Compare commits

...

21 Commits

Author SHA1 Message Date
Lance Release
392777952f [python] Bump version: 0.4.1 → 0.4.2 2023-12-29 00:19:21 +00:00
Chang She
7e75e50d3a chore(python): update embedding API to use openai 1.6.1 (#751)
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.
2023-12-28 15:05:57 -08:00
Chang She
4b8af261a3 feat: add timezone handling for datetime in pydantic (#578)
If you add timezone information in the Field annotation for a datetime
then that will now be passed to the pyarrow data type.

I'm not sure how pyarrow enforces timezones, right now, it silently
coerces to the timezone given in the column regardless of whether the
input had the matching timezone or not. This is probably not the right
behavior. Though we could just make it so the user has to make the
pydantic model do the validation instead of doing that at the pyarrow
conversion layer.
2023-12-28 11:02:56 -08:00
Chang She
c8728d4ca1 feat(python): add post filtering for full text search (#739)
Closes #721 

fts will return results as a pyarrow table. Pyarrow tables has a
`filter` method but it does not take sql filter strings (only pyarrow
compute expressions). Instead, we do one of two things to support
`tbl.search("keywords").where("foo=5").limit(10).to_arrow()`:

Default path: If duckdb is available then use duckdb to execute the sql
filter string on the pyarrow table.
Backup path: Otherwise, write the pyarrow table to a lance dataset and
then do `to_table(filter=<filter>)`

Neither is ideal. 
Default path has two issues:
1. requires installing an extra library (duckdb)
2. duckdb mangles some fields (like fixed size list => list)

Backup path incurs a latency penalty (~20ms on ssd) to write the
resultset to disk.

In the short term, once #676 is addressed, we can write the dataset to
"memory://" instead of disk, this makes the post filter evaluate much
quicker (ETA next week).

In the longer term, we'd like to be able to evaluate the filter string
on the pyarrow Table directly, one possibility being that we use
Substrait to generate pyarrow compute expressions from sql string. Or if
there's enough progress on pyarrow, it could support Substrait
expressions directly (no ETA)

---------

Co-authored-by: Will Jones <willjones127@gmail.com>
2023-12-27 09:31:04 -08:00
Aidan
446f837335 fix: createIndex index cache size (#741) 2023-12-27 09:25:13 -08:00
Chang She
8f9ad978f5 feat(python): support list of list fields from pydantic schema (#747)
For object detection, each row may correspond to an image and each image
can have multiple bounding boxes of x-y coordinates. This means that a
`bbox` field is potentially "list of list of float". This adds support
in our pydantic-pyarrow conversion for nested lists.
2023-12-27 09:10:09 -08:00
Lance Release
0df38341d5 Updating package-lock.json 2023-12-26 17:21:51 +00:00
Lance Release
60260018cf [python] Bump version: 0.4.0 → 0.4.1 2023-12-26 16:51:16 +00:00
Lance Release
bb100c5c19 Bump version: 0.4.0 → 0.4.1 2023-12-26 16:51:09 +00:00
elliottRobinson
eab9072bb5 Update default_embedding_functions.md (#744)
Modify some grammar, punctuation, and spelling errors.
2023-12-26 19:24:22 +05:30
Will Jones
ee0f0611d9 docs: update node API reference (#734)
This command hasn't been run for a while...
2023-12-22 10:14:31 -08:00
Will Jones
34966312cb docs: enhance Update user guide (#735)
Closes #705
2023-12-22 10:14:21 -08:00
Bert
756188358c docs: fix JS api docs for update method (#738) 2023-12-21 13:48:00 -05:00
Weston Pace
dc5126d8d1 feat: add the ability to create scalar indices (#679)
This is a pretty direct binding to the underlying lance capability
2023-12-21 09:50:10 -08:00
Aidan
50c20af060 feat: node list tables pagination (#733) 2023-12-21 11:37:19 -05:00
Chang She
0965d7dd5a doc(javascript): minor improvement on docs for working with tables (#736)
Closes #639 
Closes #638
2023-12-20 20:05:22 -08:00
Chang She
7bbb2872de bug(python): fix path handling in windows (#724)
Use pathlib for local paths so that pathlib
can handle the correct separator on windows.

Closes #703

---------

Co-authored-by: Will Jones <willjones127@gmail.com>
2023-12-20 15:41:36 -08:00
Will Jones
e81d2975da chore: add issue templates (#732)
This PR adds issue templates, which help two recurring issues:

* Users forget to tell us whether they are using the Node or Python SDK
* Issues don't get appropriate tags

This doesn't force the use of the templates. Because we set
`blank_issues_enabled: true`, users can still create a custom issue.
2023-12-20 15:15:24 -08:00
Will Jones
2c7f96ba4f ci: check formatting and clippy (#730) 2023-12-20 13:37:51 -08:00
Will Jones
f9dd7a5d8a fix: prevent duplicate data in FTS index (#728)
This forces the user to replace the whole FTS directory when re-creating
the index, prevent duplicate data from being created. Previously, the
whole dataset was re-added to the existing index, duplicating existing
rows in the index.

This (in combination with lancedb/lance#1707) caused #726, since the
duplicate data emitted duplicate indices for `take()` and an upstream
issue caused those queries to fail.

This solution isn't ideal, since it makes the FTS index temporarily
unavailable while the index is built. In the future, we should have
multiple FTS index directories, which would allow atomic commits of new
indexes (as well as multiple indexes for different columns).

Fixes #498.
Fixes #726.

---------

Co-authored-by: Chang She <759245+changhiskhan@users.noreply.github.com>
2023-12-20 13:07:07 -08:00
Will Jones
1d4943688d upgrade lance to v0.9.1 (#727)
This brings in some important bugfixes related to take and aarch64
Linux. See changes at:
https://github.com/lancedb/lance/releases/tag/v0.9.1
2023-12-20 13:06:54 -08:00
71 changed files with 2250 additions and 514 deletions

View File

@@ -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

33
.github/ISSUE_TEMPLATE/bug-node.yml vendored Normal file
View File

@@ -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

33
.github/ISSUE_TEMPLATE/bug-python.yml vendored Normal file
View File

@@ -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

5
.github/ISSUE_TEMPLATE/config.yml vendored Normal file
View File

@@ -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.

View File

@@ -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

31
.github/ISSUE_TEMPLATE/feature.yml vendored Normal file
View File

@@ -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

View File

@@ -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

View File

@@ -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

View File

@@ -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"

View File

@@ -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

View File

@@ -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.

View File

@@ -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.

View File

@@ -1,5 +1,7 @@
<a href="https://colab.research.google.com/github/lancedb/lancedb/blob/main/docs/src/notebooks/tables_guide.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a><br/>
A Table is a collection of Records in a LanceDB Database. You can follow along on colab!
A Table is a collection of Records in a LanceDB Database. Tables in Lance have a schema that defines the columns and their types. These schemas can include nested columns and can evolve over time.
This guide will show how to create tables, insert data into them, and update the data. You can follow along on colab!
## Creating a LanceDB Table
@@ -116,6 +118,84 @@ A Table is a collection of Records in a LanceDB Database. You can follow along o
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()`
@@ -151,7 +231,7 @@ A Table is a collection of Records in a LanceDB Database. You can follow along o
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
@@ -201,8 +281,8 @@ A Table is a collection of Records in a LanceDB Database. You can follow along o
```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"
@@ -361,19 +441,28 @@ Use the `delete()` method on tables to delete rows from a table. To choose which
await tbl.countRows() // Returns 1
```
### Updating a Table [Experimental]
EXPERIMENTAL: Update rows in the table (not threadsafe).
## Updating a Table
This can be used to update zero to all rows depending on how many rows match the where clause.
This can be used to update zero to all rows depending on how many rows match the where clause. The update queries follow the form of a SQL UPDATE statement. The `where` parameter is a SQL filter that matches on the metadata columns. The `values` or `values_sql` parameters are used to provide the new values for the columns.
| Parameter | Type | Description |
| Parameter | Type | Description |
|---|---|---|
| `where` | `str` | The SQL where clause to use when updating rows. For example, `'x = 2'` or `'x IN (1, 2, 3)'`. The filter must not be empty, or it will error. |
| `values` | `dict` | The values to update. The keys are the column names and the values are the values to set. |
| `values_sql` | `dict` | The values to update. The keys are the column names and the values are the SQL expressions to set. For example, `{'x': 'x + 1'}` will increment the value of the `x` column by 1. |
!!! info "SQL syntax"
See [SQL filters](sql.md) for more information on the supported SQL syntax.
!!! warning "Warning"
Updating nested columns is not yet supported.
=== "Python"
API Reference: [lancedb.table.Table.update][]
```python
import lancedb
import pandas as pd
@@ -403,6 +492,55 @@ This can be used to update zero to all rows depending on how many rows match the
2 2 [10.0, 10.0]
```
=== "Javascript/Typescript"
API Reference: [vectordb.Table.update](../../javascript/interfaces/Table/#update)
```javascript
const lancedb = require("vectordb");
const db = await lancedb.connect("./.lancedb");
const data = [
{x: 1, vector: [1, 2]},
{x: 2, vector: [3, 4]},
{x: 3, vector: [5, 6]},
];
const tbl = await db.createTable("my_table", data)
await tbl.update({ where: "x = 2", values: {vector: [10, 10]} })
```
The `values` parameter is used to provide the new values for the columns as literal values. You can also use the `values_sql` / `valuesSql` parameter to provide SQL expressions for the new values. For example, you can use `values_sql="x + 1"` to increment the value of the `x` column by 1.
=== "Python"
```python
# Update the table where x = 2
table.update(valuesSql={"x": "x + 1"})
print(table.to_pandas())
```
Output
```shell
x vector
0 2 [1.0, 2.0]
1 4 [5.0, 6.0]
2 3 [10.0, 10.0]
```
=== "Javascript/Typescript"
```javascript
await tbl.update({ valuesSql: { x: "x + 1" } })
```
!!! info "Note"
When rows are updated, they are moved out of the index. The row will still show up in ANN queries, but the query will not be as fast as it would be if the row was in the index. If you update a large proportion of rows, consider rebuilding the index afterwards.
## What's Next?
Learn how to Query your tables and create indices

