rust/lancedb
1
0
Fork 0
mirror of https://github.com/lancedb/lancedb.git synced 2026-10-13 07:12:27 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge main into gatekeeper/fix-4260-1

Browse Source
This commit is contained in:
Gatefixer
2026-10-01 15:17:36 +00:00
parent 19e373e751 857e455361
commit 3869ba89b7
48 changed files with 1385 additions and 244 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.bumpversion.toml
+1 -1
View File
@@ -1,5 +1,5 @@
[tool.bumpversion]
current_version = "0.40.0-beta.11"
current_version = "0.40.0-beta.12"
parse = """(?x)
(?P<major>0|[1-9]\\d*)\\.
(?P<minor>0|[1-9]\\d*)\\.
Cargo.lock
Generated
+49 -48
View File
@@ -3588,8 +3588,8 @@ checksum = "42703706b716c37f96a77aea830392ad231f44c9e9a67872fa5548707e11b11c"
[[package]]
name = "fsst"
version = "13.0.0-beta.18"
source = "git+https://github.com/lance-format/lance.git?tag=v13.0.0-beta.18#b646eda6a891f481b6f6d6baef9cd17656aef65b"
version = "13.1.0-beta.1"
source = "git+https://github.com/lance-format/lance.git?tag=v13.1.0-beta.1#e5a3553b1699a7062ff7afe4ee268d596bbf2e0d"
dependencies = [
"arrow-array",
"rand 0.9.5",
@@ -5143,8 +5143,8 @@ checksum = "e037a2e1d8d5fdbd49b16a4ea09d5d6401c1f29eca5ff29d03d3824dba16256a"
[[package]]
name = "lance"
version = "13.0.0-beta.18"
source = "git+https://github.com/lance-format/lance.git?tag=v13.0.0-beta.18#b646eda6a891f481b6f6d6baef9cd17656aef65b"
version = "13.1.0-beta.1"
source = "git+https://github.com/lance-format/lance.git?tag=v13.1.0-beta.1#e5a3553b1699a7062ff7afe4ee268d596bbf2e0d"
dependencies = [
"arc-swap",
"arrow",
@@ -5217,7 +5217,7 @@ dependencies = [
[[package]]
name = "lance-arrow"
version = "13.0.0-beta.18"
version = "13.1.0-beta.1"
dependencies = [
"arrow-array",
"arrow-buffer",
@@ -5239,7 +5239,7 @@ dependencies = [
[[package]]
name = "lance-arrow-scalar"
version = "58.0.0"
source = "git+https://github.com/lance-format/lance.git?tag=v13.0.0-beta.18#b646eda6a891f481b6f6d6baef9cd17656aef65b"
source = "git+https://github.com/lance-format/lance.git?tag=v13.1.0-beta.1#e5a3553b1699a7062ff7afe4ee268d596bbf2e0d"
dependencies = [
"arrow-array",
"arrow-buffer",
@@ -5253,7 +5253,7 @@ dependencies = [
[[package]]
name = "lance-arrow-stats"
version = "58.0.0"
source = "git+https://github.com/lance-format/lance.git?tag=v13.0.0-beta.18#b646eda6a891f481b6f6d6baef9cd17656aef65b"
source = "git+https://github.com/lance-format/lance.git?tag=v13.1.0-beta.1#e5a3553b1699a7062ff7afe4ee268d596bbf2e0d"
dependencies = [
"arrow-array",
"arrow-schema",
@@ -5262,8 +5262,8 @@ dependencies = [
[[package]]
name = "lance-bitpacking"
version = "13.0.0-beta.18"
source = "git+https://github.com/lance-format/lance.git?tag=v13.0.0-beta.18#b646eda6a891f481b6f6d6baef9cd17656aef65b"
version = "13.1.0-beta.1"
source = "git+https://github.com/lance-format/lance.git?tag=v13.1.0-beta.1#e5a3553b1699a7062ff7afe4ee268d596bbf2e0d"
dependencies = [
"arrayref",
"crunchy",
@@ -5273,8 +5273,8 @@ dependencies = [
[[package]]
name = "lance-core"
version = "13.0.0-beta.18"
source = "git+https://github.com/lance-format/lance.git?tag=v13.0.0-beta.18#b646eda6a891f481b6f6d6baef9cd17656aef65b"
version = "13.1.0-beta.1"
source = "git+https://github.com/lance-format/lance.git?tag=v13.1.0-beta.1#e5a3553b1699a7062ff7afe4ee268d596bbf2e0d"
dependencies = [
"arrow-array",
"arrow-buffer",
@@ -5311,8 +5311,8 @@ dependencies = [
[[package]]
name = "lance-datafusion"
version = "13.0.0-beta.18"
source = "git+https://github.com/lance-format/lance.git?tag=v13.0.0-beta.18#b646eda6a891f481b6f6d6baef9cd17656aef65b"
version = "13.1.0-beta.1"
source = "git+https://github.com/lance-format/lance.git?tag=v13.1.0-beta.1#e5a3553b1699a7062ff7afe4ee268d596bbf2e0d"
dependencies = [
"arrow",
"arrow-array",
@@ -5343,8 +5343,8 @@ dependencies = [
[[package]]
name = "lance-datagen"
version = "13.0.0-beta.18"
source = "git+https://github.com/lance-format/lance.git?tag=v13.0.0-beta.18#b646eda6a891f481b6f6d6baef9cd17656aef65b"
version = "13.1.0-beta.1"
source = "git+https://github.com/lance-format/lance.git?tag=v13.1.0-beta.1#e5a3553b1699a7062ff7afe4ee268d596bbf2e0d"
dependencies = [
"arrow",
"arrow-array",
@@ -5361,8 +5361,8 @@ dependencies = [
[[package]]
name = "lance-derive"
version = "13.0.0-beta.18"
source = "git+https://github.com/lance-format/lance.git?tag=v13.0.0-beta.18#b646eda6a891f481b6f6d6baef9cd17656aef65b"
version = "13.1.0-beta.1"
source = "git+https://github.com/lance-format/lance.git?tag=v13.1.0-beta.1#e5a3553b1699a7062ff7afe4ee268d596bbf2e0d"
dependencies = [
"proc-macro2",
"quote",
@@ -5371,8 +5371,8 @@ dependencies = [
[[package]]
name = "lance-encoding"
version = "13.0.0-beta.18"
source = "git+https://github.com/lance-format/lance.git?tag=v13.0.0-beta.18#b646eda6a891f481b6f6d6baef9cd17656aef65b"
version = "13.1.0-beta.1"
source = "git+https://github.com/lance-format/lance.git?tag=v13.1.0-beta.1#e5a3553b1699a7062ff7afe4ee268d596bbf2e0d"
dependencies = [
"arrow-arith",
"arrow-array",
@@ -5405,8 +5405,8 @@ dependencies = [
[[package]]
name = "lance-file"
version = "13.0.0-beta.18"
source = "git+https://github.com/lance-format/lance.git?tag=v13.0.0-beta.18#b646eda6a891f481b6f6d6baef9cd17656aef65b"
version = "13.1.0-beta.1"
source = "git+https://github.com/lance-format/lance.git?tag=v13.1.0-beta.1#e5a3553b1699a7062ff7afe4ee268d596bbf2e0d"
dependencies = [
"arrow-arith",
"arrow-array",
@@ -5438,8 +5438,8 @@ dependencies = [
[[package]]
name = "lance-geo"
version = "13.0.0-beta.18"
source = "git+https://github.com/lance-format/lance.git?tag=v13.0.0-beta.18#b646eda6a891f481b6f6d6baef9cd17656aef65b"
version = "13.1.0-beta.1"
source = "git+https://github.com/lance-format/lance.git?tag=v13.1.0-beta.1#e5a3553b1699a7062ff7afe4ee268d596bbf2e0d"
dependencies = [
"datafusion",
"geo-traits",
@@ -5453,8 +5453,8 @@ dependencies = [
[[package]]
name = "lance-index"
version = "13.0.0-beta.18"
source = "git+https://github.com/lance-format/lance.git?tag=v13.0.0-beta.18#b646eda6a891f481b6f6d6baef9cd17656aef65b"
version = "13.1.0-beta.1"
source = "git+https://github.com/lance-format/lance.git?tag=v13.1.0-beta.1#e5a3553b1699a7062ff7afe4ee268d596bbf2e0d"
dependencies = [
"arc-swap",
"arrow",
@@ -5481,6 +5481,7 @@ dependencies = [
"geoarrow-array",
"geoarrow-schema",
"half",
"hashbrown 0.16.1",
"hex",
"itertools 0.14.0",
"jieba-rs",
@@ -5524,8 +5525,8 @@ dependencies = [
[[package]]
name = "lance-index-core"
version = "13.0.0-beta.18"
source = "git+https://github.com/lance-format/lance.git?tag=v13.0.0-beta.18#b646eda6a891f481b6f6d6baef9cd17656aef65b"
version = "13.1.0-beta.1"
source = "git+https://github.com/lance-format/lance.git?tag=v13.1.0-beta.1#e5a3553b1699a7062ff7afe4ee268d596bbf2e0d"
dependencies = [
"arrow-array",
"arrow-schema",
@@ -5548,8 +5549,8 @@ dependencies = [
[[package]]
name = "lance-io"
version = "13.0.0-beta.18"
source = "git+https://github.com/lance-format/lance.git?tag=v13.0.0-beta.18#b646eda6a891f481b6f6d6baef9cd17656aef65b"
version = "13.1.0-beta.1"
source = "git+https://github.com/lance-format/lance.git?tag=v13.1.0-beta.1#e5a3553b1699a7062ff7afe4ee268d596bbf2e0d"
dependencies = [
"arrow",
"arrow-array",
@@ -5591,8 +5592,8 @@ dependencies = [
[[package]]
name = "lance-linalg"
version = "13.0.0-beta.18"
source = "git+https://github.com/lance-format/lance.git?tag=v13.0.0-beta.18#b646eda6a891f481b6f6d6baef9cd17656aef65b"
version = "13.1.0-beta.1"
source = "git+https://github.com/lance-format/lance.git?tag=v13.1.0-beta.1#e5a3553b1699a7062ff7afe4ee268d596bbf2e0d"
dependencies = [
"arrow-array",
"arrow-schema",
@@ -5606,8 +5607,8 @@ dependencies = [
[[package]]
name = "lance-namespace"
version = "13.0.0-beta.18"
source = "git+https://github.com/lance-format/lance.git?tag=v13.0.0-beta.18#b646eda6a891f481b6f6d6baef9cd17656aef65b"
version = "13.1.0-beta.1"
source = "git+https://github.com/lance-format/lance.git?tag=v13.1.0-beta.1#e5a3553b1699a7062ff7afe4ee268d596bbf2e0d"
dependencies = [
"arrow",
"async-trait",
@@ -5621,8 +5622,8 @@ dependencies = [
[[package]]
name = "lance-namespace-impls"
version = "13.0.0-beta.18"
source = "git+https://github.com/lance-format/lance.git?tag=v13.0.0-beta.18#b646eda6a891f481b6f6d6baef9cd17656aef65b"
version = "13.1.0-beta.1"
source = "git+https://github.com/lance-format/lance.git?tag=v13.1.0-beta.1#e5a3553b1699a7062ff7afe4ee268d596bbf2e0d"
dependencies = [
"arc-swap",
"arrow",
@@ -5662,9 +5663,9 @@ dependencies = [
[[package]]
name = "lance-namespace-reqwest-client"
version = "0.12.0"
version = "0.13.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d8d23e54b1634d5bbb434f8dd33dc3c05f6e58d876a9a27b3b4aef58ddbe11af"
checksum = "828f291764feda98898452bea4ce3756b73e5d5c7c67b62edda27456b7cc72c1"
dependencies = [
"reqwest 0.12.28",
"serde",
@@ -5676,8 +5677,8 @@ dependencies = [
[[package]]
name = "lance-select"
version = "13.0.0-beta.18"
source = "git+https://github.com/lance-format/lance.git?tag=v13.0.0-beta.18#b646eda6a891f481b6f6d6baef9cd17656aef65b"
version = "13.1.0-beta.1"
source = "git+https://github.com/lance-format/lance.git?tag=v13.1.0-beta.1#e5a3553b1699a7062ff7afe4ee268d596bbf2e0d"
dependencies = [
"arrow-array",
"arrow-buffer",
@@ -5691,8 +5692,8 @@ dependencies = [
[[package]]
name = "lance-table"
version = "13.0.0-beta.18"
source = "git+https://github.com/lance-format/lance.git?tag=v13.0.0-beta.18#b646eda6a891f481b6f6d6baef9cd17656aef65b"
version = "13.1.0-beta.1"
source = "git+https://github.com/lance-format/lance.git?tag=v13.1.0-beta.1#e5a3553b1699a7062ff7afe4ee268d596bbf2e0d"
dependencies = [
"arrow",
"arrow-array",
@@ -5732,8 +5733,8 @@ dependencies = [
[[package]]
name = "lance-testing"
version = "13.0.0-beta.18"
source = "git+https://github.com/lance-format/lance.git?tag=v13.0.0-beta.18#b646eda6a891f481b6f6d6baef9cd17656aef65b"
version = "13.1.0-beta.1"
