },
   "dependencies": {
-    "@apache-arrow/ts": "^12.0.0",
+    "@apache-arrow/ts": "^14.0.2",
     "@neon-rs/load": "^0.0.74",
-    "apache-arrow": "^12.0.0",
+    "apache-arrow": "^14.0.2",
     "axios": "^1.4.0"
   },
   "os": [
@@ -81,10 +81,10 @@
     }
   },
   "optionalDependencies": {
-    "@lancedb/vectordb-darwin-arm64": "0.4.1",
-    "@lancedb/vectordb-darwin-x64": "0.4.1",
-    "@lancedb/vectordb-linux-arm64-gnu": "0.4.1",
-    "@lancedb/vectordb-linux-x64-gnu": "0.4.1",
-    "@lancedb/vectordb-win32-x64-msvc": "0.4.1"
+    "@lancedb/vectordb-darwin-arm64": "0.4.3",
+    "@lancedb/vectordb-darwin-x64": "0.4.3",
+    "@lancedb/vectordb-linux-arm64-gnu": "0.4.3",
+    "@lancedb/vectordb-linux-x64-gnu": "0.4.3",
+    "@lancedb/vectordb-win32-x64-msvc": "0.4.3"
   }
 }

node/src/arrow.ts

@@ -17,10 +17,9 @@ import {
   Float32,
   makeBuilder,
   RecordBatchFileWriter,
-  Utf8,
-  type Vector,
+  Utf8, type Vector,
   FixedSizeList,
-  vectorFromArray, type Schema, Table as ArrowTable, RecordBatchStreamWriter
+  vectorFromArray, type Schema, Table as ArrowTable, RecordBatchStreamWriter, List, Float64, RecordBatch, makeData, Struct
 } from 'apache-arrow'
 import { type EmbeddingFunction } from './index'
 
@@ -59,7 +58,26 @@ export async function convertToTable<T> (data: Array<Record<string, unknown>>, e
       if (typeof values[0] === 'string') {
         // `vectorFromArray` converts strings into dictionary vectors, forcing it back to a string column
         records[columnsKey] = vectorFromArray(values, new Utf8())
+      } else if (Array.isArray(values[0])) {
+        const elementType = getElementType(values[0])
+        let innerType
+        if (elementType === 'string') {
+          innerType = new Utf8()
+        } else if (elementType === 'number') {
+          innerType = new Float64()
+        } else {
+          // TODO: pass in schema if it exists, else keep going to the next element
+          throw new Error(`Unsupported array element type ${elementType}`)
+        }
+        const listBuilder = makeBuilder({
+          type: new List(new Field('item', innerType, true))
+        })
+        for (const value of values) {
+          listBuilder.append(value)
+        }
+        records[columnsKey] = listBuilder.finish().toVector()
       } else {
+        // TODO if this is a struct field then recursively align the subfields
         records[columnsKey] = vectorFromArray(values)
       }
     }
@@ -68,6 +86,14 @@ export async function convertToTable<T> (data: Array<Record<string, unknown>>, e
   return new ArrowTable(records)
 }
 
+function getElementType (arr: any[]): string {
+  if (arr.length === 0) {
+    return 'undefined'
+  }
+
+  return typeof arr[0]
+}
+
 // Creates a new Arrow ListBuilder that stores a Vector column
 function newVectorBuilder (dim: number): FixedSizeListBuilder<Float32> {
   return makeBuilder({
@@ -84,21 +110,27 @@ function newVectorType (dim: number): FixedSizeList<Float32> {
 }
 
 // Converts an Array of records into Arrow IPC format
-export async function fromRecordsToBuffer<T> (data: Array<Record<string, unknown>>, embeddings?: EmbeddingFunction<T>): Promise<Buffer> {
-  const table = await convertToTable(data, embeddings)
+export async function fromRecordsToBuffer<T> (data: Array<Record<string, unknown>>, embeddings?: EmbeddingFunction<T>, schema?: Schema): Promise<Buffer> {
+  let table = await convertToTable(data, embeddings)
+  if (schema !== undefined) {
+    table = alignTable(table, schema)
+  }
   const writer = RecordBatchFileWriter.writeAll(table)
   return Buffer.from(await writer.toUint8Array())
 }
 
 // Converts an Array of records into Arrow IPC stream format
-export async function fromRecordsToStreamBuffer<T> (data: Array<Record<string, unknown>>, embeddings?: EmbeddingFunction<T>): Promise<Buffer> {
-  const table = await convertToTable(data, embeddings)
+export async function fromRecordsToStreamBuffer<T> (data: Array<Record<string, unknown>>, embeddings?: EmbeddingFunction<T>, schema?: Schema): Promise<Buffer> {
+  let table = await convertToTable(data, embeddings)
+  if (schema !== undefined) {
+    table = alignTable(table, schema)
+  }
   const writer = RecordBatchStreamWriter.writeAll(table)
   return Buffer.from(await writer.toUint8Array())
 }
 
 // Converts an Arrow Table into Arrow IPC format
-export async function fromTableToBuffer<T> (table: ArrowTable, embeddings?: EmbeddingFunction<T>): Promise<Buffer> {
+export async function fromTableToBuffer<T> (table: ArrowTable, embeddings?: EmbeddingFunction<T>, schema?: Schema): Promise<Buffer> {
   if (embeddings !== undefined) {
     const source = table.getChild(embeddings.sourceColumn)
 
@@ -110,12 +142,15 @@ export async function fromTableToBuffer<T> (table: ArrowTable, embeddings?: Embe
     const column = vectorFromArray(vectors, newVectorType(vectors[0].length))
     table = table.assign(new ArrowTable({ vector: column }))
   }
+  if (schema !== undefined) {
+    table = alignTable(table, schema)
+  }
   const writer = RecordBatchFileWriter.writeAll(table)
   return Buffer.from(await writer.toUint8Array())
 }
 
 // Converts an Arrow Table into Arrow IPC stream format
-export async function fromTableToStreamBuffer<T> (table: ArrowTable, embeddings?: EmbeddingFunction<T>): Promise<Buffer> {
+export async function fromTableToStreamBuffer<T> (table: ArrowTable, embeddings?: EmbeddingFunction<T>, schema?: Schema): Promise<Buffer> {
   if (embeddings !== undefined) {
     const source = table.getChild(embeddings.sourceColumn)
 
@@ -127,10 +162,36 @@ export async function fromTableToStreamBuffer<T> (table: ArrowTable, embeddings?
     const column = vectorFromArray(vectors, newVectorType(vectors[0].length))
     table = table.assign(new ArrowTable({ vector: column }))
   }
+  if (schema !== undefined) {
+    table = alignTable(table, schema)
+  }
   const writer = RecordBatchStreamWriter.writeAll(table)
   return Buffer.from(await writer.toUint8Array())
 }
 
+function alignBatch (batch: RecordBatch, schema: Schema): RecordBatch {
+  const alignedChildren = []
+  for (const field of schema.fields) {
+    const indexInBatch = batch.schema.fields?.findIndex((f) => f.name === field.name)
+    if (indexInBatch < 0) {
+      throw new Error(`The column ${field.name} was not found in the Arrow Table`)
+    }
+    alignedChildren.push(batch.data.children[indexInBatch])
+  }
+  const newData = makeData({
+    type: new Struct(schema.fields),
+    length: batch.numRows,
+    nullCount: batch.nullCount,
+    children: alignedChildren
+  })
+  return new RecordBatch(schema, newData)
+}
+
+function alignTable (table: ArrowTable, schema: Schema): ArrowTable {
+  const alignedBatches = table.batches.map(batch => alignBatch(batch, schema))
+  return new ArrowTable(schema, alignedBatches)
+}
+
 // Creates an empty Arrow Table
 export function createEmptyTable (schema: Schema): ArrowTable {
   return new ArrowTable(schema)

node/src/index.ts

@@ -14,7 +14,8 @@
 
 import {
   type Schema,
-  Table as ArrowTable
+  Table as ArrowTable,
+  tableFromIPC
 } from 'apache-arrow'
 import { createEmptyTable, fromRecordsToBuffer, fromTableToBuffer } from './arrow'
 import type { EmbeddingFunction } from './embedding/embedding_function'
@@ -24,7 +25,7 @@ import { isEmbeddingFunction } from './embedding/embedding_function'
 import { type Literal, toSQL } from './util'
 