View File

@@ -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 Windows or 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

View File

@@ -0,0 +1,41 @@
[vectordb](../README.md) / [Exports](../modules.md) / DefaultWriteOptions
# Class: DefaultWriteOptions
Write options when creating a Table.
## Implements
- [`WriteOptions`](../interfaces/WriteOptions.md)
## Table of contents
### Constructors
- [constructor](DefaultWriteOptions.md#constructor)
### Properties
- [writeMode](DefaultWriteOptions.md#writemode)
## Constructors
### constructor
**new DefaultWriteOptions**()
## Properties
### writeMode
**writeMode**: [`WriteMode`](../enums/WriteMode.md) = `WriteMode.Create`
A [WriteMode](../enums/WriteMode.md) to use on this operation
#### Implementation of
[WriteOptions](../interfaces/WriteOptions.md).[writeMode](../interfaces/WriteOptions.md#writemode)
#### Defined in
[index.ts:778](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L778)

View File

@@ -26,7 +26,7 @@ A connection to a LanceDB database.
### Methods
- [createTable](LocalConnection.md#createtable)
- [createTableArrow](LocalConnection.md#createtablearrow)
- [createTableImpl](LocalConnection.md#createtableimpl)
- [dropTable](LocalConnection.md#droptable)
- [openTable](LocalConnection.md#opentable)
- [tableNames](LocalConnection.md#tablenames)
@@ -46,7 +46,7 @@ A connection to a LanceDB database.
#### Defined in
[index.ts:184](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L184)
[index.ts:355](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L355)
## Properties
@@ -56,17 +56,25 @@ A connection to a LanceDB database.
#### Defined in
[index.ts:182](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L182)
[index.ts:353](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L353)
___
### \_options
`Private` `Readonly` **\_options**: [`ConnectionOptions`](../interfaces/ConnectionOptions.md)
`Private` `Readonly` **\_options**: () => [`ConnectionOptions`](../interfaces/ConnectionOptions.md)
#### Type declaration
▸ (): [`ConnectionOptions`](../interfaces/ConnectionOptions.md)
##### Returns
[`ConnectionOptions`](../interfaces/ConnectionOptions.md)
#### Defined in
[index.ts:181](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L181)
[index.ts:352](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L352)
## Accessors
@@ -84,27 +92,34 @@ ___
#### Defined in
[index.ts:189](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L189)
[index.ts:360](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L360)
## Methods
### createTable
**createTable**(`name`, `data`, `mode?`): `Promise`<[`Table`](../interfaces/Table.md)<`number`[]\>\>
**createTable**\<`T`\>(`name`, `data?`, `optsOrEmbedding?`, `opt?`): `Promise`\<[`Table`](../interfaces/Table.md)\<`T`\>\>
Creates a new Table and initialize it with new data.
Creates a new Table, optionally initializing it with new data.
#### Type parameters
| Name |
| :------ |
| `T` |
#### 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. |
| Name | Type |
| :------ | :------ |
| `name` | `string` \| [`CreateTableOptions`](../interfaces/CreateTableOptions.md)\<`T`\> |
| `data?` | `Record`\<`string`, `unknown`\>[] |
| `optsOrEmbedding?` | [`WriteOptions`](../interfaces/WriteOptions.md) \| [`EmbeddingFunction`](../interfaces/EmbeddingFunction.md)\<`T`\> |
| `opt?` | [`WriteOptions`](../interfaces/WriteOptions.md) |
#### Returns
`Promise`<[`Table`](../interfaces/Table.md)<`number`[]\>\>
`Promise`\<[`Table`](../interfaces/Table.md)\<`T`\>\>
#### Implementation of
@@ -112,120 +127,44 @@ Creates a new Table and initialize it with new data.
#### Defined in
[index.ts:230](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L230)
**createTable**(`name`, `data`, `mode`): `Promise`<[`Table`](../interfaces/Table.md)<`number`[]\>\>
#### Parameters
| Name | Type |
| :------ | :------ |
| `name` | `string` |
| `data` | `Record`<`string`, `unknown`\>[] |
| `mode` | [`WriteMode`](../enums/WriteMode.md) |
#### Returns
`Promise`<[`Table`](../interfaces/Table.md)<`number`[]\>\>
#### Implementation of
Connection.createTable
#### Defined in
[index.ts:231](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L231)
**createTable**<`T`\>(`name`, `data`, `mode`, `embeddings`): `Promise`<[`Table`](../interfaces/Table.md)<`T`\>\>
Creates a new Table and initialize it with new data.
#### Type parameters
| Name |
| :------ |
| `T` |
#### 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. |
| `embeddings` | [`EmbeddingFunction`](../interfaces/EmbeddingFunction.md)<`T`\> | An embedding function to use on this Table |
#### Returns
`Promise`<[`Table`](../interfaces/Table.md)<`T`\>\>
#### Implementation of
Connection.createTable
#### Defined in
[index.ts:241](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L241)
**createTable**<`T`\>(`name`, `data`, `mode`, `embeddings?`): `Promise`<[`Table`](../interfaces/Table.md)<`T`\>\>
#### Type parameters
| Name |
| :------ |
| `T` |
#### Parameters
| Name | Type |
| :------ | :------ |
| `name` | `string` |
| `data` | `Record`<`string`, `unknown`\>[] |
| `mode` | [`WriteMode`](../enums/WriteMode.md) |
| `embeddings?` | [`EmbeddingFunction`](../interfaces/EmbeddingFunction.md)<`T`\> |
#### Returns
`Promise`<[`Table`](../interfaces/Table.md)<`T`\>\>
#### Implementation of
Connection.createTable
#### Defined in
[index.ts:242](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L242)
[index.ts:395](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L395)
___
### createTableArrow
### createTableImpl
**createTableArrow**(`name`, `table`): `Promise`<[`Table`](../interfaces/Table.md)<`number`[]\>\>
`Private` **createTableImpl**\<`T`\>(`«destructured»`): `Promise`\<[`Table`](../interfaces/Table.md)\<`T`\>\>
#### Type parameters
| Name |
| :------ |
| `T` |
#### Parameters
| Name | Type |
| :------ | :------ |
| `name` | `string` |
| `table` | `Table`<`any`\> |
| `«destructured»` | `Object` |
|  `data?` | `Table`\<`any`\> \| `Record`\<`string`, `unknown`\>[] |
|  `embeddingFunction?` | [`EmbeddingFunction`](../interfaces/EmbeddingFunction.md)\<`T`\> |
|  `name` | `string` |
|  `schema?` | `Schema`\<`any`\> |
|  `writeOptions?` | [`WriteOptions`](../interfaces/WriteOptions.md) |
#### Returns
`Promise`<[`Table`](../interfaces/Table.md)<`number`[]\>\>
#### Implementation of
[Connection](../interfaces/Connection.md).[createTableArrow](../interfaces/Connection.md#createtablearrow)
`Promise`\<[`Table`](../interfaces/Table.md)\<`T`\>\>
#### Defined in
[index.ts:266](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L266)
[index.ts:413](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L413)
___
### dropTable
**dropTable**(`name`): `Promise`<`void`\>
**dropTable**(`name`): `Promise`\<`void`\>
Drop an existing table.
@@ -237,7 +176,7 @@ Drop an existing table.
#### Returns
`Promise`<`void`\>
`Promise`\<`void`\>
#### Implementation of
@@ -245,13 +184,13 @@ Drop an existing table.
#### Defined in
[index.ts:276](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L276)
[index.ts:453](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L453)
___
### openTable
**openTable**(`name`): `Promise`<[`Table`](../interfaces/Table.md)<`number`[]\>\>
**openTable**(`name`): `Promise`\<[`Table`](../interfaces/Table.md)\<`number`[]\>\>
Open a table in the database.
@@ -263,7 +202,7 @@ Open a table in the database.
#### Returns
`Promise`<[`Table`](../interfaces/Table.md)<`number`[]\>\>
`Promise`\<[`Table`](../interfaces/Table.md)\<`number`[]\>\>
#### Implementation of
@@ -271,9 +210,9 @@ Open a table in the database.
#### Defined in
[index.ts:205](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L205)
[index.ts:376](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L376)
**openTable**<`T`\>(`name`, `embeddings`): `Promise`<[`Table`](../interfaces/Table.md)<`T`\>\>
**openTable**\<`T`\>(`name`, `embeddings`): `Promise`\<[`Table`](../interfaces/Table.md)\<`T`\>\>
Open a table in the database.
@@ -288,11 +227,11 @@ Open a table in the database.
| Name | Type | Description |
| :------ | :------ | :------ |
| `name` | `string` | The name of the table. |
| `embeddings` | [`EmbeddingFunction`](../interfaces/EmbeddingFunction.md)<`T`\> | An embedding function to use on this Table |
| `embeddings` | [`EmbeddingFunction`](../interfaces/EmbeddingFunction.md)\<`T`\> | An embedding function to use on this Table |
#### Returns
`Promise`<[`Table`](../interfaces/Table.md)<`T`\>\>
`Promise`\<[`Table`](../interfaces/Table.md)\<`T`\>\>
#### Implementation of
@@ -300,9 +239,9 @@ Connection.openTable
#### Defined in
[index.ts:212](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L212)
[index.ts:384](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L384)
**openTable**<`T`\>(`name`, `embeddings?`): `Promise`<[`Table`](../interfaces/Table.md)<`T`\>\>
**openTable**\<`T`\>(`name`, `embeddings?`): `Promise`\<[`Table`](../interfaces/Table.md)\<`T`\>\>
#### Type parameters
@@ -315,11 +254,11 @@ Connection.openTable
| Name | Type |
| :------ | :------ |
| `name` | `string` |
| `embeddings?` | [`EmbeddingFunction`](../interfaces/EmbeddingFunction.md)<`T`\> |
| `embeddings?` | [`EmbeddingFunction`](../interfaces/EmbeddingFunction.md)\<`T`\> |
#### Returns
`Promise`<[`Table`](../interfaces/Table.md)<`T`\>\>
`Promise`\<[`Table`](../interfaces/Table.md)\<`T`\>\>
#### Implementation of
@@ -327,19 +266,19 @@ Connection.openTable
#### Defined in
[index.ts:213](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L213)
[index.ts:385](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L385)
___
### tableNames
**tableNames**(): `Promise`<`string`[]\>
**tableNames**(): `Promise`\<`string`[]\>
Get the names of all tables in the database.
#### Returns
`Promise`<`string`[]\>
`Promise`\<`string`[]\>
#### Implementation of
@@ -347,4 +286,4 @@ Get the names of all tables in the database.
#### Defined in
[index.ts:196](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L196)
[index.ts:367](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L367)