source = "git+https://github.com/lance-format/lance.git?tag=v13.1.0-beta.1#e5a3553b1699a7062ff7afe4ee268d596bbf2e0d"
dependencies = [
"arrow-array",
"arrow-schema",
@@ -5746,8 +5747,8 @@ dependencies = [
[[package]]
name = "lance-tokenizer"
version = "13.0.0-beta.18"
source = "git+https://github.com/lance-format/lance.git?tag=v13.0.0-beta.18#b646eda6a891f481b6f6d6baef9cd17656aef65b"
version = "13.1.0-beta.1"
source = "git+https://github.com/lance-format/lance.git?tag=v13.1.0-beta.1#e5a3553b1699a7062ff7afe4ee268d596bbf2e0d"
dependencies = [
"frostem",
"icu_segmenter",
@@ -5760,7 +5761,7 @@ dependencies = [
[[package]]
name = "lancedb"
version = "0.40.0-beta.11"
version = "0.40.0-beta.12"
dependencies = [
"ahash",
"anyhow",
@@ -5857,7 +5858,7 @@ dependencies = [
[[package]]
name = "lancedb-nodejs"
version = "0.40.0-beta.11"
version = "0.40.0-beta.12"
dependencies = [
"arrow-array",
"arrow-buffer",
@@ -5882,7 +5883,7 @@ dependencies = [
[[package]]
name = "lancedb-python"
version = "0.40.0-beta.11"
version = "0.40.0-beta.12"
dependencies = [
"arc-swap",
"arrow",
Cargo.toml
+14 -14
View File
@@ -13,20 +13,20 @@ categories = ["database-implementations"]
rust-version = "1.91.0"
[workspace.dependencies]
lance = { "version" = "=13.0.0-beta.18", default-features = false, "tag" = "v13.0.0-beta.18", "git" = "https://github.com/lance-format/lance.git" }
lance-core = { "version" = "=13.0.0-beta.18", "tag" = "v13.0.0-beta.18", "git" = "https://github.com/lance-format/lance.git" }
lance-datagen = { "version" = "=13.0.0-beta.18", "tag" = "v13.0.0-beta.18", "git" = "https://github.com/lance-format/lance.git" }
lance-file = { "version" = "=13.0.0-beta.18", "tag" = "v13.0.0-beta.18", "git" = "https://github.com/lance-format/lance.git" }
lance-io = { "version" = "=13.0.0-beta.18", default-features = false, "tag" = "v13.0.0-beta.18", "git" = "https://github.com/lance-format/lance.git" }
lance-index = { "version" = "=13.0.0-beta.18", "tag" = "v13.0.0-beta.18", "git" = "https://github.com/lance-format/lance.git" }
lance-linalg = { "version" = "=13.0.0-beta.18", "tag" = "v13.0.0-beta.18", "git" = "https://github.com/lance-format/lance.git" }
lance-namespace = { "version" = "=13.0.0-beta.18", "tag" = "v13.0.0-beta.18", "git" = "https://github.com/lance-format/lance.git" }
lance-namespace-impls = { "version" = "=13.0.0-beta.18", default-features = false, "tag" = "v13.0.0-beta.18", "git" = "https://github.com/lance-format/lance.git" }
lance-table = { "version" = "=13.0.0-beta.18", "tag" = "v13.0.0-beta.18", "git" = "https://github.com/lance-format/lance.git" }
lance-testing = { "version" = "=13.0.0-beta.18", "tag" = "v13.0.0-beta.18", "git" = "https://github.com/lance-format/lance.git" }
lance-datafusion = { "version" = "=13.0.0-beta.18", "tag" = "v13.0.0-beta.18", "git" = "https://github.com/lance-format/lance.git" }
lance-encoding = { "version" = "=13.0.0-beta.18", "tag" = "v13.0.0-beta.18", "git" = "https://github.com/lance-format/lance.git" }
lance-arrow = { version = "=13.0.0-beta.18", path = "python/vendor/lance-arrow" }
lance = { "version" = "=13.1.0-beta.1", default-features = false, "tag" = "v13.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
lance-core = { "version" = "=13.1.0-beta.1", "tag" = "v13.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
lance-datagen = { "version" = "=13.1.0-beta.1", "tag" = "v13.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
lance-file = { "version" = "=13.1.0-beta.1", "tag" = "v13.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
lance-io = { "version" = "=13.1.0-beta.1", default-features = false, "tag" = "v13.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
lance-index = { "version" = "=13.1.0-beta.1", "tag" = "v13.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
lance-linalg = { "version" = "=13.1.0-beta.1", "tag" = "v13.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
lance-namespace = { "version" = "=13.1.0-beta.1", "tag" = "v13.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
lance-namespace-impls = { "version" = "=13.1.0-beta.1", default-features = false, "tag" = "v13.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
lance-table = { "version" = "=13.1.0-beta.1", "tag" = "v13.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
lance-testing = { "version" = "=13.1.0-beta.1", "tag" = "v13.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
lance-datafusion = { "version" = "=13.1.0-beta.1", "tag" = "v13.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
lance-encoding = { "version" = "=13.1.0-beta.1", "tag" = "v13.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
lance-arrow = { version = "=13.1.0-beta.1", path = "python/vendor/lance-arrow" }
lancedb = { path = "rust/lancedb", default-features = false }
ahash = "0.8"
# Note that this one does not include pyarrow
docs/src/java/java.md
+1 -1
View File
@@ -14,7 +14,7 @@ Add the following dependency to your `pom.xml`:
<dependency>
<groupId>com.lancedb</groupId>
<artifactId>lancedb-core</artifactId>
<version>0.40.0-beta.11</version>
<version>0.40.0-beta.12</version>
</dependency>
```
docs/src/js/classes/BlobFile.md
+101 -5
View File
@@ -10,16 +10,52 @@ A lazy handle to blob bytes. Create one with [Table.fetchBlobFiles](Table.md#fet
## Methods
### close()
```ts
close(): Promise<void>
```
Releases the handle. Reads after `close()` fail. Calling it again does
nothing.
#### Returns
`Promise`&lt;`void`&gt;
***
### isClosed()
```ts
isClosed(): boolean
```
Returns true after [BlobFile.close](BlobFile.md#close).
#### Returns
`boolean`
***
### read()
```ts
read(): Promise<Buffer>
read(maxBytes?, options?): Promise<Buffer>
```
Reads from the cursor to the end and advances the cursor.
Reads from the cursor and advances the cursor.
A second call returns an empty buffer. [BlobFile.readRange](BlobFile.md#readrange) does
not move the cursor.
Reads to the end when `maxBytes` is omitted, or at most `maxBytes` bytes
otherwise. Returns an empty buffer at the end of the blob.
[BlobFile.readRange](BlobFile.md#readrange) does not move the cursor.
#### Parameters
* **maxBytes?**: `bigint`
* **options?**: [`BlobReadOptions`](../type-aliases/BlobReadOptions.md)
#### Returns
@@ -30,7 +66,10 @@ not move the cursor.
### readRange()
```ts
readRange(start, end): Promise<Buffer>
readRange(
start,
end,
options?): Promise<Buffer>
```
Reads the half-open byte range `[start, end)`.
@@ -43,12 +82,55 @@ Fails when `end` is past the blob size. Does not move the cursor.
* **end**: `bigint`
* **options?**: [`BlobReadOptions`](../type-aliases/BlobReadOptions.md)
#### Returns
`Promise`&lt;`Buffer`&gt;
***
### readRanges()
```ts
readRanges(ranges, options?): Promise<Buffer[]>
```
Reads several half-open byte ranges. Returns one buffer per range, in
the order given.
Fails when any `end` is past the blob size. Does not move the cursor.
#### Parameters
* **ranges**: [`BlobRange`](../type-aliases/BlobRange.md)[]
* **options?**: [`BlobReadOptions`](../type-aliases/BlobReadOptions.md)
#### Returns
`Promise`&lt;`Buffer`[]&gt;
***
### seek()
```ts
seek(position): Promise<void>
```
Moves the cursor to `position`, in bytes from the start of the blob.
#### Parameters
* **position**: `bigint`
#### Returns
`Promise`&lt;`void`&gt;
***
### size()
```ts
@@ -60,3 +142,17 @@ Returns the blob size in bytes.
#### Returns
`bigint`
***
### tell()
```ts
tell(): Promise<bigint>
```
Returns the cursor position in bytes.
#### Returns
`Promise`&lt;`bigint`&gt;
docs/src/js/classes/Table.md
+12 -2
View File
@@ -516,7 +516,10 @@ Drop an index from the table.
### fetchBlobFiles()
```ts
abstract fetchBlobFiles(column, rowIds): Promise<(null | BlobFile)[]>
abstract fetchBlobFiles(
column,
rowIds,
options?): Promise<(null | BlobFile)[]>
```
Opens lazy blob handles for `column` at the given row IDs using the
@@ -531,6 +534,8 @@ See [Table.fetchBlobs](Table.md#fetchblobs) for row-ID validity across versions.
* **rowIds**: readonly (`number` \| `bigint`)[]
* **options?**: [`BlobReadOptions`](../type-aliases/BlobReadOptions.md)
#### Returns
`Promise`&lt;(`null` \| [`BlobFile`](BlobFile.md))[]&gt;
@@ -540,7 +545,10 @@ See [Table.fetchBlobs](Table.md#fetchblobs) for row-ID validity across versions.
### fetchBlobs()
```ts
abstract fetchBlobs(column, rowIds): Promise<(null | Buffer)[]>
abstract fetchBlobs(
column,
rowIds,
options?): Promise<(null | Buffer)[]>
```
Bytes for `column` at row IDs from [Query.withRowId](Query.md#withrowid).
@@ -559,6 +567,8 @@ memory; use [Table.fetchBlobFiles](Table.md#fetchblobfiles) for large values.
* **rowIds**: readonly (`number` \| `bigint`)[]
* **options?**: [`BlobReadOptions`](../type-aliases/BlobReadOptions.md)
#### Returns
`Promise`&lt;(`null` \| `Buffer`)[]&gt;
docs/src/js/globals.md
+2
View File
@@ -158,6 +158,8 @@
- [AnalyzePlanDistributedMetrics](type-aliases/AnalyzePlanDistributedMetrics.md)
- [BaseTokenizer](type-aliases/BaseTokenizer.md)
- [BlobOptions](type-aliases/BlobOptions.md)
- [BlobRange](type-aliases/BlobRange.md)
- [BlobReadOptions](type-aliases/BlobReadOptions.md)
- [Data](type-aliases/Data.md)
- [DataLike](type-aliases/DataLike.md)
- [FieldLike](type-aliases/FieldLike.md)
docs/src/js/type-aliases/BlobRange.md
+27
View File
@@ -0,0 +1,27 @@
[**@lancedb/lancedb**](../README.md) • **Docs**
***
[@lancedb/lancedb](../globals.md) / BlobRange
# Type Alias: BlobRange
```ts
type BlobRange: object;
```
A half-open byte range `[start, end)` for [BlobFile.readRanges](../classes/BlobFile.md#readranges).
## Type declaration
### end
```ts
end: bigint;
```
### start
```ts
start: bigint;
```
docs/src/js/type-aliases/BlobReadOptions.md
+24
View File
@@ -0,0 +1,24 @@
[**@lancedb/lancedb**](../README.md) • **Docs**
***
[@lancedb/lancedb](../globals.md) / BlobReadOptions
# Type Alias: BlobReadOptions
```ts
type BlobReadOptions: object;
```
Options for blob reads.