 // eslint-disable-next-line @typescript-eslint/no-var-requires
-const { databaseNew, databaseTableNames, databaseOpenTable, databaseDropTable, tableCreate, tableAdd, tableCreateScalarIndex, tableCreateVectorIndex, tableCountRows, tableDelete, tableUpdate, tableCleanupOldVersions, tableCompactFiles, tableListIndices, tableIndexStats } = require('../native.js')
+const { databaseNew, databaseTableNames, databaseOpenTable, databaseDropTable, tableCreate, tableAdd, tableCreateScalarIndex, tableCreateVectorIndex, tableCountRows, tableDelete, tableUpdate, tableCleanupOldVersions, tableCompactFiles, tableListIndices, tableIndexStats, tableSchema } = require('../native.js')
 
 export { Query }
 export type { EmbeddingFunction }
@@ -354,6 +355,8 @@ export interface Table<T = number[]> {
    * Get statistics about an index.
    */
   indexStats: (indexUuid: string) => Promise<IndexStats>
+
+  schema: Promise<Schema>
 }
 
 export interface UpdateArgs {
@@ -482,10 +485,10 @@ export class LocalConnection implements Connection {
       }
       buffer = await fromTableToBuffer(createEmptyTable(schema))
     } else if (data instanceof ArrowTable) {
-      buffer = await fromTableToBuffer(data, embeddingFunction)
+      buffer = await fromTableToBuffer(data, embeddingFunction, schema)
     } else {
       // data is Array<Record<...>>
-      buffer = await fromRecordsToBuffer(data, embeddingFunction)
+      buffer = await fromRecordsToBuffer(data, embeddingFunction, schema)
     }
 
     const tbl = await tableCreate.call(this._db, name, buffer, writeOptions?.writeMode?.toString(), ...getAwsArgs(this._options()))
@@ -508,6 +511,7 @@ export class LocalConnection implements Connection {
 export class LocalTable<T = number[]> implements Table<T> {
   private _tbl: any
   private readonly _name: string
+  private readonly _isElectron: boolean
   private readonly _embeddings?: EmbeddingFunction<T>
   private readonly _options: () => ConnectionOptions
 
@@ -524,6 +528,7 @@ export class LocalTable<T = number[]> implements Table<T> {
     this._name = name
     this._embeddings = embeddings
     this._options = () => options
+    this._isElectron = this.checkElectron()
   }
 
   get name (): string {
@@ -555,9 +560,10 @@ export class LocalTable<T = number[]> implements Table<T> {
    * @return The number of rows added to the table
    */
   async add (data: Array<Record<string, unknown>>): Promise<number> {
+    const schema = await this.schema
     return tableAdd.call(
       this._tbl,
-      await fromRecordsToBuffer(data, this._embeddings),
+      await fromRecordsToBuffer(data, this._embeddings, schema),
       WriteMode.Append.toString(),
       ...getAwsArgs(this._options())
     ).then((newTable: any) => { this._tbl = newTable })
@@ -682,6 +688,27 @@ export class LocalTable<T = number[]> implements Table<T> {
   async indexStats (indexUuid: string): Promise<IndexStats> {
     return tableIndexStats.call(this._tbl, indexUuid)
   }
+
+  get schema (): Promise<Schema> {
+    // empty table
+    return this.getSchema()
+  }
+
+  private async getSchema (): Promise<Schema> {
+    const buffer = await tableSchema.call(this._tbl, this._isElectron)
+    const table = tableFromIPC(buffer)
+    return table.schema
+  }
+
+  // See https://github.com/electron/electron/issues/2288
+  private checkElectron (): boolean {
+    try {
+      // eslint-disable-next-line no-prototype-builtins
+      return (process?.versions?.hasOwnProperty('electron') || navigator?.userAgent?.toLowerCase()?.includes(' electron'))
+    } catch (e) {
+      return false
+    }
+  }
 }
 
 export interface CleanupStats {

node/src/remote/index.ts

@@ -267,7 +267,7 @@ export class RemoteTable<T = number[]> implements Table<T> {
     const column = indexParams.column ?? 'vector'
     const indexType = 'vector' // only vector index is supported for remote connections
     const metricType = indexParams.metric_type ?? 'L2'
-    const indexCacheSize = indexParams ?? null
+    const indexCacheSize = indexParams.index_cache_size ?? null
 
     const data = {
       column,

node/src/test/test.ts

@@ -176,6 +176,26 @@ describe('LanceDB client', function () {
       assert.deepEqual(await con.tableNames(), ['vectors'])
     })
 
+    it('create a table with a schema and records', async function () {
+      const dir = await track().mkdir('lancejs')
+      const con = await lancedb.connect(dir)
+
+      const schema = new Schema(
+        [new Field('id', new Int32()),
+          new Field('name', new Utf8()),
+          new Field('vector', new FixedSizeList(2, new Field('item', new Float32(), true)), false)
+        ]
+      )
+      const data = [
+        { vector: [0.5, 0.2], name: 'foo', id: 0 },
+        { vector: [0.3, 0.1], name: 'bar', id: 1 }
+      ]
+      // even thought the keys in data is out of order it should still work
+      const table = await con.createTable({ name: 'vectors', data, schema })
+      assert.equal(table.name, 'vectors')
+      assert.deepEqual(await con.tableNames(), ['vectors'])
+    })
+
     it('create a table with a empty data array', async function () {
       const dir = await track().mkdir('lancejs')
       const con = await lancedb.connect(dir)
@@ -218,6 +238,25 @@ describe('LanceDB client', function () {
       assert.equal(await table.countRows(), 2)
     })
 
+    it('creates a new table from javascript objects with variable sized list', async function () {
+      const dir = await track().mkdir('lancejs')
+      const con = await lancedb.connect(dir)
+
+      const data = [
+        { id: 1, vector: [0.1, 0.2], list_of_str: ['a', 'b', 'c'], list_of_num: [1, 2, 3] },
+        { id: 2, vector: [1.1, 1.2], list_of_str: ['x', 'y'], list_of_num: [4, 5, 6] }
+      ]
+
+      const tableName = 'with_variable_sized_list'
+      const table = await con.createTable(tableName, data) as LocalTable
+      assert.equal(table.name, tableName)
+      assert.equal(await table.countRows(), 2)
+      const rs = await table.filter('id>1').execute()
+      assert.equal(rs.length, 1)
+      assert.deepEqual(rs[0].list_of_str, ['x', 'y'])
+      assert.isTrue(rs[0].list_of_num instanceof Float64Array)
+    })
+
     it('fails to create a new table when the vector column is missing', async function () {
       const dir = await track().mkdir('lancejs')
       const con = await lancedb.connect(dir)
@@ -275,6 +314,25 @@ describe('LanceDB client', function () {
       assert.equal(await table.countRows(), 4)
     })
 