View File

@@ -1,6 +1,6 @@
[vectordb](../README.md) / [Exports](../modules.md) / LocalTable
# Class: LocalTable<T\>
# Class: LocalTable\<T\>
A LanceDB Table is the collection of Records. Each Record has one or more vector fields.
@@ -12,7 +12,7 @@ A LanceDB Table is the collection of Records. Each Record has one or more vector
## Implements
- [`Table`](../interfaces/Table.md)<`T`\>
- [`Table`](../interfaces/Table.md)\<`T`\>
## Table of contents
@@ -26,6 +26,7 @@ A LanceDB Table is the collection of Records. Each Record has one or more vector
- [\_name](LocalTable.md#_name)
- [\_options](LocalTable.md#_options)
- [\_tbl](LocalTable.md#_tbl)
- [where](LocalTable.md#where)
### Accessors
@@ -34,17 +35,23 @@ A LanceDB Table is the collection of Records. Each Record has one or more vector
### Methods
- [add](LocalTable.md#add)
- [cleanupOldVersions](LocalTable.md#cleanupoldversions)
- [compactFiles](LocalTable.md#compactfiles)
- [countRows](LocalTable.md#countrows)
- [createIndex](LocalTable.md#createindex)
- [delete](LocalTable.md#delete)
- [filter](LocalTable.md#filter)
- [indexStats](LocalTable.md#indexstats)
- [listIndices](LocalTable.md#listindices)
- [overwrite](LocalTable.md#overwrite)
- [search](LocalTable.md#search)
- [update](LocalTable.md#update)
## Constructors
### constructor
**new LocalTable**<`T`\>(`tbl`, `name`, `options`)
**new LocalTable**\<`T`\>(`tbl`, `name`, `options`)
#### Type parameters
@@ -62,9 +69,9 @@ A LanceDB Table is the collection of Records. Each Record has one or more vector
#### Defined in
[index.ts:287](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L287)
[index.ts:464](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L464)
**new LocalTable**<`T`\>(`tbl`, `name`, `options`, `embeddings`)
**new LocalTable**\<`T`\>(`tbl`, `name`, `options`, `embeddings`)
#### Type parameters
@@ -79,21 +86,21 @@ A LanceDB Table is the collection of Records. Each Record has one or more vector
| `tbl` | `any` | |
| `name` | `string` | |
| `options` | [`ConnectionOptions`](../interfaces/ConnectionOptions.md) | |
| `embeddings` | [`EmbeddingFunction`](../interfaces/EmbeddingFunction.md)<`T`\> | An embedding function to use when interacting with this table |
| `embeddings` | [`EmbeddingFunction`](../interfaces/EmbeddingFunction.md)\<`T`\> | An embedding function to use when interacting with this table |
#### Defined in
[index.ts:294](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L294)
[index.ts:471](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L471)
## Properties
### \_embeddings
`Private` `Optional` `Readonly` **\_embeddings**: [`EmbeddingFunction`](../interfaces/EmbeddingFunction.md)<`T`\>
`Private` `Optional` `Readonly` **\_embeddings**: [`EmbeddingFunction`](../interfaces/EmbeddingFunction.md)\<`T`\>
#### Defined in
[index.ts:284](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L284)
[index.ts:461](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L461)
___
@@ -103,27 +110,61 @@ ___
#### Defined in
[index.ts:283](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L283)
[index.ts:460](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L460)
___
### \_options
`Private` `Readonly` **\_options**: [`ConnectionOptions`](../interfaces/ConnectionOptions.md)
`Private` `Readonly` **\_options**: () => [`ConnectionOptions`](../interfaces/ConnectionOptions.md)
#### Type declaration
▸ (): [`ConnectionOptions`](../interfaces/ConnectionOptions.md)
##### Returns
[`ConnectionOptions`](../interfaces/ConnectionOptions.md)
#### Defined in
[index.ts:285](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L285)
[index.ts:462](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L462)
___
### \_tbl
`Private` `Readonly` **\_tbl**: `any`
`Private` **\_tbl**: `any`
#### Defined in
[index.ts:282](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L282)
[index.ts:459](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L459)
___
### where
**where**: (`value`: `string`) => [`Query`](Query.md)\<`T`\>
#### Type declaration
▸ (`value`): [`Query`](Query.md)\<`T`\>
Creates a filter query to find all rows matching the specified criteria
##### Parameters
| Name | Type | Description |
| :------ | :------ | :------ |
| `value` | `string` | The filter criteria (like SQL where clause syntax) |
##### Returns
[`Query`](Query.md)\<`T`\>
#### Defined in
[index.ts:499](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L499)
## Accessors
@@ -141,13 +182,13 @@ ___
#### Defined in
[index.ts:302](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L302)
[index.ts:479](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L479)
## Methods
### add
**add**(`data`): `Promise`<`number`\>
**add**(`data`): `Promise`\<`number`\>
Insert records into this Table.
@@ -155,11 +196,11 @@ Insert records into this Table.
| Name | Type | Description |
| :------ | :------ | :------ |
| `data` | `Record`<`string`, `unknown`\>[] | Records to be inserted into the Table |
| `data` | `Record`\<`string`, `unknown`\>[] | Records to be inserted into the Table |
#### Returns
`Promise`<`number`\>
`Promise`\<`number`\>
The number of rows added to the table
@@ -169,19 +210,69 @@ The number of rows added to the table
#### Defined in
[index.ts:320](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L320)
[index.ts:507](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L507)
___
### cleanupOldVersions
**cleanupOldVersions**(`olderThan?`, `deleteUnverified?`): `Promise`\<[`CleanupStats`](../interfaces/CleanupStats.md)\>
Clean up old versions of the table, freeing disk space.
#### Parameters
| Name | Type | Description |
| :------ | :------ | :------ |
| `olderThan?` | `number` | The minimum age in minutes of the versions to delete. If not provided, defaults to two weeks. |
| `deleteUnverified?` | `boolean` | Because they may be part of an in-progress transaction, uncommitted files newer than 7 days old are not deleted by default. This means that failed transactions can leave around data that takes up disk space for up to 7 days. You can override this safety mechanism by setting this option to `true`, only if you promise there are no in progress writes while you run this operation. Failure to uphold this promise can lead to corrupted tables. |
#### Returns
`Promise`\<[`CleanupStats`](../interfaces/CleanupStats.md)\>
#### Defined in
[index.ts:596](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L596)
___
### compactFiles
**compactFiles**(`options?`): `Promise`\<[`CompactionMetrics`](../interfaces/CompactionMetrics.md)\>
Run the compaction process on the table.
This can be run after making several small appends to optimize the table
for faster reads.
#### Parameters
| Name | Type | Description |
| :------ | :------ | :------ |
| `options?` | [`CompactionOptions`](../interfaces/CompactionOptions.md) | Advanced options configuring compaction. In most cases, you can omit this arguments, as the default options are sensible for most tables. |
#### Returns
`Promise`\<[`CompactionMetrics`](../interfaces/CompactionMetrics.md)\>
Metrics about the compaction operation.
#### Defined in
[index.ts:615](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L615)
___
### countRows
**countRows**(): `Promise`<`number`\>
**countRows**(): `Promise`\<`number`\>
Returns the number of rows in this table.
#### Returns
`Promise`<`number`\>
`Promise`\<`number`\>
#### Implementation of
@@ -189,20 +280,16 @@ Returns the number of rows in this table.
#### Defined in
[index.ts:362](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L362)
[index.ts:543](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L543)
___
### createIndex
**createIndex**(`indexParams`): `Promise`<`any`\>
**createIndex**(`indexParams`): `Promise`\<`any`\>
Create an ANN index on this Table vector index.
**`See`**
VectorIndexParams.
#### Parameters
| Name | Type | Description |
@@ -211,7 +298,11 @@ VectorIndexParams.
#### Returns
`Promise`<`any`\>
`Promise`\<`any`\>
**`See`**
VectorIndexParams.
#### Implementation of
@@ -219,13 +310,13 @@ VectorIndexParams.
#### Defined in
[index.ts:355](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L355)
[index.ts:536](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L536)
___
### delete
**delete**(`filter`): `Promise`<`void`\>
**delete**(`filter`): `Promise`\<`void`\>
Delete rows from this table.
@@ -237,7 +328,7 @@ Delete rows from this table.
#### Returns
`Promise`<`void`\>
`Promise`\<`void`\>
#### Implementation of
@@ -245,13 +336,81 @@ Delete rows from this table.
#### Defined in
[index.ts:371](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L371)
[index.ts:552](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L552)
___
### filter
**filter**(`value`): [`Query`](Query.md)\<`T`\>
Creates a filter query to find all rows matching the specified criteria
#### Parameters
| Name | Type | Description |
| :------ | :------ | :------ |
| `value` | `string` | The filter criteria (like SQL where clause syntax) |
#### Returns
[`Query`](Query.md)\<`T`\>
#### Defined in
[index.ts:495](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L495)
___
### indexStats
**indexStats**(`indexUuid`): `Promise`\<[`IndexStats`](../interfaces/IndexStats.md)\>
Get statistics about an index.
#### Parameters
| Name | Type |
| :------ | :------ |
| `indexUuid` | `string` |
#### Returns
`Promise`\<[`IndexStats`](../interfaces/IndexStats.md)\>
#### Implementation of
[Table](../interfaces/Table.md).[indexStats](../interfaces/Table.md#indexstats)
#### Defined in
[index.ts:628](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L628)
___
### listIndices
**listIndices**(): `Promise`\<[`VectorIndex`](../interfaces/VectorIndex.md)[]\>
List the indicies on this table.
#### Returns
`Promise`\<[`VectorIndex`](../interfaces/VectorIndex.md)[]\>
#### Implementation of
[Table](../interfaces/Table.md).[listIndices](../interfaces/Table.md#listindices)
#### Defined in
[index.ts:624](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L624)
___
### overwrite
**overwrite**(`data`): `Promise`<`number`\>
**overwrite**(`data`): `Promise`\<`number`\>
Insert records into this Table, replacing its contents.
@@ -259,11 +418,11 @@ Insert records into this Table, replacing its contents.
| Name | Type | Description |
| :------ | :------ | :------ |
| `data` | `Record`<`string`, `unknown`\>[] | Records to be inserted into the Table |
| `data` | `Record`\<`string`, `unknown`\>[] | Records to be inserted into the Table |
#### Returns
`Promise`<`number`\>
`Promise`\<`number`\>
The number of rows added to the table
@@ -273,13 +432,13 @@ The number of rows added to the table
#### Defined in
[index.ts:338](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L338)
[index.ts:522](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L522)
___
### search
**search**(`query`): [`Query`](Query.md)<`T`\>
**search**(`query`): [`Query`](Query.md)\<`T`\>
Creates a search query to find the nearest neighbors of the given search term
@@ -291,7 +450,7 @@ Creates a search query to find the nearest neighbors of the given search term
#### Returns
[`Query`](Query.md)<`T`\>
[`Query`](Query.md)\<`T`\>
#### Implementation of
@@ -299,4 +458,30 @@ Creates a search query to find the nearest neighbors of the given search term
#### Defined in
[index.ts:310](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L310)
[index.ts:487](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L487)
___
### update
**update**(`args`): `Promise`\<`void`\>
Update rows in this table.
#### Parameters
| Name | Type | Description |
| :------ | :------ | :------ |
| `args` | [`UpdateArgs`](../interfaces/UpdateArgs.md) \| [`UpdateSqlArgs`](../interfaces/UpdateSqlArgs.md) | see [UpdateArgs](../interfaces/UpdateArgs.md) and [UpdateSqlArgs](../interfaces/UpdateSqlArgs.md) for more details |
#### Returns
`Promise`\<`void`\>
#### Implementation of
[Table](../interfaces/Table.md).[update](../interfaces/Table.md#update)
#### Defined in
[index.ts:563](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L563)