## Type declaration
### signal?
```ts
optional signal: AbortSignal;
```
Cancels the read. The call rejects with `signal.reason`, and the native
read stops, including in-flight requests to a remote table.
java/lancedb-core/pom.xml
+1 -1
View File
@@ -8,7 +8,7 @@
<parent>
<groupId>com.lancedb</groupId>
<artifactId>lancedb-parent</artifactId>
<version>0.40.0-beta.11</version>
<version>0.40.0-beta.12</version>
<relativePath>../pom.xml</relativePath>
</parent>
java/pom.xml
+2 -2
View File
@@ -6,7 +6,7 @@
<groupId>com.lancedb</groupId>
<artifactId>lancedb-parent</artifactId>
<version>0.40.0-beta.11</version>
<version>0.40.0-beta.12</version>
<packaging>pom</packaging>
<name>${project.artifactId}</name>
<description>LanceDB Java SDK Parent POM</description>
@@ -28,7 +28,7 @@
<properties>
<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
<arrow.version>15.0.0</arrow.version>
<lance-core.version>13.0.0-beta.18</lance-core.version>
<lance-core.version>13.1.0-beta.1</lance-core.version>
<spotless.skip>false</spotless.skip>
<spotless.version>2.30.0</spotless.version>
<spotless.java.googlejavaformat.version>1.7</spotless.java.googlejavaformat.version>
nodejs/Cargo.toml
+1 -1
View File
@@ -1,7 +1,7 @@
[package]
name = "lancedb-nodejs"
edition.workspace = true
version = "0.40.0-beta.11"
version = "0.40.0-beta.12"
publish = false
license.workspace = true
description.workspace = true
nodejs/__test__/table.test.ts
+196
View File
@@ -2,6 +2,7 @@
// SPDX-FileCopyrightText: Copyright The LanceDB Authors
import * as fs from "fs";
import { getEventListeners } from "node:events";
import { pathToFileURL } from "node:url";
import * as path from "path";
import * as tmp from "tmp";
@@ -92,6 +93,38 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
await expect(table.countRows()).resolves.toBe(3);
});
it("creates and adds Arrow tables with large string and binary columns", async () => {
const data = new arrow.Table({
text: arrow.vectorFromArray(["alpha", "beta"], new arrow.LargeUtf8()),
bytes: arrow.vectorFromArray(
[Buffer.from("one"), Buffer.from("two")],
new arrow.LargeBinary(),
),
});
const conn = await connect(tmpDir.name);
const largeTable = await conn.createTable("large_columns", data);
await largeTable.add(data);
const rows = await largeTable.query().toArray();
expect(rows.map((row) => row.text)).toEqual([
"alpha",
"beta",
"alpha",
"beta",
]);
expect(rows.map((row) => Buffer.from(row.bytes).toString())).toEqual([
"one",
"two",
"one",
"two",
]);
const fields = (await largeTable.schema()).fields;
expect(fields.map((field) => field.type.typeId)).toEqual([
arrow.Type.LargeUtf8,
arrow.Type.LargeBinary,
]);
});
it("should support a foreign Float64 vector schema end to end", async () => {
const conn = await connect(tmpDir.name);
const schema = new arrow.Schema([
@@ -2601,6 +2634,27 @@ describe("when dealing with blob columns", () => {
expect(Buffer.from(await files[1]!.read()).toString()).toBe("beta");
});
it("adds a LargeBinary Arrow column to a blob table", async () => {
const db = await connect(tmpDir.name);
const schema = new Schema([new Field("id", new Int64()), blob("image")]);
const table = await db.createTable(
"blobs",
[{ id: 1n, image: Buffer.from("alpha") }],
{ schema },
);
const payload = Buffer.from("beta");
const data = new arrow18.Table({
id: arrow18.vectorFromArray([2n], new arrow18.Int64()),
image: arrow18.vectorFromArray([payload], new arrow18.LargeBinary()),
});
await table.add(data);
const rows = await table.query().withRowId().toArray();
const rowId = rows.find((row) => row.id === 2n)!._rowid as bigint;
const [actual] = await table.fetchBlobs("image", [rowId]);
expect(actual).toEqual(payload);
});
it("reads a half-open range", async () => {
const { table, rowIds } = await openBlobTable();
const files = await table.fetchBlobFiles("image", rowIds);
@@ -2625,6 +2679,148 @@ describe("when dealing with blob columns", () => {
).rejects.toThrow(/exceeds blob size/);
});
it("reads at most maxBytes and advances the cursor", async () => {
const { table, rowIds } = await openBlobTable();
const [handle] = await table.fetchBlobFiles("image", rowIds);
expect((await handle!.read(2n)).toString()).toBe("al");
expect(await handle!.tell()).toBe(2n);
expect((await handle!.read(2n)).toString()).toBe("ph");
expect((await handle!.read(10n)).toString()).toBe("a");
expect(await handle!.tell()).toBe(5n);
expect(await handle!.read(1n)).toEqual(Buffer.alloc(0));
});
it("seeks the cursor", async () => {
const { table, rowIds, alpha } = await openBlobTable();
const [handle] = await table.fetchBlobFiles("image", rowIds);
await handle!.seek(3n);
expect(await handle!.tell()).toBe(3n);
expect((await handle!.read()).toString()).toBe("ha");
await handle!.seek(0n);
expect(await handle!.read()).toEqual(alpha);
});
it("rejects a negative seek position", async () => {
const { table, rowIds } = await openBlobTable();
const [handle] = await table.fetchBlobFiles("image", rowIds);
await expect(handle!.seek(-1n)).rejects.toThrow(/cannot be negative/);
});
it("readRanges returns one buffer per range in order", async () => {
const { table, rowIds } = await openBlobTable();
const [handle] = await table.fetchBlobFiles("image", rowIds);
const buffers = await handle!.readRanges([
{ start: 3n, end: 5n },
{ start: 0n, end: 2n },
{ start: 3n, end: 5n },
]);
expect(buffers.map((b) => b.toString())).toEqual(["ha", "al", "ha"]);
expect(await handle!.tell()).toBe(0n);
});
it("fails when a readRanges end is past the blob size", async () => {
const { table, rowIds, alpha } = await openBlobTable();
const [handle] = await table.fetchBlobFiles("image", rowIds);
await expect(
handle!.readRanges([
{ start: 0n, end: 1n },
{ start: 0n, end: BigInt(alpha.length + 1) },
]),
).rejects.toThrow(/exceeds blob size/);
});
it("fails reads after close and closes once", async () => {
const { table, rowIds } = await openBlobTable();
const [handle] = await table.fetchBlobFiles("image", rowIds);
expect(handle!.isClosed()).toBe(false);
await handle!.close();
expect(handle!.isClosed()).toBe(true);
await expect(handle!.close()).resolves.toBeUndefined();
await expect(handle!.read()).rejects.toThrow(/already closed/);
await expect(handle!.read(1n)).rejects.toThrow(/already closed/);
await expect(handle!.readRange(0n, 1n)).rejects.toThrow(/already closed/);
await expect(handle!.readRanges([{ start: 0n, end: 1n }])).rejects.toThrow(
/already closed/,
);
await expect(handle!.seek(0n)).rejects.toThrow(/already closed/);
await expect(handle!.tell()).rejects.toThrow(/already closed/);
expect(handle!.size()).toBe(5n);
});
it("rejects reads with an already aborted signal", async () => {
const { table, rowIds, alpha } = await openBlobTable();
const [handle] = await table.fetchBlobFiles("image", rowIds);
const signal = AbortSignal.abort();
const abortError = { name: "AbortError" };
await expect(handle!.read(undefined, { signal })).rejects.toMatchObject(
abortError,
);
await expect(handle!.read(2n, { signal })).rejects.toMatchObject(
abortError,
);
await expect(handle!.readRange(0n, 1n, { signal })).rejects.toMatchObject(
abortError,
);
await expect(
handle!.readRanges([{ start: 0n, end: 1n }], { signal }),
).rejects.toMatchObject(abortError);
await expect(
table.fetchBlobs("image", rowIds, { signal }),
).rejects.toMatchObject(abortError);
await expect(
table.fetchBlobFiles("image", rowIds, { signal }),
).rejects.toMatchObject(abortError);
expect(await handle!.read()).toEqual(alpha);
});
it("rejects with the abort reason", async () => {
const { table, rowIds } = await openBlobTable();
const [handle] = await table.fetchBlobFiles("image", rowIds);
const reason = new Error("caller gave up");
await expect(
handle!.readRange(0n, 1n, { signal: AbortSignal.abort(reason) }),
).rejects.toBe(reason);
});
it("reads with a signal and removes its abort listener", async () => {
const { table, rowIds, alpha, beta } = await openBlobTable();
const controller = new AbortController();
const { signal } = controller;
const [handle] = await table.fetchBlobFiles("image", rowIds, { signal });
expect((await handle!.readRange(0n, 2n, { signal })).toString()).toBe("al");
expect(await table.fetchBlobs("image", rowIds, { signal })).toEqual([
alpha,
beta,
null,
]);
expect(getEventListeners(signal, "abort")).toHaveLength(0);
controller.abort();
expect(await handle!.read()).toEqual(alpha);
});
it("cancels an in-flight read", async () => {
const db = await connect(tmpDir.name);
const schema = new Schema([
new Field("id", new Int64(), true),
blob("payload", { inlineSizeThreshold: 0, dedicatedSizeThreshold: 1 }),
]);
const payload = Buffer.alloc(32 * 1024 * 1024, 7);
const table = await db.createTable("large_blobs", [{ id: 1n, payload }], {
schema,
});
const [row] = await table.query().withRowId().toArray();
const [handle] = await table.fetchBlobFiles("payload", [
row._rowid as bigint,
]);
const controller = new AbortController();
const pending = handle!.readRange(0n, handle!.size(), {
signal: controller.signal,
});
controller.abort();
await expect(pending).rejects.toMatchObject({ name: "AbortError" });
expect(await handle!.readRange(0n, 4n)).toEqual(payload.subarray(0, 4));
});
it("rejects fetchBlobs on a non-blob column", async () => {
const { table, rowIds } = await openBlobTable();
await expect(table.fetchBlobs("id", rowIds)).rejects.toThrow(/blob/i);
nodejs/lancedb/blob.ts
+95 -7
View File
@@ -141,13 +141,16 @@ export class BlobFile {
}
/**
* Reads from the cursor to the end and advances the cursor.
* Reads from the cursor and advances the cursor.
*
* A second call returns an empty buffer. {@link BlobFile.readRange} does
* not move the cursor.
* Reads to the end when `maxBytes` is omitted, or at most `maxBytes` bytes
* otherwise. Returns an empty buffer at the end of the blob.
* {@link BlobFile.readRange} does not move the cursor.
*/
read(): Promise<Buffer> {
return this.inner.read();
read(maxBytes?: bigint, options?: BlobReadOptions): Promise<Buffer> {
return runWithSignal(options?.signal, (signal) =>
this.inner.read(maxBytes, signal),
);
}
/**
@@ -155,11 +158,96 @@ export class BlobFile {
*
* Fails when `end` is past the blob size. Does not move the cursor.
*/
readRange(start: bigint, end: bigint): Promise<Buffer> {
return this.inner.readRange(start, end);
readRange(
start: bigint,
end: bigint,
options?: BlobReadOptions,
): Promise<Buffer> {
return runWithSignal(options?.signal, (signal) =>
this.inner.readRange(start, end, signal),
);
}
/**
* Reads several half-open byte ranges. Returns one buffer per range, in
* the order given.
*
* Fails when any `end` is past the blob size. Does not move the cursor.
*/
readRanges(
ranges: BlobRange[],
options?: BlobReadOptions,
): Promise<Buffer[]> {
return runWithSignal(options?.signal, (signal) =>
this.inner.readRanges(ranges, signal),
);
}
/** Moves the cursor to `position`, in bytes from the start of the blob. */
seek(position: bigint): Promise<void> {
return this.inner.seek(position);
}
/** Returns the cursor position in bytes. */
tell(): Promise<bigint> {
return this.inner.tell();
}
/**
* Releases the handle. Reads after `close()` fail. Calling it again does
* nothing.
*/
close(): Promise<void> {
return this.inner.close();
}
/** Returns true after {@link BlobFile.close}. */
isClosed(): boolean {
return this.inner.isClosed();
}
}
/** Options for blob reads. */
export type BlobReadOptions = {
/**
* Cancels the read. The call rejects with `signal.reason`, and the native
* read stops, including in-flight requests to a remote table.
