[python] Bump version: 0.4.1 → 0.4.2

API has changed significantly, namely `openai.Embedding.create` no
longer exists.
https://github.com/openai/openai-python/discussions/742

Update the OpenAI embedding function and put a minimum on the openai sdk
version.

.bumpversion.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 0.4.0
+current_version = 0.4.1
 commit = True
 message = Bump version: {current_version} → {new_version}
 tag = True

.github/ISSUE_TEMPLATE/bug-node.yml

@@ -0,0 +1,33 @@
+name: Bug Report - Node / Typescript
+description: File a bug report
+title: "bug(node): "
+labels: [bug, typescript]
+body:
+  - type: markdown
+    attributes:
+      value: |
+        Thanks for taking the time to fill out this bug report!
+  - type: input
+    id: version
+    attributes:
+      label: LanceDB version
+      description: What version of LanceDB are you using? `npm list | grep vectordb`.
+      placeholder: v0.3.2
+    validations:
+      required: false
+  - type: textarea
+    id: what-happened
+    attributes:
+      label: What happened?
+      description: Also tell us, what did you expect to happen?
+    validations:
+      required: true
+  - type: textarea
+    id: reproduction
+    attributes:
+      label: Are there known steps to reproduce?
+      description: |
+        Let us know how to reproduce the bug and we may be able to fix it more
+        quickly. This is not required, but it is helpful.
+    validations:
+      required: false

.github/ISSUE_TEMPLATE/bug-python.yml

@@ -0,0 +1,33 @@
+name: Bug Report - Python
+description: File a bug report
+title: "bug(python): "
+labels: [bug, python]
+body:
+  - type: markdown
+    attributes:
+      value: |
+        Thanks for taking the time to fill out this bug report!
+  - type: input
+    id: version
+    attributes:
+      label: LanceDB version
+      description: What version of LanceDB are you using? `python -c "import lancedb; print(lancedb.__version__)"`.
+      placeholder: v0.3.2
+    validations:
+      required: false
+  - type: textarea
+    id: what-happened
+    attributes:
+      label: What happened?
+      description: Also tell us, what did you expect to happen?
+    validations:
+      required: true
+  - type: textarea
+    id: reproduction
+    attributes:
+      label: Are there known steps to reproduce?
+      description: |
+        Let us know how to reproduce the bug and we may be able to fix it more
+        quickly. This is not required, but it is helpful.
+    validations:
+      required: false

.github/ISSUE_TEMPLATE/config.yml

@@ -0,0 +1,5 @@
+blank_issues_enabled: true
+contact_links:
+  - name: Discord Community Support
+    url: https://discord.com/invite/zMM32dvNtd
+    about: Please ask and answer questions here.

.github/ISSUE_TEMPLATE/documentation.yml

@@ -0,0 +1,23 @@
+name: 'Documentation improvement'
+description: Report an issue with the documentation.
+labels: [documentation]
+
+body:
+  - type: textarea
+    id: description
+    attributes:
+      label: Description
+      description: >
+        Describe the issue with the documentation and how it can be fixed or improved.
+    validations:
+      required: true
+
+  - type: input
+    id: link
+    attributes:
+      label: Link
+      description: >
+        Provide a link to the existing documentation, if applicable.
+      placeholder: ex. https://lancedb.github.io/lancedb/guides/tables/...
+    validations:
+      required: false

.github/ISSUE_TEMPLATE/feature.yml

@@ -0,0 +1,31 @@
+name: Feature suggestion
+description: Suggestion a new feature for LanceDB
+title: "Feature: "
+labels: [enhancement]
+body:
+  - type: markdown
+    attributes:
+      value: |
+        Share a new idea for a feature or improvement. Be sure to search existing
+        issues first to avoid duplicates.
+  - type: dropdown
+    id: sdk
+    attributes:
+      label: SDK
+      description: Which SDK are you using? This helps us prioritize.
+      options:
+        - Python
+        - Node
+        - Rust
+      default: 0
+    validations:
+      required: false
+  - type: textarea
+    id: description
+    attributes:
+      label: Description
+      description: |
+        Describe the feature and why it would be useful. If applicable, consider
+        providing a code example of what it might be like to use the feature.
+    validations:
+      required: true

.github/workflows/python.yml

@@ -44,12 +44,19 @@ jobs:
       run: pytest -m "not slow" -x -v --durations=30 tests
     - name: doctest
       run: pytest --doctest-modules lancedb
-  mac:
+  platform:
+    name: "Platform: ${{ matrix.config.name }}"
     timeout-minutes: 30
     strategy:
       matrix:
-        mac-runner: [ "macos-13", "macos-13-xlarge" ]
-    runs-on: "${{ matrix.mac-runner }}"
+        config: 
+          - name: x86 Mac
+            runner: macos-13
+          - name: Arm Mac
+            runner: macos-13-xlarge
+          - name: x86 Windows
+            runner: windows-latest
+    runs-on: "${{ matrix.config.runner }}"
     defaults:
       run:
         shell: bash

.github/workflows/rust.yml

@@ -24,6 +24,29 @@ env:
   RUST_BACKTRACE: "1"
 
 jobs:
+  lint:
+    timeout-minutes: 30
+    runs-on: ubuntu-22.04
+    defaults:
+      run:
+        shell: bash
+        working-directory: rust
+    steps:
+    - uses: actions/checkout@v3
+      with:
+          fetch-depth: 0
+          lfs: true
+    - uses: Swatinem/rust-cache@v2
+      with:
+        workspaces: rust
+    - name: Install dependencies
+      run: |
+          sudo apt update
+          sudo apt install -y protobuf-compiler libssl-dev
+    - name: Run format
+      run: cargo fmt --all -- --check
+    - name: Run clippy
+      run: cargo clippy --all --all-features -- -D warnings
   linux:
     timeout-minutes: 30
     runs-on: ubuntu-22.04

Cargo.toml

@@ -5,24 +5,24 @@ exclude = ["python"]
 resolver = "2"
 
 [workspace.dependencies]
-lance = { "version" = "=0.9.0", "features" = ["dynamodb"] }
-lance-index = { "version" = "=0.9.0" }
-lance-linalg = { "version" = "=0.9.0" }
-lance-testing = { "version" = "=0.9.0" }
+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" }
 # Note that this one does not include pyarrow
-arrow = { version = "47.0.0", optional = false }
-arrow-array = "47.0"
-arrow-data = "47.0"
-arrow-ipc = "47.0"
-arrow-ord = "47.0"
-arrow-schema = "47.0"
-arrow-arith = "47.0"
-arrow-cast = "47.0"
+arrow = { version = "49.0.0", optional = false }
+arrow-array = "49.0"
+arrow-data = "49.0"
+arrow-ipc = "49.0"
+arrow-ord = "49.0"
+arrow-schema = "49.0"
+arrow-arith = "49.0"
+arrow-cast = "49.0"
 chrono = "0.4.23"
 half = { "version" = "=2.3.1", default-features = false, features = [
     "num-traits",
 ] }
 log = "0.4"
-object_store = "0.7.1"
+object_store = "0.8.0"
 snafu = "0.7.4"
 url = "2"

docs/src/basic.md

@@ -64,18 +64,26 @@ We'll cover the basics of using LanceDB on your local machine in this section.
       tbl = db.create_table("table_from_df", data=df)
       ```
 