View File

@@ -6,7 +6,7 @@ An embedding function that automatically creates vector representation for a giv
## Implements
- [`EmbeddingFunction`](../interfaces/EmbeddingFunction.md)<`string`\>
- [`EmbeddingFunction`](../interfaces/EmbeddingFunction.md)\<`string`\>
## Table of contents
@@ -40,7 +40,7 @@ An embedding function that automatically creates vector representation for a giv
#### Defined in
[embedding/openai.ts:21](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/embedding/openai.ts#L21)
[embedding/openai.ts:21](https://github.com/lancedb/lancedb/blob/7856a94/node/src/embedding/openai.ts#L21)
## Properties
@@ -50,7 +50,7 @@ An embedding function that automatically creates vector representation for a giv
#### Defined in
[embedding/openai.ts:19](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/embedding/openai.ts#L19)
[embedding/openai.ts:19](https://github.com/lancedb/lancedb/blob/7856a94/node/src/embedding/openai.ts#L19)
___
@@ -60,7 +60,7 @@ ___
#### Defined in
[embedding/openai.ts:18](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/embedding/openai.ts#L18)
[embedding/openai.ts:18](https://github.com/lancedb/lancedb/blob/7856a94/node/src/embedding/openai.ts#L18)
___
@@ -76,13 +76,13 @@ The name of the column that will be used as input for the Embedding Function.
#### Defined in
[embedding/openai.ts:50](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/embedding/openai.ts#L50)
[embedding/openai.ts:50](https://github.com/lancedb/lancedb/blob/7856a94/node/src/embedding/openai.ts#L50)
## Methods
### embed
**embed**(`data`): `Promise`<`number`[][]\>
**embed**(`data`): `Promise`\<`number`[][]\>
Creates a vector representation for the given values.
@@ -94,7 +94,7 @@ Creates a vector representation for the given values.
#### Returns
`Promise`<`number`[][]\>
`Promise`\<`number`[][]\>
#### Implementation of
@@ -102,4 +102,4 @@ Creates a vector representation for the given values.
#### Defined in
[embedding/openai.ts:38](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/embedding/openai.ts#L38)
[embedding/openai.ts:38](https://github.com/lancedb/lancedb/blob/7856a94/node/src/embedding/openai.ts#L38)