*/
signal?: AbortSignal;
};
/** @ignore */
export async function runWithSignal<T>(
signal: AbortSignal | undefined,
run: (signal: AbortSignal | undefined) => Promise<T>,
): Promise<T> {
if (signal === undefined) {
return run(undefined);
}
signal.throwIfAborted();
// napi-rs replaces `onabort` on the signal it receives, so pass a private
// signal and forward the caller's abort to it.
const controller = new AbortController();
const onAbort = () => controller.abort();
signal.addEventListener("abort", onAbort, { once: true });
try {
return await run(controller.signal);
} catch (err) {
if (signal.aborted) {
throw signal.reason;
}
throw err;
} finally {
signal.removeEventListener("abort", onAbort);
}
}
/** A half-open byte range `[start, end)` for {@link BlobFile.readRanges}. */
export type BlobRange = {
start: bigint;
end: bigint;
};
export function coerceBlobValue(value: unknown): BlobInput | null {
if (value == null) {
return null;
nodejs/lancedb/index.ts
+1 -1
View File
@@ -84,7 +84,7 @@ export {
} from "./arrow";
export { blob, isBlobField, BlobFile } from "./blob";
export type { BlobOptions } from "./blob";
export type { BlobOptions, BlobRange, BlobReadOptions } from "./blob";
export {
Connection,
nodejs/lancedb/sanitize.ts
+6
View File
@@ -43,6 +43,8 @@ import {
Interval,
IntervalDayTime,
IntervalYearMonth,
LargeBinary,
LargeUtf8,
List,
Map_,
Null,
@@ -465,8 +467,12 @@ function sanitizeTypeById(
return sanitizeFloat(typeLike);
case Type.Binary:
return new Binary();
case Type.LargeBinary:
return new LargeBinary();
case Type.Utf8:
return new Utf8();
case Type.LargeUtf8:
return new LargeUtf8();
case Type.Bool:
return new Bool();
case Type.Decimal:
nodejs/lancedb/table.ts
+10 -5
View File
@@ -17,7 +17,7 @@ import {
tableFromIPC,
} from "./arrow";
import { BlobFile } from "./blob";
import { BlobFile, BlobReadOptions, runWithSignal } from "./blob";
import { EmbeddingFunctionConfig, getRegistry } from "./embedding/registry";
import { IndexOptions } from "./indices";
import { Job } from "./job";
@@ -545,6 +545,7 @@ export abstract class Table {
abstract fetchBlobs(
column: string,
rowIds: readonly (bigint | number)[],
options?: BlobReadOptions,
): Promise<(Buffer | null)[]>;
/**
@@ -557,6 +558,7 @@ export abstract class Table {
abstract fetchBlobFiles(
column: string,
rowIds: readonly (bigint | number)[],
options?: BlobReadOptions,
): Promise<(BlobFile | null)[]>;
/**
@@ -1248,8 +1250,11 @@ export class LocalTable extends Table {
async fetchBlobs(
column: string,
rowIds: readonly (bigint | number)[],
options?: BlobReadOptions,
): Promise<(Buffer | null)[]> {
const values = await this.inner.fetchBlobs(column, rowIdsToBigInts(rowIds));
const values = await runWithSignal(options?.signal, (signal) =>
this.inner.fetchBlobs(column, rowIdsToBigInts(rowIds), signal),
);
// N-API Option maps missing values to undefined. Collapse those to null.
return values.map((value) => value ?? null);
}
@@ -1257,10 +1262,10 @@ export class LocalTable extends Table {
async fetchBlobFiles(
column: string,
rowIds: readonly (bigint | number)[],
options?: BlobReadOptions,
): Promise<(BlobFile | null)[]> {
const files = await this.inner.fetchBlobFiles(
column,
rowIdsToBigInts(rowIds),
const files = await runWithSignal(options?.signal, (signal) =>
this.inner.fetchBlobFiles(column, rowIdsToBigInts(rowIds), signal),
);
// N-API Option maps missing values to undefined. Collapse those to null.
return files.map((file) =>
nodejs/npm/darwin-arm64/package.json
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "@lancedb/lancedb-darwin-arm64",
"version": "0.40.0-beta.11",
"version": "0.40.0-beta.12",
"os": ["darwin"],
"cpu": ["arm64"],
"main": "lancedb.darwin-arm64.node",
nodejs/npm/linux-arm64-gnu/package.json
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "@lancedb/lancedb-linux-arm64-gnu",
"version": "0.40.0-beta.11",
"version": "0.40.0-beta.12",
"os": ["linux"],
"cpu": ["arm64"],
"main": "lancedb.linux-arm64-gnu.node",
nodejs/npm/linux-arm64-musl/package.json
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "@lancedb/lancedb-linux-arm64-musl",
"version": "0.40.0-beta.11",
"version": "0.40.0-beta.12",
"os": ["linux"],
"cpu": ["arm64"],
"main": "lancedb.linux-arm64-musl.node",
nodejs/npm/linux-x64-gnu/package.json
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "@lancedb/lancedb-linux-x64-gnu",
"version": "0.40.0-beta.11",
"version": "0.40.0-beta.12",
"os": ["linux"],
"cpu": ["x64"],
"main": "lancedb.linux-x64-gnu.node",
nodejs/npm/linux-x64-musl/package.json
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "@lancedb/lancedb-linux-x64-musl",
"version": "0.40.0-beta.11",
"version": "0.40.0-beta.12",
"os": ["linux"],
"cpu": ["x64"],
"main": "lancedb.linux-x64-musl.node",
nodejs/npm/win32-arm64-msvc/package.json
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "@lancedb/lancedb-win32-arm64-msvc",
"version": "0.40.0-beta.11",
"version": "0.40.0-beta.12",
"os": [
"win32"
],
nodejs/npm/win32-x64-msvc/package.json
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "@lancedb/lancedb-win32-x64-msvc",
"version": "0.40.0-beta.11",
"version": "0.40.0-beta.12",
"os": ["win32"],
"cpu": ["x64"],
"main": "lancedb.win32-x64-msvc.node",
nodejs/package.json
+1 -1
View File
@@ -11,7 +11,7 @@
"ann"
],
"private": false,
"version": "0.40.0-beta.11",
"version": "0.40.0-beta.12",
"main": "dist/index.js",
"exports": {
".": "./dist/index.js",
nodejs/src/blob.rs
+133 -10
View File
@@ -1,25 +1,45 @@
// SPDX-License-Identifier: Apache-2.0
// SPDX-FileCopyrightText: Copyright The LanceDB Authors
use std::future::Future;
use std::ops::Range;
use std::sync::Arc;
use std::sync::atomic::{AtomicBool, Ordering};
use arrow_array::{Array, LargeBinaryArray};
use futures::future::abortable;
use lancedb::blob::BlobFile as LanceBlobFile;
use napi::Env;
use napi::bindgen_prelude::*;
use napi_derive::napi;
use crate::error::convert_error;
#[napi(object)]
pub struct BlobRange {
pub start: BigInt,
pub end: BigInt,
}
#[napi]
pub struct BlobFile {
inner: Arc<LanceBlobFile>,
closed: AtomicBool,
}
impl BlobFile {
pub(crate) fn new(inner: LanceBlobFile) -> Self {
Self {
inner: Arc::new(inner),
closed: AtomicBool::new(false),
}
}
fn ensure_open(&self) -> napi::Result<()> {
if self.closed.load(Ordering::Acquire) {
Err(napi::Error::from_reason("blob file is already closed"))
} else {
Ok(())
}
}
}
@@ -32,21 +52,124 @@ impl BlobFile {
}
#[napi]
pub async fn read(&self) -> napi::Result<Buffer> {
let bytes = self.inner.read().await.map_err(|err| convert_error(&err))?;
Ok(Buffer::from(bytes.as_ref()))
pub fn read<'env>(
&self,
env: &'env Env,
max_bytes: Option<BigInt>,
signal: Option<AbortSignal>,
) -> napi::Result<PromiseRaw<'env, Buffer>> {
self.ensure_open()?;
let max_bytes = max_bytes
.map(|max_bytes| {
usize::try_from(parse_u64(max_bytes, "maxBytes")?)
.map_err(|_| napi::Error::from_reason("maxBytes is too large"))
})
.transpose()?;
let inner = self.inner.clone();
spawn_abortable(env, signal, async move {
let bytes = match max_bytes {
None => inner.read().await,
Some(max_bytes) => inner.read_up_to(max_bytes).await,
}
.map_err(|err| convert_error(&err))?;
Ok(Buffer::from(bytes.as_ref()))
})
}
#[napi]
pub async fn read_range(&self, start: BigInt, end: BigInt) -> napi::Result<Buffer> {
pub fn read_range<'env>(
&self,
env: &'env Env,
start: BigInt,
end: BigInt,
signal: Option<AbortSignal>,
) -> napi::Result<PromiseRaw<'env, Buffer>> {
self.ensure_open()?;
let range = bigint_range(start, end)?;
let bytes = self
.inner
.read_range(range)
.await
.map_err(|err| convert_error(&err))?;
Ok(Buffer::from(bytes.as_ref()))
let inner = self.inner.clone();
spawn_abortable(env, signal, async move {
let bytes = inner
.read_range(range)
.await
.map_err(|err| convert_error(&err))?;
Ok(Buffer::from(bytes.as_ref()))
})
}
#[napi]
pub fn read_ranges<'env>(
&self,
env: &'env Env,
ranges: Vec<BlobRange>,
signal: Option<AbortSignal>,
) -> napi::Result<PromiseRaw<'env, Vec<Buffer>>> {
self.ensure_open()?;
let ranges = ranges
.into_iter()
.map(|range| bigint_range(range.start, range.end))
.collect::<napi::Result<Vec<_>>>()?;
let inner = self.inner.clone();
spawn_abortable(env, signal, async move {
let buffers = inner
.read_ranges(&ranges)
.await
.map_err(|err| convert_error(&err))?;
Ok(buffers
.iter()
.map(|bytes| Buffer::from(bytes.as_ref()))
.collect())
})
}
#[napi]
pub async fn seek(&self, position: BigInt) -> napi::Result<()> {
self.ensure_open()?;
let position = parse_u64(position, "position")?;
self.inner
.seek(position)
.await
.map_err(|err| convert_error(&err))
}
#[napi]
pub async fn tell(&self) -> napi::Result<BigInt> {
self.ensure_open()?;
let position = self.inner.tell().await.map_err(|err| convert_error(&err))?;
Ok(BigInt::from(position))
}
#[napi]
pub async fn close(&self) -> napi::Result<()> {
if self.closed.swap(true, Ordering::AcqRel) {
return Ok(());
}
self.inner.close().await.map_err(|err| convert_error(&err))
}
#[napi]
pub fn is_closed(&self) -> bool {
self.closed.load(Ordering::Acquire)
}
}
/// Runs `fut` on the napi runtime. Aborting `signal` drops the future, which
/// cancels in-flight reads.
pub fn spawn_abortable<'env, T>(
env: &'env Env,
signal: Option<AbortSignal>,
fut: impl Future<Output = napi::Result<T>> + Send + 'static,
) -> napi::Result<PromiseRaw<'env, T>>
where
T: ToNapiValue + Send + 'static,
{
let (fut, handle) = abortable(fut);
if let Some(signal) = signal {
signal.on_abort(move || handle.abort());
}
env.spawn_future(async move {
fut.await
.unwrap_or_else(|_| Err(napi::Error::from_reason("blob read aborted")))
})
}
fn bigint_range(start: BigInt, end: BigInt) -> napi::Result<Range<u64>> {
nodejs/src/table.rs
+29 -20
View File
@@ -11,11 +11,12 @@ use lancedb::table::{
FieldMetadataUpdate as LanceFieldMetadataUpdate, FtsToken as LanceDbFtsToken,
NewColumnTransform, OptimizeAction, OptimizeOptions, Ref, Table as LanceDbTable,
};
use napi::Env;
use napi::bindgen_prelude::*;
use napi::threadsafe_function::{ThreadsafeFunction, ThreadsafeFunctionCallMode};
use napi_derive::napi;
use crate::blob::{BlobFile, copy_blob_buffers, parse_row_ids};
use crate::blob::{BlobFile, copy_blob_buffers, parse_row_ids, spawn_abortable};
use crate::error::NapiErrorExt;
use crate::index::Index;
use crate::merge::NativeMergeInsertBuilder;
@@ -340,36 +341,44 @@ impl Table {
}
#[napi(catch_unwind)]
pub async fn fetch_blobs(
pub fn fetch_blobs<'env>(
&self,
env: &'env Env,
column: String,
row_ids: Vec<BigInt>,
) -> napi::Result<Vec<Option<Buffer>>> {
signal: Option<AbortSignal>,
) -> napi::Result<PromiseRaw<'env, Vec<Option<Buffer>>>> {
let row_ids = parse_row_ids(row_ids)?;
let array = self
.inner_ref()?
