Bump version: 0.38.0-beta.16 → 0.38.0

.bumpversion.toml

@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.39.0-beta.6"
+current_version = "0.38.0"
 parse = """(?x)
     (?P<major>0|[1-9]\\d*)\\.
     (?P<minor>0|[1-9]\\d*)\\.

.github/workflows/rust.yml

@@ -232,10 +232,7 @@ jobs:
           ALL_FEATURES=`cargo metadata --format-version=1 --no-deps \
             | jq -r '.packages[] | .features | keys | .[]' \
             | grep -v s3-test | sort | uniq | paste -s -d "," -`
-          # Run doctests before test binaries fill the runner disk. Examples are
-          # already built by the Linux job, so avoid retaining them here.
-          cargo test --profile ci --features $ALL_FEATURES --locked --doc
-          cargo test --profile ci --features $ALL_FEATURES --locked --lib --tests
+          cargo test --profile ci --features $ALL_FEATURES --locked
 
   windows:
     strategy:

.github/workflows/typos.yml

@@ -1,20 +0,0 @@
-name: Typo checker
-on:
-  push:
-    branches:
-      - main
-  pull_request:
-
-permissions:
-  contents: read
-
-jobs:
-  run:
-    name: Spell Check with Typos
-    runs-on: ubuntu-latest
-    steps:
-      - name: Check out code
-        uses: actions/checkout@v6
-
-      - name: Check spelling of the entire repository
-        uses: crate-ci/typos@6802cc60d4e7f78b9d5454f6cf3935c042d5e1e3 # v1.26.0

.pre-commit-config.yaml

@@ -10,10 +10,6 @@ repos:
     rev: v0.9.9
     hooks:
       - id: ruff
-  - repo: https://github.com/crate-ci/typos
-    rev: v1.26.0
-    hooks:
-      - id: typos
   # - repo: https://github.com/RobertCraigie/pyright-python
   #   rev: v1.1.395
   #   hooks:

.typos.toml

@@ -1,19 +0,0 @@
-[default]
-extend-ignore-re = ["(?Rm)^.*(#|//)\\s*spellchecker:disable-line$"]
-
-[default.extend-words]
-# Azure Kubernetes Service, mentioned in rust/lancedb/src/remote/oauth.rs.
-AKS = "AKS"
-# RabitQ is the name of a vector quantization algorithm, not a typo of "Rabbit".
-Rabit = "Rabit"
-# `VarBuilder::from_mmaped_safetensors` is the real (if oddly-spelled) name of
-# the candle-core API we call in rust/lancedb/src/embeddings/sentence_transformers.rs.
-mmaped = "mmaped"
-# `WriteableBuffer` is the real name of a type from Python's `_typeshed` stubs,
-# used in python/python/lancedb/_blob.py.
-Writeable = "Writeable"
-
-[files]
-extend-exclude = [
-    "*_THIRD_PARTY_LICENSES.*",
-]

Cargo.toml

@@ -13,20 +13,20 @@ categories = ["database-implementations"]
 rust-version = "1.91.0"
 
 [workspace.dependencies]
-lance = { "version" = "=12.0.0-beta.17", default-features = false, "tag" = "v12.0.0-beta.17", "git" = "https://github.com/lance-format/lance.git" }
-lance-core = { "version" = "=12.0.0-beta.17", "tag" = "v12.0.0-beta.17", "git" = "https://github.com/lance-format/lance.git" }
-lance-datagen = { "version" = "=12.0.0-beta.17", "tag" = "v12.0.0-beta.17", "git" = "https://github.com/lance-format/lance.git" }
-lance-file = { "version" = "=12.0.0-beta.17", "tag" = "v12.0.0-beta.17", "git" = "https://github.com/lance-format/lance.git" }
-lance-io = { "version" = "=12.0.0-beta.17", default-features = false, "tag" = "v12.0.0-beta.17", "git" = "https://github.com/lance-format/lance.git" }
-lance-index = { "version" = "=12.0.0-beta.17", "tag" = "v12.0.0-beta.17", "git" = "https://github.com/lance-format/lance.git" }
-lance-linalg = { "version" = "=12.0.0-beta.17", "tag" = "v12.0.0-beta.17", "git" = "https://github.com/lance-format/lance.git" }
-lance-namespace = { "version" = "=12.0.0-beta.17", "tag" = "v12.0.0-beta.17", "git" = "https://github.com/lance-format/lance.git" }
-lance-namespace-impls = { "version" = "=12.0.0-beta.17", default-features = false, "tag" = "v12.0.0-beta.17", "git" = "https://github.com/lance-format/lance.git" }
-lance-table = { "version" = "=12.0.0-beta.17", "tag" = "v12.0.0-beta.17", "git" = "https://github.com/lance-format/lance.git" }
-lance-testing = { "version" = "=12.0.0-beta.17", "tag" = "v12.0.0-beta.17", "git" = "https://github.com/lance-format/lance.git" }
-lance-datafusion = { "version" = "=12.0.0-beta.17", "tag" = "v12.0.0-beta.17", "git" = "https://github.com/lance-format/lance.git" }
-lance-encoding = { "version" = "=12.0.0-beta.17", "tag" = "v12.0.0-beta.17", "git" = "https://github.com/lance-format/lance.git" }
-lance-arrow = { "version" = "=12.0.0-beta.17", "tag" = "v12.0.0-beta.17", "git" = "https://github.com/lance-format/lance.git" }
+lance = { "version" = "=11.0.0", default-features = false }
+lance-core = "=11.0.0"
+lance-datagen = "=11.0.0"
+lance-file = "=11.0.0"
+lance-io = { "version" = "=11.0.0", default-features = false }
+lance-index = "=11.0.0"
+lance-linalg = "=11.0.0"
+lance-namespace = "=11.0.0"
+lance-namespace-impls = { "version" = "=11.0.0", default-features = false }
+lance-table = "=11.0.0"
+lance-testing = "=11.0.0"
+lance-datafusion = "=11.0.0"
+lance-encoding = "=11.0.0"
+lance-arrow = "=11.0.0"
 lancedb = { path = "rust/lancedb", default-features = false }
 ahash = "0.8"
 # Note that this one does not include pyarrow
@@ -39,7 +39,6 @@ arrow-ord = "58.0.0"
 arrow-schema = "58.0.0"
 arrow-select = "58.0.0"
 arrow-cast = "58.0.0"
-arrow-flight = { version = "58.0.0", features = ["flight-sql-experimental"] }
 async-trait = "0"
 bytes = "1"
 datafusion = { version = "54.0.0", default-features = false }
@@ -60,7 +59,7 @@ log = "0.4"
 metrics = "0.24"
 metrics-util = "0.19"
 moka = { version = "0.12", features = ["future"] }
-object_store = "0.14.1"
+object_store = "0.13.2"
 pin-project = "1.0.7"
 rand = "0.9"
 snafu = "0.8"
@@ -72,8 +71,7 @@ serde = "1"
 serde_json = "1"
 tempfile = "3.5.0"
 tokio = { version = "1.23", features = ["rt-multi-thread", "sync"] }
-tonic = { version = "0.14", features = ["tls-native-roots", "tls-ring"] }
-uuid = { version = "1.7.0", features = ["v4", "v7"] }
+uuid = { version = "1.7.0", features = ["v4"] }
 chrono = { version = "0.4", default-features = false, features = ["clock"] }
 
 [profile.ci]

docs/openapi.yml

@@ -155,7 +155,7 @@ paths:
                 vector:
                   type: FixedSizeList
                   description: |
-                    The targeted vector to search for. Required.
+                    The targetted vector to search for. Required.
                 vector_column:
                   type: string
                   description: |
@@ -446,15 +446,6 @@ paths:
               properties:
                 column:
                   type: string
-                name:
-                  type: string
-                  description: Optional name for the created index.
-                replace:
-                  type: boolean
-                  default: true
-                  description: |
-                    Whether to replace an existing index with the same resolved
-                    name. Defaults to true.
                 metric_type:
                   type: string
                   nullable: false

docs/src/java/java.md

@@ -14,7 +14,7 @@ Add the following dependency to your `pom.xml`:
 <dependency>
     <groupId>com.lancedb</groupId>
     <artifactId>lancedb-core</artifactId>
-    <version>0.39.0-beta.6</version>
+    <version>0.38.0</version>
 </dependency>
 ```
 

docs/src/js/classes/Connection.md

@@ -448,6 +448,26 @@ on the returned job to know when cleanup has finished.
 
 ***
 
+### getJob()
+
+```ts
+abstract getJob(jobId): Promise<null | JobDescription>
+```
+
+Describe a single server-side job by id.
+
+Resolves to `null` when the server has no such job.
+
+#### Parameters
+
+* **jobId**: `string`
+
+#### Returns
+
+`Promise`&lt;`null` \| [`JobDescription`](../interfaces/JobDescription.md)&gt;
+
+***
+
 ### isOpen()
 
 ```ts
@@ -462,6 +482,48 @@ Return true if the connection has not been closed
 
 ***
 
+### job()
+
+```ts
+abstract job(jobId): Job
+```
+
+A [Job](Job.md) handle for a server-side job by id.
+
+The handle is constructed without a server round trip; an unknown id
+surfaces when the handle is used. Dropping the handle has no effect on
+the job itself.
+
+#### Parameters
+
+* **jobId**: `string`
+
+#### Returns
+
+[`Job`](Job.md)
+
+***
+
+### jobHistory()
+
+```ts
+abstract jobHistory(jobId?): Promise<Table<any>>
+```
+
+The lifecycle event history of a server-side job, as an Arrow table.
+
+Lists history across all jobs when `jobId` is omitted.
+
+#### Parameters
+
+* **jobId?**: `string`
+
+#### Returns
+
+`Promise`&lt;`Table`&lt;`any`&gt;&gt;
+
+***
+
 ### listJobs()
 
 ```ts
@@ -586,30 +648,6 @@ A page of table names and an
 
 ***
 
-### openJob()
-
-```ts
-abstract openJob(jobId): Promise<Job>
-```
-
-Open a server-side job by id, returning a handle with its record already
-populated. Rejects when the server has no such job, the way
-[Connection.openTable](Connection.md#opentable) does for a missing table.
-
-The returned [Job](Job.md) answers for its own state, specification,
-result, failure and event history, so there is no separate
-connection-level call for any of them.
-
-#### Parameters
-
-* **jobId**: `string`
-
-#### Returns
-
-`Promise`&lt;[`Job`](Job.md)&gt;
-
-***
-
 ### openMaterializedView()
 
 ```ts

docs/src/js/classes/Job.md

@@ -8,116 +8,28 @@
 
 A handle to an operation that may still be running.
 