View File

@@ -1,6 +1,6 @@
[vectordb](../README.md) / [Exports](../modules.md) / Query
# Class: Query<T\>
# Class: Query\<T\>
A builder for nearest neighbor queries for LanceDB.
@@ -23,6 +23,7 @@ A builder for nearest neighbor queries for LanceDB.
- [\_limit](Query.md#_limit)
- [\_metricType](Query.md#_metrictype)
- [\_nprobes](Query.md#_nprobes)
- [\_prefilter](Query.md#_prefilter)
- [\_query](Query.md#_query)
- [\_queryVector](Query.md#_queryvector)
- [\_refineFactor](Query.md#_refinefactor)
@@ -34,9 +35,11 @@ A builder for nearest neighbor queries for LanceDB.
- [execute](Query.md#execute)
- [filter](Query.md#filter)
- [isElectron](Query.md#iselectron)
- [limit](Query.md#limit)
- [metricType](Query.md#metrictype)
- [nprobes](Query.md#nprobes)
- [prefilter](Query.md#prefilter)
- [refineFactor](Query.md#refinefactor)
- [select](Query.md#select)
@@ -44,7 +47,7 @@ A builder for nearest neighbor queries for LanceDB.
### constructor
**new Query**<`T`\>(`tbl`, `query`, `embeddings?`)
**new Query**\<`T`\>(`query?`, `tbl?`, `embeddings?`)
#### Type parameters
@@ -56,23 +59,23 @@ A builder for nearest neighbor queries for LanceDB.
| Name | Type |
| :------ | :------ |
| `tbl` | `any` |
| `query` | `T` |
| `embeddings?` | [`EmbeddingFunction`](../interfaces/EmbeddingFunction.md)<`T`\> |
| `query?` | `T` |
| `tbl?` | `any` |
| `embeddings?` | [`EmbeddingFunction`](../interfaces/EmbeddingFunction.md)\<`T`\> |
#### Defined in
[index.ts:448](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L448)
[query.ts:38](https://github.com/lancedb/lancedb/blob/7856a94/node/src/query.ts#L38)
## Properties
### \_embeddings
`Private` `Optional` `Readonly` **\_embeddings**: [`EmbeddingFunction`](../interfaces/EmbeddingFunction.md)<`T`\>
`Protected` `Optional` `Readonly` **\_embeddings**: [`EmbeddingFunction`](../interfaces/EmbeddingFunction.md)\<`T`\>
#### Defined in
[index.ts:446](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L446)
[query.ts:36](https://github.com/lancedb/lancedb/blob/7856a94/node/src/query.ts#L36)
___
@@ -82,17 +85,17 @@ ___
#### Defined in
[index.ts:444](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L444)
[query.ts:33](https://github.com/lancedb/lancedb/blob/7856a94/node/src/query.ts#L33)
___
### \_limit
`Private` **\_limit**: `number`
`Private` `Optional` **\_limit**: `number`
#### Defined in
[index.ts:440](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L440)
[query.ts:29](https://github.com/lancedb/lancedb/blob/7856a94/node/src/query.ts#L29)
___
@@ -102,7 +105,7 @@ ___
#### Defined in
[index.ts:445](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L445)
[query.ts:34](https://github.com/lancedb/lancedb/blob/7856a94/node/src/query.ts#L34)
___
@@ -112,17 +115,27 @@ ___
#### Defined in
[index.ts:442](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L442)
[query.ts:31](https://github.com/lancedb/lancedb/blob/7856a94/node/src/query.ts#L31)
___
### \_prefilter
`Private` **\_prefilter**: `boolean`
#### Defined in
[query.ts:35](https://github.com/lancedb/lancedb/blob/7856a94/node/src/query.ts#L35)
___
### \_query
`Private` `Readonly` **\_query**: `T`
`Private` `Optional` `Readonly` **\_query**: `T`
#### Defined in
[index.ts:438](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L438)
[query.ts:26](https://github.com/lancedb/lancedb/blob/7856a94/node/src/query.ts#L26)
___
@@ -132,7 +145,7 @@ ___
#### Defined in
[index.ts:439](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L439)
[query.ts:28](https://github.com/lancedb/lancedb/blob/7856a94/node/src/query.ts#L28)
___
@@ -142,7 +155,7 @@ ___
#### Defined in
[index.ts:441](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L441)
[query.ts:30](https://github.com/lancedb/lancedb/blob/7856a94/node/src/query.ts#L30)
___
@@ -152,27 +165,27 @@ ___
#### Defined in
[index.ts:443](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L443)
[query.ts:32](https://github.com/lancedb/lancedb/blob/7856a94/node/src/query.ts#L32)
___
### \_tbl
`Private` `Readonly` **\_tbl**: `any`
`Private` `Optional` `Readonly` **\_tbl**: `any`
#### Defined in
[index.ts:437](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L437)
[query.ts:27](https://github.com/lancedb/lancedb/blob/7856a94/node/src/query.ts#L27)
___
### where
**where**: (`value`: `string`) => [`Query`](Query.md)<`T`\>
**where**: (`value`: `string`) => [`Query`](Query.md)\<`T`\>
#### Type declaration
▸ (`value`): [`Query`](Query.md)<`T`\>
▸ (`value`): [`Query`](Query.md)\<`T`\>
A filter statement to be applied to this query.
@@ -184,17 +197,17 @@ A filter statement to be applied to this query.
##### Returns
[`Query`](Query.md)<`T`\>
[`Query`](Query.md)\<`T`\>
#### Defined in
[index.ts:496](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L496)
[query.ts:87](https://github.com/lancedb/lancedb/blob/7856a94/node/src/query.ts#L87)
## Methods
### execute
**execute**<`T`\>(): `Promise`<`T`[]\>
**execute**\<`T`\>(): `Promise`\<`T`[]\>
Execute the query and return the results as an Array of Objects
@@ -202,21 +215,21 @@ Execute the query and return the results as an Array of Objects
| Name | Type |
| :------ | :------ |
| `T` | `Record`<`string`, `unknown`\> |
| `T` | `Record`\<`string`, `unknown`\> |
#### Returns
`Promise`<`T`[]\>
`Promise`\<`T`[]\>
#### Defined in
[index.ts:519](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L519)
[query.ts:115](https://github.com/lancedb/lancedb/blob/7856a94/node/src/query.ts#L115)
___
### filter
**filter**(`value`): [`Query`](Query.md)<`T`\>
**filter**(`value`): [`Query`](Query.md)\<`T`\>
A filter statement to be applied to this query.
@@ -228,17 +241,31 @@ A filter statement to be applied to this query.
#### Returns
[`Query`](Query.md)<`T`\>
[`Query`](Query.md)\<`T`\>
#### Defined in
[index.ts:491](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L491)
[query.ts:82](https://github.com/lancedb/lancedb/blob/7856a94/node/src/query.ts#L82)
___
### isElectron
`Private` **isElectron**(): `boolean`
#### Returns
`boolean`
#### Defined in
[query.ts:142](https://github.com/lancedb/lancedb/blob/7856a94/node/src/query.ts#L142)
___
### limit
**limit**(`value`): [`Query`](Query.md)<`T`\>
**limit**(`value`): [`Query`](Query.md)\<`T`\>
Sets the number of results that will be returned
@@ -250,24 +277,20 @@ Sets the number of results that will be returned
#### Returns
[`Query`](Query.md)<`T`\>
[`Query`](Query.md)\<`T`\>
#### Defined in
[index.ts:464](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L464)
[query.ts:55](https://github.com/lancedb/lancedb/blob/7856a94/node/src/query.ts#L55)
___
### metricType
**metricType**(`value`): [`Query`](Query.md)<`T`\>
**metricType**(`value`): [`Query`](Query.md)\<`T`\>
The MetricType used for this Query.
**`See`**
MetricType for the different options
#### Parameters
| Name | Type | Description |
@@ -276,17 +299,21 @@ MetricType for the different options
#### Returns
[`Query`](Query.md)<`T`\>
[`Query`](Query.md)\<`T`\>
**`See`**
MetricType for the different options
#### Defined in
[index.ts:511](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L511)
[query.ts:102](https://github.com/lancedb/lancedb/blob/7856a94/node/src/query.ts#L102)
___
### nprobes
**nprobes**(`value`): [`Query`](Query.md)<`T`\>
**nprobes**(`value`): [`Query`](Query.md)\<`T`\>
The number of probes used. A higher number makes search more accurate but also slower.
@@ -298,17 +325,37 @@ The number of probes used. A higher number makes search more accurate but also s
#### Returns
[`Query`](Query.md)<`T`\>
[`Query`](Query.md)\<`T`\>
#### Defined in
[index.ts:482](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L482)
[query.ts:73](https://github.com/lancedb/lancedb/blob/7856a94/node/src/query.ts#L73)
___
### prefilter
**prefilter**(`value`): [`Query`](Query.md)\<`T`\>
#### Parameters
| Name | Type |
| :------ | :------ |
| `value` | `boolean` |
#### Returns
[`Query`](Query.md)\<`T`\>
#### Defined in
[query.ts:107](https://github.com/lancedb/lancedb/blob/7856a94/node/src/query.ts#L107)
___
### refineFactor
**refineFactor**(`value`): [`Query`](Query.md)<`T`\>
**refineFactor**(`value`): [`Query`](Query.md)\<`T`\>
Refine the results by reading extra elements and re-ranking them in memory.
@@ -320,17 +367,17 @@ Refine the results by reading extra elements and re-ranking them in memory.
#### Returns
[`Query`](Query.md)<`T`\>
[`Query`](Query.md)\<`T`\>
#### Defined in
[index.ts:473](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L473)
[query.ts:64](https://github.com/lancedb/lancedb/blob/7856a94/node/src/query.ts#L64)
___
### select
**select**(`value`): [`Query`](Query.md)<`T`\>
**select**(`value`): [`Query`](Query.md)\<`T`\>
Return only the specified columns.
@@ -342,8 +389,8 @@ Return only the specified columns.
#### Returns
[`Query`](Query.md)<`T`\>
[`Query`](Query.md)\<`T`\>
#### Defined in
[index.ts:502](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L502)
[query.ts:93](https://github.com/lancedb/lancedb/blob/7856a94/node/src/query.ts#L93)

View File

@@ -22,7 +22,7 @@ Cosine distance
#### Defined in
[index.ts:567](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L567)
[index.ts:798](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L798)
___
@@ -34,7 +34,7 @@ Dot product
#### Defined in
[index.ts:572](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L572)
[index.ts:803](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L803)
___
@@ -46,4 +46,4 @@ Euclidean distance
#### Defined in
[index.ts:562](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L562)
[index.ts:793](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L793)

View File

@@ -22,7 +22,7 @@ Append new data to the table.
#### Defined in
[index.ts:552](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L552)
[index.ts:766](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L766)
___
@@ -34,7 +34,7 @@ Create a new [Table](../interfaces/Table.md).
#### Defined in
[index.ts:548](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L548)
[index.ts:762](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L762)
___
@@ -46,4 +46,4 @@ Overwrite the existing [Table](../interfaces/Table.md) if presented.
#### Defined in
[index.ts:550](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L550)
[index.ts:764](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L764)

View File

@@ -18,7 +18,7 @@
#### Defined in
[index.ts:31](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L31)
[index.ts:34](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L34)
___
@@ -28,7 +28,7 @@ ___
#### Defined in
[index.ts:33](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L33)
[index.ts:36](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L36)
___
@@ -38,4 +38,4 @@ ___
#### Defined in
[index.ts:35](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L35)
[index.ts:38](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L38)

View File

@@ -0,0 +1,34 @@
[vectordb](../README.md) / [Exports](../modules.md) / CleanupStats
# Interface: CleanupStats
## Table of contents
### Properties
- [bytesRemoved](CleanupStats.md#bytesremoved)
- [oldVersions](CleanupStats.md#oldversions)
## Properties
### bytesRemoved
**bytesRemoved**: `number`
The number of bytes removed from disk.
#### Defined in
[index.ts:637](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L637)
___
### oldVersions
**oldVersions**: `number`
The number of old table versions removed.
#### Defined in
[index.ts:641](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L641)

View File

@@ -0,0 +1,62 @@
[vectordb](../README.md) / [Exports](../modules.md) / CompactionMetrics
# Interface: CompactionMetrics
## Table of contents
### Properties
- [filesAdded](CompactionMetrics.md#filesadded)
- [filesRemoved](CompactionMetrics.md#filesremoved)
- [fragmentsAdded](CompactionMetrics.md#fragmentsadded)
- [fragmentsRemoved](CompactionMetrics.md#fragmentsremoved)
## Properties
### filesAdded
**filesAdded**: `number`
The number of files added. This is typically equal to the number of
fragments added.
#### Defined in
[index.ts:692](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L692)
___
### filesRemoved
**filesRemoved**: `number`
The number of files that were removed. Each fragment may have more than one
file.
#### Defined in
[index.ts:687](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L687)
___
### fragmentsAdded
**fragmentsAdded**: `number`
The number of new fragments that were created.
#### Defined in
[index.ts:682](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L682)
___
### fragmentsRemoved
**fragmentsRemoved**: `number`
The number of fragments that were removed.
#### Defined in
[index.ts:678](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L678)

View File

@@ -0,0 +1,80 @@
[vectordb](../README.md) / [Exports](../modules.md) / CompactionOptions
# Interface: CompactionOptions
## Table of contents
### Properties
- [materializeDeletions](CompactionOptions.md#materializedeletions)
- [materializeDeletionsThreshold](CompactionOptions.md#materializedeletionsthreshold)
- [maxRowsPerGroup](CompactionOptions.md#maxrowspergroup)
- [numThreads](CompactionOptions.md#numthreads)
- [targetRowsPerFragment](CompactionOptions.md#targetrowsperfragment)
## Properties
### materializeDeletions
`Optional` **materializeDeletions**: `boolean`
If true, fragments that have rows that are deleted may be compacted to
remove the deleted rows. This can improve the performance of queries.
Default is true.
#### Defined in
[index.ts:660](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L660)
___
### materializeDeletionsThreshold
`Optional` **materializeDeletionsThreshold**: `number`
A number between 0 and 1, representing the proportion of rows that must be
marked deleted before a fragment is a candidate for compaction to remove
the deleted rows. Default is 10%.
#### Defined in
[index.ts:666](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L666)
___
### maxRowsPerGroup
`Optional` **maxRowsPerGroup**: `number`
The maximum number of rows per group. Defaults to 1024.
#### Defined in
[index.ts:654](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L654)
___
### numThreads
`Optional` **numThreads**: `number`
The number of threads to use for compaction. If not provided, defaults to
the number of cores on the machine.
#### Defined in
[index.ts:671](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L671)
___
### targetRowsPerFragment
`Optional` **targetRowsPerFragment**: `number`
The number of rows per fragment to target. Fragments that have fewer rows
will be compacted into adjacent fragments to produce larger fragments.
Defaults to 1024 * 1024.
#### Defined in
[index.ts:650](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L650)