.fetch_blobs(column.as_str(), &row_ids)
.await
.default_error()?;
Ok(copy_blob_buffers(array))
let table = self.inner_ref()?.clone();
spawn_abortable(env, signal, async move {
let array = table
.fetch_blobs(column.as_str(), &row_ids)
.await
.default_error()?;
Ok(copy_blob_buffers(array))
})
}
#[napi(catch_unwind)]
pub async fn fetch_blob_files(
pub fn fetch_blob_files<'env>(
&self,
env: &'env Env,
column: String,
row_ids: Vec<BigInt>,
) -> napi::Result<Vec<Option<BlobFile>>> {
signal: Option<AbortSignal>,
) -> napi::Result<PromiseRaw<'env, Vec<Option<BlobFile>>>> {
let row_ids = parse_row_ids(row_ids)?;
let files = self
.inner_ref()?
.fetch_blob_files(column.as_str(), &row_ids)
.await
.default_error()?;
Ok(files
.into_iter()
.map(|file| file.map(BlobFile::new))
.collect())
let table = self.inner_ref()?.clone();
spawn_abortable(env, signal, async move {
let files = table
.fetch_blob_files(column.as_str(), &row_ids)
.await
.default_error()?;
Ok(files
.into_iter()
.map(|file| file.map(BlobFile::new))
.collect())
})
}
#[napi(catch_unwind)]
python/Cargo.toml
+1 -1
View File
@@ -1,6 +1,6 @@
[package]
name = "lancedb-python"
version = "0.40.0-beta.11"
version = "0.40.0-beta.12"
publish = false
edition.workspace = true
description = "Python bindings for LanceDB"
python/python/lancedb/_lancedb.pyi
+13 -5
View File
@@ -149,12 +149,20 @@ class Connection(object):
limit: Optional[int],
) -> list[str]: ... # Deprecated: Use list_tables instead
async def open_job(self, job_id: str) -> Job: ...
async def create_function_async(self, request_json: str) -> Job: ...
async def get_function(self, name: str, version: str) -> str: ...
async def list_functions(self) -> List[str]: ...
async def drop_function(self, name: str, version: str) -> bool: ...
async def create_function_async(
self, request_json: str, namespace_path: Optional[List[str]] = None
) -> Job: ...
async def get_function(
self, name: str, version: str, namespace_path: Optional[List[str]] = None
) -> str: ...
async def list_functions(
self, namespace_path: Optional[List[str]] = None
) -> List[str]: ...
async def drop_function(
self, name: str, version: str, namespace_path: Optional[List[str]] = None
) -> bool: ...
async def drop_function_async(
self, name: str, version: str
self, name: str, version: str, namespace_path: Optional[List[str]] = None
) -> Tuple[bool, Job]: ...
async def create_secret(
self, name: str, value: str, namespace_path: Optional[List[str]] = None
python/python/lancedb/db.py
+123 -31
View File
@@ -784,6 +784,7 @@ class DBConnection(EnforceOverrides):
definition: UdfDefinition,
*,
secrets: Optional[Sequence[EnvVarSecret]] = None,
namespace_path: Optional[List[str]] = None,
) -> FunctionVersion:
"""Build and register a scalar Python UDF, then return its version.
@@ -800,6 +801,9 @@ class DBConnection(EnforceOverrides):
Function needs, each naming a Secret and the environment variable
its value arrives in. The Function's source is unchanged by this;
it reads the variable the way it already did.
namespace_path : list of str, optional
The namespace holding the Function. None or an empty list is the
root namespace.
Examples
--------
@@ -815,13 +819,16 @@ class DBConnection(EnforceOverrides):
)
```
"""
return self.create_function_async(definition, secrets=secrets).wait()
return self.create_function_async(
definition, secrets=secrets, namespace_path=namespace_path
).wait()
def create_function_async(
self,
definition: UdfDefinition,
*,
secrets: Optional[Sequence[EnvVarSecret]] = None,
namespace_path: Optional[List[str]] = None,
) -> Job[FunctionVersion]:
"""Submit a scalar Python UDF for building and registration.
@@ -833,17 +840,26 @@ class DBConnection(EnforceOverrides):
"Function catalog operations are not supported for this connection type"
)
def get_function(self, name: str, *, version: str) -> FunctionVersion:
def get_function(
self,
name: str,
*,
version: str,
namespace_path: Optional[List[str]] = None,
) -> FunctionVersion:
"""Open one exact immutable Function version from the remote catalog."""
raise NotImplementedError(
"Function catalog operations are not supported for this connection type"
)
def list_functions(self) -> List[FunctionVersion]:
"""List every published immutable Function version.
def list_functions(
self, *, namespace_path: Optional[List[str]] = None
) -> List[FunctionVersion]:
"""List every published immutable Function version in a namespace.
Results are ordered by Function name then version. Local connections
raise ``NotImplementedError``.
Functions in child namespaces are not included. Results are ordered by
Function name then version. Local connections raise
``NotImplementedError``.
Examples
--------
@@ -857,7 +873,13 @@ class DBConnection(EnforceOverrides):
"Function catalog operations are not supported for this connection type"
)
def drop_function(self, name: str, *, version: str) -> bool:
def drop_function(
self,
name: str,
*,
version: str,
namespace_path: Optional[List[str]] = None,
) -> bool:
"""Drop a Function name and the object it was bound to.
The requested version must exist in the currently named object. Returns
@@ -870,7 +892,13 @@ class DBConnection(EnforceOverrides):
"Function catalog operations are not supported for this connection type"
)
def drop_function_async(self, name: str, *, version: str) -> Tuple[bool, Job]:
def drop_function_async(
self,
name: str,
*,
version: str,
namespace_path: Optional[List[str]] = None,
) -> Tuple[bool, Job]:
"""Drop a Function name and return its cleanup job.
The name is unbound before this returns; the object's content may still
@@ -1808,25 +1836,62 @@ class LanceDBConnection(DBConnection):
definition: UdfDefinition,
*,
secrets: Optional[Sequence[EnvVarSecret]] = None,
namespace_path: Optional[List[str]] = None,
) -> Job[FunctionVersion]:
job = LOOP.run(self._conn.create_function_async(definition, secrets=secrets))
job = LOOP.run(
self._conn.create_function_async(
definition, secrets=secrets, namespace_path=namespace_path
)
)
return Job(job)
@override
def get_function(self, name: str, *, version: str) -> FunctionVersion:
return LOOP.run(self._conn.get_function(name, version=version))
def get_function(
self,
name: str,
*,
version: str,
namespace_path: Optional[List[str]] = None,
) -> FunctionVersion:
return LOOP.run(
self._conn.get_function(
name, version=version, namespace_path=namespace_path
)
)
@override
def list_functions(self) -> List[FunctionVersion]:
return LOOP.run(self._conn.list_functions())
def list_functions(
self, *, namespace_path: Optional[List[str]] = None
) -> List[FunctionVersion]:
return LOOP.run(self._conn.list_functions(namespace_path=namespace_path))
@override
def drop_function(self, name: str, *, version: str) -> bool:
return LOOP.run(self._conn.drop_function(name, version=version))
def drop_function(
self,
name: str,
*,
version: str,
namespace_path: Optional[List[str]] = None,
) -> bool:
return LOOP.run(
self._conn.drop_function(
name, version=version, namespace_path=namespace_path
)
)
@override
def drop_function_async(self, name: str, *, version: str) -> Tuple[bool, Job]:
dropped, job = LOOP.run(self._conn.drop_function_async(name, version=version))
def drop_function_async(
self,
name: str,
*,
version: str,
namespace_path: Optional[List[str]] = None,
) -> Tuple[bool, Job]:
dropped, job = LOOP.run(
self._conn.drop_function_async(
name, version=version, namespace_path=namespace_path
)
)
return dropped, Job(job)
@override
@@ -2787,6 +2852,7 @@ class AsyncConnection(object):
definition: UdfDefinition,
*,
secrets: Optional[Sequence[EnvVarSecret]] = None,
namespace_path: Optional[List[str]] = None,
) -> AsyncJob[FunctionVersion]:
"""Submit a scalar Python UDF for building and registration.
@@ -2794,36 +2860,60 @@ class AsyncConnection(object):
artifact. Waiting on the job returns the immutable Function version.
``secrets`` is a sequence of
[EnvVarSecret][lancedb.secrets.EnvVarSecret], each naming a Secret and
the environment variable its value arrives in. Local connections raise
``NotImplementedError``.
the environment variable its value arrives in. ``namespace_path`` is
the namespace the Function is registered in; None or an empty list is
the root. Local connections raise ``NotImplementedError``.
"""
if not isinstance(definition, UdfDefinition):
raise TypeError("create_function_async requires a @udf definition")
request = definition.bind_secrets(secrets)
inner = await self._inner.create_function_async(request.to_canonical_json())
inner = await self._inner.create_function_async(
request.to_canonical_json(), namespace_path
)
return _typed_job(inner, FunctionVersion.from_json)
async def get_function(self, name: str, *, version: str) -> FunctionVersion:
async def get_function(
self,
name: str,
*,
version: str,
namespace_path: Optional[List[str]] = None,
) -> FunctionVersion:
"""Open one exact immutable Function version from the remote catalog."""
return FunctionVersion.from_json(await self._inner.get_function(name, version))
return FunctionVersion.from_json(
await self._inner.get_function(name, version, namespace_path)
)
async def list_functions(self) -> List[FunctionVersion]:
"""List every published immutable Function version.
async def list_functions(
self, *, namespace_path: Optional[List[str]] = None
) -> List[FunctionVersion]:
"""List every published immutable Function version in a namespace.
Results are ordered by Function name then version. Local connections
raise ``NotImplementedError``.
Functions in child namespaces are not included. Results are ordered by
Function name then version. Local connections raise
``NotImplementedError``.
"""
return [
FunctionVersion.from_json(value)
for value in await self._inner.list_functions()
for value in await self._inner.list_functions(namespace_path)
]
async def drop_function(self, name: str, *, version: str) -> bool:
async def drop_function(
self,
name: str,
*,
version: str,
namespace_path: Optional[List[str]] = None,
) -> bool:
"""Drop a Function name and the object it was bound to."""
return await self._inner.drop_function(name, version)
return await self._inner.drop_function(name, version, namespace_path)
async def drop_function_async(
self, name: str, *, version: str
self,
name: str,
*,
version: str,
namespace_path: Optional[List[str]] = None,
) -> Tuple[bool, AsyncJob]:
"""Drop a Function name and return its cleanup job.
@@ -2831,7 +2921,9 @@ class AsyncConnection(object):
be being deleted. Await :meth:`AsyncJob.wait` to wait for that to
finish.
"""
dropped, job = await self._inner.drop_function_async(name, version)
dropped, job = await self._inner.drop_function_async(
name, version, namespace_path
)
return dropped, AsyncJob(job)
async def create_secret(
python/python/lancedb/embeddings/base.py
+5 -1
View File
@@ -182,7 +182,11 @@ class EmbeddingFunction(BaseModel, ABC):
def VectorField(self, **kwargs):
"""
Creates a pydantic Field that can automatically annotate
the target vector column for this embedding function
the target vector column for this embedding function.
The field can be annotated as ``list[float]`` for compatibility with
static type checkers. LanceDB will infer the fixed vector dimension from
this embedding function.
"""
return Field(json_schema_extra={"vector_column_for": self}, **kwargs)
python/python/lancedb/functions.py
+10 -1
View File
@@ -356,9 +356,16 @@ _ObjectVersion = Annotated[
class FunctionVersion(_RemoteValue):
"""A pinned object revision, independent of its executable image digest."""
"""A pinned object revision, independent of its executable image digest.
``name`` and ``namespace_path`` are the Function's parts, as a
[SecretReference][lancedb.functions.SecretReference] carries a Secret's;
they are what [get_function][lancedb.db.DBConnection.get_function] takes.
An empty ``namespace_path`` is the root namespace.