+      !!! warning
+
+            If the table already exists, LanceDB will raise an error by default.
+            If you want to overwrite the table, you can pass in `mode="overwrite"`
+            to the `createTable` function.
+
 === "Javascript"
       ```javascript
-      const tb = await db.createTable("my_table",
-                        data=[{"vector": [3.1, 4.1], "item": "foo", "price": 10.0},
-                              {"vector": [5.9, 26.5], "item": "bar", "price": 20.0}])
+      const tb = await db.createTable(
+        "myTable",
+        [{"vector": [3.1, 4.1], "item": "foo", "price": 10.0},
+         {"vector": [5.9, 26.5], "item": "bar", "price": 20.0}])
       ```
-      
-!!! warning
 
-      If the table already exists, LanceDB will raise an error by default.
-      If you want to overwrite the table, you can pass in `mode="overwrite"`
-      to the `createTable` function.
+      !!! warning
+
+            If the table already exists, LanceDB will raise an error by default.
+            If you want to overwrite the table, you can pass in `"overwrite"`
+            to the `createTable` function like this: `await con.createTable(tableName, data, { writeMode: WriteMode.Overwrite })`
+      
 
 ??? info "Under the hood, LanceDB is converting the input data into an Apache Arrow table and persisting it to disk in [Lance format](https://www.github.com/lancedb/lance)."
 
@@ -108,7 +116,7 @@ Once created, you can open a table using the following code:
 
 === "Javascript"
       ```javascript
-      const tbl = await db.openTable("my_table");
+      const tbl = await db.openTable("myTable");
       ```
 
       If you forget the name of your table, you can always get a listing of all table names:
@@ -194,10 +202,17 @@ Use the `drop_table()` method on the database to remove a table.
       db.drop_table("my_table")
       ```
 
-This permanently removes the table and is not recoverable, unlike deleting rows.
-By default, if the table does not exist an exception is raised. To suppress this,
-you can pass in `ignore_missing=True`.
+      This permanently removes the table and is not recoverable, unlike deleting rows.
+      By default, if the table does not exist an exception is raised. To suppress this,
+      you can pass in `ignore_missing=True`.
 
+=== "JavaScript"
+      ```javascript
+      await db.dropTable('myTable')
+      ```
+
+      This permanently removes the table and is not recoverable, unlike deleting rows.
+      If the table does not exist an exception is raised. 
 
 ## What's next
 

docs/src/embeddings/default_embedding_functions.md

@@ -1,9 +1,9 @@
-There are various Embedding functions available out of the box with lancedb. We're working on supporting other popular embedding APIs.
+There are various Embedding functions available out of the box with LanceDB. We're working on supporting other popular embedding APIs.
 
 ## Text Embedding Functions
 Here are the text embedding functions registered by default.
-Embedding functions have inbuilt rate limit handler wrapper for source and query embedding function calls that retry with exponential standoff. 
-Each `EmbeddingFunction` implementation automatically takes `max_retries` as an argument which has the deafult value of 7.
+Embedding functions have an inbuilt rate limit handler wrapper for source and query embedding function calls that retry with exponential standoff. 
+Each `EmbeddingFunction` implementation automatically takes `max_retries` as an argument which has the default value of 7.
 
 ### Sentence Transformers
 Here are the parameters that you can set when registering a `sentence-transformers` object, and their default values:
@@ -69,15 +69,15 @@ print(actual.text)
 ```
 
 ### Instructor Embeddings
-Instructor is an instruction-finetuned text embedding model that can generate text embeddings tailored to any task (e.g., classification, retrieval, clustering, text evaluation, etc.) and domains (e.g., science, finance, etc.) by simply providing the task instruction, without any finetuning
+Instructor is an instruction-finetuned text embedding model that can generate text embeddings tailored to any task (e.g. classification, retrieval, clustering, text evaluation, etc.) and domains (e.g. science, finance, etc.) by simply providing the task instruction, without any finetuning.
 
 If you want to calculate customized embeddings for specific sentences, you may follow the unified template to write instructions:
 
                           Represent the `domain` `text_type` for `task_objective`:
 
-* `domain` is optional, and it specifies the domain of the text, e.g., science, finance, medicine, etc.
-* `text_type` is required, and it specifies the encoding unit, e.g., sentence, document, paragraph, etc.
-* `task_objective` is optional, and it specifies the objective of embedding, e.g., retrieve a document, classify the sentence, etc.
+* `domain` is optional, and it specifies the domain of the text, e.g. science, finance, medicine, etc.
+* `text_type` is required, and it specifies the encoding unit, e.g. sentence, document, paragraph, etc.
+* `task_objective` is optional, and it specifies the objective of embedding, e.g. retrieve a document, classify the sentence, etc.
 
 More information about the model can be found here - https://github.com/xlang-ai/instructor-embedding
 
@@ -119,10 +119,10 @@ tbl.add(texts)
 ```
 
 ## Multi-modal embedding functions
-Multi-modal embedding functions allow you query your table using both images and text.
+Multi-modal embedding functions allow you to query your table using both images and text.
 
 ### OpenClipEmbeddings
-We support CLIP model embeddings using the open souce alternbative, open-clip which support various customizations. It is registered as `open-clip` and supports following customizations.
+We support CLIP model embeddings using the open source alternative, open-clip which supports various customizations. It is registered as `open-clip` and supports the following customizations:
 
 
 | Parameter | Type | Default Value | Description |
@@ -205,4 +205,4 @@ print(actual.label)
 
 ```
 
-If you have any questions about the embeddings API, supported models, or see a relevant model missing, please raise an issue.
+If you have any questions about the embeddings API, supported models, or see a relevant model missing, please raise an issue.

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 +65,23 @@ 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()
+```
+
 ## 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
@@ -203,8 +281,8 @@ This guide will show how to create tables, insert data into them, and update the
     ```javascript
     data
     const tb = await db.createTable("my_table",
-                  data=[{"vector": [3.1, 4.1], "item": "foo", "price": 10.0},
-                        {"vector": [5.9, 26.5], "item": "bar", "price": 20.0}])
+      [{"vector": [3.1, 4.1], "item": "foo", "price": 10.0},
+       {"vector": [5.9, 26.5], "item": "bar", "price": 20.0}])
     ```
 
     !!! info "Note"

docs/src/javascript/README.md

@@ -11,8 +11,13 @@ 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 musl-based Linux (such as Alpine Linux).
+support:
+
+* Linux (x86_64 and aarch64)
+* MacOS (Intel and ARM/M1/M2)
+* Windows (x86_64 only)
+
+We do not yet support musl-based Linux (such as Alpine Linux) or aarch64 Windows.
 
 ## Usage
 

docs/src/sql.md

@@ -22,7 +22,7 @@ import numpy as np
 uri = "data/sample-lancedb"
 db = lancedb.connect(uri)
 
-data = [{"vector": row, "item": f"item {i}"}
+data = [{"vector": row, "item": f"item {i}", "id": i}
      for i, row in enumerate(np.random.random((10_000, 2)).astype('int'))]
 
 tbl = db.create_table("my_vectors", data=data)
@@ -35,33 +35,25 @@ const db = await vectordb.connect('data/sample-lancedb')
 
 let data = []
 for (let i = 0; i < 10_000; i++) {
-     data.push({vector: Array(1536).fill(i), id: `${i}`, content: "", longId: `${i}`},)
+     data.push({vector: Array(1536).fill(i), id: i, item: `item ${i}`, strId: `${i}`})
 }
-const tbl = await db.createTable('my_vectors', data)
+const tbl = await db.createTable('myVectors', data)
 ```
 -->
 === "Python"
 