View File

@@ -19,7 +19,6 @@ Connection could be local against filesystem or remote against a server.
### Methods
- [createTable](Connection.md#createtable)
- [createTableArrow](Connection.md#createtablearrow)
- [dropTable](Connection.md#droptable)
- [openTable](Connection.md#opentable)
- [tableNames](Connection.md#tablenames)
@@ -32,13 +31,76 @@ Connection could be local against filesystem or remote against a server.
#### Defined in
[index.ts:70](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L70)
[index.ts:125](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L125)
## Methods
### createTable
**createTable**<`T`\>(`name`, `data`, `mode?`, `embeddings?`): `Promise`<[`Table`](Table.md)<`T`\>\>
**createTable**\<`T`\>(`«destructured»`): `Promise`\<[`Table`](Table.md)\<`T`\>\>
Creates a new Table, optionally initializing it with new data.
#### Type parameters
| Name |
| :------ |
| `T` |
#### Parameters
| Name | Type |
| :------ | :------ |
| `«destructured»` | [`CreateTableOptions`](CreateTableOptions.md)\<`T`\> |
#### Returns
`Promise`\<[`Table`](Table.md)\<`T`\>\>
#### Defined in
[index.ts:146](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L146)
**createTable**(`name`, `data`): `Promise`\<[`Table`](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 |
#### Returns
`Promise`\<[`Table`](Table.md)\<`number`[]\>\>
#### Defined in
[index.ts:154](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L154)
**createTable**(`name`, `data`, `options`): `Promise`\<[`Table`](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 |
| `options` | [`WriteOptions`](WriteOptions.md) | The write options to use when creating the table. |
#### Returns
`Promise`\<[`Table`](Table.md)\<`number`[]\>\>
#### Defined in
[index.ts:163](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L163)
**createTable**\<`T`\>(`name`, `data`, `embeddings`): `Promise`\<[`Table`](Table.md)\<`T`\>\>
Creates a new Table and initialize it with new data.
@@ -53,44 +115,49 @@ Creates a new Table and initialize it with new data.
| 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. |
| `embeddings?` | [`EmbeddingFunction`](EmbeddingFunction.md)<`T`\> | An embedding function to use on this table |
| `data` | `Record`\<`string`, `unknown`\>[] | Non-empty Array of Records to be inserted into the table |
| `embeddings` | [`EmbeddingFunction`](EmbeddingFunction.md)\<`T`\> | An embedding function to use on this table |
#### Returns
`Promise`<[`Table`](Table.md)<`T`\>\>
`Promise`\<[`Table`](Table.md)\<`T`\>\>
#### Defined in
[index.ts:90](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L90)
[index.ts:172](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L172)
___
**createTable**\<`T`\>(`name`, `data`, `embeddings`, `options`): `Promise`\<[`Table`](Table.md)\<`T`\>\>
### createTableArrow
Creates a new Table and initialize it with new data.
**createTableArrow**(`name`, `table`): `Promise`<[`Table`](Table.md)<`number`[]\>\>
#### Type parameters
| Name |
| :------ |
| `T` |
#### Parameters
| Name | Type |
| :------ | :------ |
| `name` | `string` |
| `table` | `Table`<`any`\> |
| 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 |
| `embeddings` | [`EmbeddingFunction`](EmbeddingFunction.md)\<`T`\> | An embedding function to use on this table |
| `options` | [`WriteOptions`](WriteOptions.md) | The write options to use when creating the table. |
#### Returns
`Promise`<[`Table`](Table.md)<`number`[]\>\>
`Promise`\<[`Table`](Table.md)\<`T`\>\>
#### Defined in
[index.ts:92](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L92)
[index.ts:181](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L181)
___
### dropTable
**dropTable**(`name`): `Promise`<`void`\>
**dropTable**(`name`): `Promise`\<`void`\>
Drop an existing table.
@@ -102,17 +169,17 @@ Drop an existing table.
#### Returns
`Promise`<`void`\>
`Promise`\<`void`\>
#### Defined in
[index.ts:98](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L98)
[index.ts:187](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L187)
___
### openTable
**openTable**<`T`\>(`name`, `embeddings?`): `Promise`<[`Table`](Table.md)<`T`\>\>
**openTable**\<`T`\>(`name`, `embeddings?`): `Promise`\<[`Table`](Table.md)\<`T`\>\>
Open a table in the database.
@@ -127,26 +194,26 @@ Open a table in the database.
| Name | Type | Description |
| :------ | :------ | :------ |
| `name` | `string` | The name of the table. |
| `embeddings?` | [`EmbeddingFunction`](EmbeddingFunction.md)<`T`\> | An embedding function to use on this table |
| `embeddings?` | [`EmbeddingFunction`](EmbeddingFunction.md)\<`T`\> | An embedding function to use on this table |
#### Returns
`Promise`<[`Table`](Table.md)<`T`\>\>
`Promise`\<[`Table`](Table.md)\<`T`\>\>
#### Defined in
[index.ts:80](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L80)
[index.ts:135](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L135)
___
### tableNames
**tableNames**(): `Promise`<`string`[]\>
**tableNames**(): `Promise`\<`string`[]\>
#### Returns
`Promise`<`string`[]\>
`Promise`\<`string`[]\>
#### Defined in
[index.ts:72](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L72)
[index.ts:127](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L127)

View File

@@ -6,18 +6,62 @@
### Properties
- [apiKey](ConnectionOptions.md#apikey)
- [awsCredentials](ConnectionOptions.md#awscredentials)
- [awsRegion](ConnectionOptions.md#awsregion)
- [hostOverride](ConnectionOptions.md#hostoverride)
- [region](ConnectionOptions.md#region)
- [uri](ConnectionOptions.md#uri)
## Properties
### apiKey
`Optional` **apiKey**: `string`
#### Defined in
[index.ts:49](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L49)
___
### awsCredentials
`Optional` **awsCredentials**: [`AwsCredentials`](AwsCredentials.md)
#### Defined in
[index.ts:40](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L40)
[index.ts:44](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L44)
___
### awsRegion
`Optional` **awsRegion**: `string`
#### Defined in
[index.ts:46](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L46)
___
### hostOverride
`Optional` **hostOverride**: `string`
#### Defined in
[index.ts:54](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L54)
___
### region
`Optional` **region**: `string`
#### Defined in
[index.ts:51](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L51)
___
@@ -27,4 +71,4 @@ ___
#### Defined in
[index.ts:39](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L39)
[index.ts:42](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L42)

View File

@@ -0,0 +1,69 @@
[vectordb](../README.md) / [Exports](../modules.md) / CreateTableOptions
# Interface: CreateTableOptions\<T\>
## Type parameters
| Name |
| :------ |
| `T` |
## Table of contents
### Properties
- [data](CreateTableOptions.md#data)
- [embeddingFunction](CreateTableOptions.md#embeddingfunction)
- [name](CreateTableOptions.md#name)
- [schema](CreateTableOptions.md#schema)
- [writeOptions](CreateTableOptions.md#writeoptions)
## Properties
### data
`Optional` **data**: `Table`\<`any`\> \| `Record`\<`string`, `unknown`\>[]
#### Defined in
[index.ts:79](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L79)
___
### embeddingFunction
`Optional` **embeddingFunction**: [`EmbeddingFunction`](EmbeddingFunction.md)\<`T`\>
#### Defined in
[index.ts:85](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L85)
___
### name
**name**: `string`
#### Defined in
[index.ts:76](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L76)
___
### schema
`Optional` **schema**: `Schema`\<`any`\>
#### Defined in
[index.ts:82](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L82)
___
### writeOptions
`Optional` **writeOptions**: [`WriteOptions`](WriteOptions.md)
#### Defined in
[index.ts:88](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L88)

View File

@@ -1,6 +1,6 @@
[vectordb](../README.md) / [Exports](../modules.md) / EmbeddingFunction
# Interface: EmbeddingFunction<T\>
# Interface: EmbeddingFunction\<T\>
An embedding function that automatically creates vector representation for a given column.
@@ -25,11 +25,11 @@ An embedding function that automatically creates vector representation for a giv
### embed
**embed**: (`data`: `T`[]) => `Promise`<`number`[][]\>
**embed**: (`data`: `T`[]) => `Promise`\<`number`[][]\>
#### Type declaration
▸ (`data`): `Promise`<`number`[][]\>
▸ (`data`): `Promise`\<`number`[][]\>
Creates a vector representation for the given values.
@@ -41,11 +41,11 @@ Creates a vector representation for the given values.
##### Returns
`Promise`<`number`[][]\>
`Promise`\<`number`[][]\>
#### Defined in
[embedding/embedding_function.ts:27](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/embedding/embedding_function.ts#L27)
[embedding/embedding_function.ts:27](https://github.com/lancedb/lancedb/blob/7856a94/node/src/embedding/embedding_function.ts#L27)
___
@@ -57,4 +57,4 @@ The name of the column that will be used as input for the Embedding Function.
#### Defined in
[embedding/embedding_function.ts:22](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/embedding/embedding_function.ts#L22)
[embedding/embedding_function.ts:22](https://github.com/lancedb/lancedb/blob/7856a94/node/src/embedding/embedding_function.ts#L22)