-The operation may already be complete when the handle is created.
+## Constructors
 
-The detail getters read what the handle last observed. Submitting an
-operation returns only a job id, so populating them eagerly would cost an
-extra round trip on every call:
+### new Job()
 
-- [Job.refresh](Job.md#refresh) and [Job.status](Job.md#status) fetch the whole record.
-- [Job.wait](Job.md#wait) records the terminal state it establishes, but not the
-  rest of the record.
-- Everything is null until one of those runs.
+```ts
+new Job(): Job
+```
+
+#### Returns
+
+[`Job`](Job.md)
 
 ## Accessors
 
-### creationMs
-
-```ts
-get creationMs(): null | number
-```
-
-When the job was created, in milliseconds since the epoch.
-
-#### Returns
-
-`null` \| `number`
-
-***
-
-### failure
-
-```ts
-get failure(): null | JobFailureInfo
-```
-
-Why the job failed, when it failed and the server reports a reason.
-
-#### Returns
-
-`null` \| [`JobFailureInfo`](../interfaces/JobFailureInfo.md)
-
-***
-
 ### id
 
 ```ts
 get id(): null | string
 ```
 
-Identifies the operation on the server that is running it.
-
-Operations that run in this process have no server id. The value is
-opaque: parsing it or storing it to resume the job later is not supported.
-
-#### Returns
-
-`null` \| `string`
-
-***
-
-### jobType
-
-```ts
-get jobType(): null | string
-```
-
-The job's type, as the server names it. Null for an in-process job, which
-has no server-side record.
-
-#### Returns
-
-`null` \| `string`
-
-***
-
-### result
-
-```ts
-get result(): any
-```
-
-The job-type-specific terminal result. Null until the job succeeds, so a
-job that never terminates reports its progress through [Job.events](Job.md#events)
-instead.
-
-#### Returns
-
-`any`
-
-***
-
-### spec
-
-```ts
-get spec(): any
-```
-
-The job-type-specific specification it was submitted with.
-
-#### Returns
-
-`any`
-
-***
-
-### state
-
-```ts
-get state(): null | string
-```
-
-The last observed lifecycle state, without contacting the backend.
+Identifies the operation on the server that is running it. Operations
+that run in this process have no server id. The value is opaque.
 
 #### Returns
 
@@ -139,61 +51,18 @@ Request cancellation. Cancelling a finished operation is a no-op.
 
 ***
 
-### events()
-
-```ts
-events(options?): Promise<Table<any>>
-```
-
-This job's recorded lifecycle events.
-
-Where the getters above report a terminal result only once the job reaches
-one, events are written as the job runs and outlive the workers that
-produced them. A distributed job records a `claim`/`claim_complete` pair
-per unit of work, each carrying `rows_processed`, so a job that never
-finishes still accounts for what it did.
-
-The server caps results at 1000 rows by default and 10,000 at most, and
-truncates without saying so, so pass `limit` for a job that emits an event
-per fragment. `filter` is a SQL-like expression over the `state`,
-`updated_by`, `emitted_from`, `emitted_by`, and `claim_entity` columns.
-
-#### Parameters
-
-* **options?**: [`JobEventsOptions`](../interfaces/JobEventsOptions.md)
-
-#### Returns
-
-`Promise`&lt;`Table`&lt;`any`&gt;&gt;
-
-***
-
-### refresh()
-
-```ts
-refresh(): Promise<void>
-```
-
-Ask the backend for this job's current state, and for a server-side job
-its full record, then cache it for the getters above.
-
-#### Returns
-
-`Promise`&lt;`void`&gt;
-
-***
-
 ### status()
 
 ```ts
 status(): Promise<string>
 ```
 
-The operation's current lifecycle state: "running", "finished", "failed",
-or "cancelled".
+The operation's current lifecycle state: "running", "finished",
+"failed", or "cancelled".
 
-A point snapshot; unlike [Job.wait](Job.md#wait) it does not block or reject on a
-terminal failure state. Also refreshes the getters above.
+A point snapshot; unlike [Job.wait](Job.md#wait) it does not block or reject
+on a terminal failure state. States a newer server reports that this
+client version does not know pass through as-is.
 
 #### Returns
 
@@ -201,22 +70,6 @@ terminal failure state. Also refreshes the getters above.
 
 ***
 
-### toString()
-
-```ts
-toString(): string
-```
-
-Every field the handle currently knows, one per line, with the JSON
-payloads indented -- a refresh job's spec and result are the point of
-printing it.
-
-#### Returns
-
-`string`
-
-***
-
 ### wait()
 
 ```ts

docs/src/js/classes/MergeInsertBuilder.md

@@ -141,7 +141,7 @@ Currently this causes multiple copies of the row to be created
 but that behavior is subject to change.
 
 An optional condition may be specified.  If it is, then only
-matched rows that satisfy the condition will be updated.  Any
+matched rows that satisfy the condtion will be updated.  Any
 rows that do not satisfy the condition will be left as they
 are.  Failing to satisfy the condition does not cause a
 "matched row" to become a "not matched" row.

docs/src/js/classes/Table.md

@@ -676,17 +676,9 @@ List all the versions of the table
 abstract mergeInsert(on): MergeInsertBuilder
 ```
 
-Create a [MergeInsertBuilder](MergeInsertBuilder.md), which combines new data with the
-existing table in a single transaction — inserting, updating and deleting
-rows depending on how they match.
-
 #### Parameters
 
 * **on**: `string` \| `string`[]
-    The column, or columns, to match source rows against target
-    rows on. Typically a key or id column. Several columns match on the
-    composite key: a source row updates a target row only when it agrees on
-    every one of them.
 
 #### Returns
 
@@ -1266,7 +1258,7 @@ value is 0")
 Note: if your condition is something like "some_id_column == 7" and
 you are updating many rows (with different ids) then you will get
 better performance with a single [`merge_insert`] call instead of
-repeatedly calling this method.
+repeatedly calilng this method.
 
 ##### Parameters
 

docs/src/js/globals.md

@@ -96,7 +96,7 @@
 - [IvfFlatOptions](interfaces/IvfFlatOptions.md)
 - [IvfPqOptions](interfaces/IvfPqOptions.md)
 - [IvfRqOptions](interfaces/IvfRqOptions.md)
-- [JobEventsOptions](interfaces/JobEventsOptions.md)
+- [JobDescription](interfaces/JobDescription.md)
 - [JobFailureInfo](interfaces/JobFailureInfo.md)
 - [JobInfo](interfaces/JobInfo.md)
 - [ListNamespacesOptions](interfaces/ListNamespacesOptions.md)

docs/src/js/interfaces/HnswPqOptions.md

@@ -118,7 +118,7 @@ Number of sub-vectors of PQ.
 This value controls how much the vector is compressed during the quantization step.
 The more sub vectors there are the less the vector is compressed.  The default is
 the dimension of the vector divided by 16.  If the dimension is not evenly divisible
-by 16 we use the dimension divided by 8.
+by 16 we use the dimension divded by 8.
 
 The above two cases are highly preferred.  Having 8 or 16 values per subvector allows
 us to use efficient SIMD instructions.

docs/src/js/interfaces/IndexOptions.md

@@ -16,7 +16,7 @@ optional config: Index;
 
 Advanced index configuration
 
-This option allows you to specify a specific index to create and also
+This option allows you to specify a specfic index to create and also
 allows you to pass in configuration for training the index.
 
 See the static methods on Index for details on the various index types.

docs/src/js/interfaces/IvfPqOptions.md

@@ -112,7 +112,7 @@ Number of sub-vectors of PQ.
 This value controls how much the vector is compressed during the quantization step.
 The more sub vectors there are the less the vector is compressed.  The default is
 the dimension of the vector divided by 16.  If the dimension is not evenly divisible
-by 16 we use the dimension divided by 8.
+by 16 we use the dimension divded by 8.
 
 The above two cases are highly preferred.  Having 8 or 16 values per subvector allows
 us to use efficient SIMD instructions.

docs/src/js/interfaces/JobDescription.md

@@ -0,0 +1,66 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / JobDescription
+
+# Interface: JobDescription
+
+A described job from `Connection.getJob`.
+
+## Properties
+
+### creationMs
+
+```ts
+creationMs: number;
+```
+
+When the job was created, in milliseconds since the epoch.
+
+***
+
+### failure?
+
+```ts
+optional failure: JobFailureInfo;
+```
+
+Why the job failed, when the job is failed and the server reports a
+reason.
+
+***
+
+### jobId
+
+```ts
+jobId: string;
+```
+
+***
+
+### jobType
+
+```ts
+jobType: string;
+```
+
+***
+
+### specJson?
+
+```ts
+optional specJson: string;
+```
+
+The job-type-specific specification as a JSON string, when present.
+
+***
+
+### state
+
+```ts
+state: string;
+```
+
+Lifecycle state: "running", "finished", "failed", or "cancelled".

docs/src/js/interfaces/JobEventsOptions.md

@@ -1,29 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / JobEventsOptions
-
-# Interface: JobEventsOptions
-
-Which of a job's events [Job.events](../classes/Job.md#events) returns.
-
-## Properties
-
-### filter?
-
-```ts
-optional filter: string;
-```
-
-SQL-like filter over the event columns.
-
-***
-
-### limit?
-
-```ts
-optional limit: number;
-```
-
-Maximum event rows to return, up to the server maximum of 10,000.

docs/src/js/interfaces/JobInfo.md

@@ -26,7 +26,7 @@ When the job was created, in milliseconds since the epoch.
 jobId: string;
 ```
 
-The job id -- what `Connection.openJob` and `Connection.cancelJob`
+The job id -- what `Connection.getJob` and `Connection.cancelJob`
 accept.
 
 ***

docs/src/js/interfaces/MaterializedViewDefinition.md

@@ -50,16 +50,6 @@ projections: [string, string][];
 
 ***
 
-### sourceNamespace
-
-```ts
-sourceNamespace: string[];
-```
-
-Namespace holding the source table; empty is the root namespace.
-
-***
-
 ### sourceTable
 
 ```ts

docs/src/python/python.md

@@ -28,59 +28,6 @@ is also an [asynchronous API client](#connections-asynchronous).
 