+    it('appends records with fields in a different order', async function () {
+      const dir = await track().mkdir('lancejs')
+      const con = await lancedb.connect(dir)
+
+      const data = [
+        { id: 1, vector: [0.1, 0.2], price: 10, name: 'a' },
+        { id: 2, vector: [1.1, 1.2], price: 50, name: 'b' }
+      ]
+
+      const table = await con.createTable('vectors', data)
+
+      const dataAdd = [
+        { id: 3, vector: [2.1, 2.2], name: 'c', price: 10 },
+        { id: 4, vector: [3.1, 3.2], name: 'd', price: 50 }
+      ]
+      await table.add(dataAdd)
+      assert.equal(await table.countRows(), 4)
+    })
+
     it('overwrite all records in a table', async function () {
       const uri = await createTestDB()
       const con = await lancedb.connect(uri)
@@ -479,6 +537,27 @@ describe('LanceDB client', function () {
       assert.equal(results.length, 2)
     })
   })
+
+  describe('when inspecting the schema', function () {
+    it('should return the schema', async function () {
+      const uri = await createTestDB()
+      const db = await lancedb.connect(uri)
+      // the fsl inner field must be named 'item' and be nullable
+      const expectedSchema = new Schema(
+        [
+          new Field('id', new Int32()),
+          new Field('vector', new FixedSizeList(128, new Field('item', new Float32(), true))),
+          new Field('s', new Utf8())
+        ]
+      )
+      const table = await db.createTable({
+        name: 'some_table',
+        schema: expectedSchema
+      })
+      const schema = await table.schema
+      assert.deepEqual(expectedSchema, schema)
+    })
+  })
 })
 
 describe('Remote LanceDB client', function () {

python/.bumpversion.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 0.4.1
+current_version = 0.4.4
 commit = True
 message = [python] Bump version: {current_version} → {new_version}
 tag = True

python/README.md

@@ -45,8 +45,8 @@ pytest
 To run linter and automatically fix all errors:
 
 ```bash
-black .
-isort .
+ruff format python
+ruff --fix python
 ```
 