View File

@@ -0,0 +1,30 @@
[vectordb](../README.md) / [Exports](../modules.md) / IndexStats
# Interface: IndexStats
## Table of contents
### Properties
- [numIndexedRows](IndexStats.md#numindexedrows)
- [numUnindexedRows](IndexStats.md#numunindexedrows)
## Properties
### numIndexedRows
**numIndexedRows**: ``null`` \| `number`
#### Defined in
[index.ts:344](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L344)
___
### numUnindexedRows
• **numUnindexedRows**: ``null`` \| `number`
#### Defined in
[index.ts:345](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L345)

View File

@@ -7,6 +7,7 @@
### Properties
- [column](IvfPQIndexConfig.md#column)
- [index\_cache\_size](IvfPQIndexConfig.md#index_cache_size)
- [index\_name](IvfPQIndexConfig.md#index_name)
- [max\_iters](IvfPQIndexConfig.md#max_iters)
- [max\_opq\_iters](IvfPQIndexConfig.md#max_opq_iters)
@@ -28,7 +29,19 @@ The column to be indexed
#### Defined in
[index.ts:382](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L382)
[index.ts:701](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L701)
___
### index\_cache\_size
`Optional` **index\_cache\_size**: `number`
Cache size of the index
#### Defined in
[index.ts:750](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L750)
___
@@ -40,7 +53,7 @@ A unique name for the index
#### Defined in
[index.ts:387](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L387)
[index.ts:706](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L706)
___
@@ -52,7 +65,7 @@ The max number of iterations for kmeans training.
#### Defined in
[index.ts:402](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L402)
[index.ts:721](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L721)
___
@@ -64,7 +77,7 @@ Max number of iterations to train OPQ, if `use_opq` is true.
#### Defined in
[index.ts:421](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L421)
[index.ts:740](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L740)
___
@@ -76,7 +89,7 @@ Metric type, L2 or Cosine
#### Defined in
[index.ts:392](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L392)
[index.ts:711](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L711)
___
@@ -88,7 +101,7 @@ The number of bits to present one PQ centroid.
#### Defined in
[index.ts:416](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L416)
[index.ts:735](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L735)
___
@@ -100,7 +113,7 @@ The number of partitions this index
#### Defined in
[index.ts:397](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L397)
[index.ts:716](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L716)
___
@@ -112,7 +125,7 @@ Number of subvectors to build PQ code
#### Defined in
[index.ts:412](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L412)
[index.ts:731](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L731)
___
@@ -124,7 +137,7 @@ Replace an existing index with the same name if it exists.
#### Defined in
[index.ts:426](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L426)
[index.ts:745](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L745)
___
@@ -134,7 +147,7 @@ ___
#### Defined in
[index.ts:428](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L428)
[index.ts:752](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L752)
___
@@ -146,4 +159,4 @@ Train as optimized product quantization.
#### Defined in
[index.ts:407](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L407)
[index.ts:726](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L726)

View File

@@ -1,6 +1,6 @@
[vectordb](../README.md) / [Exports](../modules.md) / Table
# Interface: Table<T\>
# Interface: Table\<T\>
A LanceDB Table is the collection of Records. Each Record has one or more vector fields.
@@ -22,19 +22,22 @@ A LanceDB Table is the collection of Records. Each Record has one or more vector
- [countRows](Table.md#countrows)
- [createIndex](Table.md#createindex)
- [delete](Table.md#delete)
- [indexStats](Table.md#indexstats)
- [listIndices](Table.md#listindices)
- [name](Table.md#name)
- [overwrite](Table.md#overwrite)
- [search](Table.md#search)
- [update](Table.md#update)
## Properties
### add
**add**: (`data`: `Record`<`string`, `unknown`\>[]) => `Promise`<`number`\>
**add**: (`data`: `Record`\<`string`, `unknown`\>[]) => `Promise`\<`number`\>
#### Type declaration
▸ (`data`): `Promise`<`number`\>
▸ (`data`): `Promise`\<`number`\>
Insert records into this Table.
@@ -42,54 +45,50 @@ Insert records into this Table.
| Name | Type | Description |
| :------ | :------ | :------ |
| `data` | `Record`<`string`, `unknown`\>[] | Records to be inserted into the Table |
| `data` | `Record`\<`string`, `unknown`\>[] | Records to be inserted into the Table |
##### Returns
`Promise`<`number`\>
`Promise`\<`number`\>
The number of rows added to the table
#### Defined in
[index.ts:120](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L120)
[index.ts:209](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L209)
___
### countRows
**countRows**: () => `Promise`<`number`\>
**countRows**: () => `Promise`\<`number`\>
#### Type declaration
▸ (): `Promise`<`number`\>
▸ (): `Promise`\<`number`\>
Returns the number of rows in this table.
##### Returns
`Promise`<`number`\>
`Promise`\<`number`\>
#### Defined in
[index.ts:140](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L140)
[index.ts:229](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L229)
___
### createIndex
**createIndex**: (`indexParams`: [`IvfPQIndexConfig`](IvfPQIndexConfig.md)) => `Promise`<`any`\>
**createIndex**: (`indexParams`: [`IvfPQIndexConfig`](IvfPQIndexConfig.md)) => `Promise`\<`any`\>
#### Type declaration
▸ (`indexParams`): `Promise`<`any`\>
▸ (`indexParams`): `Promise`\<`any`\>
Create an ANN index on this Table vector index.
**`See`**
VectorIndexParams.
##### Parameters
| Name | Type | Description |
@@ -98,27 +97,41 @@ VectorIndexParams.
##### Returns
`Promise`<`any`\>
`Promise`\<`any`\>
**`See`**
VectorIndexParams.
#### Defined in
[index.ts:135](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L135)
[index.ts:224](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L224)
___
### delete
**delete**: (`filter`: `string`) => `Promise`<`void`\>
**delete**: (`filter`: `string`) => `Promise`\<`void`\>
#### Type declaration
▸ (`filter`): `Promise`<`void`\>
▸ (`filter`): `Promise`\<`void`\>
Delete rows from this table.
This can be used to delete a single row, many rows, all rows, or
sometimes no rows (if your predicate matches nothing).
##### Parameters
| Name | Type | Description |
| :------ | :------ | :------ |
| `filter` | `string` | A filter in the same format used by a sql WHERE clause. The filter must not be empty. |
##### Returns
`Promise`\<`void`\>
**`Examples`**
```ts
@@ -142,19 +155,55 @@ await tbl.delete(`id IN (${to_remove.join(",")})`)
await tbl.countRows() // Returns 1
```
#### Defined in
[index.ts:263](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L263)
___
### indexStats
**indexStats**: (`indexUuid`: `string`) => `Promise`\<[`IndexStats`](IndexStats.md)\>
#### Type declaration
▸ (`indexUuid`): `Promise`\<[`IndexStats`](IndexStats.md)\>
Get statistics about an index.
##### Parameters
| Name | Type | Description |
| :------ | :------ | :------ |
| `filter` | `string` | A filter in the same format used by a sql WHERE clause. The filter must not be empty. |
| Name | Type |
| :------ | :------ |
| `indexUuid` | `string` |
##### Returns
`Promise`<`void`\>
`Promise`\<[`IndexStats`](IndexStats.md)\>
#### Defined in
[index.ts:174](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L174)
[index.ts:306](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L306)
___
### listIndices
**listIndices**: () => `Promise`\<[`VectorIndex`](VectorIndex.md)[]\>
#### Type declaration
▸ (): `Promise`\<[`VectorIndex`](VectorIndex.md)[]\>
List the indicies on this table.
##### Returns
`Promise`\<[`VectorIndex`](VectorIndex.md)[]\>
#### Defined in
[index.ts:301](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L301)
___
@@ -164,17 +213,17 @@ ___
#### Defined in
[index.ts:106](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L106)
[index.ts:195](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L195)
___
### overwrite
**overwrite**: (`data`: `Record`<`string`, `unknown`\>[]) => `Promise`<`number`\>
**overwrite**: (`data`: `Record`\<`string`, `unknown`\>[]) => `Promise`\<`number`\>
#### Type declaration
▸ (`data`): `Promise`<`number`\>
▸ (`data`): `Promise`\<`number`\>
Insert records into this Table, replacing its contents.
@@ -182,27 +231,27 @@ Insert records into this Table, replacing its contents.
| Name | Type | Description |
| :------ | :------ | :------ |
| `data` | `Record`<`string`, `unknown`\>[] | Records to be inserted into the Table |
| `data` | `Record`\<`string`, `unknown`\>[] | Records to be inserted into the Table |
##### Returns
`Promise`<`number`\>
`Promise`\<`number`\>
The number of rows added to the table
#### Defined in
[index.ts:128](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L128)
[index.ts:217](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L217)
___
### search
**search**: (`query`: `T`) => [`Query`](../classes/Query.md)<`T`\>
**search**: (`query`: `T`) => [`Query`](../classes/Query.md)\<`T`\>
#### Type declaration
▸ (`query`): [`Query`](../classes/Query.md)<`T`\>
▸ (`query`): [`Query`](../classes/Query.md)\<`T`\>
Creates a search query to find the nearest neighbors of the given search term
@@ -214,8 +263,59 @@ Creates a search query to find the nearest neighbors of the given search term
##### Returns
[`Query`](../classes/Query.md)<`T`\>
[`Query`](../classes/Query.md)\<`T`\>
#### Defined in
[index.ts:112](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L112)
[index.ts:201](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L201)
___
### update
**update**: (`args`: [`UpdateArgs`](UpdateArgs.md) \| [`UpdateSqlArgs`](UpdateSqlArgs.md)) => `Promise`\<`void`\>
#### Type declaration
▸ (`args`): `Promise`\<`void`\>
Update rows in this table.
This can be used to update a single row, many rows, all rows, or
sometimes no rows (if your predicate matches nothing).
##### Parameters
| Name | Type | Description |
| :------ | :------ | :------ |
| `args` | [`UpdateArgs`](UpdateArgs.md) \| [`UpdateSqlArgs`](UpdateSqlArgs.md) | see [UpdateArgs](UpdateArgs.md) and [UpdateSqlArgs](UpdateSqlArgs.md) for more details |
##### Returns
`Promise`\<`void`\>
**`Examples`**
```ts
const con = await lancedb.connect("./.lancedb")
const data = [
{id: 1, vector: [3, 3], name: 'Ye'},
{id: 2, vector: [4, 4], name: 'Mike'},
];
const tbl = await con.createTable("my_table", data)
await tbl.update({
filter: "id = 2",
updates: { vector: [2, 2], name: "Michael" },
})
let results = await tbl.search([1, 1]).execute();
// Returns [
// {id: 2, vector: [2, 2], name: 'Michael'}
// {id: 1, vector: [3, 3], name: 'Ye'}
// ]
```
#### Defined in
[index.ts:296](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L296)