 ::: lancedb.Session
 
-## Remote SQL
-
-Submit SQL against a remote LanceDB database through the connection.
-The connected database and `default_namespace_path=["public"]` are used for
-unqualified tables. Fully qualified references can still query other databases
-and namespaces available to the same deployment. `execute_query` returns a
-reader as soon as its initial result stream is available. `execute_query_async`
-returns a query handle immediately; use it to inspect progress, open a reader,
-or cancel the query. The SQL client is initialized by the first query and
-retained for the lifetime of the remote connection. Query ids are random,
-connection-scoped references rather than encoded SQL or durable resume tokens:
-
-```python
-import lancedb
-
-db = lancedb.connect(
-    "db://analytics",
-    api_key="ldb_...",
-    host_override="https://api.example.com",
-    sql_host_override="grpc+tls://sql.example.com:10026",
-)
-reader = db.execute_query(
-    """
-    SELECT events.id, accounts.name
-    FROM analytics.public.events AS events
-    JOIN users.public.accounts AS accounts ON events.user_id = accounts.id
-    """,
-    default_namespace_path=["public"],
-)
-for batch in reader:
-    print(batch.num_rows)
-
-query = db.execute_query_async("SELECT * FROM events")
-print(query.id)
-print(query.describe().status)
-for batch in query.reader():
-    print(batch.num_rows)
-
-# The async connection exposes the same lifecycle without blocking:
-# async_db = await lancedb.connect_async(
-#     "db://analytics",
-#     api_key="ldb_...",
-#     host_override="https://api.example.com",
-#     sql_host_override="grpc+tls://sql.example.com:10026",
-# )
-# reader = await async_db.execute_query("SELECT * FROM events")
-# query = await async_db.execute_query_async("SELECT * FROM events")
-# description = await async_db.describe_query(query.id)
-# async for batch in await query.reader():
-#     print(batch.num_rows)
-# await query.cancel()
-```
-
 ## Namespaces (Synchronous)
 
 A namespace-backed connection resolves tables through a
@@ -147,8 +94,6 @@ listing a storage directory.
 
 ::: lancedb.functions.OutputMapping
 
-::: lancedb.functions.AssignmentMapping
-
 ::: lancedb.functions.FunctionBinding
 
 ::: lancedb.functions.RefreshColumnResult
@@ -157,18 +102,6 @@ listing a storage directory.
 
 ::: lancedb.job.AsyncJob
 
-::: lancedb.job.JobInfo
-
-::: lancedb.job.JobDescription
-
-::: lancedb.job.JobFailureInfo
-
-::: lancedb.sql.Query
-
-::: lancedb.sql.AsyncQuery
-
-::: lancedb.sql.QueryDescription
-
 ## Materialized Views (Synchronous)
 
 ::: lancedb.materialized_view.MaterializedView
@@ -316,12 +249,6 @@ still work. Queries return descriptors. Call
 
 ::: lancedb.exceptions.MissingColumnError
 
-::: lancedb.exceptions.JobNotFoundError
-
-::: lancedb.exceptions.JobFailedError
-
-::: lancedb.exceptions.JobCancelledError
-
 ## Integrations
 
 ## Pydantic

java/lancedb-core/pom.xml

@@ -8,7 +8,7 @@
     <parent>
       <groupId>com.lancedb</groupId>
       <artifactId>lancedb-parent</artifactId>
-      <version>0.39.0-beta.6</version>
+      <version>0.38.0-final.0</version>
       <relativePath>../pom.xml</relativePath>
     </parent>
 

java/pom.xml

@@ -6,7 +6,7 @@
 
     <groupId>com.lancedb</groupId>
     <artifactId>lancedb-parent</artifactId>
-    <version>0.39.0-beta.6</version>
+    <version>0.38.0-final.0</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>12.0.0-beta.17</lance-core.version>
+        <lance-core.version>11.0.0</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

@@ -1,7 +1,7 @@
 [package]
 name = "lancedb-nodejs"
 edition.workspace = true
-version = "0.39.0-beta.6"
+version = "0.38.0"
 publish = false
 license.workspace = true
 description.workspace = true

nodejs/__test__/materialized_view.test.ts

@@ -48,28 +48,6 @@ describe("materialized views", () => {
     expect(definitionFromMetadata(safe, "v").limit).toBe(42);
   });
 
-  it("reads the namespaced select kind and refuses unknown kinds", () => {
-    // "namespaced_select" is the namespaced form of "select": same shape, a
-    // separate kind so readers that predate it refuse instead of resolving
-    // the source at the root.
-    const namespaced = new Map([
-      [
-        DEFINITION_META_KEY,
-        '{"kind":"namespaced_select","source_table":"people","source_namespace":["ns"]}',
-      ],
-    ]);
-    const definition = definitionFromMetadata(namespaced, "v");
-    expect(definition.sourceTable).toBe("people");
-    expect(definition.sourceNamespace).toEqual(["ns"]);
-
-    const unknown = new Map([
-      [DEFINITION_META_KEY, '{"kind":"select_v3","source_table":"people"}'],
-    ]);
-    expect(() => definitionFromMetadata(unknown, "v")).toThrow(
-      /cannot refresh/,
-    );
-  });
-
   it("creates, refreshes and queries a view", async () => {
     const view = await db.createMaterializedView("adults", "people", {
       select: ["name", ["shout", "upper(name)"]],

nodejs/__test__/remote.test.ts

@@ -939,7 +939,6 @@ describe("remote connection jobs surface", () => {
     const { tableFromArrays, tableToIPC } = await import("apache-arrow");
     const eventsTable = tableFromArrays({ state: ["created", "succeeded"] });
     const eventsBody = Buffer.from(tableToIPC(eventsTable, "stream"));
-    const queryEventsPayloads: Record<string, unknown>[] = [];
 
     await withMockDatabase(
       (req, res) => {
@@ -968,16 +967,6 @@ describe("remote connection jobs surface", () => {
                 );
             }
           } else if (req.url === "/v1/jobs/describe") {
-            if (payload["job_id"] === "job-2") {
-              res
-                .writeHead(200, { "Content-Type": "application/json" })
-                .end(
-                  '{"job_id": "job-2", "job_type": "refresh_column", ' +
-                    '"job_state": "DONE", "creation_ms": 2000, ' +
-                    '"result": {"rows_assigned": 1000000}}',
-                );
-              return;
-            }
             if (payload["job_id"] !== "job-1") {
               res.writeHead(404).end("no such job");
               return;
@@ -999,7 +988,6 @@ describe("remote connection jobs surface", () => {
               .writeHead(200, { "Content-Type": "application/json" })
               .end('{"job_id": "job-1"}');
           } else if (req.url === "/v1/jobs/query_events") {
-            queryEventsPayloads.push(payload);
             res
               .writeHead(200, {
                 "Content-Type": "application/vnd.apache.arrow.stream",
@@ -1016,65 +1004,22 @@ describe("remote connection jobs surface", () => {
         expect(jobs[0].state).toEqual("running");
         expect(jobs[1].state).toEqual("finished");
 
+        const description = await db.getJob("job-1");
+        expect(description?.state).toEqual("failed");
+        expect(JSON.parse(description?.specJson ?? "")).toEqual({
+          column: "vec",
+        });
+        expect(description?.failure?.message).toEqual("worker died");
+        expect(await db.getJob("missing")).toBeNull();
+
         expect(await db.cancelJob("job-1")).toBe(true);
         expect(await db.cancelJob("missing")).toBe(false);
 
-        // Opening a job hands back a populated handle; a missing one rejects.
-        await expect(db.openJob("missing")).rejects.toThrow("not found");
-        const finished = await db.openJob("job-2");
-        expect(finished.state).toEqual("finished");
-        expect(finished.result).toEqual({
-          // biome-ignore lint/style/useNamingConvention: snake_case mandated by the server wire format
-          rows_assigned: 1000000,
-        });
+        const history = await db.jobHistory("job-1");
+        expect(history.numRows).toEqual(2);
 
-        const job = await db.openJob("job-1");
+        const job = db.job("job-1");
         expect(job.id).toEqual("job-1");
-
-        // openJob already populated the handle; refresh() re-reads it.
-        expect(job.state).toEqual("failed");
-        await job.refresh();
-        expect(job.state).toEqual("failed");
-        expect(job.jobType).toEqual("create_index");
-        expect(job.creationMs).toEqual(1000);
-        expect(job.spec).toEqual({ column: "vec" });
-        expect(job.result).toBeNull();
-        expect(job.failure?.message).toEqual("worker died");
-
-        // The handle reaches its own events, supplying its job id.
-        const jobEvents = await job.events({
-          limit: 500,
-          filter: "state = 'claim_complete'",
-        });
-        expect(jobEvents.numRows).toEqual(2);
-        expect(queryEventsPayloads.pop()).toEqual({
-          // biome-ignore lint/style/useNamingConvention: snake_case mandated by the server wire format
-          job_id: "job-1",
-          limit: 500,
-          filter: "state = 'claim_complete'",
-        });
-
-        // Printing lays every known field out on its own line, with the JSON
-        // payloads indented rather than crammed onto one line.
-        expect(`${job}`).toEqual(
-          [
-            "Job(",
-            '    id="job-1",',
-            '    state="failed",',
-            '    jobType="create_index",',
-            "    creationMs=1000,",
-            "    spec={",
-            '        "column": "vec"',
-            "    },",
-            "    failure={",
-            '        "phase": "execute",',
-            '        "message": "worker died",',
-            '        "retryable": true',
-            "    },",
-            ")",
-          ].join("\n"),
-        );
-
         expect(await job.status()).toEqual("failed");
         await expect(job.wait()).rejects.toThrow("worker died");
       },

nodejs/__test__/table.test.ts

@@ -281,7 +281,7 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
         numIndices: 0,
         numRows: 3,
         // Full on-disk size of the two data files, footers and metadata included.
-        totalBytes: 550,
+        totalBytes: 684,
       });
 