 If any packages are missing, install them with:
@@ -82,4 +82,4 @@ pip install tantivy
 To run the unit tests:
 ```bash
 pytest
-```
+```

python/lancedb/embeddings/openai.py

@@ -10,6 +10,7 @@
 #  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
+from functools import cached_property
 from typing import List, Union
 
 import numpy as np
@@ -44,6 +45,10 @@ class OpenAIEmbeddings(TextEmbeddingFunction):
             The texts to embed
         """
         # TODO retry, rate limit, token limit
+        rs = self._openai_client.embeddings.create(input=texts, model=self.name)
+        return [v.embedding for v in rs.data]
+
+    @cached_property
+    def _openai_client(self):
         openai = self.safe_import("openai")
-        rs = openai.Embedding.create(input=texts, model=self.name)["data"]
-        return [v["embedding"] for v in rs]
+        return openai.OpenAI()

python/lancedb/embeddings/utils.py

@@ -249,7 +249,7 @@ def retry_with_exponential_backoff(
 
                 if num_retries > max_retries:
                     raise Exception(
-                        f"Maximum number of retries ({max_retries}) exceeded."
+                        f"Maximum number of retries ({max_retries}) exceeded.", e
                     )
 
                 delay *= exponential_base * (1 + jitter * random.random())

python/lancedb/fts.py

@@ -13,7 +13,7 @@
 
 """Full text search index using tantivy-py"""
 import os
-from typing import List, Tuple
+from typing import List, Optional, Tuple
 
 import pyarrow as pa
 
@@ -56,7 +56,12 @@ def create_index(index_path: str, text_fields: List[str]) -> tantivy.Index:
     return index
 
 
-def populate_index(index: tantivy.Index, table: LanceTable, fields: List[str]) -> int:
+def populate_index(
+    index: tantivy.Index,
+    table: LanceTable,
+    fields: List[str],
+    writer_heap_size: int = 1024 * 1024 * 1024,
+) -> int:
     """
     Populate an index with data from a LanceTable
 
@@ -68,6 +73,8 @@ def populate_index(index: tantivy.Index, table: LanceTable, fields: List[str]) -
         The table to index
     fields : List[str]
         List of fields to index
+    writer_heap_size : int
+        The writer heap size in bytes, defaults to 1GB
 
     Returns
     -------
@@ -87,7 +94,7 @@ def populate_index(index: tantivy.Index, table: LanceTable, fields: List[str]) -
             raise TypeError(f"Field {name} is not a string type")
 
     # create a tantivy writer
-    writer = index.writer()
+    writer = index.writer(heap_size=writer_heap_size)
     # write data into index
     dataset = table.to_lance()
     row_id = 0
@@ -103,10 +110,13 @@ def populate_index(index: tantivy.Index, table: LanceTable, fields: List[str]) -
                 b = b.flatten()
         for i in range(b.num_rows):
             doc = tantivy.Document()
-            doc.add_integer("doc_id", row_id)
             for name in fields:
-                doc.add_text(name, b[name][i].as_py())
-            writer.add_document(doc)
+                value = b[name][i].as_py()
+                if value is not None:
+                    doc.add_text(name, value)
+            if not doc.is_empty:
+                doc.add_integer("doc_id", row_id)
+                writer.add_document(doc)
             row_id += 1
     # commit changes
     writer.commit()

python/lancedb/pydantic.py

@@ -26,6 +26,7 @@ import numpy as np
 import pyarrow as pa
 import pydantic
 import semver
+from pydantic.fields import FieldInfo
 
 from .embeddings import EmbeddingFunctionRegistry
 
@@ -142,8 +143,8 @@ def Vector(
     return FixedSizeList
 
 
-def _py_type_to_arrow_type(py_type: Type[Any]) -> pa.DataType:
-    """Convert Python Type to Arrow DataType.
+def _py_type_to_arrow_type(py_type: Type[Any], field: FieldInfo) -> pa.DataType:
+    """Convert a field with native Python type to Arrow data type.
 
     Raises
     ------
@@ -163,9 +164,13 @@ def _py_type_to_arrow_type(py_type: Type[Any]) -> pa.DataType:
     elif py_type == date:
         return pa.date32()
     elif py_type == datetime:
-        return pa.timestamp("us")
+        tz = get_extras(field, "tz")
+        return pa.timestamp("us", tz=tz)
+    elif getattr(py_type, "__origin__", None) in (list, tuple):
+        child = py_type.__args__[0]
+        return pa.list_(_py_type_to_arrow_type(child, field))
     raise TypeError(
-        f"Converting Pydantic type to Arrow Type: unsupported type {py_type}"
+        f"Converting Pydantic type to Arrow Type: unsupported type {py_type}."
     )
 
 
@@ -187,6 +192,7 @@ else:
 
 def _pydantic_to_arrow_type(field: pydantic.fields.FieldInfo) -> pa.DataType:
     """Convert a Pydantic FieldInfo to Arrow DataType"""
+
     if isinstance(field.annotation, _GenericAlias) or (
         sys.version_info > (3, 9) and isinstance(field.annotation, types.GenericAlias)
     ):
@@ -194,10 +200,17 @@ def _pydantic_to_arrow_type(field: pydantic.fields.FieldInfo) -> pa.DataType:
         args = field.annotation.__args__
         if origin == list:
             child = args[0]
-            return pa.list_(_py_type_to_arrow_type(child))
+            return pa.list_(_py_type_to_arrow_type(child, field))
         elif origin == Union:
             if len(args) == 2 and args[1] == type(None):
-                return _py_type_to_arrow_type(args[0])
+                return _py_type_to_arrow_type(args[0], field)
+    elif sys.version_info >= (3, 10) and isinstance(field.annotation, types.UnionType):
+        args = field.annotation.__args__
+        if len(args) == 2:
+            for typ in args:
+                if typ == type(None):
+                    continue
+                return _py_type_to_arrow_type(typ, field)
     elif inspect.isclass(field.annotation):
         if issubclass(field.annotation, pydantic.BaseModel):
             # Struct
@@ -205,7 +218,7 @@ def _pydantic_to_arrow_type(field: pydantic.fields.FieldInfo) -> pa.DataType:
             return pa.struct(fields)
         elif issubclass(field.annotation, FixedSizeListMixin):
             return pa.list_(field.annotation.value_arrow_type(), field.annotation.dim())
-    return _py_type_to_arrow_type(field.annotation)
+    return _py_type_to_arrow_type(field.annotation, field)
 
 
 def is_nullable(field: pydantic.fields.FieldInfo) -> bool:
@@ -216,6 +229,11 @@ def is_nullable(field: pydantic.fields.FieldInfo) -> bool:
         if origin == Union:
             if len(args) == 2 and args[1] == type(None):
                 return True
+    elif sys.version_info >= (3, 10) and isinstance(field.annotation, types.UnionType):
+        args = field.annotation.__args__
+        for typ in args:
+            if typ == type(None):
+                return True
     return False
 
 

python/lancedb/query.py

@@ -14,6 +14,7 @@
 from __future__ import annotations
 
 from abc import ABC, abstractmethod
+from pathlib import Path
 from typing import TYPE_CHECKING, List, Literal, Optional, Type, Union
 
 import deprecation
@@ -70,7 +71,7 @@ class Query(pydantic.BaseModel):
     vector_column: str = VECTOR_COLUMN_NAME
 
     # vector to search for
-    vector: List[float]
+    vector: Union[List[float], List[List[float]]]
 
     # sql filter to refine the query with
     filter: Optional[str] = None
@@ -259,20 +260,30 @@ class LanceQueryBuilder(ABC):
             for row in self.to_arrow().to_pylist()
         ]
 
-    def limit(self, limit: int) -> LanceQueryBuilder:
+    def limit(self, limit: Union[int, None]) -> LanceQueryBuilder:
         """Set the maximum number of results to return.
 
         Parameters
         ----------
         limit: int
             The maximum number of results to return.
+            By default the query is limited to the first 10.
+            Call this method and pass 0, a negative value,
+            or None to remove the limit.
+            *WARNING* if you have a large dataset, removing
+            the limit can potentially result in reading a
+            large amount of data into memory and cause
+            out of memory issues.
 
         Returns
         -------
         LanceQueryBuilder
             The LanceQueryBuilder object.
         """
-        self._limit = limit
+        if limit is None or limit <= 0:
+            self._limit = None
+        else:
+            self._limit = limit
         return self
 
     def select(self, columns: list) -> LanceQueryBuilder:
@@ -421,6 +432,8 @@ class LanceVectorQueryBuilder(LanceQueryBuilder):
         vector and the returned vectors.
         """
         vector = self._query if isinstance(self._query, list) else self._query.tolist()
+        if isinstance(vector[0], np.ndarray):
+            vector = [v.tolist() for v in vector]
         query = Query(
             vector=vector,
             filter=self._where,
@@ -465,6 +478,24 @@ class LanceFtsQueryBuilder(LanceQueryBuilder):
     def __init__(self, table: "lancedb.table.Table", query: str):
         super().__init__(table)
         self._query = query
+        self._phrase_query = False
+
+    def phrase_query(self, phrase_query: bool = True) -> LanceFtsQueryBuilder:
+        """Set whether to use phrase query.
+
+        Parameters
+        ----------
+        phrase_query: bool, default True
+            If True, then the query will be wrapped in quotes and
+            double quotes replaced by single quotes.
+
+        Returns
+        -------
+        LanceFtsQueryBuilder
+            The LanceFtsQueryBuilder object.
+        """
+        self._phrase_query = phrase_query
+        return self
 
     def to_arrow(self) -> pa.Table:
         try:
@@ -478,16 +509,47 @@ class LanceFtsQueryBuilder(LanceQueryBuilder):
 
         # get the index path
         index_path = self._table._get_fts_index_path()
+        # check if the index exist
+        if not Path(index_path).exists():
+            raise FileNotFoundError(
+                "Fts index does not exist."
+                f"Please first call table.create_fts_index(['<field_names>']) to create the fts index."
+            )
         # open the index
         index = tantivy.Index.open(index_path)
         # get the scores and doc ids
-        row_ids, scores = search_index(index, self._query, self._limit)
+        query = self._query
+        if self._phrase_query:
+            query = query.replace('"', "'")
+            query = f'"{query}"'
+        row_ids, scores = search_index(index, query, self._limit)
         if len(row_ids) == 0:
             empty_schema = pa.schema([pa.field("score", pa.float32())])
             return pa.Table.from_pylist([], schema=empty_schema)
         scores = pa.array(scores)
         output_tbl = self._table.to_lance().take(row_ids, columns=self._columns)
         output_tbl = output_tbl.append_column("score", scores)
+
+        if self._where is not None:
+            try:
+                # TODO would be great to have Substrait generate pyarrow compute expressions
+                # or conversely have pyarrow support SQL expressions using Substrait
+                import duckdb
+
+                output_tbl = (
+                    duckdb.sql(f"SELECT * FROM output_tbl")
+                    .filter(self._where)
+                    .to_arrow_table()
+                )
+            except ImportError:
+                import lance
+                import tempfile
+
+                # TODO Use "memory://" instead once that's supported
+                with tempfile.TemporaryDirectory() as tmp:
+                    ds = lance.write_dataset(output_tbl, tmp)
+                    output_tbl = ds.to_table(filter=self._where)
+
         return output_tbl
 
 

python/lancedb/remote/client.py

@@ -13,9 +13,10 @@
 
 
 import functools
-from typing import Any, Callable, Dict, Iterable, Optional, Union
+from typing import Any, Callable, Dict, Iterable, List, Optional, Union
+from urllib.parse import urljoin
 
-import aiohttp
+import requests
 import attrs
 import pyarrow as pa
 from pydantic import BaseModel
@@ -37,8 +38,8 @@ def _check_not_closed(f):
     return wrapped
 
 
-async def _read_ipc(resp: aiohttp.ClientResponse) -> pa.Table:
-    resp_body = await resp.read()
+def _read_ipc(resp: requests.Response) -> pa.Table:
+    resp_body = resp.content
     with pa.ipc.open_file(pa.BufferReader(resp_body)) as reader:
         return reader.read_all()
 
@@ -53,15 +54,18 @@ class RestfulLanceDBClient:
     closed: bool = attrs.field(default=False, init=False)
 
     @functools.cached_property
-    def session(self) -> aiohttp.ClientSession:
-        url = (
+    def session(self) -> requests.Session:
+        return requests.Session()
+
+    @property
+    def url(self) -> str:
+        return (
             self.host_override
             or f"https://{self.db_name}.{self.region}.api.lancedb.com"
         )
-        return aiohttp.ClientSession(url)
 
-    async def close(self):
-        await self.session.close()
+    def close(self):
+        self.session.close()
         self.closed = True
 
     @functools.cached_property
@@ -76,38 +80,38 @@ class RestfulLanceDBClient:
         return headers
 
     @staticmethod
-    async def _check_status(resp: aiohttp.ClientResponse):
-        if resp.status == 404:
-            raise LanceDBClientError(f"Not found: {await resp.text()}")
-        elif 400 <= resp.status < 500:
+    def _check_status(resp: requests.Response):
+        if resp.status_code == 404:
+            raise LanceDBClientError(f"Not found: {resp.text}")
+        elif 400 <= resp.status_code < 500:
             raise LanceDBClientError(
-                f"Bad Request: {resp.status}, error: {await resp.text()}"
+                f"Bad Request: {resp.status_code}, error: {resp.text}"
             )
-        elif 500 <= resp.status < 600:
+        elif 500 <= resp.status_code < 600:
             raise LanceDBClientError(
-                f"Internal Server Error: {resp.status}, error: {await resp.text()}"
+                f"Internal Server Error: {resp.status_code}, error: {resp.text}"
             )
-        elif resp.status != 200:
+        elif resp.status_code != 200:
             raise LanceDBClientError(
-                f"Unknown Error: {resp.status}, error: {await resp.text()}"
+                f"Unknown Error: {resp.status_code}, error: {resp.text}"
             )
 
     @_check_not_closed
-    async def get(self, uri: str, params: Union[Dict[str, Any], BaseModel] = None):
+    def get(self, uri: str, params: Union[Dict[str, Any], BaseModel] = None):
         """Send a GET request and returns the deserialized response payload."""
         if isinstance(params, BaseModel):
             params: Dict[str, Any] = params.dict(exclude_none=True)
-        async with self.session.get(
-            uri,
+        with self.session.get(
+            urljoin(self.url, uri),
             params=params,
             headers=self.headers,
-            timeout=aiohttp.ClientTimeout(total=30),
+            timeout=(5.0, 30.0),
         ) as resp:
-            await self._check_status(resp)
-            return await resp.json()
+            self._check_status(resp)
+            return resp.json()
 
     @_check_not_closed
-    async def post(
+    def post(
         self,
         uri: str,
         data: Optional[Union[Dict[str, Any], BaseModel, bytes]] = None,
@@ -139,31 +143,26 @@ class RestfulLanceDBClient:
             headers["content-type"] = content_type
         if request_id is not None:
             headers["x-request-id"] = request_id
-        async with self.session.post(
-            uri,
+        with self.session.post(
+            urljoin(self.url, uri),
             headers=headers,
             params=params,
-            timeout=aiohttp.ClientTimeout(total=30),
+            timeout=(5.0, 30.0),
             **req_kwargs,
         ) as resp:
-            resp: aiohttp.ClientResponse = resp
-            await self._check_status(resp)
-            return await deserialize(resp)
+            self._check_status(resp)
+            return deserialize(resp)
 
     @_check_not_closed
-    async def list_tables(
-        self, limit: int, page_token: Optional[str] = None
-    ) -> Iterable[str]:
+    def list_tables(self, limit: int, page_token: Optional[str] = None) -> List[str]:
         """List all tables in the database."""
         if page_token is None:
             page_token = ""
-        json = await self.get("/v1/table/", {"limit": limit, "page_token": page_token})
+        json = self.get("/v1/table/", {"limit": limit, "page_token": page_token})
         return json["tables"]
 
     @_check_not_closed
-    async def query(self, table_name: str, query: VectorQuery) -> VectorQueryResult:
+    def query(self, table_name: str, query: VectorQuery) -> VectorQueryResult:
         """Query a table."""
-        tbl = await self.post(