"""
name: str
namespace_path: tuple[str, ...] = ()
object_id: str
location: str
version: _ObjectVersion
@@ -444,6 +451,7 @@ class FunctionVersion(_RemoteValue):
return FunctionApplication(
function=FunctionVersionRef(
name=self.name,
namespace_path=self.namespace_path,
object_id=self.object_id,
location=self.location,
version=self.version,
@@ -502,6 +510,7 @@ class FunctionRegistrationRequest(_RemoteValue):
class FunctionVersionRef(_OpenRemoteValue):
name: str
namespace_path: tuple[str, ...] = ()
object_id: str
location: str
version: _ObjectVersion
python/python/lancedb/pydantic.py
+39
View File
@@ -88,6 +88,17 @@ def Vector(
... pa.field("url", pa.utf8(), False),
... pa.field("embeddings", pa.list_(pa.float32(), 768))
... ])
Notes
-----
``Vector`` creates a type dynamically, so calls such as ``Vector(768)`` are
not valid static type annotations. For an embedding field, use the standard
``list[float]`` annotation when running mypy; ``VectorField`` supplies the
fixed dimension to LanceDB::
class MyModel(LanceModel):
text: str = embeddings.SourceField()
vector: list[float] = embeddings.VectorField()
"""
# TODO: make a public parameterized type.
@@ -313,6 +324,10 @@ def _unwrap_optional_annotation(annotation: Any) -> Any | None:
def _pydantic_to_arrow_type(field: FieldInfo) -> pa.DataType:
"""Convert a Pydantic FieldInfo to Arrow DataType"""
embedding_vector_type = _embedding_vector_to_arrow_type(field)
if embedding_vector_type is not None:
return embedding_vector_type
unwrapped = _unwrap_optional_annotation(field.annotation)
if unwrapped is not None:
return _pydantic_type_to_arrow_type(unwrapped, field)
@@ -326,8 +341,32 @@ def _pydantic_to_arrow_type(field: FieldInfo) -> pa.DataType:
return _pydantic_type_to_arrow_type(field.annotation, field)
def _embedding_vector_to_arrow_type(field: FieldInfo) -> pa.DataType | None:
"""Infer a fixed-size vector type from ``VectorField`` metadata."""
if not _is_embedding_vector_annotation(field):
return None
function = get_extras(field, "vector_column_for")
return pa.list_(pa.float32(), function.ndims())
def _is_embedding_vector_annotation(field: FieldInfo) -> bool:
if get_extras(field, "vector_column_for") is None:
return False
annotation = _unwrap_optional_annotation(field.annotation)
if annotation is None:
annotation = field.annotation
origin = getattr(annotation, "__origin__", None)
args = getattr(annotation, "__args__", ())
return origin is list and args == (float,)
def is_nullable(field: FieldInfo) -> bool:
"""Check if a Pydantic FieldInfo is nullable."""
if _is_embedding_vector_annotation(field):
return True
if _unwrap_optional_annotation(field.annotation) is not None:
return True
if isinstance(field.annotation, (_GenericAlias, GenericAlias)):
python/python/lancedb/remote/db.py
+46 -9
View File
@@ -862,25 +862,62 @@ class RemoteDBConnection(DBConnection):
definition: UdfDefinition,
*,
secrets: Optional[Sequence[EnvVarSecret]] = None,
namespace_path: Optional[List[str]] = None,
) -> Job[FunctionVersion]:
job = LOOP.run(self._conn.create_function_async(definition, secrets=secrets))
job = LOOP.run(
self._conn.create_function_async(
definition, secrets=secrets, namespace_path=namespace_path
)
)
return Job(job)
@override
def get_function(self, name: str, *, version: str) -> FunctionVersion:
return LOOP.run(self._conn.get_function(name, version=version))
def get_function(
self,
name: str,
*,
version: str,
namespace_path: Optional[List[str]] = None,
) -> FunctionVersion:
return LOOP.run(
self._conn.get_function(
name, version=version, namespace_path=namespace_path
)
)
@override
def list_functions(self) -> List[FunctionVersion]:
return LOOP.run(self._conn.list_functions())
def list_functions(
self, *, namespace_path: Optional[List[str]] = None
) -> List[FunctionVersion]:
return LOOP.run(self._conn.list_functions(namespace_path=namespace_path))
@override
def drop_function(self, name: str, *, version: str) -> bool:
return LOOP.run(self._conn.drop_function(name, version=version))
def drop_function(
self,
name: str,
*,
version: str,
namespace_path: Optional[List[str]] = None,
) -> bool:
return LOOP.run(
self._conn.drop_function(
name, version=version, namespace_path=namespace_path
)
)
@override
def drop_function_async(self, name: str, *, version: str) -> Tuple[bool, Job]:
dropped, job = LOOP.run(self._conn.drop_function_async(name, version=version))
def drop_function_async(
self,
name: str,
*,
version: str,
namespace_path: Optional[List[str]] = None,
) -> Tuple[bool, Job]:
dropped, job = LOOP.run(
self._conn.drop_function_async(
name, version=version, namespace_path=namespace_path
)
)
return dropped, Job(job)
@override
python/python/tests/test_blob.py
+1 -1
View File
@@ -1506,7 +1506,7 @@ def test_merge_insert_mixed_python_blobs_validates_external_uri(tmp_path, as_pan
{"id": 2, "image": blob_path.as_uri()},
]
with pytest.raises(ValueError, match="allow_external_blob_outside_bases"):
with pytest.raises(ValueError, match="outside registered external bases"):
(
table.merge_insert("id")
.when_matched_update_all()
python/python/tests/test_first_class_function_slice1.py
+23
View File
@@ -162,6 +162,29 @@ def test_function_version_binds_named_columns_as_one_immutable_application():
] == [("text", "column", "documents.body")]
def test_function_version_names_its_namespace_as_a_separate_field():
"""A Function is named by its parts, as a Secret is; a root one states no
namespace."""
value = job_result("remote_function_job.json")
root = FunctionVersion.from_json(json.dumps(value))
assert root.namespace_path == ()
assert "namespace_path" not in json.loads(root.to_canonical_json())
nested = FunctionVersion(**{**value, "namespace_path": ["analytics", "features"]})
assert nested.name == "embed"
assert nested.namespace_path == ("analytics", "features")
assert json.loads(nested.to_canonical_json())["namespace_path"] == [
"analytics",
"features",
]
application = nested(text=col("documents.body"))
assert application.function.name == "embed"
assert application.function.namespace_path == ("analytics", "features")
assert json.loads(application.to_canonical_json())["function"][
"namespace_path"
] == ["analytics", "features"]
def test_function_version_binding_validates_names_and_direct_columns():
version = FunctionVersion.from_json(
json.dumps(job_result("remote_function_job.json"))
python/python/tests/test_first_class_function_slice2.py
+114 -4
View File
@@ -1539,8 +1539,10 @@ def _mock_remote_function_catalog():
else (None, None)
)
if function_action[1] == "create":
*namespace_path, name = function_action[0].split("$")
state["version"] = {
"name": "normalize_score",
"name": name,
**({"namespace_path": namespace_path} if namespace_path else {}),
"version": FUNCTION_VERSION,
"object_id": "fixture",
"location": "memory:///fixture",
@@ -1565,10 +1567,18 @@ def _mock_remote_function_catalog():
"job_state": "DONE",
"result": state["version"],
}
elif self.path == "/v1/function/normalize_score/describe":
# A namespaced Function's id is its namespace path and name joined
# by `$`, so the name is the last segment of it.
elif (
function_action[1] == "describe"
and function_action[0].split("$")[-1] == "normalize_score"
):
assert body == {"version": FUNCTION_VERSION}
response = state["version"]
elif self.path == "/v1/function/normalize_score/drop":
elif (
function_action[1] == "drop"
and function_action[0].split("$")[-1] == "normalize_score"
):
assert body == {"version": FUNCTION_VERSION}
response = {"dropped": True}
elif secret_action[1] in ("create", "alter"):
@@ -1602,7 +1612,8 @@ def _mock_remote_function_catalog():
assert query["page_token"] == "next"
self._write_response(200, {"secrets": [{"name": "hf-prod"}]})
return
if url.path != "/v1/namespace/$/function/list":
parts = url.path.strip("/").split("/")
if parts[:2] != ["v1", "namespace"] or parts[3:] != ["function", "list"]:
self._write_response(404, {"error": "not found"})
return
assert query["include_definition"] == "true"
@@ -1840,3 +1851,102 @@ async def test_async_remote_drop_function_sends_exact_version():
{"version": FUNCTION_VERSION},
)
]
def test_remote_function_verbs_address_a_namespace_in_the_path():
"""A Function's namespace is part of the identifier each route addresses;
no body carries it, so a namespaced request differs only in its path."""
namespace = ["analytics", "features"]
with _mock_remote_function_catalog() as (host, state):
db = lancedb.connect(
"db://dev",
api_key="fake",
host_override=host,
client_config={"retry_config": {"retries": 0}},
)
created = db.create_function(normalize_score, namespace_path=namespace)
# The returned parts are what the other verbs take, so a created
# Function reopens from its own fields.
assert created.name == "normalize_score"
assert created.namespace_path == tuple(namespace)
reopened = db.get_function(
created.name,
version=created.version,
namespace_path=list(created.namespace_path),
)
assert reopened == created
assert reopened(value=lancedb.col("score")).function.namespace_path == tuple(
namespace
)
db.list_functions(namespace_path=namespace)
assert (
db.drop_function(
"normalize_score", version=FUNCTION_VERSION, namespace_path=namespace
)
is True
)
dropped, _ = db.drop_function_async(
"normalize_score", version=FUNCTION_VERSION, namespace_path=namespace
)
assert dropped is True
assert [path for path, _ in state["requests"]] == [
"/v1/function/analytics$features$normalize_score/create",
"/v1/jobs/describe",
"/v1/function/analytics$features$normalize_score/describe",
"/v1/namespace/analytics$features/function/list",
"/v1/namespace/analytics$features/function/list",
"/v1/function/analytics$features$normalize_score/drop",
"/v1/function/analytics$features$normalize_score/drop",
]
@pytest.mark.asyncio
async def test_async_remote_function_verbs_address_a_namespace_in_the_path():
namespace = ["analytics", "features"]
with _mock_remote_function_catalog() as (host, state):
db = await lancedb.connect_async(
"db://dev",
api_key="fake",
host_override=host,
client_config={"retry_config": {"retries": 0}},
)
registration = await db.create_function_async(
normalize_score, namespace_path=namespace
)
await registration.wait()
await db.get_function(
"normalize_score", version=FUNCTION_VERSION, namespace_path=namespace
)
await db.list_functions(namespace_path=namespace)
assert (
await db.drop_function(
"normalize_score", version=FUNCTION_VERSION, namespace_path=namespace
)
is True
)
assert [path for path, _ in state["requests"]] == [
"/v1/function/analytics$features$normalize_score/create",
"/v1/jobs/describe",
"/v1/function/analytics$features$normalize_score/describe",
"/v1/namespace/analytics$features/function/list",
"/v1/namespace/analytics$features/function/list",
"/v1/function/analytics$features$normalize_score/drop",
]
def test_a_function_namespace_path_must_be_a_list_of_segments():
"""A bare string is refused rather than read as a sequence of one-character
segments, and nothing reaches the service."""
with _mock_remote_function_catalog() as (host, state):
db = lancedb.connect(
"db://dev",
api_key="fake",
host_override=host,
client_config={"retry_config": {"retries": 0}},
)
with pytest.raises(TypeError):
db.list_functions(namespace_path="analytics")
assert state["requests"] == []
python/python/tests/test_pydantic.py
+20
View File
@@ -9,6 +9,7 @@ from typing import List, Optional, Tuple
import pyarrow as pa
import pydantic
import pytest
from lancedb.conftest import MockTextEmbeddingFunction
from lancedb.pydantic import (
LanceModel,
MultiVector,
@@ -425,6 +426,25 @@ def test_bare_vector_raises_clear_error():
exec("class TestModel(LanceModel):\n vector: Vector", namespace)
def test_embedding_vector_list_annotation():
embedding = MockTextEmbeddingFunction.create()
class StaticTypingModel(LanceModel):
text: str = embedding.SourceField()
vector: list[float] = embedding.VectorField()
schema = pydantic_to_schema(StaticTypingModel)
assert schema == pa.schema(
[
pa.field("text", pa.utf8(), False),
pa.field("vector", pa.list_(pa.float32(), embedding.ndims()), True),
]
)
model = StaticTypingModel(text="hello", vector=[0.0] * embedding.ndims())
assert model.vector == [0.0] * embedding.ndims()
def test_fixed_size_list_field():
class TestModel(pydantic.BaseModel):
vec: Vector(16)
python/src/connection.rs
+26 -6
View File
@@ -754,31 +754,37 @@ impl Connection {
})
}
#[pyo3(signature = (request_json, namespace_path=None))]
pub fn create_function_async(
self_: PyRef<'_, Self>,
request_json: String,
namespace_path: Option<Vec<String>>,
) -> PyResult<Bound<'_, PyAny>> {
let inner = self_.get_inner()?.clone();
let request = lancedb::function::FunctionRegistrationRequest::from_json(&request_json)
.infer_error()?;
let namespace_path = namespace_path.unwrap_or_default();
future_into_py(self_.py(), async move {
inner
.create_function_async(request)
.create_function_async(request, &namespace_path)
.await
.infer_error()
.map(crate::job::Job::new_typed)
})
}
#[pyo3(signature = (name, version, namespace_path=None))]
pub fn get_function(
self_: PyRef<'_, Self>,
name: String,
version: String,
namespace_path: Option<Vec<String>>,
) -> PyResult<Bound<'_, PyAny>> {
let inner = self_.get_inner()?.clone();
let namespace_path = namespace_path.unwrap_or_default();
future_into_py(self_.py(), async move {
inner
.get_function(name, version)
.get_function(name, version, &namespace_path)
.await
.infer_error()?