       // Index files count toward totalBytes too (only deletion files and
@@ -289,7 +289,7 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
       await table.createIndex("id", { config: Index.btree() });
       const statsWithIndex = await table.stats();
       expect(statsWithIndex.numIndices).toBe(1);
-      expect(statsWithIndex.totalBytes).toBeGreaterThan(550);
+      expect(statsWithIndex.totalBytes).toBeGreaterThan(684);
     });
 
     it("should overwrite data if asked", async () => {
@@ -737,12 +737,11 @@ it("should query documents with LangChain PDF metadata", async () => {
 
 describe("merge insert", () => {
   let tmpDir: tmp.DirResult;
-  let conn: Connection;
   let table: Table;
 
   beforeEach(async () => {
     tmpDir = tmp.dirSync({ unsafeCleanup: true });
-    conn = await connect(tmpDir.name);
+    const conn = await connect(tmpDir.name);
 
     table = await conn.createTable("some_table", [
       { a: 1, b: "a" },
@@ -780,38 +779,6 @@ describe("merge insert", () => {
 
     expect(result.map((row) => ({ ...row }))).toEqual(expected);
   });
-  test("upsert on a composite key", async () => {
-    const composite = await conn.createTable("composite", [
-      { shard: "a", id: 1, val: "x" },
-      { shard: "a", id: 2, val: "y" },
-      { shard: "b", id: 1, val: "z" },
-    ]);
-
-    // ("a", 1) matches an existing row and updates it. ("b", 2) agrees with an
-    // existing row on each key column separately but on neither pair, so it is
-    // an insert.
-    const mergeInsertRes = await composite
-      .mergeInsert(["shard", "id"])
-      .whenMatchedUpdateAll()
-      .whenNotMatchedInsertAll()
-      .execute([
-        { shard: "a", id: 1, val: "X" },
-        { shard: "b", id: 2, val: "W" },
-      ]);
-    expect(mergeInsertRes.numUpdatedRows).toBe(1);
-    expect(mergeInsertRes.numInsertedRows).toBe(1);
-
-    const result = (await composite.toArrow())
-      .toArray()
-      .sort((a, b) => a.shard.localeCompare(b.shard) || a.id - b.id);
-
-    expect(result.map((row) => ({ ...row }))).toEqual([
-      { shard: "a", id: 1, val: "X" },
-      { shard: "a", id: 2, val: "y" },
-      { shard: "b", id: 1, val: "z" },
-      { shard: "b", id: 2, val: "W" },
-    ]);
-  });
   test("conditional update", async () => {
     const newData = [
       { a: 2, b: "x" },
@@ -3252,7 +3219,7 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
       const db = await connect(tmpDir.name);
       const data = [
         { text: "fa", vector: [0.1, 0.2, 0.3] },
-        { text: "fo", vector: [0.4, 0.5, 0.6] }, // spellchecker:disable-line
+        { text: "fo", vector: [0.4, 0.5, 0.6] },
         { text: "fob", vector: [0.4, 0.5, 0.6] },
         { text: "focus", vector: [0.4, 0.5, 0.6] },
         { text: "foo", vector: [0.4, 0.5, 0.6] },
@@ -3277,7 +3244,7 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
       const resultSet = new Set(fuzzyResults.map((r) => r.text));
       expect(resultSet.has("foo")).toBe(true);
       expect(resultSet.has("fob")).toBe(true);
-      expect(resultSet.has("fo")).toBe(true); // spellchecker:disable-line
+      expect(resultSet.has("fo")).toBe(true);
       expect(resultSet.has("food")).toBe(true);
 
       const prefixResults = await table

nodejs/lancedb/arrow.ts

@@ -600,7 +600,7 @@ function makeVector(
   }
   if (values.length === 0) {
     throw Error(
-      "makeVector requires at least one value or the type must be specified",
+      "makeVector requires at least one value or the type must be specfied",
     );
   }
   const sampleValue = values.find((val) => val !== null && val !== undefined);
@@ -858,7 +858,7 @@ async function applyEmbeddings<T>(
  * customized by the `embeddingDataType` property of the embedding function.
  *
  * If a schema is provided in `makeTableOptions` then it should include the
- * embedding columns.  If no schema is provided then embedding columns will
+ * embedding columns.  If no schema is provded then embedding columns will
  * be placed at the end of the table, after all of the input columns.
  */
 export async function convertToTable(

nodejs/lancedb/connection.ts

@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: Apache-2.0
 // SPDX-FileCopyrightText: Copyright The LanceDB Authors
 
+import { tableFromIPC } from "apache-arrow";
 import {
   Data,
   SchemaLike,
@@ -15,7 +16,6 @@ import {
   makeEmptyTable,
 } from "./arrow";
 import { EmbeddingFunctionConfig, getRegistry } from "./embedding/registry";
-import { Job } from "./job";
 import {
   MaterializedView,
   MaterializedViewSelect,
@@ -27,6 +27,8 @@ import type {
   CreateNamespaceResponse,
   DescribeNamespaceResponse,
   DropNamespaceResponse,
+  Job,
+  JobDescription,
   JobInfo,
   ListNamespacesResponse,
   ListTablesResponse,
@@ -555,19 +557,24 @@ export abstract class Connection {
   ): Promise<void>;
 
   /**
-   * Open a server-side job by id, returning a handle with its record already
-   * populated. Rejects when the server has no such job, the way
-   * {@link Connection.openTable} does for a missing table.
+   * A {@link Job} handle for a server-side job by id.
    *
-   * The returned {@link Job} answers for its own state, specification,
-   * result, failure and event history, so there is no separate
-   * connection-level call for any of them.
+   * The handle is constructed without a server round trip; an unknown id
+   * surfaces when the handle is used. Dropping the handle has no effect on
+   * the job itself.
    */
-  abstract openJob(jobId: string): Promise<Job>;
+  abstract job(jobId: string): Job;
 
   /** List server-side jobs across the database's tables. */
   abstract listJobs(): Promise<JobInfo[]>;
 
+  /**
+   * Describe a single server-side job by id.
+   *
+   * Resolves to `null` when the server has no such job.
+   */
+  abstract getJob(jobId: string): Promise<JobDescription | null>;
+
   /**
    * Request cancellation of a server-side job by id.
    *
@@ -575,6 +582,13 @@ export abstract class Connection {
    * such job exists. Cancelling an already-terminal job is a no-op success.
    */
   abstract cancelJob(jobId: string): Promise<boolean>;
+
+  /**
+   * The lifecycle event history of a server-side job, as an Arrow table.
+   *
+   * Lists history across all jobs when `jobId` is omitted.
+   */
+  abstract jobHistory(jobId?: string): Promise<ArrowTable>;
 }
 
 /** @hideconstructor */
@@ -855,7 +869,7 @@ export class LocalConnection extends Connection {
   }
 
   async dropTableAsync(name: string, namespacePath?: string[]): Promise<Job> {
-    return new Job(await this.inner.dropTableAsync(name, namespacePath ?? []));
+    return this.inner.dropTableAsync(name, namespacePath ?? []);
   }
 
   async dropAllTables(namespacePath?: string[]): Promise<void> {
@@ -914,17 +928,29 @@ export class LocalConnection extends Connection {
     );
   }
 
-  async openJob(jobId: string): Promise<Job> {
-    return new Job(await this.inner.openJob(jobId));
+  job(jobId: string): Job {
+    return this.inner.job(jobId);
   }
 
   async listJobs(): Promise<JobInfo[]> {
     return this.inner.listJobs();
   }
 
+  async getJob(jobId: string): Promise<JobDescription | null> {
+    return this.inner.getJob(jobId);
+  }
+
   async cancelJob(jobId: string): Promise<boolean> {
     return this.inner.cancelJob(jobId);
   }
+
+  async jobHistory(jobId?: string): Promise<ArrowTable> {
+    const buf = await this.inner.jobHistory(jobId);
+    if (buf.length === 0) {
+      return new ArrowTable();
+    }
+    return tableFromIPC(buf);
+  }
 }
 
 /**

nodejs/lancedb/index.ts

@@ -94,9 +94,13 @@ export {
   RenameTableOptions,
 } from "./connection";
 
-export { JobFailureInfo, JobInfo, Session } from "./native.js";
-
-export { Job, JobEventsOptions } from "./job";
+export {
+  Job,
+  JobDescription,
+  JobFailureInfo,
+  JobInfo,
+  Session,
+} from "./native.js";
 
 export {
   AutoQuery,

nodejs/lancedb/indices.ts

@@ -26,7 +26,7 @@ export interface IvfPqOptions {
    * This value controls how much the vector is compressed during the quantization step.
    * The more sub vectors there are the less the vector is compressed.  The default is
    * the dimension of the vector divided by 16.  If the dimension is not evenly divisible
-   * by 16 we use the dimension divided by 8.
+   * by 16 we use the dimension divded by 8.
    *
    * The above two cases are highly preferred.  Having 8 or 16 values per subvector allows
    * us to use efficient SIMD instructions.
@@ -228,7 +228,7 @@ export interface HnswPqOptions {
    * This value controls how much the vector is compressed during the quantization step.
    * The more sub vectors there are the less the vector is compressed.  The default is
    * the dimension of the vector divided by 16.  If the dimension is not evenly divisible
-   * by 16 we use the dimension divided by 8.
+   * by 16 we use the dimension divded by 8.
    *
    * The above two cases are highly preferred.  Having 8 or 16 values per subvector allows
    * us to use efficient SIMD instructions.
@@ -825,7 +825,7 @@ export interface IndexOptions {
   /**
    * Advanced index configuration
    *
-   * This option allows you to specify a specific index to create and also
+   * This option allows you to specify a specfic index to create and also
    * allows you to pass in configuration for training the index.
    *
    * See the static methods on Index for details on the various index types.