     ```python
     tbl.search([100, 102]) \
-       .where("""(
-        (label IN [10, 20])
-        AND
-        (note.email IS NOT NULL)
-        ) OR NOT note.created
-        """)
-
+       .where("(item IN ('item 0', 'item 2')) AND (id > 10)") \
+       .to_arrow()
     ```
+
 === "Javascript"
 
     ```javascript
-    tbl.search([100, 102])
-       .where(`(
-            (label IN [10, 20])
-            AND
-            (note.email IS NOT NULL)
-        ) OR NOT note.created
-       `)
+    await tbl.search(Array(1536).fill(0))
+       .where("(item IN ('item 0', 'item 2')) AND (id > 10)")
+       .execute()
     ```
 
 
@@ -118,3 +110,22 @@ The mapping from SQL types to Arrow types is:
 
 [^1]: See precision mapping in previous table.
 
+
+## Filtering without Vector Search
+
+You can also filter your data without search.
+
+=== "Python"
+      ```python
+      tbl.search().where("id=10").limit(10).to_arrow()
+      ```
+
+=== "JavaScript"
+      ```javascript
+      await tbl.where('id=10').limit(10).execute()
+      ```
+
+!!! warning
+    If your table is large, this could potentially return a very large
+    amount of data. Please be sure to use a `limit` clause unless
+    you're sure you want to return the whole result set.

node/README.md

@@ -9,8 +9,13 @@ 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 musl-based Linux (such as Alpine Linux).
+support:
+
+* Linux (x86_64 and aarch64)
+* MacOS (Intel and ARM/M1/M2)
+* Windows (x86_64 only)
+
+We do not yet support musl-based Linux (such as Alpine Linux) or aarch64 Windows.
 
 ## Usage
 

node/package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "vectordb",
-  "version": "0.4.0",
+  "version": "0.4.1",
   "lockfileVersion": 2,
   "requires": true,
   "packages": {
     "": {
       "name": "vectordb",
-      "version": "0.4.0",
+      "version": "0.4.1",
       "cpu": [
         "x64",
         "arm64"
@@ -53,11 +53,11 @@
         "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": "0.4.1",
+        "@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"
       }
     },
     "node_modules/@apache-arrow/ts": {
@@ -317,9 +317,9 @@
       }
     },
     "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": "0.4.1",
+      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-darwin-arm64/-/vectordb-darwin-arm64-0.4.1.tgz",
+      "integrity": "sha512-ul/Hvv5RX2RThpKSuiUjJRVrmXuBPvpU+HrLjcBmu4dzpuWN4+IeHIUM6xe79gLxOKlwkscVweTOuZnmMfsZeg==",
       "cpu": [
         "arm64"
       ],
@@ -329,9 +329,9 @@
       ]
     },
     "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": "0.4.1",
+      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-darwin-x64/-/vectordb-darwin-x64-0.4.1.tgz",
+      "integrity": "sha512-sJtF2Cv6T9RhUpdeHNkryiJwPuW9QPQ3aMs5fID1hMCJA2U3BX27t/WlkiPT2+kTLeUcwF1JvAOgsfvZkfvI8w==",
       "cpu": [
         "x64"
       ],
@@ -341,9 +341,9 @@
       ]
     },
     "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": "0.4.1",
+      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-linux-arm64-gnu/-/vectordb-linux-arm64-gnu-0.4.1.tgz",
+      "integrity": "sha512-tNnziT0BRjPsznKI4GgWROFdCOsCGx0inFu0z+WV1UomwXKcMWGslpWBqKE8IUiCq14duPVx/ie7Wwcf51IeJQ==",
       "cpu": [
         "arm64"
       ],
@@ -353,9 +353,9 @@
       ]
     },
     "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": "0.4.1",
+      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-linux-x64-gnu/-/vectordb-linux-x64-gnu-0.4.1.tgz",
+      "integrity": "sha512-PAcF2p1FUsC0AD+qkLfgE5+ZlQwlHe9eTP9dSsX43V/NGPDQ9+gBzaBTEDbvyHj1wl2Wft2NwOqB1HAFhilSDg==",
       "cpu": [
         "x64"
       ],
@@ -365,9 +365,9 @@
       ]
     },
     "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": "0.4.1",
+      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-win32-x64-msvc/-/vectordb-win32-x64-msvc-0.4.1.tgz",
+      "integrity": "sha512-8mvThCppI/AfSPby6Y3t6xpCfbo8IY6JH5exO8fDGTwBFHOqgwR4Izb2K7FgXxkwUYcN4EfGSsk/6B1GpwMudg==",
       "cpu": [
         "x64"
       ],
@@ -4869,33 +4869,33 @@
       }
     },
     "@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": "0.4.1",
+      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-darwin-arm64/-/vectordb-darwin-arm64-0.4.1.tgz",
+      "integrity": "sha512-ul/Hvv5RX2RThpKSuiUjJRVrmXuBPvpU+HrLjcBmu4dzpuWN4+IeHIUM6xe79gLxOKlwkscVweTOuZnmMfsZeg==",
       "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": "0.4.1",
+      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-darwin-x64/-/vectordb-darwin-x64-0.4.1.tgz",
+      "integrity": "sha512-sJtF2Cv6T9RhUpdeHNkryiJwPuW9QPQ3aMs5fID1hMCJA2U3BX27t/WlkiPT2+kTLeUcwF1JvAOgsfvZkfvI8w==",
       "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": "0.4.1",
+      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-linux-arm64-gnu/-/vectordb-linux-arm64-gnu-0.4.1.tgz",
+      "integrity": "sha512-tNnziT0BRjPsznKI4GgWROFdCOsCGx0inFu0z+WV1UomwXKcMWGslpWBqKE8IUiCq14duPVx/ie7Wwcf51IeJQ==",
       "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": "0.4.1",
+      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-linux-x64-gnu/-/vectordb-linux-x64-gnu-0.4.1.tgz",
+      "integrity": "sha512-PAcF2p1FUsC0AD+qkLfgE5+ZlQwlHe9eTP9dSsX43V/NGPDQ9+gBzaBTEDbvyHj1wl2Wft2NwOqB1HAFhilSDg==",
       "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": "0.4.1",
+      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-win32-x64-msvc/-/vectordb-win32-x64-msvc-0.4.1.tgz",
+      "integrity": "sha512-8mvThCppI/AfSPby6Y3t6xpCfbo8IY6JH5exO8fDGTwBFHOqgwR4Izb2K7FgXxkwUYcN4EfGSsk/6B1GpwMudg==",
       "optional": true
     },
     "@neon-rs/cli": {