.to_canonical_json()
@@ -786,11 +792,16 @@ impl Connection {
})
}
pub fn list_functions(self_: PyRef<'_, Self>) -> PyResult<Bound<'_, PyAny>> {
#[pyo3(signature = (namespace_path=None))]
pub fn list_functions(
self_: PyRef<'_, Self>,
namespace_path: Option<Vec<String>>,
) -> PyResult<Bound<'_, PyAny>> {
let inner = self_.get_inner()?.clone();
let namespace_path = namespace_path.unwrap_or_default();
future_into_py(self_.py(), async move {
inner
.list_functions()
.list_functions(&namespace_path)
.await
.infer_error()?
.into_iter()
@@ -799,26 +810,35 @@ impl Connection {
})
}
#[pyo3(signature = (name, version, namespace_path=None))]
pub fn drop_function(
self_: PyRef<'_, Self>,
name: String,
version: String,
namespace_path: Option<Vec<String>>,
) -> PyResult<Bound<'_, PyAny>> {
let inner = self_.get_inner()?.clone();
let namespace_path = namespace_path.unwrap_or_default();
future_into_py(self_.py(), async move {
inner.drop_function(name, version).await.infer_error()
inner
.drop_function(name, version, &namespace_path)
.await
.infer_error()
})
}
#[pyo3(signature = (name, version, namespace_path=None))]
pub fn drop_function_async(
self_: PyRef<'_, Self>,
name: String,
version: String,
namespace_path: Option<Vec<String>>,
) -> PyResult<Bound<'_, PyAny>> {
let inner = self_.get_inner()?.clone();
let namespace_path = namespace_path.unwrap_or_default();
future_into_py(self_.py(), async move {
inner
.drop_function_async(name, version)
.drop_function_async(name, version, &namespace_path)
.await
.infer_error()
.map(|(dropped, job)| (dropped, crate::job::Job::new(job)))
python/vendor/lance-arrow/Cargo.toml
Vendored
+1 -1
View File
@@ -1,6 +1,6 @@
[package]
name = "lance-arrow"
version = "13.0.0-beta.18"
version = "13.1.0-beta.1"
edition = "2024"
authors = ["Lance Devs <dev@lance.org>"]
license = "Apache-2.0"
python/vendor/lance-arrow/README.lancedb.md
Vendored
+2 -2
View File
@@ -1,5 +1,5 @@
This directory contains `rust/lance-arrow` from Lance tag `v13.0.0-beta.18`
(commit `b646eda6a891f481b6f6d6baef9cd17656aef65b`), licensed under Apache-2.0.
This directory contains `rust/lance-arrow` from Lance tag `v13.1.0-beta.1`
(commit `e5a3553b1699a7062ff7afe4ee268d596bbf2e0d`), licensed under Apache-2.0.
LanceDB carries a local fix in `src/lib.rs` for sliced child validity bitmaps
until a Lance release includes the fix. The patch is selected in the root
rust/lancedb/Cargo.toml
+1 -1
View File
@@ -1,6 +1,6 @@
[package]
name = "lancedb"
version = "0.40.0-beta.11"
version = "0.40.0-beta.12"
edition.workspace = true
description = "LanceDB: A serverless, low-latency vector database for AI applications"
license.workspace = true
rust/lancedb/src/connection.rs
+20 -9
View File
@@ -587,7 +587,8 @@ impl Connection {
)
}
/// Build and register a Python callable as an immutable Function version.
/// Build and register a Python callable as an immutable Function version
/// in `namespace_path`, which is empty for the root namespace.
///
/// The server-side job builds the OCI image, then registers the completed
/// artifact. Waiting on the returned typed job yields the durable
@@ -597,8 +598,11 @@ impl Connection {
pub async fn create_function_async(
&self,
request: crate::function::FunctionRegistrationRequest,
namespace_path: &[String],
) -> Result<crate::job::Job<crate::function::FunctionVersion>> {
self.internal.create_function_async(request).await
self.internal
.create_function_async(request, namespace_path)
.await
}
/// Look up one exact immutable Function version in the remote catalog.
@@ -610,13 +614,15 @@ impl Connection {
&self,
name: impl AsRef<str>,
version: impl AsRef<str>,
namespace_path: &[String],
) -> Result<crate::function::FunctionVersion> {
self.internal
.get_function(name.as_ref(), version.as_ref())
.get_function(name.as_ref(), version.as_ref(), namespace_path)
.await
}
/// List every published immutable Function version in the remote catalog.
/// List every published immutable Function version in `namespace_path` of
/// the remote catalog. Functions in child namespaces are not included.
///
/// Results are ordered by Function name then version. The client walks all
/// server pages before returning. Local databases return
@@ -628,14 +634,17 @@ impl Connection {
/// # async fn list_functions(
/// # connection: &lancedb::Connection,
/// # ) -> Result<(), Box<dyn std::error::Error>> {
/// for function in connection.list_functions().await? {
/// for function in connection.list_functions(&[]).await? {
/// println!("{} {}", function.name(), function.version());
/// }
/// # Ok(())
/// # }
/// ```
pub async fn list_functions(&self) -> Result<Vec<crate::function::FunctionVersion>> {
self.internal.list_functions().await
pub async fn list_functions(
&self,
namespace_path: &[String],
) -> Result<Vec<crate::function::FunctionVersion>> {
self.internal.list_functions(namespace_path).await
}
/// Remove the current Function name binding, retaining the object history.
@@ -647,9 +656,10 @@ impl Connection {
&self,
name: impl AsRef<str>,
version: impl AsRef<str>,
namespace_path: &[String],
) -> Result<bool> {
self.internal
.drop_function(name.as_ref(), version.as_ref())
.drop_function(name.as_ref(), version.as_ref(), namespace_path)
.await
}
@@ -663,9 +673,10 @@ impl Connection {
&self,
name: impl AsRef<str>,
version: impl AsRef<str>,
namespace_path: &[String],
) -> Result<(bool, crate::job::Job)> {
self.internal
.drop_function_async(name.as_ref(), version.as_ref())
.drop_function_async(name.as_ref(), version.as_ref(), namespace_path)
.await
}
rust/lancedb/src/database.rs
+18 -5
View File
@@ -333,10 +333,12 @@ pub trait Database:
///
/// See [`CloneTableRequest`] for detailed documentation and examples.
async fn clone_table(&self, request: CloneTableRequest) -> Result<Arc<dyn BaseTable>>;
/// Submit a Function creation job that builds an image and registers it.
/// Submit a Function creation job that builds an image and registers it
/// in `namespace_path`.
async fn create_function_async(
&self,
_request: crate::function::FunctionRegistrationRequest,
_namespace_path: &[String],
) -> Result<crate::job::Job<crate::function::FunctionVersion>> {
function_catalog_not_supported()
}
@@ -412,15 +414,25 @@ pub trait Database:
&self,
_name: &str,
_version: &str,
_namespace_path: &[String],
) -> Result<crate::function::FunctionVersion> {
function_catalog_not_supported()
}
/// List every published immutable Function version in the remote catalog.
async fn list_functions(&self) -> Result<Vec<crate::function::FunctionVersion>> {
/// List every published immutable Function version in one namespace of the
/// remote catalog.
async fn list_functions(
&self,
_namespace_path: &[String],
) -> Result<Vec<crate::function::FunctionVersion>> {
function_catalog_not_supported()
}
/// Remove the current Function name binding, retaining the object history.
async fn drop_function(&self, _name: &str, _version: &str) -> Result<bool> {
async fn drop_function(
&self,
_name: &str,
_version: &str,
_namespace_path: &[String],
) -> Result<bool> {
function_catalog_not_supported()
}
/// Start dropping a Function and return a handle to the cleanup job.
@@ -431,8 +443,9 @@ pub trait Database:
&self,
name: &str,
version: &str,
namespace_path: &[String],
) -> Result<(bool, crate::job::Job)> {
let dropped = self.drop_function(name, version).await?;
let dropped = self.drop_function(name, version, namespace_path).await?;
Ok((dropped, crate::job::Job::new_done()))
}
/// Create a named Secret in this database. Fails if the name is taken, so
rust/lancedb/src/function.rs
+71 -12
View File
@@ -85,22 +85,25 @@ fn has_unknown_keys(value: &Value, allowed: &[&str]) -> bool {
.is_some_and(|object| object.keys().any(|key| !allowed.contains(&key.as_str())))
}
/// Every field a [`FunctionVersionRef`] document may carry. An application or
/// binding with any other key comes from a newer contract.
pub(crate) const FUNCTION_VERSION_REF_FIELDS: &[&str] = &[
"name",
"namespace_path",
"object_id",
"location",
"version",
"manifest_digest",
];
fn application_has_unknown_nested_fields(value: &Value) -> bool {
let Some(application) = value.as_object() else {
return false;
};
if application.get("function").is_some_and(|value| {
has_unknown_keys(
value,
&[
"name",
"object_id",
"location",
"version",
"manifest_digest",
],
)
}) {
if application
.get("function")
.is_some_and(|value| has_unknown_keys(value, FUNCTION_VERSION_REF_FIELDS))
{
return true;
}
if application
@@ -431,9 +434,17 @@ fn deserialize_object_version<'de, D: Deserializer<'de>>(
}
/// One immutable Function object revision and its executable artifact.
///
/// The Function is named by its parts, `name` and `namespace_path`, the way a
/// [`SecretReference`](crate::secrets::SecretReference) names a Secret.
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
pub struct FunctionVersion {
name: String,
/// The namespace holding the Function. Empty is the root, and is absent
/// from the wire, as a [`SecretReference`](crate::secrets::SecretReference)
/// omits it.
#[serde(default, skip_serializing_if = "Vec::is_empty")]
namespace_path: Vec<String>,
object_id: String,
location: String,
#[serde(deserialize_with = "deserialize_object_version")]
@@ -463,6 +474,7 @@ impl FunctionVersion {
pub fn reference(&self) -> FunctionVersionRef {
FunctionVersionRef {
name: self.name.clone(),
namespace_path: self.namespace_path.clone(),
object_id: self.object_id.clone(),
location: self.location.clone(),
version: self.version.clone(),
@@ -472,6 +484,9 @@ impl FunctionVersion {
pub fn name(&self) -> &str {
&self.name
}
pub fn namespace_path(&self) -> &[String] {
&self.namespace_path
}
pub fn version(&self) -> &str {
&self.version
}
@@ -556,6 +571,10 @@ impl_json!(FunctionRegistrationRequest);
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
pub struct FunctionVersionRef {
pub name: String,
/// The namespace holding the Function; empty is the root and is absent
/// from the wire.
#[serde(default, skip_serializing_if = "Vec::is_empty")]
pub namespace_path: Vec<String>,
pub object_id: String,
pub location: String,
#[serde(deserialize_with = "deserialize_object_version")]
@@ -954,6 +973,46 @@ mod tests {
);
}
/// A Function is named by its parts, and a root one states no namespace.