nodejs/lancedb/job.ts

@@ -1,188 +0,0 @@
-// SPDX-License-Identifier: Apache-2.0
-// SPDX-FileCopyrightText: Copyright The LanceDB Authors
-
-import { Table as ArrowTable, tableFromIPC } from "apache-arrow";
-import { JobFailureInfo, Job as NativeJob } from "./native";
-
-/** Which of a job's events {@link Job.events} returns. */
-export interface JobEventsOptions {
-  /** Maximum event rows to return, up to the server maximum of 10,000. */
-  limit?: number;
-  /** SQL-like filter over the event columns. */
-  filter?: string;
-}
-
-/**
- * A handle to an operation that may still be running.
- *
- * The operation may already be complete when the handle is created.
- *
- * The detail getters read what the handle last observed. Submitting an
- * operation returns only a job id, so populating them eagerly would cost an
- * extra round trip on every call:
- *
- * - {@link Job.refresh} and {@link Job.status} fetch the whole record.
- * - {@link Job.wait} records the terminal state it establishes, but not the
- *   rest of the record.
- * - Everything is null until one of those runs.
- *
- * @hideconstructor
- */
-export class Job {
-  private readonly inner: NativeJob;
-
-  constructor(inner: NativeJob) {
-    this.inner = inner;
-  }
-
-  /**
-   * Identifies the operation on the server that is running it.
-   *
-   * Operations that run in this process have no server id. The value is
-   * opaque: parsing it or storing it to resume the job later is not supported.
-   */
-  get id(): string | null {
-    return this.inner.id ?? null;
-  }
-
-  /** The last observed lifecycle state, without contacting the backend. */
-  get state(): string | null {
-    return this.inner.state ?? null;
-  }
-
-  /**
-   * The job's type, as the server names it. Null for an in-process job, which
-   * has no server-side record.
-   */
-  get jobType(): string | null {
-    return this.inner.jobType ?? null;
-  }
-
-  /** When the job was created, in milliseconds since the epoch. */
-  get creationMs(): number | null {
-    return this.inner.creationMs ?? null;
-  }
-
-  /** The job-type-specific specification it was submitted with. */
-  // biome-ignore lint/suspicious/noExplicitAny: shape varies by job type
-  get spec(): any | null {
-    return parseJson(this.inner.specJson);
-  }
-
-  /**
-   * The job-type-specific terminal result. Null until the job succeeds, so a
-   * job that never terminates reports its progress through {@link Job.events}
-   * instead.
-   */
-  // biome-ignore lint/suspicious/noExplicitAny: shape varies by job type
-  get result(): any | null {
-    return parseJson(this.inner.resultJson);
-  }
-
-  /** Why the job failed, when it failed and the server reports a reason. */
-  get failure(): JobFailureInfo | null {
-    return this.inner.failure ?? null;
-  }
-
-  /**
-   * The operation's current lifecycle state: "running", "finished", "failed",
-   * or "cancelled".
-   *
-   * A point snapshot; unlike {@link Job.wait} it does not block or reject on a
-   * terminal failure state. Also refreshes the getters above.
-   */
-  async status(): Promise<string> {
-    return this.inner.status();
-  }
-
-  /** Wait until the operation reaches a terminal state. */
-  async wait(): Promise<void> {
-    return this.inner.wait();
-  }
-
-  /** Request cancellation. Cancelling a finished operation is a no-op. */
-  async cancel(): Promise<void> {
-    return this.inner.cancel();
-  }
-
-  /**
-   * Ask the backend for this job's current state, and for a server-side job
-   * its full record, then cache it for the getters above.
-   */
-  async refresh(): Promise<void> {
-    return this.inner.refresh();
-  }
-
-  /**
-   * This job's recorded lifecycle events.
-   *
-   * Where the getters above report a terminal result only once the job reaches
-   * one, events are written as the job runs and outlive the workers that
-   * produced them. A distributed job records a `claim`/`claim_complete` pair
-   * per unit of work, each carrying `rows_processed`, so a job that never
-   * finishes still accounts for what it did.
-   *
-   * The server caps results at 1000 rows by default and 10,000 at most, and
-   * truncates without saying so, so pass `limit` for a job that emits an event
-   * per fragment. `filter` is a SQL-like expression over the `state`,
-   * `updated_by`, `emitted_from`, `emitted_by`, and `claim_entity` columns.
-   */
-  async events(options?: JobEventsOptions): Promise<ArrowTable> {
-    const buf = await this.inner.events(options?.limit, options?.filter);
-    if (buf.length === 0) {
-      return new ArrowTable();
-    }
-    return tableFromIPC(buf);
-  }
-
-  /**
-   * Every field the handle currently knows, one per line, with the JSON
-   * payloads indented -- a refresh job's spec and result are the point of
-   * printing it.
-   */
-  toString(): string {
-    if (this.state === null) {
-      const known = this.id === null ? "" : `id=${JSON.stringify(this.id)}, `;
-      return `Job(${known}not refreshed)`;
-    }
-    const fields: string[] = [];
-    if (this.id !== null) {
-      fields.push(`id=${JSON.stringify(this.id)}`);
-    }
-    fields.push(`state=${JSON.stringify(this.state)}`);
-    if (this.jobType !== null) {
-      fields.push(`jobType=${JSON.stringify(this.jobType)}`);
-    }
-    if (this.creationMs !== null) {
-      fields.push(`creationMs=${this.creationMs}`);
-    }
-    for (const [name, value] of [
-      ["spec", this.spec],
-      ["result", this.result],
-    ] as const) {
-      if (value !== null) {
-        fields.push(`${name}=${indentJson(value)}`);
-      }
-    }
-    if (this.failure !== null) {
-      fields.push(`failure=${indentJson(this.failure)}`);
-    }
-    return `Job(${fields.map((field) => `\n${REPR_INDENT}${field},`).join("")}\n)`;
-  }
-
-  [Symbol.for("nodejs.util.inspect.custom")](): string {
-    return this.toString();
-  }
-}
-
-const REPR_INDENT = "    ";
-
-// biome-ignore lint/suspicious/noExplicitAny: shape varies by job type
-function indentJson(value: any): string {
-  return JSON.stringify(value, null, 4).replace(/\n/g, `\n${REPR_INDENT}`);
-}
-
-// biome-ignore lint/suspicious/noExplicitAny: shape varies by job type
-function parseJson(raw: string | null | undefined): any | null {
-  return raw === null || raw === undefined ? null : JSON.parse(raw);
-}

nodejs/lancedb/materialized_view.ts

@@ -19,8 +19,6 @@ export interface MaterializedViewDefinition {
   limit?: number;
   /** Source columns the projections and filter read. */
   inputs: string[];
-  /** Namespace holding the source table; empty is the root namespace. */
-  sourceNamespace: string[];
 }
 
 /**
@@ -80,8 +78,7 @@ export function definitionFromMetadata(
   }
   // biome-ignore lint/suspicious/noExplicitAny: raw JSON
   const value: any = JSON.parse(raw);
-  // "namespaced_select" keeps older readers from resolving the source at root.
-  if (value.kind !== "select" && value.kind !== "namespaced_select") {
+  if (value.kind !== "select") {
     throw new Error(
       `materialized view '${name}' is defined by '${value.kind}', which this ` +
         "version of lancedb cannot refresh",
@@ -106,7 +103,6 @@ export function definitionFromMetadata(
     filter: value.filter ?? undefined,
     limit,
     inputs: value.inputs ?? [],
-    sourceNamespace: value.source_namespace ?? [],
   };
 }
 

nodejs/lancedb/merge.ts

@@ -27,7 +27,7 @@ export class MergeInsertBuilder {
    * but that behavior is subject to change.
    *
    * An optional condition may be specified.  If it is, then only
-   * matched rows that satisfy the condition will be updated.  Any
+   * matched rows that satisfy the condtion will be updated.  Any
    * rows that do not satisfy the condition will be left as they
    * are.  Failing to satisfy the condition does not cause a
    * "matched row" to become a "not matched" row.

nodejs/lancedb/sanitize.ts

@@ -3,7 +3,7 @@
 
 // The utilities in this file help sanitize data from the user's arrow
 // library into the types expected by vectordb's arrow library.  Node
-// generally allows for multiple versions of the same library (and sometimes
+// generally allows for mulitple versions of the same library (and sometimes
 // even multiple copies of the same version) to be installed at the same
 // time.  However, arrow-js uses instanceof which expected that the input
 // comes from the exact same library instance.  This is not always the case

nodejs/lancedb/table.ts

@@ -19,7 +19,6 @@ import {
 
 import { EmbeddingFunctionConfig, getRegistry } from "./embedding/registry";
 import { IndexOptions } from "./indices";
-import { Job } from "./job";
 import { MergeInsertBuilder } from "./merge";
 import {
   AddColumnsResult,
@@ -31,6 +30,7 @@ import {
   DropColumnsResult,
   IndexConfig,
   IndexStatistics,
+  Job,
   LsmStats,
   Branches as NativeBranches,
   OptimizeStats,
@@ -313,7 +313,7 @@ export abstract class Table {
    * Note: if your condition is something like "some_id_column == 7" and
    * you are updating many rows (with different ids) then you will get
    * better performance with a single [`merge_insert`] call instead of
-   * repeatedly calling this method.
+   * repeatedly calilng this method.
    * @param {Map<string, string> | Record<string, string>} updates - the
    * columns to update
    * @returns {Promise<UpdateResult>} A promise that resolves to an object
@@ -919,16 +919,6 @@ export abstract class Table {
   /** Return the table as an arrow table */
   abstract toArrow(): Promise<ArrowTable>;
 