-            f"/v1/table/{table_name}/query/", query, deserialize=_read_ipc
-        )
+        tbl = self.post(f"/v1/table/{table_name}/query/", query, deserialize=_read_ipc)
         return VectorQueryResult(tbl)

python/lancedb/remote/db.py

@@ -50,10 +50,6 @@ class RemoteDBConnection(DBConnection):
         self._client = RestfulLanceDBClient(
             self.db_name, region, api_key, host_override
         )
-        try:
-            self._loop = asyncio.get_running_loop()
-        except RuntimeError:
-            self._loop = asyncio.get_event_loop()
 
     def __repr__(self) -> str:
         return f"RemoteConnect(name={self.db_name})"
@@ -76,9 +72,8 @@ class RemoteDBConnection(DBConnection):
         An iterator of table names.
         """
         while True:
-            result = self._loop.run_until_complete(
-                self._client.list_tables(limit, page_token)
-            )
+            result = self._client.list_tables(limit, page_token)
+
             if len(result) > 0:
                 page_token = result[len(result) - 1]
             else:
@@ -103,9 +98,7 @@ class RemoteDBConnection(DBConnection):
 
         # check if table exists
         try:
-            self._loop.run_until_complete(
-                self._client.post(f"/v1/table/{name}/describe/")
-            )
+            self._client.post(f"/v1/table/{name}/describe/")
         except LanceDBClientError as err:
             if str(err).startswith("Not found"):
                 logging.error(
@@ -248,14 +241,13 @@ class RemoteDBConnection(DBConnection):
         data = to_ipc_binary(data)
         request_id = uuid.uuid4().hex
 
-        self._loop.run_until_complete(
-            self._client.post(
-                f"/v1/table/{name}/create/",
-                data=data,
-                request_id=request_id,
-                content_type=ARROW_STREAM_CONTENT_TYPE,
-            )
+        self._client.post(
+            f"/v1/table/{name}/create/",
+            data=data,
+            request_id=request_id,
+            content_type=ARROW_STREAM_CONTENT_TYPE,
         )
+
         return RemoteTable(self, name)
 
     @override
@@ -267,13 +259,11 @@ class RemoteDBConnection(DBConnection):
         name: str
             The name of the table.
         """
-        self._loop.run_until_complete(
-            self._client.post(
-                f"/v1/table/{name}/drop/",
-            )
+
+        self._client.post(
+            f"/v1/table/{name}/drop/",
         )
 
     async def close(self):
         """Close the connection to the database."""
-        self._loop.close()
-        await self._client.close()
+        self._client.close()

python/lancedb/remote/table.py

@@ -11,6 +11,7 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 
+import asyncio
 import uuid
 from functools import cached_property
 from typing import Dict, Optional, Union
@@ -42,18 +43,14 @@ class RemoteTable(Table):
         of this Table
 
         """
-        resp = self._conn._loop.run_until_complete(
-            self._conn._client.post(f"/v1/table/{self._name}/describe/")
-        )
+        resp = self._conn._client.post(f"/v1/table/{self._name}/describe/")
         schema = json_to_schema(resp["schema"])
         return schema
 
     @property
     def version(self) -> int:
         """Get the current version of the table"""
-        resp = self._conn._loop.run_until_complete(
-            self._conn._client.post(f"/v1/table/{self._name}/describe/")
-        )
+        resp = self._conn._client.post(f"/v1/table/{self._name}/describe/")
         return resp["version"]
 
     def to_arrow(self) -> pa.Table:
@@ -115,9 +112,10 @@ class RemoteTable(Table):
             "metric_type": metric,
             "index_cache_size": index_cache_size,
         }
-        resp = self._conn._loop.run_until_complete(
-            self._conn._client.post(f"/v1/table/{self._name}/create_index/", data=data)
+        resp = self._conn._client.post(
+            f"/v1/table/{self._name}/create_index/", data=data
         )
+
         return resp
 
     def add(
@@ -160,13 +158,11 @@ class RemoteTable(Table):
 
         request_id = uuid.uuid4().hex
 
-        self._conn._loop.run_until_complete(
-            self._conn._client.post(
-                f"/v1/table/{self._name}/insert/",
-                data=payload,
-                params={"request_id": request_id, "mode": mode},
-                content_type=ARROW_STREAM_CONTENT_TYPE,
-            )
+        self._conn._client.post(
+            f"/v1/table/{self._name}/insert/",
+            data=payload,
+            params={"request_id": request_id, "mode": mode},
+            content_type=ARROW_STREAM_CONTENT_TYPE,
         )
 
     def search(
@@ -227,8 +223,24 @@ class RemoteTable(Table):
         return LanceVectorQueryBuilder(self, query, vector_column_name)
 
     def _execute_query(self, query: Query) -> pa.Table:
-        result = self._conn._client.query(self._name, query)
-        return self._conn._loop.run_until_complete(result).to_arrow()
+        if (
+            query.vector is not None
+            and len(query.vector) > 0
+            and not isinstance(query.vector[0], float)
+        ):
+            results = []
+            for v in query.vector:
+                v = list(v)
+                q = query.copy()
+                q.vector = v
+                results.append(self._conn._client.query(self._name, q))
+
+            return pa.concat_tables(
+                [add_index(r.to_arrow(), i) for i, r in enumerate(results)]
+            )
+        else:
+            result = self._conn._client.query(self._name, query)
+            return result.to_arrow()
 
     def delete(self, predicate: str):
         """Delete rows from the table.
@@ -277,9 +289,7 @@ class RemoteTable(Table):
         0  2  [3.0, 4.0]       85.0 # doctest: +SKIP
         """
         payload = {"predicate": predicate}
-        self._conn._loop.run_until_complete(
-            self._conn._client.post(f"/v1/table/{self._name}/delete/", data=payload)
-        )
+        self._conn._client.post(f"/v1/table/{self._name}/delete/", data=payload)
 
     def update(
         self,
@@ -339,6 +349,12 @@ class RemoteTable(Table):
             updates = [[k, v] for k, v in values_sql.items()]
 
         payload = {"predicate": where, "updates": updates}
-        self._conn._loop.run_until_complete(
-            self._conn._client.post(f"/v1/table/{self._name}/update/", data=payload)
-        )
+        self._conn._client.post(f"/v1/table/{self._name}/update/", data=payload)
+
+
+def add_index(tbl: pa.Table, i: int) -> pa.Table:
+    return tbl.add_column(
+        0,
+        pa.field("query_index", pa.uint32()),
+        pa.array([i] * len(tbl), pa.uint32()),
+    )

python/lancedb/table.py

@@ -647,8 +647,19 @@ class LanceTable(Table):
         self._dataset.restore()
         self._reset_dataset()
 
+    def count_rows(self, filter: Optional[str] = None) -> int:
+        """
+        Count the number of rows in the table.
+
+        Parameters
+        ----------
+        filter: str, optional
+            A SQL where clause to filter the rows to count.
+        """
+        return self._dataset.count_rows(filter)
+
     def __len__(self):
-        return self._dataset.count_rows()
+        return self.count_rows()
 
     def __repr__(self) -> str:
         return f"LanceTable({self.name})"
@@ -709,7 +720,11 @@ class LanceTable(Table):
         self._dataset.create_scalar_index(column, index_type="BTREE", replace=replace)
 
     def create_fts_index(
-        self, field_names: Union[str, List[str]], *, replace: bool = False
+        self,
+        field_names: Union[str, List[str]],
+        *,
+        replace: bool = False,
+        writer_heap_size: Optional[int] = 1024 * 1024 * 1024,
     ):
         """Create a full-text search index on the table.
 
@@ -724,6 +739,7 @@ class LanceTable(Table):
             If True, replace the existing index if it exists. Note that this is
             not yet an atomic operation; the index will be temporarily
             unavailable while the new index is being created.
+        writer_heap_size: int, default 1GB
         """
         from .fts import create_index, populate_index
 
@@ -740,7 +756,7 @@ class LanceTable(Table):
             fs.delete_dir(path)
 
         index = create_index(self._get_fts_index_path(), field_names)