node/package.json

@@ -1,6 +1,6 @@
 {
   "name": "vectordb",
-  "version": "0.4.0",
+  "version": "0.4.1",
   "description": " Serverless, low-latency vector database for AI applications",
   "main": "dist/index.js",
   "types": "dist/index.d.ts",
@@ -81,10 +81,10 @@
     }
   },
   "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": "0.4.1",
+    "@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"
   }
 }

node/src/index.ts

@@ -24,7 +24,7 @@ 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, 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 } = require('../native.js')
 
 export { Query }
 export type { EmbeddingFunction }
@@ -223,6 +223,56 @@ export interface Table<T = number[]> {
    */
   createIndex: (indexParams: VectorIndexParams) => Promise<any>
 
+  /**
+   * Create a scalar index on this Table for the given column
+   *
+   * @param column The column to index
+   * @param replace If false, fail if an index already exists on the column
+   *
+   * Scalar indices, like vector indices, can be used to speed up scans.  A scalar
+   * index can speed up scans that contain filter expressions on the indexed column.
+   * For example, the following scan will be faster if the column `my_col` has
+   * a scalar index:
+   *
+   * ```ts
+   * const con = await lancedb.connect('./.lancedb');
+   * const table = await con.openTable('images');
+   * const results = await table.where('my_col = 7').execute();
+   * ```
+   *
+   * Scalar indices can also speed up scans containing a vector search and a
+   * prefilter:
+   *
+   * ```ts
+   * const con = await lancedb.connect('././lancedb');
+   * const table = await con.openTable('images');
+   * const results = await table.search([1.0, 2.0]).where('my_col != 7').prefilter(true);
+   * ```
+   *
+   * Scalar indices can only speed up scans for basic filters using
+   * equality, comparison, range (e.g. `my_col BETWEEN 0 AND 100`), and set
+   * membership (e.g. `my_col IN (0, 1, 2)`)
+   *
+   * Scalar indices can be used if the filter contains multiple indexed columns and
+   * the filter criteria are AND'd or OR'd together
+   * (e.g. `my_col < 0 AND other_col> 100`)
+   *
+   * Scalar indices may be used if the filter contains non-indexed columns but,
+   * depending on the structure of the filter, they may not be usable.  For example,
+   * if the column `not_indexed` does not have a scalar index then the filter
+   * `my_col = 0 OR not_indexed = 1` will not be able to use any scalar index on
+   * `my_col`.
+   *
+   * @examples
+   *
+   * ```ts
+   * const con = await lancedb.connect('././lancedb')
+   * const table = await con.openTable('images')
+   * await table.createScalarIndex('my_col')
+   * ```
+   */
+  createScalarIndex: (column: string, replace: boolean) => Promise<void>
+
   /**
    * Returns the number of rows in this table.
    */
@@ -281,8 +331,8 @@ export interface Table<T = number[]> {
    * const tbl = await con.createTable("my_table", data)
    *
    * await tbl.update({
-   *   filter: "id = 2",
-   *   updates: { vector: [2, 2], name: "Michael" },
+   *   where: "id = 2",
+   *   values: { vector: [2, 2], name: "Michael" },
    * })
    *
    * let results = await tbl.search([1, 1]).execute();
@@ -537,6 +587,10 @@ export class LocalTable<T = number[]> implements Table<T> {
     return tableCreateVectorIndex.call(this._tbl, indexParams).then((newTable: any) => { this._tbl = newTable })
   }
 
+  async createScalarIndex (column: string, replace: boolean): Promise<void> {
+    return tableCreateScalarIndex.call(this._tbl, column, replace)
+  }
+
   /**
    * Returns the number of rows in this table.
    */

node/src/remote/index.ts

@@ -57,8 +57,8 @@ export class RemoteConnection implements Connection {
     return 'db://' + this._client.uri
   }
 
-  async tableNames (): Promise<string[]> {
-    const response = await this._client.get('/v1/table/')
+  async tableNames (pageToken: string = '', limit: number = 10): Promise<string[]> {
+    const response = await this._client.get('/v1/table/', { limit, page_token: pageToken })
     return response.data.tables
   }
 
@@ -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,
@@ -283,6 +283,10 @@ export class RemoteTable<T = number[]> implements Table<T> {
     }
   }
 
+  async createScalarIndex (column: string, replace: boolean): Promise<void> {
+    throw new Error('Not implemented')
+  }
+
   async countRows (): Promise<number> {
     const result = await this._client.post(`/v1/table/${this._name}/describe/`)
     return result.data?.stats?.num_rows

node/src/test/test.ts

@@ -135,6 +135,17 @@ describe('LanceDB client', function () {
       assert.isTrue(results.length === 10)
     })
 
+    it('should allow creation and use of scalar indices', async function () {
+      const uri = await createTestDB(16, 300)
+      const con = await lancedb.connect(uri)
+      const table = await con.openTable('vectors')
+      await table.createScalarIndex('id', true)
+
+      // Prefiltering should still work the same
+      const results = await table.search(new Array(16).fill(0.1)).limit(10).filter('id >= 10').prefilter(true).execute()
+      assert.isTrue(results.length === 10)
+    })
+
     it('select only a subset of columns', async function () {
       const uri = await createTestDB()
       const con = await lancedb.connect(uri)

python/.bumpversion.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 0.4.0
+current_version = 0.4.2
 commit = True
 message = [python] Bump version: {current_version} → {new_version}
 tag = True

python/lancedb/db.py

@@ -23,7 +23,7 @@ from overrides import EnforceOverrides, override
 from pyarrow import fs
 
 from .table import LanceTable, Table
-from .util import fs_from_uri, get_uri_location, get_uri_scheme
+from .util import fs_from_uri, get_uri_location, get_uri_scheme, join_uri
 
 if TYPE_CHECKING:
     from .common import DATA, URI
@@ -288,14 +288,13 @@ class LanceDBConnection(DBConnection):
             A list of table names.
         """
         try:
-            filesystem, path = fs_from_uri(self.uri)
+            filesystem = fs_from_uri(self.uri)[0]
         except pa.ArrowInvalid:
             raise NotImplementedError("Unsupported scheme: " + self.uri)
 
         try:
-            paths = filesystem.get_file_info(
-                fs.FileSelector(get_uri_location(self.uri))
-            )
+            loc = get_uri_location(self.uri)
+            paths = filesystem.get_file_info(fs.FileSelector(loc))
         except FileNotFoundError:
             # It is ok if the file does not exist since it will be created
             paths = []
@@ -373,7 +372,7 @@ class LanceDBConnection(DBConnection):
         """
         try:
             filesystem, path = fs_from_uri(self.uri)
-            table_path = os.path.join(path, name + ".lance")
+            table_path = join_uri(path, name + ".lance")
             filesystem.delete_dir(table_path)
         except FileNotFoundError:
             if not ignore_missing:

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/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}."
     )
 
 
@@ -194,10 +199,10 @@ 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 inspect.isclass(field.annotation):
         if issubclass(field.annotation, pydantic.BaseModel):
             # Struct
@@ -205,7 +210,7 @@ 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:

python/lancedb/query.py

@@ -488,6 +488,27 @@ class LanceFtsQueryBuilder(LanceQueryBuilder):
         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/table.py

@@ -64,6 +64,12 @@ class RemoteTable(Table):
         """to_pandas() is not supported on the LanceDB cloud"""
         return NotImplementedError("to_pandas() is not supported on the LanceDB cloud")
 
+    def create_scalar_index(self, *args, **kwargs):
+        """Creates a scalar index"""
+        return NotImplementedError(
+            "create_scalar_index() is not supported on the LanceDB cloud"
+        )
+
     def create_index(
         self,
         metric="L2",

python/lancedb/table.py

@@ -23,6 +23,7 @@ import lance
 import numpy as np
 import pyarrow as pa
 import pyarrow.compute as pc
+import pyarrow.fs as pa_fs
 from lance import LanceDataset
 from lance.vector import vec_to_table
 
@@ -30,7 +31,7 @@ from .common import DATA, VEC, VECTOR_COLUMN_NAME
 from .embeddings import EmbeddingFunctionConfig, EmbeddingFunctionRegistry
 from .pydantic import LanceModel, model_to_dict
 from .query import LanceQueryBuilder, Query
-from .util import fs_from_uri, safe_import_pandas, value_to_sql
+from .util import fs_from_uri, safe_import_pandas, value_to_sql, join_uri
 from .utils.events import register_event
 
 if TYPE_CHECKING:
@@ -220,6 +221,77 @@ class Table(ABC):
         """
         raise NotImplementedError
 
+    @abstractmethod
+    def create_scalar_index(
+        self,
+        column: str,
+        *,
+        replace: bool = True,
+    ):
+        """Create a scalar index on a column.
+
+        Scalar indices, like vector indices, can be used to speed up scans.  A scalar
+        index can speed up scans that contain filter expressions on the indexed column.
+        For example, the following scan will be faster if the column ``my_col`` has
+        a scalar index:
+
+        .. code-block:: python
+
+            import lancedb
+
+            db = lancedb.connect("/data/lance")
+            img_table = db.open_table("images")
+            my_df = img_table.search().where("my_col = 7", prefilter=True).to_pandas()
+
+        Scalar indices can also speed up scans containing a vector search and a
+        prefilter:
+
+        .. code-block::python
+
+            import lancedb
+
+            db = lancedb.connect("/data/lance")
+            img_table = db.open_table("images")
+            img_table.search([1, 2, 3, 4], vector_column_name="vector")
+                .where("my_col != 7", prefilter=True)
+                .to_pandas()
+
+        Scalar indices can only speed up scans for basic filters using
+        equality, comparison, range (e.g. ``my_col BETWEEN 0 AND 100``), and set
+        membership (e.g. `my_col IN (0, 1, 2)`)
+
+        Scalar indices can be used if the filter contains multiple indexed columns and
+        the filter criteria are AND'd or OR'd together
+        (e.g. ``my_col < 0 AND other_col> 100``)
+
+        Scalar indices may be used if the filter contains non-indexed columns but,
+        depending on the structure of the filter, they may not be usable.  For example,
+        if the column ``not_indexed`` does not have a scalar index then the filter
+        ``my_col = 0 OR not_indexed = 1`` will not be able to use any scalar index on
+        ``my_col``.
+
+        **Experimental API**
+
+        Parameters
+        ----------
+        column : str
+            The column to be indexed.  Must be a boolean, integer, float,
+            or string column.
+        replace : bool, default True
+            Replace the existing index if it exists.
+
+        Examples
+        --------
+
+        .. code-block:: python
+
+            import lance
+
+            dataset = lance.dataset("/tmp/images.lance")
+            dataset.create_scalar_index("category")
+        """
+        raise NotImplementedError
+
     @abstractmethod
     def add(
         self,
@@ -439,6 +511,7 @@ class Table(ABC):
         """
         raise NotImplementedError
 
+
 class LanceTable(Table):
     """
     A table in a LanceDB database.
@@ -606,7 +679,7 @@ class LanceTable(Table):
 
     @property
     def _dataset_uri(self) -> str:
-        return os.path.join(self._conn.uri, f"{self.name}.lance")
+        return join_uri(self._conn.uri, f"{self.name}.lance")
 
     def create_index(
         self,
@@ -632,7 +705,12 @@ class LanceTable(Table):
         self._reset_dataset()
         register_event("create_index")
 
-    def create_fts_index(self, field_names: Union[str, List[str]]):
+    def create_scalar_index(self, column: str, *, replace: bool = True):
+        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
+    ):
         """Create a full-text search index on the table.
 
         Warning - this API is highly experimental and is highly likely to change
@@ -642,17 +720,31 @@ class LanceTable(Table):
         ----------
         field_names: str or list of str
             The name(s) of the field to index.
+        replace: bool, default False
+            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.
         """
         from .fts import create_index, populate_index
 
         if isinstance(field_names, str):
             field_names = [field_names]
+
+        fs, path = fs_from_uri(self._get_fts_index_path())
+        index_exists = fs.get_file_info(path).type != pa_fs.FileType.NotFound
+        if index_exists:
+            if not replace:
+                raise ValueError(
+                    f"Index already exists. Use replace=True to overwrite."
+                )
+            fs.delete_dir(path)
+
         index = create_index(self._get_fts_index_path(), field_names)
         populate_index(index, self, field_names)
         register_event("create_fts_index")
 
     def _get_fts_index_path(self):
-        return os.path.join(self._dataset_uri, "_indices", "tantivy")
+        return join_uri(self._dataset_uri, "_indices", "tantivy")
 
     @cached_property
     def _dataset(self) -> LanceDataset:

python/lancedb/util.py

@@ -14,7 +14,8 @@
 import os
 from datetime import date, datetime
 from functools import singledispatch
-from typing import Tuple
+import pathlib
+from typing import Tuple, Union
 from urllib.parse import urlparse
 
 import numpy as np
@@ -62,6 +63,12 @@ def get_uri_location(uri: str) -> str:
     str: Location part of the URL, without scheme
     """
     parsed = urlparse(uri)
+    if len(parsed.scheme) == 1:
+        # Windows drive names are parsed as the scheme
+        # e.g. "c:\path" -> ParseResult(scheme="c", netloc="", path="/path", ...)
+        # So we add special handling here for schemes that are a single character
+        return uri
+
     if not parsed.netloc:
         return parsed.path
     else:
@@ -84,6 +91,29 @@ def fs_from_uri(uri: str) -> Tuple[pa_fs.FileSystem, str]:
     return pa_fs.FileSystem.from_uri(uri)
 