-  /**
-   * Create a {@link MergeInsertBuilder}, which combines new data with the
-   * existing table in a single transaction — inserting, updating and deleting
-   * rows depending on how they match.
-   *
-   * @param on - The column, or columns, to match source rows against target
-   * rows on. Typically a key or id column. Several columns match on the
-   * composite key: a source row updates a target row only when it agrees on
-   * every one of them.
-   */
   abstract mergeInsert(on: string | string[]): MergeInsertBuilder;
 
   /** List all the stats of a specified index
@@ -1124,15 +1114,13 @@ export class LocalTable extends Table {
   ): Promise<Job> {
     // biome-ignore lint/suspicious/noExplicitAny: skip
     const nativeIndex = (options?.config as any)?.inner;
-    return new Job(
-      await this.inner.createIndexAsync(
-        nativeIndex,
-        column,
-        options?.replace,
-        options?.waitTimeoutSeconds,
-        options?.name,
-        options?.train,
-      ),
+    return await this.inner.createIndexAsync(
+      nativeIndex,
+      column,
+      options?.replace,
+      options?.waitTimeoutSeconds,
+      options?.name,
+      options?.train,
     );
   }
 
@@ -1315,7 +1303,7 @@ export class LocalTable extends Table {
   }
 
   async refreshColumnAsync(column: string): Promise<Job> {
-    return new Job(await this.inner.refreshColumnAsync(column));
+    return await this.inner.refreshColumnAsync(column);
   }
 
   async refreshMaterializedView(

nodejs/npm/darwin-arm64/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-darwin-arm64",
-	"version": "0.39.0-beta.6",
+	"version": "0.38.0",
 	"os": ["darwin"],
 	"cpu": ["arm64"],
 	"main": "lancedb.darwin-arm64.node",

nodejs/npm/linux-arm64-gnu/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-arm64-gnu",
-	"version": "0.39.0-beta.6",
+	"version": "0.38.0",
 	"os": ["linux"],
 	"cpu": ["arm64"],
 	"main": "lancedb.linux-arm64-gnu.node",

nodejs/npm/linux-arm64-musl/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-arm64-musl",
-	"version": "0.39.0-beta.6",
+	"version": "0.38.0",
 	"os": ["linux"],
 	"cpu": ["arm64"],
 	"main": "lancedb.linux-arm64-musl.node",

nodejs/npm/linux-x64-gnu/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-x64-gnu",
-	"version": "0.39.0-beta.6",
+	"version": "0.38.0",
 	"os": ["linux"],
 	"cpu": ["x64"],
 	"main": "lancedb.linux-x64-gnu.node",

nodejs/npm/linux-x64-musl/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-x64-musl",
-	"version": "0.39.0-beta.6",
+	"version": "0.38.0",
 	"os": ["linux"],
 	"cpu": ["x64"],
 	"main": "lancedb.linux-x64-musl.node",

nodejs/npm/win32-arm64-msvc/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@lancedb/lancedb-win32-arm64-msvc",
-  "version": "0.39.0-beta.6",
+  "version": "0.38.0",
   "os": [
     "win32"
   ],

nodejs/npm/win32-x64-msvc/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-win32-x64-msvc",
-	"version": "0.39.0-beta.6",
+	"version": "0.38.0",
 	"os": ["win32"],
 	"cpu": ["x64"],
 	"main": "lancedb.win32-x64-msvc.node",

nodejs/package.json

@@ -11,7 +11,7 @@
     "ann"
   ],
   "private": false,
-  "version": "0.39.0-beta.6",
+  "version": "0.38.0",
   "main": "dist/index.js",
   "exports": {
     ".": "./dist/index.js",
@@ -44,7 +44,7 @@
     "@biomejs/biome": "^1.7.3",
     "@jest/globals": "^29.7.0",
     "@napi-rs/cli": "3.7.0",
-    "@opentelemetry/sdk-metrics": "^2.10.0",
+    "@opentelemetry/sdk-metrics": "^1.30.0",
     "@types/axios": "^0.14.0",
     "@types/jest": "^29.1.2",
     "@types/node": "22.7.4",
@@ -56,7 +56,7 @@
     "eslint": "^8.57.0",
     "jest": "^29.7.0",
     "shx": "^0.3.4",
-    "tmp": "^0.2.7",
+    "tmp": "^0.2.3",
     "ts-jest": "^29.1.2",
     "typedoc": "0.26.4",
     "typedoc-plugin-markdown": "4.2.1",

nodejs/pnpm-workspace.yaml

@@ -16,41 +16,3 @@ allowBuilds:
   onnxruntime-node: true
   protobufjs: true
   sharp: true
-
-minimumReleaseAgeExclude:
-  - protobufjs@7.5.8
-  - tmp@0.2.6
-  - form-data@4.0.6
-  - tar@7.5.16
-  - markdown-it@14.1.2
-  - linkify-it@5.0.1
-  - js-yaml@3.15.0
-  - js-yaml@4.1.2
-  - protobufjs@7.6.1
-  - protobufjs@7.6.3
-  - '@babel/core@7.29.1'
-  - axios@1.18.0
-  - brace-expansion@2.1.2
-  - brace-expansion@1.1.16
-  - js-yaml@4.3.0
-  - tar@7.5.18
-  - tar@7.5.19
-  - tar@7.5.17
-  - protobufjs@7.6.5
-  - linkify-it@5.0.2
-  - sharp@0.35.0
-  - brace-expansion@1.1.17
-  - brace-expansion@2.1.3
-  - brace-expansion@2.1.4
-  - brace-expansion@1.1.18
-  - js-yaml@3.15.1
-  - js-yaml@4.3.1
-  - tar@7.5.21
-  - '@opentelemetry/core@2.8.0'
-
-# @huggingface/transformers pins sharp ^0.33.5 and no released version has moved
-# past ^0.34.5, all of which inherit the libvips CVEs in GHSA-f88m-g3jw-g9cj.
-# Force the patched line. sharp is only reached by transformers' image pipeline,
-# which LanceDB's text embedding function never uses.
-overrides:
-  sharp: ^0.35.4

nodejs/src/connection.rs

@@ -442,15 +442,13 @@ impl Connection {
         self.get_inner()?.drop_all_tables(&ns).await.default_error()
     }
 
-    /// Open a server-side job by id, returning a handle with its record
-    /// already populated. Rejects when the server has no such job.
+    /// A `Job` handle for a server-side job by id.
     ///
-    /// The returned handle answers for its own state, specification, result,
-    /// failure and event history, so there is no separate connection-level
-    /// call for any of them.
-    #[napi(catch_unwind)]
-    pub async fn open_job(&self, job_id: String) -> napi::Result<crate::job::Job> {
-        let job = self.get_inner()?.open_job(&job_id).await.default_error()?;
+    /// The handle is constructed without a server round trip; an unknown id
+    /// surfaces when the handle is used.
+    #[napi]
+    pub fn job(&self, job_id: String) -> napi::Result<crate::job::Job> {
+        let job = self.get_inner()?.job(job_id).default_error()?;
         Ok(crate::job::Job::new(job))
     }
 
@@ -461,6 +459,17 @@ impl Connection {
         Ok(jobs.into_iter().map(Into::into).collect())
     }
 
+    /// Describe a single server-side job by id. `null` when the server has
+    /// no such job.
+    #[napi(catch_unwind)]
+    pub async fn get_job(
+        &self,
+        job_id: String,
+    ) -> napi::Result<Option<crate::job::JobDescription>> {
+        let description = self.get_inner()?.get_job(&job_id).await.default_error()?;
+        Ok(description.map(Into::into))
+    }
+
     /// Request cancellation of a server-side job by id. Returns true if the
     /// server accepted the cancellation, false if no such job exists.
     #[napi(catch_unwind)]
@@ -468,6 +477,34 @@ impl Connection {
         self.get_inner()?.cancel_job(&job_id).await.default_error()
     }
 
+    /// The lifecycle event history of a server-side job (all jobs when
+    /// `job_id` is null), as an Arrow IPC stream buffer. Empty when there is
+    /// no history.
+    #[napi(catch_unwind)]
+    pub async fn job_history(&self, job_id: Option<String>) -> napi::Result<Buffer> {
+        let batches = self
+            .get_inner()?
+            .job_history(job_id.as_deref())
+            .await
+            .default_error()?;
+        let Some(first) = batches.first() else {
+            return Ok(Buffer::from(Vec::<u8>::new()));
+        };
+        let mut out = Vec::new();
+        let mut writer = arrow_ipc::writer::StreamWriter::try_new(&mut out, &first.schema())
+            .map_err(|e| napi::Error::from_reason(e.to_string()))?;
+        for batch in &batches {
+            writer
+                .write(batch)
+                .map_err(|e| napi::Error::from_reason(e.to_string()))?;
+        }
+        writer
+            .finish()
+            .map_err(|e| napi::Error::from_reason(e.to_string()))?;
+        drop(writer);
+        Ok(Buffer::from(out))
+    }
+
     #[napi(catch_unwind)]
     /// Describe a namespace and return its properties.
     pub async fn describe_namespace(

nodejs/src/job.rs

@@ -3,9 +3,6 @@
 
 use std::sync::Arc;
 