-        populate_index(index, self, field_names)
+        populate_index(index, self, field_names, writer_heap_size=writer_heap_size)
         register_event("create_fts_index")
 
     def _get_fts_index_path(self):

python/pyproject.toml

@@ -1,13 +1,12 @@
 [project]
 name = "lancedb"
-version = "0.4.1"
+version = "0.4.4"
 dependencies = [
     "deprecation",
-    "pylance==0.9.1",
+    "pylance==0.9.6",
     "ratelimiter~=1.0",
     "retry>=0.9.2",
     "tqdm>=4.27.0",
-    "aiohttp",
     "pydantic>=1.10",
     "attrs>=21.3.0",
     "semver>=3.0",
@@ -49,11 +48,11 @@ classifiers = [
 repository = "https://github.com/lancedb/lancedb"
 
 [project.optional-dependencies]
-tests = ["pandas>=1.4", "pytest", "pytest-mock", "pytest-asyncio", "requests"]
-dev = ["ruff", "pre-commit", "black"]
+tests = ["aiohttp", "pandas>=1.4", "pytest", "pytest-mock", "pytest-asyncio", "duckdb", "pytz"]
+dev = ["ruff", "pre-commit"]
 docs = ["mkdocs", "mkdocs-jupyter", "mkdocs-material", "mkdocstrings[python]"]
 clip = ["torch", "pillow", "open-clip"]
-embeddings = ["openai", "sentence-transformers", "torch", "pillow", "open-clip-torch", "cohere", "InstructorEmbedding"]
+embeddings = ["openai>=1.6.1", "sentence-transformers", "torch", "pillow", "open-clip-torch", "cohere", "InstructorEmbedding"]
 
 [project.scripts]
 lancedb = "lancedb.cli.cli:cli"
@@ -62,9 +61,6 @@ lancedb = "lancedb.cli.cli:cli"
 requires = ["setuptools", "wheel"]
 build-backend = "setuptools.build_meta"
 
-[tool.isort]
-profile = "black"
-
 [tool.ruff]
 select = ["F", "E", "W", "I", "G", "TCH", "PERF"]
 

python/tests/test_embeddings_slow.py

@@ -29,7 +29,7 @@ from lancedb.pydantic import LanceModel, Vector
 
 @pytest.mark.slow
 @pytest.mark.parametrize("alias", ["sentence-transformers", "openai"])
-def test_sentence_transformer(alias, tmp_path):
+def test_basic_text_embeddings(alias, tmp_path):
     db = lancedb.connect(tmp_path)
     registry = get_registry()
     func = registry.get(alias).create(max_retries=0)

python/tests/test_fts.py

@@ -12,6 +12,7 @@
 #  limitations under the License.
 import os
 import random
+from unittest import mock
 
 import numpy as np
 import pandas as pd
@@ -47,6 +48,7 @@ def table(tmp_path) -> ldb.table.LanceTable:
         data=pd.DataFrame(
             {
                 "vector": vectors,
+                "id": [i % 2 for i in range(100)],
                 "text": text,
                 "text2": text,
                 "nested": [{"text": t} for t in text],
@@ -80,7 +82,7 @@ def test_search_index(tmp_path, table):
 def test_create_index_from_table(tmp_path, table):
     table.create_fts_index("text")
     df = table.search("puppy").limit(10).select(["text"]).to_pandas()
-    assert len(df) == 10
+    assert len(df) <= 10
     assert "text" in df.columns
 
     # Check whether it can be updated
@@ -88,6 +90,7 @@ def test_create_index_from_table(tmp_path, table):
         [
             {
                 "vector": np.random.randn(128),
+                "id": 101,
                 "text": "gorilla",
                 "text2": "gorilla",
                 "nested": {"text": "gorilla"},
@@ -121,3 +124,61 @@ def test_nested_schema(tmp_path, table):
     table.create_fts_index("nested.text")
     rs = table.search("puppy").limit(10).to_list()
     assert len(rs) == 10
+
+
+def test_search_index_with_filter(table):
+    table.create_fts_index("text")
+    orig_import = __import__
+
+    def import_mock(name, *args):
+        if name == "duckdb":
+            raise ImportError
+        return orig_import(name, *args)
+
+    # no duckdb
+    with mock.patch("builtins.__import__", side_effect=import_mock):
+        rs = table.search("puppy").where("id=1").limit(10).to_list()
+        for r in rs:
+            assert r["id"] == 1
+
+    # yes duckdb
+    rs2 = table.search("puppy").where("id=1").limit(10).to_list()
+    for r in rs2:
+        assert r["id"] == 1
+
+    assert rs == rs2
+
+
+def test_null_input(table):
+    table.add(
+        [
+            {
+                "vector": np.random.randn(128),
+                "id": 101,
+                "text": None,
+                "text2": None,
+                "nested": {"text": None},
+            }
+        ]
+    )
+    table.create_fts_index("text")
+
+
+def test_syntax(table):
+    # https://github.com/lancedb/lancedb/issues/769
+    table.create_fts_index("text")
+    with pytest.raises(ValueError, match="Syntax Error"):
+        table.search("they could have been dogs OR cats").limit(10).to_list()
+    table.search("they could have been dogs OR cats").phrase_query().limit(10).to_list()
+    # this should work
+    table.search('"they could have been dogs OR cats"').limit(10).to_list()
+    # this should work too
+    table.search('''"the cats OR dogs were not really 'pets' at all"''').limit(
+        10
+    ).to_list()
+    table.search('the cats OR dogs were not really "pets" at all').phrase_query().limit(
+        10
+    ).to_list()
+    table.search('the cats OR dogs were not really "pets" at all').phrase_query().limit(
+        10
+    ).to_list()

python/tests/test_pydantic.py

@@ -13,9 +13,10 @@
 
 
 import json
+import pytz
 import sys
 from datetime import date, datetime
-from typing import List, Optional
+from typing import List, Optional, Tuple
 
 import pyarrow as pa
 import pydantic
@@ -38,11 +39,14 @@ def test_pydantic_to_arrow():
         id: int
         s: str
         vec: list[float]
-        li: List[int]
+        li: list[int]
+        lili: list[list[float]]
+        litu: list[tuple[float, float]]
         opt: Optional[str] = None
         st: StructModel
         dt: date
         dtt: datetime
+        dt_with_tz: datetime = Field(json_schema_extra={"tz": "Asia/Shanghai"})
         # d: dict
 
     m = TestModel(
@@ -50,9 +54,12 @@ def test_pydantic_to_arrow():
         s="hello",
         vec=[1.0, 2.0, 3.0],
         li=[2, 3, 4],
+        lili=[[2.5, 1.5], [3.5, 4.5], [5.5, 6.5]],
+        litu=[(2.5, 1.5), (3.5, 4.5), (5.5, 6.5)],
         st=StructModel(a="a", b=1.0),
         dt=date.today(),
         dtt=datetime.now(),
+        dt_with_tz=datetime.now(pytz.timezone("Asia/Shanghai")),
     )
 
     schema = pydantic_to_schema(TestModel)
@@ -63,6 +70,8 @@ def test_pydantic_to_arrow():
             pa.field("s", pa.utf8(), False),
             pa.field("vec", pa.list_(pa.float64()), False),
             pa.field("li", pa.list_(pa.int64()), False),
+            pa.field("lili", pa.list_(pa.list_(pa.float64())), False),
+            pa.field("litu", pa.list_(pa.list_(pa.float64())), False),
             pa.field("opt", pa.utf8(), True),
             pa.field(
                 "st",
@@ -73,11 +82,38 @@ def test_pydantic_to_arrow():
             ),
             pa.field("dt", pa.date32(), False),
             pa.field("dtt", pa.timestamp("us"), False),
+            pa.field("dt_with_tz", pa.timestamp("us", tz="Asia/Shanghai"), False),
         ]
     )
     assert schema == expect_schema
 
 
+@pytest.mark.skipif(
+    sys.version_info < (3, 10),
+    reason="using | type syntax requires python3.10 or higher",
+)
+def test_optional_types_py310():
+    class TestModel(pydantic.BaseModel):
+        a: str | None
+        b: None | str
+        c: Optional[str]
+
+    schema = pydantic_to_schema(TestModel)
+
+    expect_schema = pa.schema(
+        [
+            pa.field("a", pa.utf8(), True),
+            pa.field("b", pa.utf8(), True),
+            pa.field("c", pa.utf8(), True),
+        ]
+    )
+    assert schema == expect_schema
+
+
+@pytest.mark.skipif(
+    sys.version_info > (3, 8),
+    reason="using native type alias requires python3.9 or higher",
+)
 def test_pydantic_to_arrow_py38():
     class StructModel(pydantic.BaseModel):
         a: str
@@ -88,10 +124,13 @@ def test_pydantic_to_arrow_py38():
         s: str
         vec: List[float]
         li: List[int]
+        lili: List[List[float]]
+        litu: List[Tuple[float, float]]
         opt: Optional[str] = None
         st: StructModel
         dt: date
         dtt: datetime
+        dt_with_tz: datetime = Field(json_schema_extra={"tz": "Asia/Shanghai"})
         # d: dict
 
     m = TestModel(
@@ -99,9 +138,12 @@ def test_pydantic_to_arrow_py38():
         s="hello",
         vec=[1.0, 2.0, 3.0],
         li=[2, 3, 4],
+        lili=[[2.5, 1.5], [3.5, 4.5], [5.5, 6.5]],
+        litu=[(2.5, 1.5), (3.5, 4.5), (5.5, 6.5)],