 
+def join_uri(base: Union[str, pathlib.Path], *parts: str) -> str:
+    """
+    Join a URI with multiple parts, handles both local and remote paths
+
+    Parameters
+    ----------
+    base : str
+        The base URI
+    parts : str
+        The parts to join to the base URI, each separated by the
+        appropriate path separator for the URI scheme and OS
+    """
+    if isinstance(base, pathlib.Path):
+        return base.joinpath(*parts)
+    base = str(base)
+    if get_uri_scheme(base) == "file":
+        # using pathlib for local paths make this windows compatible
+        # `get_uri_scheme` returns `file` for windows drive names (e.g. `c:\path`)
+        return str(pathlib.Path(base, *parts))
+    # for remote paths, just use os.path.join
+    return "/".join([p.rstrip("/") for p in [base, *parts]])
+
+
 def safe_import_pandas():
     try:
         import pandas as pd

python/pyproject.toml

@@ -1,9 +1,9 @@
 [project]
 name = "lancedb"
-version = "0.4.0"
+version = "0.4.2"
 dependencies = [
     "deprecation",
-    "pylance==0.9.0",
+    "pylance==0.9.1",
     "ratelimiter~=1.0",
     "retry>=0.9.2",
     "tqdm>=4.27.0",
@@ -49,11 +49,11 @@ classifiers = [
 repository = "https://github.com/lancedb/lancedb"
 
 [project.optional-dependencies]
-tests = ["pandas>=1.4", "pytest", "pytest-mock", "pytest-asyncio", "requests"]
+tests = ["pandas>=1.4", "pytest", "pytest-mock", "pytest-asyncio", "requests", "duckdb", "pytz"]
 dev = ["ruff", "pre-commit", "black"]
 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"

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],
@@ -83,6 +85,25 @@ def test_create_index_from_table(tmp_path, table):
     assert len(df) == 10
     assert "text" in df.columns
 
+    # Check whether it can be updated
+    table.add(
+        [
+            {
+                "vector": np.random.randn(128),
+                "id": 101,
+                "text": "gorilla",
+                "text2": "gorilla",
+                "nested": {"text": "gorilla"},
+            }
+        ]
+    )
+
+    with pytest.raises(ValueError, match="already exists"):
+        table.create_fts_index("text")
+
+    table.create_fts_index("text", replace=True)
+    assert len(table.search("gorilla").limit(1).to_pandas()) == 1
+
 
 def test_create_index_multiple_columns(tmp_path, table):
     table.create_fts_index(["text", "text2"])
@@ -103,3 +124,26 @@ 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

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 +82,16 @@ 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, 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 +102,13 @@ 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 +116,12 @@ 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 +132,8 @@ 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 +144,7 @@ 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_table.py

@@ -21,8 +21,8 @@ import lance
 import numpy as np
 import pandas as pd
 import pyarrow as pa
-from pydantic import BaseModel
 import pytest
+from pydantic import BaseModel
 
 from lancedb.conftest import MockTextEmbeddingFunction
 from lancedb.db import LanceDBConnection
@@ -532,6 +532,33 @@ def test_multiple_vector_columns(db):
     assert result1["text"].iloc[0] != result2["text"].iloc[0]
 
 
+def test_create_scalar_index(db):
+    vec_array = pa.array(
+        [[1, 1], [2, 2], [3, 3], [4, 4], [5, 5]], pa.list_(pa.float32(), 2)
+    )
+    test_data = pa.Table.from_pydict(
+        {"x": ["c", "b", "a", "e", "b"], "y": [1, 2, 3, 4, 5], "vector": vec_array}
+    )
+    table = LanceTable.create(
+        db,
+        "my_table",
+        data=test_data,
+    )
+    table.create_scalar_index("x")
+    indices = table.to_lance().list_indices()
+    assert len(indices) == 1
+    scalar_index = indices[0]
+    assert scalar_index["type"] == "Scalar"
+
+    # Confirm that prefiltering still works with the scalar index column
+    results = table.search().where("x = 'c'").to_arrow()
+    assert results == test_data.slice(0, 1)
+    results = table.search([5, 5]).to_arrow()
+    assert results["_distance"][0].as_py() == 0
+    results = table.search([5, 5]).where("x != 'b'").to_arrow()
+    assert results["_distance"][0].as_py() > 0
+
+
 def test_empty_query(db):
     table = LanceTable.create(
         db,

python/tests/test_util.py

@@ -11,7 +11,12 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 
-from lancedb.util import get_uri_scheme
+import os
+import pathlib
+
+import pytest
+
+from lancedb.util import get_uri_scheme, join_uri
 
 
 def test_normalize_uri():
@@ -28,3 +33,55 @@ def test_normalize_uri():
     for uri, expected_scheme in zip(uris, schemes):
         parsed_scheme = get_uri_scheme(uri)
         assert parsed_scheme == expected_scheme
+
+
+def test_join_uri_remote():
+    schemes = ["s3", "az", "gs"]
+    for scheme in schemes:
+        expected = f"{scheme}://bucket/path/to/table.lance"
+        base_uri = f"{scheme}://bucket/path/to/"
+        parts = ["table.lance"]
+        assert join_uri(base_uri, *parts) == expected
+
+        base_uri = f"{scheme}://bucket"
+        parts = ["path", "to", "table.lance"]
+        assert join_uri(base_uri, *parts) == expected
+
+
+# skip this test if on windows
+@pytest.mark.skipif(os.name == "nt", reason="Windows paths are not POSIX")
+def test_join_uri_posix():
+    for base in [
+        # relative path
+        "relative/path",
+        "relative/path/",
+        # an absolute path
+        "/absolute/path",
+        "/absolute/path/",
+        # a file URI
+        "file:///absolute/path",
+        "file:///absolute/path/",
+    ]:
+        joined = join_uri(base, "table.lance")
+        assert joined == str(pathlib.Path(base) / "table.lance")
+        joined = join_uri(pathlib.Path(base), "table.lance")
+        assert joined == pathlib.Path(base) / "table.lance"
+
+
+# skip this test if not on windows
+@pytest.mark.skipif(os.name != "nt", reason="Windows paths are not POSIX")
+def test_local_join_uri_windows():
+    # https://learn.microsoft.com/en-us/dotnet/standard/io/file-path-formats
+    for base in [
+        # windows relative path
+        "relative\\path",
+        "relative\\path\\",
+        # windows absolute path from current drive
+        "c:\\absolute\\path",
+        # relative path from root of current drive
+        "\\relative\\path",
+    ]:
+        joined = join_uri(base, "table.lance")
+        assert joined == str(pathlib.Path(base) / "table.lance")
+        joined = join_uri(pathlib.Path(base), "table.lance")
+        assert joined == pathlib.Path(base) / "table.lance"

rust/ffi/node/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "vectordb-node"
-version = "0.4.0"
+version = "0.4.1"
 description = "Serverless, low-latency vector database for AI applications"
 license = "Apache-2.0"
 edition = "2018"

rust/ffi/node/src/error.rs

@@ -23,7 +23,7 @@ pub enum Error {
     #[snafu(display("column '{name}' is missing"))]
     MissingColumn { name: String },
     #[snafu(display("{name}: {message}"))]
-    RangeError { name: String, message: String },
+    OutOfRange { name: String, message: String },
     #[snafu(display("{index_type} is not a valid index type"))]
     InvalidIndexType { index_type: String },
 

rust/ffi/node/src/index.rs

@@ -12,4 +12,5 @@
 // See the License for the specific language governing permissions and
 // limitations under the License.
 