-use arrow_array::RecordBatch;
-use lancedb::job::JobEventsRequest;
-use napi::bindgen_prelude::Buffer;
 use napi_derive::napi;
 
 use crate::error::NapiErrorExt;
@@ -58,98 +55,12 @@ impl Job {
     pub async fn cancel(&self) -> napi::Result<()> {
         self.inner.cancel().await.default_error()
     }
-
-    /// Ask the backend for this job's current state, and for a server-side job
-    /// its full record, then cache it for the getters below.
-    ///
-    /// They are all null until this runs, because submitting an operation
-    /// returns only a job id. {@link Job.status} fetches the whole record too;
-    /// {@link Job.wait} records only the terminal state it establishes.
-    #[napi(catch_unwind)]
-    pub async fn refresh(&self) -> napi::Result<()> {
-        self.inner.refresh().await.default_error()
-    }
-
-    /// The last observed lifecycle state, without contacting the backend.
-    #[napi(getter)]
-    pub fn state(&self) -> Option<String> {
-        self.inner.state()
-    }
-
-    /// The job's type, as the server names it. Null for an in-process job,
-    /// which has no server-side record.
-    #[napi(getter)]
-    pub fn job_type(&self) -> Option<String> {
-        self.inner.job_type()
-    }
-
-    /// When the job was created, in milliseconds since the epoch.
-    #[napi(getter)]
-    pub fn creation_ms(&self) -> Option<i64> {
-        self.inner.creation_ms()
-    }
-
-    /// The job-type-specific specification as a JSON string, when present.
-    #[napi(getter)]
-    pub fn spec_json(&self) -> Option<String> {
-        self.inner.spec().map(|spec| spec.to_string())
-    }
-
-    /// The job-type-specific terminal result as a JSON string. Null until the
-    /// job succeeds, so a job that never terminates reports its progress
-    /// through {@link Job.events} instead.
-    #[napi(getter)]
-    pub fn result_json(&self) -> Option<String> {
-        self.inner.result().map(|result| result.to_string())
-    }
-
-    /// Why the job failed, when it failed and the server reports a reason.
-    #[napi(getter)]
-    pub fn failure(&self) -> Option<JobFailureInfo> {
-        self.inner.failure().map(|failure| JobFailureInfo {
-            phase: failure.phase,
-            message: failure.message,
-            retryable: failure.retryable,
-        })
-    }
-
-    /// This job's recorded lifecycle events, as an Arrow IPC stream buffer.
-    /// The TypeScript wrapper turns it into an Arrow table.
-    #[napi(catch_unwind)]
-    pub async fn events(&self, limit: Option<u32>, filter: Option<String>) -> napi::Result<Buffer> {
-        let batches = self
-            .inner
-            .events(JobEventsRequest { limit, filter })
-            .await
-            .default_error()?;
-        batches_to_ipc_buffer(&batches)
-    }
-}
-
-/// Serialise Arrow batches as a single IPC stream for the TypeScript layer.
-fn batches_to_ipc_buffer(batches: &[RecordBatch]) -> napi::Result<Buffer> {
-    let Some(first) = batches.first() else {
-        return Ok(Buffer::from(Vec::<u8>::new()));
-    };
-    let mut out = Vec::new();
-    let mut writer = arrow_ipc::writer::StreamWriter::try_new(&mut out, &first.schema())
-        .map_err(|e| napi::Error::from_reason(e.to_string()))?;
-    for batch in batches {
-        writer
-            .write(batch)
-            .map_err(|e| napi::Error::from_reason(e.to_string()))?;
-    }
-    writer
-        .finish()
-        .map_err(|e| napi::Error::from_reason(e.to_string()))?;
-    drop(writer);
-    Ok(Buffer::from(out))
 }
 
 /// A row from `Connection.listJobs`: one server-side job.
 #[napi(object)]
 pub struct JobInfo {
-    /// The job id -- what `Connection.openJob` and `Connection.cancelJob`
+    /// The job id -- what `Connection.getJob` and `Connection.cancelJob`
     /// accept.
     pub job_id: String,
     /// The table the job runs against, without URI or namespace.
@@ -180,3 +91,36 @@ pub struct JobFailureInfo {
     pub message: Option<String>,
     pub retryable: Option<bool>,
 }
+
+/// A described job from `Connection.getJob`.
+#[napi(object)]
+pub struct JobDescription {
+    pub job_id: String,
+    pub job_type: String,
+    /// Lifecycle state: "running", "finished", "failed", or "cancelled".
+    pub state: String,
+    /// When the job was created, in milliseconds since the epoch.
+    pub creation_ms: i64,
+    /// The job-type-specific specification as a JSON string, when present.
+    pub spec_json: Option<String>,
+    /// Why the job failed, when the job is failed and the server reports a
+    /// reason.
+    pub failure: Option<JobFailureInfo>,
+}
+
+impl From<lancedb::database::JobDescription> for JobDescription {
+    fn from(description: lancedb::database::JobDescription) -> Self {
+        Self {
+            job_id: description.job_id,
+            job_type: description.job_type,
+            state: description.state,
+            creation_ms: description.creation_ms,
+            spec_json: (!description.spec.is_null()).then(|| description.spec.to_string()),
+            failure: description.failure.map(|failure| JobFailureInfo {
+                phase: failure.phase,
+                message: failure.message,
+                retryable: failure.retryable,
+            }),
+        }
+    }
+}

nodejs/src/query.rs

@@ -664,11 +664,7 @@ impl JsFullTextQuery {
 }
 
 fn parse_fts_query(query: Object) -> napi::Result<FullTextSearchQuery> {
-    // `&JsFullTextQuery` recovers a native class reference through napi's borrow-tracked
-    // path, which is only usable from generated `#[napi]` argument conversion. This is a
-    // manual lookup on a nested `Object` property instead, so use `ClassInstance`, which
-    // unwraps the class without requiring a borrow scope.
-    if let Ok(Some(query)) = query.get::<ClassInstance<JsFullTextQuery>>("query") {
+    if let Ok(Some(query)) = query.get::<&JsFullTextQuery>("query") {
         Ok(FullTextSearchQuery::new_query(query.inner.clone()))
     } else if let Ok(Some(query_text)) = query.get::<String>("query") {
         let mut query_text = query_text;

python/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "lancedb-python"
-version = "0.39.0-beta.6"
+version = "0.38.0"
 publish = false
 edition.workspace = true
 description = "Python bindings for LanceDB"
@@ -28,7 +28,7 @@ env_logger.workspace = true
 log.workspace = true
 # Maturin enables extension-module mode for Python builds. Keeping it out of
 # Cargo features lets Rust unit tests link against libpython.
-pyo3 = { version = "0.28", features = ["abi3-py310", "chrono", "uuid"] }
+pyo3 = { version = "0.28", features = ["abi3-py310", "chrono"] }
 chrono.workspace = true
 pyo3-async-runtimes = { version = "0.28", features = [
     "attributes",
@@ -40,7 +40,6 @@ serde.workspace = true
 serde_json.workspace = true
 snafu.workspace = true
 tokio.workspace = true
-uuid.workspace = true
 libc = "0.2"
 
 [build-dependencies]

python/pyproject.toml

@@ -139,7 +139,6 @@ include = [
     "python/lancedb/exceptions.py",
     "python/lancedb/background_loop.py",
     "python/lancedb/schema.py",
-    "python/lancedb/sql.py",
     "python/lancedb/remote/__init__.py",
     "python/lancedb/remote/errors.py",
     "python/lancedb/embeddings/__init__.py",

python/python/lancedb/__init__.py

@@ -22,11 +22,7 @@ from .remote.db import RemoteDBConnection
 from .expr import Expr, col, lit, func
 from .schema import blob, vector
 from .job import AsyncJob, Job
-from .sql import AsyncQuery as AsyncSqlQuery
-from .sql import Query as SqlQuery
-from .sql import QueryDescription
 from .functions import (
-    AssignmentMapping as AssignmentMapping,
     FunctionArtifactRequest as FunctionArtifactRequest,
     FunctionApplication as FunctionApplication,
     FunctionBinding as FunctionBinding,
@@ -105,7 +101,6 @@ def connect(
     api_key: Optional[str] = None,
     region: str = "us-east-1",
     host_override: Optional[str] = None,
-    sql_host_override: Optional[str] = None,
     read_consistency_interval: Optional[timedelta] = None,
     request_thread_pool: Optional[Union[int, ThreadPoolExecutor]] = None,
     client_config: Union[ClientConfig, Dict[str, Any], None] = None,
@@ -134,9 +129,6 @@ def connect(
         The region to use for LanceDB Cloud.
     host_override: str, optional
         The override url for LanceDB Cloud.
-    sql_host_override: str, optional
-        The remote SQL service endpoint override. The client connects lazily when SQL
-        is first executed and retains that connection.
     read_consistency_interval: timedelta, default None
         The interval at which to check for updates to the table from other
         processes. If None, then consistency is not checked. For performance
@@ -278,7 +270,6 @@ def connect(
             api_key,
             region,
             host_override,
-            sql_host_override=sql_host_override,
             # TODO: remove this (deprecation warning downstream)
             request_thread_pool=request_thread_pool,
             client_config=client_config,
@@ -421,7 +412,6 @@ def deserialize_conn(
             parsed["api_key"],
             parsed.get("region", "us-east-1"),
             host_override=parsed.get("host_override"),
-            sql_host_override=parsed.get("sql_host_override"),
             client_config=parsed.get("client_config"),
             storage_options=storage_options,
         )
@@ -435,7 +425,6 @@ async def connect_async(
     api_key: Optional[str] = None,
     region: str = "us-east-1",
     host_override: Optional[str] = None,
-    sql_host_override: Optional[str] = None,
     read_consistency_interval: Optional[timedelta] = None,
     client_config: Optional[Union[ClientConfig, Dict[str, Any]]] = None,
     storage_options: Optional[Dict[str, str]] = None,
@@ -458,9 +447,6 @@ async def connect_async(
         The region to use for LanceDB Cloud.
     host_override: str, optional
         The override url for LanceDB Cloud.
-    sql_host_override: str, optional
-        The remote SQL service endpoint override. The client connects lazily when SQL
-        is first executed and retains that connection.
     read_consistency_interval: timedelta, default None
         The interval at which to check for updates to the table from other
         processes. If None, then consistency is not checked. For performance
@@ -548,7 +534,6 @@ async def connect_async(
             api_key,
             region,
             host_override,
-            sql_host_override,
             read_consistency_interval_secs,
             client_config,
             storage_options,
@@ -571,7 +556,6 @@ __all__ = [
     "connect_namespace_async",
     "AsyncConnection",
     "AsyncJob",
-    "AsyncSqlQuery",
     "AsyncLanceNamespaceDBConnection",
     "AsyncTable",
     "FtsToken",
@@ -586,8 +570,6 @@ __all__ = [
     "vector",
     "DBConnection",
     "Job",
-    "QueryDescription",
-    "SqlQuery",
     "LanceDBConnection",
     "LanceNamespaceDBConnection",
     "LsmWriteSpec",