View File

@@ -0,0 +1,36 @@
[vectordb](../README.md) / [Exports](../modules.md) / UpdateArgs
# Interface: UpdateArgs
## Table of contents
### Properties
- [values](UpdateArgs.md#values)
- [where](UpdateArgs.md#where)
## Properties
### values
**values**: `Record`\<`string`, `Literal`\>
A key-value map of updates. The keys are the column names, and the values are the
new values to set
#### Defined in
[index.ts:320](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L320)
___
### where
`Optional` **where**: `string`
A filter in the same format used by a sql WHERE clause. The filter may be empty,
in which case all rows will be updated.
#### Defined in
[index.ts:314](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L314)

View File

@@ -0,0 +1,36 @@
[vectordb](../README.md) / [Exports](../modules.md) / UpdateSqlArgs
# Interface: UpdateSqlArgs
## Table of contents
### Properties
- [valuesSql](UpdateSqlArgs.md#valuessql)
- [where](UpdateSqlArgs.md#where)
## Properties
### valuesSql
**valuesSql**: `Record`\<`string`, `string`\>
A key-value map of updates. The keys are the column names, and the values are the
new values to set as SQL expressions.
#### Defined in
[index.ts:334](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L334)
___
### where
`Optional` **where**: `string`
A filter in the same format used by a sql WHERE clause. The filter may be empty,
in which case all rows will be updated.
#### Defined in
[index.ts:328](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L328)

View File

@@ -0,0 +1,41 @@
[vectordb](../README.md) / [Exports](../modules.md) / VectorIndex
# Interface: VectorIndex
## Table of contents
### Properties
- [columns](VectorIndex.md#columns)
- [name](VectorIndex.md#name)
- [uuid](VectorIndex.md#uuid)
## Properties
### columns
**columns**: `string`[]
#### Defined in
[index.ts:338](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L338)
___
### name
**name**: `string`
#### Defined in
[index.ts:339](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L339)
___
### uuid
**uuid**: `string`
#### Defined in
[index.ts:340](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L340)

View File

@@ -0,0 +1,27 @@
[vectordb](../README.md) / [Exports](../modules.md) / WriteOptions
# Interface: WriteOptions
Write options when creating a Table.
## Implemented by
- [`DefaultWriteOptions`](../classes/DefaultWriteOptions.md)
## Table of contents
### Properties
- [writeMode](WriteOptions.md#writemode)
## Properties
### writeMode
`Optional` **writeMode**: [`WriteMode`](../enums/WriteMode.md)
A [WriteMode](../enums/WriteMode.md) to use on this operation
#### Defined in
[index.ts:774](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L774)

View File

@@ -11,6 +11,7 @@
### Classes
- [DefaultWriteOptions](classes/DefaultWriteOptions.md)
- [LocalConnection](classes/LocalConnection.md)
- [LocalTable](classes/LocalTable.md)
- [OpenAIEmbeddingFunction](classes/OpenAIEmbeddingFunction.md)
@@ -19,11 +20,20 @@
### Interfaces
- [AwsCredentials](interfaces/AwsCredentials.md)
- [CleanupStats](interfaces/CleanupStats.md)
- [CompactionMetrics](interfaces/CompactionMetrics.md)
- [CompactionOptions](interfaces/CompactionOptions.md)
- [Connection](interfaces/Connection.md)
- [ConnectionOptions](interfaces/ConnectionOptions.md)
- [CreateTableOptions](interfaces/CreateTableOptions.md)
- [EmbeddingFunction](interfaces/EmbeddingFunction.md)
- [IndexStats](interfaces/IndexStats.md)
- [IvfPQIndexConfig](interfaces/IvfPQIndexConfig.md)
- [Table](interfaces/Table.md)
- [UpdateArgs](interfaces/UpdateArgs.md)
- [UpdateSqlArgs](interfaces/UpdateSqlArgs.md)
- [VectorIndex](interfaces/VectorIndex.md)
- [WriteOptions](interfaces/WriteOptions.md)
### Type Aliases
@@ -32,6 +42,7 @@
### Functions
- [connect](modules.md#connect)
- [isWriteOptions](modules.md#iswriteoptions)
## Type Aliases
@@ -41,13 +52,13 @@
#### Defined in
[index.ts:431](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L431)
[index.ts:755](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L755)
## Functions
### connect
**connect**(`uri`): `Promise`<[`Connection`](interfaces/Connection.md)\>
**connect**(`uri`): `Promise`\<[`Connection`](interfaces/Connection.md)\>
Connect to a LanceDB instance at the given URI
@@ -59,24 +70,44 @@ Connect to a LanceDB instance at the given URI
#### Returns
`Promise`<[`Connection`](interfaces/Connection.md)\>
`Promise`\<[`Connection`](interfaces/Connection.md)\>
#### Defined in
[index.ts:47](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L47)
[index.ts:95](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L95)
**connect**(`opts`): `Promise`<[`Connection`](interfaces/Connection.md)\>
**connect**(`opts`): `Promise`\<[`Connection`](interfaces/Connection.md)\>
#### Parameters
| Name | Type |
| :------ | :------ |
| `opts` | `Partial`<[`ConnectionOptions`](interfaces/ConnectionOptions.md)\> |
| `opts` | `Partial`\<[`ConnectionOptions`](interfaces/ConnectionOptions.md)\> |
#### Returns
`Promise`<[`Connection`](interfaces/Connection.md)\>
`Promise`\<[`Connection`](interfaces/Connection.md)\>
#### Defined in
[index.ts:48](https://github.com/lancedb/lancedb/blob/b1eeb90/node/src/index.ts#L48)
[index.ts:96](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L96)
___
### isWriteOptions
**isWriteOptions**(`value`): value is WriteOptions
#### Parameters
| Name | Type |
| :------ | :------ |
| `value` | `any` |
#### Returns
value is WriteOptions
#### Defined in
[index.ts:781](https://github.com/lancedb/lancedb/blob/7856a94/node/src/index.ts#L781)

View File

@@ -1,7 +1,7 @@
# SQL filters
LanceDB embraces the utilization of standard SQL expressions as predicates for hybrid
filters. It can be used during hybrid vector search and deletion operations.
filters. It can be used during hybrid vector search, update, and deletion operations.
Currently, Lance supports a growing list of expressions.
@@ -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.

View File

@@ -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

74
node/package-lock.json generated
View File

@@ -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": {

View File

@@ -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"
}
}

View File

@@ -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.
*/

View File

@@ -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

View File

@@ -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)

View File

@@ -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

View File

@@ -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:

View File

@@ -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()

View File

@@ -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())

View File

@@ -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:

View File

@@ -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

View File

@@ -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",

View File

@@ -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,
@@ -383,6 +455,62 @@ class Table(ABC):
"""
raise NotImplementedError
@abstractmethod
def update(
self,
where: Optional[str] = None,
values: Optional[dict] = None,
*,
values_sql: Optional[Dict[str, str]] = None,
):
"""
This can be used to update zero to all rows depending on how many
rows match the where clause. If no where clause is provided, then
all rows will be updated.
Either `values` or `values_sql` must be provided. You cannot provide
both.
Parameters
----------
where: str, optional
The SQL where clause to use when updating rows. For example, 'x = 2'
or 'x IN (1, 2, 3)'. The filter must not be empty, or it will error.
values: dict, optional
The values to update. The keys are the column names and the values
are the values to set.
values_sql: dict, optional
The values to update, expressed as SQL expression strings. These can
reference existing columns. For example, {"x": "x + 1"} will increment
the x column by 1.
Examples
--------
>>> import lancedb
>>> import pandas as pd
>>> data = pd.DataFrame({"x": [1, 2, 3], "vector": [[1, 2], [3, 4], [5, 6]]})
>>> db = lancedb.connect("./.lancedb")
>>> table = db.create_table("my_table", data)
>>> table.to_pandas()
x vector
0 1 [1.0, 2.0]
1 2 [3.0, 4.0]
2 3 [5.0, 6.0]
>>> table.update(where="x = 2", values={"vector": [10, 10]})
>>> table.to_pandas()
x vector
0 1 [1.0, 2.0]
1 3 [5.0, 6.0]
2 2 [10.0, 10.0]
>>> table.update(values_sql={"x": "x + 1"})
>>> table.to_pandas()
x vector
0 2 [1.0, 2.0]
1 4 [5.0, 6.0]
2 3 [10.0, 10.0]
"""
raise NotImplementedError
class LanceTable(Table):
"""
@@ -551,7 +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,
@@ -577,7 +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
@@ -587,17 +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:

View File

@@ -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

View File

@@ -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"

View File

@@ -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)

View File

@@ -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

View File

@@ -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

View File

@@ -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,

View File

@@ -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"

View File

@@ -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"

View File

@@ -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 },

View File

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

View File

@@ -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)
}

View File

@@ -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)
}

View File

@@ -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,

View File

@@ -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(),
},

View File

@@ -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)

View File

@@ -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| {

View File

@@ -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"

View File

@@ -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> {

View File

@@ -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();