+pub mod scalar;
 pub mod vector;

rust/ffi/node/src/index/scalar.rs

@@ -0,0 +1,43 @@
+// Copyright 2023 Lance Developers.
+//
+// Licensed under the Apache License, Version 2.0 (the "License");
+// you may not use this file except in compliance with the License.
+// You may obtain a copy of the License at
+//
+//     http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing, software
+// distributed under the License is distributed on an "AS IS" BASIS,
+// 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.
+
+use neon::{
+    context::{Context, FunctionContext},
+    result::JsResult,
+    types::{JsBoolean, JsBox, JsPromise, JsString},
+};
+
+use crate::{error::ResultExt, runtime, table::JsTable};
+
+pub(crate) fn table_create_scalar_index(mut cx: FunctionContext) -> JsResult<JsPromise> {
+    let js_table = cx.this().downcast_or_throw::<JsBox<JsTable>, _>(&mut cx)?;
+    let column = cx.argument::<JsString>(0)?.value(&mut cx);
+    let replace = cx.argument::<JsBoolean>(1)?.value(&mut cx);
+
+    let rt = runtime(&mut cx)?;
+
+    let (deferred, promise) = cx.promise();
+    let channel = cx.channel();
+    let mut table = js_table.table.clone();
+
+    rt.spawn(async move {
+        let idx_result = table.create_scalar_index(&column, replace).await;
+
+        deferred.settle_with(&channel, move |mut cx| {
+            idx_result.or_throw(&mut cx)?;
+            Ok(cx.undefined())
+        });
+    });
+    Ok(promise)
+}

rust/ffi/node/src/index/vector.rs

@@ -65,12 +65,10 @@ fn get_index_params_builder(
             obj.get_opt::<JsString, _, _>(cx, "index_name")?
                 .map(|s| index_builder.index_name(s.value(cx)));
 
-            obj.get_opt::<JsString, _, _>(cx, "metric_type")?
-                .map(|s| MetricType::try_from(s.value(cx).as_str()))
-                .map(|mt| {
-                    let metric_type = mt.unwrap();
-                    index_builder.metric_type(metric_type);
-                });
+            if let Some(metric_type) = obj.get_opt::<JsString, _, _>(cx, "metric_type")? {
+                let metric_type = MetricType::try_from(metric_type.value(cx).as_str()).unwrap();
+                index_builder.metric_type(metric_type);
+            }
 
             let num_partitions = obj.get_opt_usize(cx, "num_partitions")?;
             let max_iters = obj.get_opt_usize(cx, "max_iters")?;
@@ -85,23 +83,29 @@ fn get_index_params_builder(
                 index_builder.ivf_params(ivf_params)
             });
 
-            obj.get_opt::<JsBoolean, _, _>(cx, "use_opq")?
-                .map(|s| pq_params.use_opq = s.value(cx));
+            if let Some(use_opq) = obj.get_opt::<JsBoolean, _, _>(cx, "use_opq")? {
+                pq_params.use_opq = use_opq.value(cx);
+            }
 
-            obj.get_opt_usize(cx, "num_sub_vectors")?
-                .map(|s| pq_params.num_sub_vectors = s);
+            if let Some(num_sub_vectors) = obj.get_opt_usize(cx, "num_sub_vectors")? {
+                pq_params.num_sub_vectors = num_sub_vectors;
+            }
 
-            obj.get_opt_usize(cx, "num_bits")?
-                .map(|s| pq_params.num_bits = s);
+            if let Some(num_bits) = obj.get_opt_usize(cx, "num_bits")? {
+                pq_params.num_bits = num_bits;
+            }
 
-            obj.get_opt_usize(cx, "max_iters")?
-                .map(|s| pq_params.max_iters = s);
+            if let Some(max_iters) = obj.get_opt_usize(cx, "max_iters")? {
+                pq_params.max_iters = max_iters;
+            }
 
-            obj.get_opt_usize(cx, "max_opq_iters")?
-                .map(|s| pq_params.max_opq_iters = s);
+            if let Some(max_opq_iters) = obj.get_opt_usize(cx, "max_opq_iters")? {
+                pq_params.max_opq_iters = max_opq_iters;
+            }
 
-            obj.get_opt::<JsBoolean, _, _>(cx, "replace")?
-                .map(|s| index_builder.replace(s.value(cx)));
+            if let Some(replace) = obj.get_opt::<JsBoolean, _, _>(cx, "replace")? {
+                index_builder.replace(replace.value(cx));
+            }
 
             Ok(index_builder)
         }

rust/ffi/node/src/lib.rs

@@ -242,6 +242,10 @@ fn main(mut cx: ModuleContext) -> NeonResult<()> {
     cx.export_function("tableCompactFiles", JsTable::js_compact)?;
     cx.export_function("tableListIndices", JsTable::js_list_indices)?;
     cx.export_function("tableIndexStats", JsTable::js_index_stats)?;
+    cx.export_function(
+        "tableCreateScalarIndex",
+        index::scalar::table_create_scalar_index,
+    )?;
     cx.export_function(
         "tableCreateVectorIndex",
         index::vector::table_create_vector_index,

rust/ffi/node/src/neon_ext/js_object_ext.rs

@@ -47,15 +47,15 @@ fn f64_to_u32_safe(n: f64, key: &str) -> Result<u32> {
     use conv::*;
 
     n.approx_as::<u32>().map_err(|e| match e {
-        FloatError::NegOverflow(_) => Error::RangeError {
+        FloatError::NegOverflow(_) => Error::OutOfRange {
             name: key.into(),
             message: "must be > 0".to_string(),
         },
-        FloatError::PosOverflow(_) => Error::RangeError {
+        FloatError::PosOverflow(_) => Error::OutOfRange {
             name: key.into(),
             message: format!("must be < {}", u32::MAX),
         },
-        FloatError::NotANumber(_) => Error::RangeError {
+        FloatError::NotANumber(_) => Error::OutOfRange {
             name: key.into(),
             message: "not a valid number".to_string(),
         },
@@ -66,15 +66,15 @@ fn f64_to_usize_safe(n: f64, key: &str) -> Result<usize> {
     use conv::*;
 