         st=StructModel(a="a", b=1.0),
         dt=date.today(),
         dtt=datetime.now(),
+        dt_with_tz=datetime.now(pytz.timezone("Asia/Shanghai")),
     )
 
     schema = pydantic_to_schema(TestModel)
@@ -112,6 +154,8 @@ def test_pydantic_to_arrow_py38():
             pa.field("s", pa.utf8(), False),
             pa.field("vec", pa.list_(pa.float64()), False),
             pa.field("li", pa.list_(pa.int64()), False),
+            pa.field("lili", pa.list_(pa.list_(pa.float64())), False),
+            pa.field("litu", pa.list_(pa.list_(pa.float64())), False),
             pa.field("opt", pa.utf8(), True),
             pa.field(
                 "st",
@@ -122,6 +166,7 @@ def test_pydantic_to_arrow_py38():
             ),
             pa.field("dt", pa.date32(), False),
             pa.field("dtt", pa.timestamp("us"), False),
+            pa.field("dt_with_tz", pa.timestamp("us", tz="Asia/Shanghai"), False),
         ]
     )
     assert schema == expect_schema

python/tests/test_remote_db.py

@@ -18,15 +18,15 @@ from lancedb.remote.client import VectorQuery, VectorQueryResult
 
 
 class FakeLanceDBClient:
-    async def close(self):
+    def close(self):
         pass
 
-    async def query(self, table_name: str, query: VectorQuery) -> VectorQueryResult:
+    def query(self, table_name: str, query: VectorQuery) -> VectorQueryResult:
         assert table_name == "test"
         t = pa.schema([]).empty_table()
         return VectorQueryResult(t)
 
-    async def post(self, path: str):
+    def post(self, path: str):
         pass
 
 

python/tests/test_table.py

@@ -569,6 +569,14 @@ def test_empty_query(db):
     val = df.id.iloc[0]
     assert val == 1
 
+    table = LanceTable.create(db, "my_table2", data=[{"id": i} for i in range(100)])
+    df = table.search().select(["id"]).to_pandas()
+    assert len(df) == 10
+    df = table.search().select(["id"]).limit(None).to_pandas()
+    assert len(df) == 100
+    df = table.search().select(["id"]).limit(-1).to_pandas()
+    assert len(df) == 100
+
 
 def test_compact_cleanup(db):
     table = LanceTable.create(
@@ -597,3 +605,14 @@ def test_compact_cleanup(db):
 
     with pytest.raises(Exception, match="Version 3 no longer exists"):
         table.checkout(3)
+
+
+def test_count_rows(db):
+    table = LanceTable.create(
+        db,
+        "my_table",
+        data=[{"text": "foo", "id": 0}, {"text": "bar", "id": 1}],
+    )
+    assert len(table) == 2
+    assert table.count_rows() == 2
+    assert table.count_rows(filter="text='bar'") == 1

rust/ffi/node/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "vectordb-node"
-version = "0.4.1"
+version = "0.4.3"
 description = "Serverless, low-latency vector database for AI applications"
 license = "Apache-2.0"
 edition = "2018"

rust/ffi/node/src/arrow.rs

@@ -36,7 +36,7 @@ fn validate_vector_column(record_batch: &RecordBatch) -> Result<()> {
 pub(crate) fn arrow_buffer_to_record_batch(slice: &[u8]) -> Result<(Vec<RecordBatch>, SchemaRef)> {
     let mut batches: Vec<RecordBatch> = Vec::new();
     let file_reader = FileReader::try_new(Cursor::new(slice), None)?;
-    let schema = file_reader.schema().clone();
+    let schema = file_reader.schema();
     for b in file_reader {
         let record_batch = b?;
         validate_vector_column(&record_batch)?;
@@ -50,7 +50,7 @@ pub(crate) fn record_batch_to_buffer(batches: Vec<RecordBatch>) -> Result<Vec<u8
         return Ok(Vec::new());
     }
 
-    let schema = batches.get(0).unwrap().schema();
+    let schema = batches.first().unwrap().schema();
     let mut fr = FileWriter::try_new(Vec::new(), schema.deref())?;
     for batch in batches.iter() {
         fr.write(batch)?

rust/ffi/node/src/convert.rs

@@ -13,6 +13,9 @@
 // limitations under the License.
 
 use neon::prelude::*;
+use neon::types::buffer::TypedArray;
+
+use crate::error::ResultExt;
 
 pub(crate) fn vec_str_to_array<'a, C: Context<'a>>(
     vec: &Vec<String>,
@@ -34,3 +37,20 @@ pub(crate) fn js_array_to_vec(array: &JsArray, cx: &mut FunctionContext) -> Vec<
     }
     query_vec
 }
+
+// Creates a new JsBuffer from a rust buffer with a special logic for electron
+pub(crate) fn new_js_buffer<'a>(
+    buffer: Vec<u8>,
+    cx: &mut TaskContext<'a>,
+    is_electron: bool,
+) -> NeonResult<Handle<'a, JsBuffer>> {
+    if is_electron {
+        // Electron does not support `external`: https://github.com/neon-bindings/neon/pull/937
+        let mut js_buffer = JsBuffer::new(cx, buffer.len()).or_throw(cx)?;
+        let buffer_data = js_buffer.as_mut_slice(cx);
+        buffer_data.copy_from_slice(buffer.as_slice());
+        Ok(js_buffer)
+    } else {
+        Ok(JsBuffer::external(cx, buffer))
+    }
+}

rust/ffi/node/src/lib.rs

@@ -250,5 +250,6 @@ fn main(mut cx: ModuleContext) -> NeonResult<()> {
         "tableCreateVectorIndex",
         index::vector::table_create_vector_index,
     )?;
+    cx.export_function("tableSchema", JsTable::js_schema)?;
     Ok(())
 }

rust/ffi/node/src/query.rs

@@ -7,7 +7,6 @@ use lance_linalg::distance::MetricType;
 use neon::context::FunctionContext;
 use neon::handle::Handle;
 use neon::prelude::*;
-use neon::types::buffer::TypedArray;
 
 use crate::arrow::record_batch_to_buffer;
 use crate::error::ResultExt;
@@ -96,26 +95,9 @@ impl JsQuery {
             deferred.settle_with(&channel, move |mut cx| {
                 let results = results.or_throw(&mut cx)?;
                 let buffer = record_batch_to_buffer(results).or_throw(&mut cx)?;
-                Self::new_js_buffer(buffer, &mut cx, is_electron)
+                convert::new_js_buffer(buffer, &mut cx, is_electron)
             });
         });
         Ok(promise)
     }
-
-    // Creates a new JsBuffer from a rust buffer with a special logic for electron
-    fn new_js_buffer<'a>(
-        buffer: Vec<u8>,
-        cx: &mut TaskContext<'a>,
-        is_electron: bool,
-    ) -> NeonResult<Handle<'a, JsBuffer>> {
-        if is_electron {
-            // Electron does not support `external`: https://github.com/neon-bindings/neon/pull/937
-            let mut js_buffer = JsBuffer::new(cx, buffer.len()).or_throw(cx)?;
-            let buffer_data = js_buffer.as_mut_slice(cx);
-            buffer_data.copy_from_slice(buffer.as_slice());
-            Ok(js_buffer)
-        } else {
-            Ok(JsBuffer::external(cx, buffer))
-        }
-    }
 }

rust/ffi/node/src/table.rs

@@ -12,18 +12,18 @@
 // See the License for the specific language governing permissions and
 // limitations under the License.
 
-use arrow_array::RecordBatchIterator;
+use arrow_array::{RecordBatch, RecordBatchIterator};
 use lance::dataset::optimize::CompactionOptions;
 use lance::dataset::{WriteMode, WriteParams};
 use lance::io::object_store::ObjectStoreParams;
 
-use crate::arrow::arrow_buffer_to_record_batch;
+use crate::arrow::{arrow_buffer_to_record_batch, record_batch_to_buffer};
 use neon::prelude::*;
 use neon::types::buffer::TypedArray;
 use vectordb::Table;
 
 use crate::error::ResultExt;
-use crate::{get_aws_creds, get_aws_region, runtime, JsDatabase};
+use crate::{convert, get_aws_creds, get_aws_region, runtime, JsDatabase};
 
 pub(crate) struct JsTable {
     pub table: Table,
@@ -426,4 +426,27 @@ impl JsTable {
 
         Ok(promise)
     }
+
+    pub(crate) fn js_schema(mut cx: FunctionContext) -> JsResult<JsPromise> {
+        let js_table = cx.this().downcast_or_throw::<JsBox<JsTable>, _>(&mut cx)?;
+        let rt = runtime(&mut cx)?;
+        let (deferred, promise) = cx.promise();
+        let channel = cx.channel();
+        let table = js_table.table.clone();
+
+        let is_electron = cx
+            .argument::<JsBoolean>(0)
+            .or_throw(&mut cx)?
+            .value(&mut cx);
+
+        rt.spawn(async move {
+            deferred.settle_with(&channel, move |mut cx| {
+                let schema = table.schema();
+                let batches = vec![RecordBatch::new_empty(schema)];
+                let buffer = record_batch_to_buffer(batches).or_throw(&mut cx)?;
+                convert::new_js_buffer(buffer, &mut cx, is_electron)
+            })
+        });
+        Ok(promise)
+    }
 }

rust/vectordb/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "vectordb"
-version = "0.4.1"
+version = "0.4.3"
 edition = "2021"
 description = "LanceDB: A serverless, low-latency vector database for AI applications"
 license = "Apache-2.0"