#[test]
fn function_version_carries_its_namespace_as_a_separate_field() {
const VERSION: &str = include_str!(
"../tests/fixtures/first_class_functions/v1/remote_function_version.canonical.json"
);
let root = FunctionVersion::from_json(VERSION).unwrap();
assert!(root.namespace_path().is_empty());
assert_eq!(root.to_canonical_json().unwrap(), VERSION.trim_end());
let mut document: Value = serde_json::from_str(VERSION).unwrap();
document["namespace_path"] = serde_json::json!(["analytics", "features"]);
let nested = FunctionVersion::from_json(&document.to_string()).unwrap();
assert_eq!(nested.name(), "embed");
assert_eq!(nested.namespace_path(), ["analytics", "features"]);
let reference = nested.reference();
assert_eq!(reference.name, "embed");
assert_eq!(reference.namespace_path, ["analytics", "features"]);
let reference: Value = serde_json::to_value(&reference).unwrap();
assert_eq!(
reference["namespace_path"],
serde_json::json!(["analytics", "features"])
);
let root_reference = serde_json::to_value(root.reference()).unwrap();
assert!(root_reference.get("namespace_path").is_none());
// An application carrying the namespace is not from a newer contract.
let application = serde_json::json!({
"function": reference,
"inputs": [],
"output": serde_json::to_value(nested.signature().output.clone()).unwrap(),
});
let application = FunctionApplication::from_json(&application.to_string()).unwrap();
assert!(!application.has_unknown_fields());
assert_eq!(
application.function().namespace_path,
["analytics", "features"]
);
}
/// Arrays are ordered by the caller, so canonicalization must leave them
/// alone -- sorting them would change what a signature means.
#[test]
rust/lancedb/src/remote/db.rs
+117 -19
View File
@@ -979,8 +979,9 @@ impl<S: HttpSend> Database for RemoteDatabase<S> {
async fn create_function_async(
&self,
request: FunctionRegistrationRequest,
namespace_path: &[String],
) -> Result<Job<FunctionVersion>> {
let function_id = build_object_identifier("Function name", &request.name, &[])?;
let function_id = build_object_identifier("Function name", &request.name, namespace_path)?;
let req = self
.client
.post(&format!("/v1/function/{function_id}/create"))
@@ -1005,8 +1006,13 @@ impl<S: HttpSend> Database for RemoteDatabase<S> {
))))
}
async fn get_function(&self, name: &str, version: &str) -> Result<FunctionVersion> {
let function_id = build_object_identifier("Function name", name, &[])?;
async fn get_function(
&self,
name: &str,
version: &str,
namespace_path: &[String],
) -> Result<FunctionVersion> {
let function_id = build_object_identifier("Function name", name, namespace_path)?;
let req = self
.client
.post(&format!("/v1/function/{function_id}/describe"))
@@ -1018,8 +1024,8 @@ impl<S: HttpSend> Database for RemoteDatabase<S> {
response.json().await.err_to_http(request_id)
}
async fn list_functions(&self) -> Result<Vec<FunctionVersion>> {
let namespace_id = build_namespace_identifier(&[])?;
async fn list_functions(&self, namespace_path: &[String]) -> Result<Vec<FunctionVersion>> {
let namespace_id = build_namespace_identifier(namespace_path)?;
let path = format!("/v1/namespace/{namespace_id}/function/list");
let mut functions = Vec::new();
let mut page_token: Option<String> = None;
@@ -1059,12 +1065,25 @@ impl<S: HttpSend> Database for RemoteDatabase<S> {
Ok(functions)
}
async fn drop_function(&self, name: &str, version: &str) -> Result<bool> {
Ok(self.drop_function_async(name, version).await?.0)
async fn drop_function(
&self,
name: &str,
version: &str,
namespace_path: &[String],
) -> Result<bool> {
Ok(self
.drop_function_async(name, version, namespace_path)
.await?
.0)
}
async fn drop_function_async(&self, name: &str, version: &str) -> Result<(bool, Job)> {
let function_id = build_object_identifier("Function name", name, &[])?;
async fn drop_function_async(
&self,
name: &str,
version: &str,
namespace_path: &[String],
) -> Result<(bool, Job)> {
let function_id = build_object_identifier("Function name", name, namespace_path)?;
let req = self
.client
.post(&format!("/v1/function/{function_id}/drop"))
@@ -2004,7 +2023,7 @@ mod tests {
.body(serde_json::json!({"dropped": true, "job_id": "j1-fn-drop"}).to_string())
.unwrap()
});
let (dropped, job) = db.drop_function_async("embed", "1").await.unwrap();
let (dropped, job) = db.drop_function_async("embed", "1", &[]).await.unwrap();
assert!(dropped);
assert_eq!(job.id(), Some("j1-fn-drop"));
}
@@ -2019,7 +2038,7 @@ mod tests {
.body(serde_json::json!({"dropped": false}).to_string())
.unwrap()
});
let (dropped, job) = db.drop_function_async("embed", "1").await.unwrap();
let (dropped, job) = db.drop_function_async("embed", "1", &[]).await.unwrap();
assert!(!dropped);
assert_eq!(job.id(), None);
assert_eq!(job.status().await.unwrap(), "finished");
@@ -2036,7 +2055,11 @@ mod tests {
let db = super::RemoteDatabase::new_mock(move |_| {
http::Response::builder().status(202).body(body).unwrap()
});
let error = db.drop_function_async("embed", "1").await.err().unwrap();
let error = db
.drop_function_async("embed", "1", &[])
.await
.err()
.unwrap();
assert!(error.to_string().contains("valid job_id"));
}
}
@@ -3905,7 +3928,7 @@ mod tests {
http::Response::builder().status(200).body("{}").unwrap()
});
let error = conn
.drop_function(name, "fv_1")
.drop_function(name, "fv_1", &[])
.await
.expect_err("a dot-only Function name must be refused");
assert!(
@@ -4307,7 +4330,7 @@ mod tests {
path => panic!("unexpected path: {path}"),
});
let request = crate::function::FunctionRegistrationRequest::from_json(REQUEST).unwrap();
let job = conn.create_function_async(request).await.unwrap();
let job = conn.create_function_async(request, &[]).await.unwrap();
assert_eq!(job.id(), Some("job-function-1"));
let version = job.wait().await.unwrap();
assert_eq!(version.name(), "embed");
@@ -4327,7 +4350,7 @@ mod tests {
assert_eq!(body, serde_json::json!({"version": "1"}));
http::Response::builder().status(200).body(VERSION).unwrap()
});
let version = conn.get_function("embed", "1").await.unwrap();
let version = conn.get_function("embed", "1", &[]).await.unwrap();
assert_eq!(version.name(), "embed");
assert_eq!(version.version(), "1");
}
@@ -4370,7 +4393,7 @@ mod tests {
}
}
});
let functions = conn.list_functions().await.unwrap();
let functions = conn.list_functions(&[]).await.unwrap();
assert_eq!(functions.len(), 1);
assert_eq!(functions[0].name(), "embed");
assert_eq!(functions[0].version(), "1");
@@ -4393,7 +4416,7 @@ mod tests {
.unwrap()
});
let functions = conn.list_functions().await.unwrap();
let functions = conn.list_functions(&[]).await.unwrap();
assert!(functions.is_empty());
assert_eq!(requests.load(Ordering::SeqCst), 1);
}
@@ -4434,7 +4457,7 @@ mod tests {
.unwrap()
});
let error = conn.list_functions().await.unwrap_err();
let error = conn.list_functions(&[]).await.unwrap_err();
assert!(
matches!(
&error,
@@ -4461,7 +4484,82 @@ mod tests {
.body(r#"{"dropped":false}"#)
.unwrap()
});
assert!(!conn.drop_function("embed", "1").await.unwrap());
assert!(!conn.drop_function("embed", "1", &[]).await.unwrap());
}
/// A Function's namespace is addressed in the path the way a Secret's is:
/// every route takes the joined identifier and no body carries the
/// namespace, so a namespaced request differs from a root one only in its
/// path.
#[tokio::test]
async fn test_a_function_namespace_path_is_addressed_in_the_path() {
const REQUEST: &str = include_str!(
"../../tests/fixtures/first_class_functions/v1/remote_function_registration_request.json"
);
const VERSION: &str = include_str!(
"../../tests/fixtures/first_class_functions/v1/remote_function_version.canonical.json"
);
let namespace = ["analytics".to_string(), "features".to_string()];
let mut expected_create: serde_json::Value = serde_json::from_str(REQUEST).unwrap();
expected_create.as_object_mut().unwrap().remove("name");
let conn = Connection::new_with_handler(move |request| {
let body = request
.body()
.and_then(|body| body.as_bytes())
.map(|bytes| serde_json::from_slice::<serde_json::Value>(bytes).unwrap());
match request.url().path() {
"/v1/function/analytics$features$normalize_score/create" => {
assert_eq!(body.unwrap(), expected_create);
http::Response::builder()
.status(202)
.body(r#"{"job_id":"job-function-1"}"#.to_string())
.unwrap()
}
"/v1/function/analytics$features$embed/describe" => {
assert_eq!(body.unwrap(), serde_json::json!({"version": "1"}));
http::Response::builder()
.status(200)
.body(VERSION.to_string())
.unwrap()
}
"/v1/function/analytics$features$embed/drop" => {
assert_eq!(body.unwrap(), serde_json::json!({"version": "1"}));
http::Response::builder()
.status(200)
.body(r#"{"dropped":true}"#.to_string())
.unwrap()
}
// Listing is namespace-scoped, so the namespace is the whole
// identifier.
"/v1/namespace/analytics$features/function/list" => http::Response::builder()
.status(200)
.body(r#"{"functions":[]}"#.to_string())
.unwrap(),
path => panic!("unexpected path: {path}"),
}
});
let request = crate::function::FunctionRegistrationRequest::from_json(REQUEST).unwrap();
let job = conn
.create_function_async(request, &namespace)
.await
.unwrap();
assert_eq!(job.id(), Some("job-function-1"));
conn.get_function("embed", "1", &namespace).await.unwrap();
assert!(conn.list_functions(&namespace).await.unwrap().is_empty());
assert!(conn.drop_function("embed", "1", &namespace).await.unwrap());
}
/// Each namespace segment is checked before a request is built, so an
/// empty segment cannot collapse the identifier onto the parent namespace.
#[tokio::test]
async fn test_an_unaddressable_function_namespace_segment_is_refused() {
let conn = Connection::new_with_handler(|request| -> http::Response<String> {
panic!("reached the transport: {}", request.url().path())
});
let namespace = ["analytics".to_string(), String::new()];
assert!(conn.get_function("embed", "1", &namespace).await.is_err());
assert!(conn.list_functions(&namespace).await.is_err());
assert!(conn.drop_function("embed", "1", &namespace).await.is_err());
}
#[tokio::test]
rust/lancedb/src/table/computed_columns.rs
+15 -7
View File
@@ -704,13 +704,7 @@ fn ensure_known_binding_shape(value: &Value) -> Result<()> {
object
.get("function")
.ok_or_else(|| invalid_function("Function binding is missing its exact version"))?,
&[
"name",
"object_id",
"location",
"version",
"manifest_digest",
],
crate::function::FUNCTION_VERSION_REF_FIELDS,
"version reference",
)?;
for input in object
@@ -3760,6 +3754,20 @@ mod tests {
ensure_known_binding_shape(&raw_binding).unwrap();
}
/// A binding names its Function by parts, so one declared against a
/// namespaced Function is part of the known contract too.
#[test]
fn test_namespaced_bindings_are_a_known_shape() {
let mut raw_binding: Value = serde_json::from_str(include_str!(
"../../tests/fixtures/first_class_functions/v1/remote_initialized_function_binding.json"
))
.unwrap();
raw_binding["function"]["namespace_path"] = serde_json::json!(["analytics", "features"]);
ensure_known_binding_shape(&raw_binding).unwrap();
let binding = FunctionBinding::from_json(&raw_binding.to_string()).unwrap();
assert_eq!(binding.function().namespace_path, ["analytics", "features"]);
}
#[test]
fn test_named_struct_can_be_kept_as_one_nullable_physical_column() {
let application = named_struct_application("{}");
rust/lancedb/tests/first_class_function_slice2.rs
+6 -3
View File
@@ -97,13 +97,16 @@ async fn local_function_catalog_operations_return_stable_not_supported() {
))
.unwrap();
let create_error = connection.create_function_async(request).await.unwrap_err();
let create_error = connection
.create_function_async(request, &[])
.await
.unwrap_err();
let lookup_error = connection
.get_function("normalize_score", "1")
.get_function("normalize_score", "1", &[])
.await
.unwrap_err();
let drop_error = connection
.drop_function("normalize_score", "1")
.drop_function("normalize_score", "1", &[])
.await
.unwrap_err();
for error in [create_error, lookup_error, drop_error] {