     n.approx_as::<usize>().map_err(|e| match e {
-        FloatError::NegOverflow(_) => Error::RangeError {
+        FloatError::NegOverflow(_) => Error::OutOfRange {
             name: key.into(),
             message: "must be > 0".to_string(),
         },
-        FloatError::PosOverflow(_) => Error::RangeError {
+        FloatError::PosOverflow(_) => Error::OutOfRange {
             name: key.into(),
             message: format!("must be < {}", usize::MAX),
         },
-        FloatError::NotANumber(_) => Error::RangeError {
+        FloatError::NotANumber(_) => Error::OutOfRange {
             name: key.into(),
             message: "not a valid number".to_string(),
         },

rust/ffi/node/src/query.rs

@@ -25,11 +25,11 @@ impl JsQuery {
         let limit = query_obj
             .get_opt::<JsNumber, _, _>(&mut cx, "_limit")?
             .map(|value| {
-                let limit = value.value(&mut cx) as u64;
-                if limit <= 0 {
+                let limit = value.value(&mut cx);
+                if limit <= 0.0 {
                     panic!("Limit must be a positive integer");
                 }
-                limit
+                limit as u64
             });
         let select = query_obj
             .get_opt::<JsArray, _, _>(&mut cx, "_select")?
@@ -73,7 +73,7 @@ impl JsQuery {
 
         rt.spawn(async move {
             let mut builder = table
-                .search(query.map(|q| Float32Array::from(q)))
+                .search(query.map(Float32Array::from))
                 .refine_factor(refine_factor)
                 .nprobes(nprobes)
                 .filter(filter)

rust/ffi/node/src/table.rs

@@ -45,7 +45,7 @@ impl JsTable {
         let table_name = cx.argument::<JsString>(0)?.value(&mut cx);
         let buffer = cx.argument::<JsBuffer>(1)?;
         let (batches, schema) =
-            arrow_buffer_to_record_batch(buffer.as_slice(&mut cx)).or_throw(&mut cx)?;
+            arrow_buffer_to_record_batch(buffer.as_slice(&cx)).or_throw(&mut cx)?;
 
         // Write mode
         let mode = match cx.argument::<JsString>(2)?.value(&mut cx).as_str() {
@@ -93,7 +93,7 @@ impl JsTable {
         let buffer = cx.argument::<JsBuffer>(0)?;
         let write_mode = cx.argument::<JsString>(1)?.value(&mut cx);
         let (batches, schema) =
-            arrow_buffer_to_record_batch(buffer.as_slice(&mut cx)).or_throw(&mut cx)?;
+            arrow_buffer_to_record_batch(buffer.as_slice(&cx)).or_throw(&mut cx)?;
         let rt = runtime(&mut cx)?;
         let channel = cx.channel();
         let mut table = js_table.table.clone();
@@ -186,7 +186,7 @@ impl JsTable {
                 .downcast_or_throw::<JsString, _>(&mut cx)?;
 
             let value = updates_arg
-                .get_value(&mut cx, property.clone())?
+                .get_value(&mut cx, property)?
                 .downcast_or_throw::<JsString, _>(&mut cx)?;
 
             let property = property.value(&mut cx);
@@ -216,7 +216,7 @@ impl JsTable {
                 .map(|(k, v)| (k.as_str(), v.as_str()))
                 .collect::<Vec<_>>();
 
-            let predicate = predicate.as_ref().map(|s| s.as_str());
+            let predicate = predicate.as_deref();
 
             let update_result = table.update(predicate, updates_arg).await;
             deferred.settle_with(&channel, move |mut cx| {

rust/vectordb/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "vectordb"
-version = "0.4.0"
+version = "0.4.1"
 edition = "2021"
 description = "LanceDB: A serverless, low-latency vector database for AI applications"
 license = "Apache-2.0"

rust/vectordb/src/io/object_store.rs

@@ -26,7 +26,7 @@ use futures::{stream::BoxStream, FutureExt, StreamExt};
 use lance::io::object_store::WrappingObjectStore;
 use object_store::{
     path::Path, Error, GetOptions, GetResult, ListResult, MultipartId, ObjectMeta, ObjectStore,
-    Result,
+    PutOptions, PutResult, Result,
 };
 
 use async_trait::async_trait;
@@ -72,13 +72,28 @@ impl PrimaryOnly for Path {
 /// Note: this object store does not mirror writes to *.manifest files
 #[async_trait]
 impl ObjectStore for MirroringObjectStore {
-    async fn put(&self, location: &Path, bytes: Bytes) -> Result<()> {
+    async fn put(&self, location: &Path, bytes: Bytes) -> Result<PutResult> {
         if location.primary_only() {
             self.primary.put(location, bytes).await
         } else {
             self.secondary.put(location, bytes.clone()).await?;
-            self.primary.put(location, bytes).await?;
-            Ok(())
+            self.primary.put(location, bytes).await
+        }
+    }
+
+    async fn put_opts(
+        &self,
+        location: &Path,
+        bytes: Bytes,
+        options: PutOptions,
+    ) -> Result<PutResult> {
+        if location.primary_only() {
+            self.primary.put_opts(location, bytes, options).await
+        } else {
+            self.secondary
+                .put_opts(location, bytes.clone(), options.clone())
+                .await?;
+            self.primary.put_opts(location, bytes, options).await
         }
     }
 
@@ -129,8 +144,8 @@ impl ObjectStore for MirroringObjectStore {
         self.primary.delete(location).await
     }
 
-    async fn list(&self, prefix: Option<&Path>) -> Result<BoxStream<'_, Result<ObjectMeta>>> {
-        self.primary.list(prefix).await
+    fn list(&self, prefix: Option<&Path>) -> BoxStream<'_, Result<ObjectMeta>> {
+        self.primary.list(prefix)
     }
 
     async fn list_with_delimiter(&self, prefix: Option<&Path>) -> Result<ListResult> {

rust/vectordb/src/table.rs

@@ -14,6 +14,7 @@
 
 use chrono::Duration;
 use lance::dataset::builder::DatasetBuilder;
+use lance::index::scalar::ScalarIndexParams;
 use lance_index::IndexType;
 use std::sync::Arc;
 
@@ -262,6 +263,16 @@ impl Table {
         Ok(())
     }
 
+    /// Create a scalar index on the table
+    pub async fn create_scalar_index(&mut self, column: &str, replace: bool) -> Result<()> {
+        let mut dataset = self.dataset.as_ref().clone();
+        let params = ScalarIndexParams::default();
+        dataset
+            .create_index(&[column], IndexType::Scalar, None, &params, replace)
+            .await?;
+        Ok(())
+    }
+
     pub async fn optimize_indices(&mut self) -> Result<()> {
         let mut dataset = self.dataset.as_ref().clone();