python/python/lancedb/_lancedb.pyi

@@ -1,7 +1,6 @@
 from datetime import date, datetime, timedelta
 from decimal import Decimal
 from typing import Dict, List, Optional, Tuple, Any, TypedDict, Union, Literal
-from uuid import UUID
 
 import pyarrow as pa
 
@@ -148,20 +147,15 @@ class Connection(object):
         start_after: Optional[str],
         limit: Optional[int],
     ) -> list[str]: ...  # Deprecated: Use list_tables instead
-    async def open_job(self, job_id: str) -> Job: ...
+    def 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 list_jobs(self) -> List[JobInfo]: ...
+    async def get_job(self, job_id: str) -> Optional[JobDescription]: ...
     async def cancel_job(self, job_id: str) -> bool: ...
-    async def execute_query_async(
-        self,
-        query: str,
-        *,
-        default_namespace_path: Optional[List[str]] = None,
-    ) -> SqlQuery: ...
-    async def describe_query(self, query_id: UUID) -> QueryDescription: ...
+    async def job_history(
+        self, job_id: Optional[str] = None
+    ) -> List[pa.RecordBatch]: ...
     async def create_table(
         self,
         name: str,
@@ -240,20 +234,9 @@ class BlobFile:
 class Job:
     @property
     def id(self) -> Optional[str]: ...
-    @property
-    def _state(self) -> Optional[str]: ...
-    @property
-    def _description(self) -> Optional[JobDescription]: ...
     async def status(self) -> str: ...
     async def wait(self) -> Optional[str]: ...
     async def cancel(self) -> None: ...
-    async def refresh(self) -> None: ...
-    async def events(
-        self,
-        *,
-        limit: Optional[int] = None,
-        filter: Optional[str] = None,
-    ) -> pa.Table: ...
 
 class JobInfo:
     @property
@@ -285,33 +268,10 @@ class JobDescription:
     @property
     def creation_ms(self) -> int: ...
     @property
-    def _spec_json(self) -> Optional[str]: ...
-    @property
-    def _result_json(self) -> Optional[str]: ...
-    @property
-    def spec(self) -> Optional[Any]: ...
-    @property
-    def result(self) -> Optional[Any]: ...
+    def spec_json(self) -> Optional[str]: ...
     @property
     def failure(self) -> Optional[JobFailureInfo]: ...
 
-class SqlQuery:
-    @property
-    def id(self) -> UUID: ...
-    async def describe(self) -> QueryDescription: ...
-    async def reader(self) -> RecordBatchStream: ...
-    async def cancel(self) -> None: ...
-
-class QueryDescription:
-    @property
-    def id(self) -> UUID: ...
-    @property
-    def status(self) -> str: ...
-    @property
-    def progress(self) -> Optional[float]: ...
-    @property
-    def expires_at(self) -> Optional[datetime]: ...
-
 class Table:
     def name(self) -> str: ...
     def __repr__(self) -> str: ...
@@ -490,7 +450,6 @@ async def connect(
     api_key: Optional[str],
     region: Optional[str],
     host_override: Optional[str],
-    sql_host_override: Optional[str],
     read_consistency_interval: Optional[float],
     client_config: Optional[Union[ClientConfig, Dict[str, Any]]],
     storage_options: Optional[Dict[str, str]],
@@ -647,7 +606,6 @@ class FullTextQuery:
 class PyQueryRequest:
     limit: Optional[int]
     offset: Optional[int]
-    take_offsets: Optional[List[int]]
     filter: Optional[Union[str, bytes]]
     full_text_search: Optional[FullTextQuery]
     select: Optional[Union[str, List[str]]]

python/python/lancedb/db.py

@@ -19,7 +19,6 @@ from typing import (
     Optional,
     Union,
 )
-from uuid import UUID
 
 if sys.version_info >= (3, 12):
     from typing import override
@@ -48,9 +47,6 @@ from . import __version__
 from ._lancedb import connect as lancedb_connect  # type: ignore
 from .functions import FunctionVersion, UdfDefinition
 from .job import AsyncJob, Job, _typed_job
-from .sql import AsyncQuery as AsyncSqlQuery
-from .sql import Query as SqlQuery
-from .sql import QueryDescription
 from .materialized_view import (
     AsyncMaterializedView,
     MaterializedView,
@@ -72,11 +68,10 @@ import deprecation
 
 if TYPE_CHECKING:
     import pyarrow as pa
-    from .arrow import AsyncRecordBatchReader
     from .pydantic import LanceModel
 
     from ._lancedb import Connection as LanceDbConnection
-    from ._lancedb import JobInfo
+    from ._lancedb import JobDescription, JobInfo
     from .common import DATA, URI
     from .embeddings import EmbeddingFunctionConfig
     from ._lancedb import Session
@@ -717,51 +712,26 @@ class DBConnection(EnforceOverrides):
             "Function catalog operations are not supported for this connection type"
         )
 
-    def list_functions(self) -> List[FunctionVersion]:
-        """List every published immutable Function version.
+    def job(self, job_id: str) -> Job:
+        """A [Job][lancedb.job.Job] handle for a server-side job by id.
 
-        Results are ordered by Function name then version. Local connections
-        raise ``NotImplementedError``.
-
-        Examples
-        --------
-        List the identities available to use in Function-backed columns:
-
-        ```python
-        [(function.name, function.version) for function in db.list_functions()]
-        ```
+        The handle is constructed without a server round trip; an unknown id
+        surfaces when the handle is used. Dropping the handle has no effect
+        on the job itself.
         """
-        raise NotImplementedError(
-            "Function catalog operations are not supported for this connection type"
-        )
-
-    def drop_function(self, name: str, *, version: str) -> bool:
-        """Drop one exact immutable Function version from the remote catalog.
-
-        Returns True when the version changed to Dropped and False for an
-        idempotent replay. Local connections raise NotImplementedError.
-        """
-        raise NotImplementedError(
-            "Function catalog operations are not supported for this connection type"
-        )
-
-    def open_job(self, job_id: str) -> Job:
-        """Open a server-side job by id, returning a handle with its record
-        already populated.
-
-        The returned [Job][lancedb.job.Job] answers for its own state,
-        specification, result, failure and event history, so there is no
-        separate connection-level call for any of them.
-
-        Raises `JobNotFoundError` when the server has no such job, the way
-        `open_table` does for a missing table.
-        """
-        raise NotImplementedError("open_job is not supported for this connection type")
+        raise NotImplementedError("job is not supported for this connection type")
 
     def list_jobs(self) -> List[JobInfo]:
         """List server-side jobs across the database's tables."""
         raise NotImplementedError("list_jobs is not supported for this connection type")
 
+    def get_job(self, job_id: str) -> Optional[JobDescription]:
+        """Describe a single server-side job by id.
+
+        Returns None when the server has no such job.
+        """
+        raise NotImplementedError("get_job is not supported for this connection type")
+
     def cancel_job(self, job_id: str) -> bool:
         """Request cancellation of a server-side job by id.
 
@@ -773,38 +743,14 @@ class DBConnection(EnforceOverrides):
             "cancel_job is not supported for this connection type"
         )
 
-    def execute_query(
-        self,
-        query: str,
-        *,
-        default_namespace_path: Optional[List[str]] = None,
-    ) -> pa.RecordBatchReader:
-        """Execute SQL and return a blocking Arrow reader.
+    def job_history(self, job_id: Optional[str] = None) -> List[pa.RecordBatch]:
+        """The lifecycle event history of a server-side job, as Arrow batches.
 
-        This submits through :meth:`execute_query_async` and waits until the
-        initial result stream is readable. It does not wait for the full query
-        to finish.
+        Lists history across all jobs when `job_id` is None.
         """
-        return self.execute_query_async(
-            query,
-            default_namespace_path=default_namespace_path,
-        ).reader()
-
-    def execute_query_async(
-        self,
-        query: str,
-        *,
-        default_namespace_path: Optional[List[str]] = None,
-    ) -> SqlQuery:
-        """Start executing SQL and return its query handle.
-
-        Local connections do not support SQL.
-        """
-        raise NotImplementedError("SQL is not supported for this connection type")
-
-    def describe_query(self, query_id: UUID) -> QueryDescription:
-        """Describe a submitted SQL query by its connection-scoped id."""
-        raise NotImplementedError("SQL is not supported for this connection type")
+        raise NotImplementedError(
+            "job_history is not supported for this connection type"
+        )
 
 
 class LanceDBConnection(DBConnection):
@@ -901,7 +847,6 @@ class LanceDBConnection(DBConnection):
                 None,
                 None,
                 None,
-                None,
                 read_consistency_interval_secs,
                 None,
                 storage_options,
@@ -1450,11 +1395,14 @@ class LanceDBConnection(DBConnection):
         )
 
     @override
-    def open_job(self, job_id: str) -> Job:
-        """Open a server-side job by id. See
-        [DBConnection.open_job][lancedb.db.DBConnection.open_job].
+    def job(self, job_id: str) -> Job:
+        """A [Job][lancedb.job.Job] handle for a server-side job by id.
+
+        The handle is constructed without a server round trip; an unknown id
+        surfaces when the handle is used. Dropping the handle has no effect
+        on the job itself.
         """
-        return Job(LOOP.run(self._conn.open_job(job_id)))
+        return Job(self._conn.job(job_id))
 
     @override
     def create_function_async(self, definition: UdfDefinition) -> Job[FunctionVersion]:
@@ -1465,19 +1413,19 @@ class LanceDBConnection(DBConnection):
     def get_function(self, name: str, *, version: str) -> FunctionVersion:
         return LOOP.run(self._conn.get_function(name, version=version))
 
-    @override
-    def list_functions(self) -> List[FunctionVersion]:
-        return LOOP.run(self._conn.list_functions())
-
-    @override
-    def drop_function(self, name: str, *, version: str) -> bool:
-        return LOOP.run(self._conn.drop_function(name, version=version))
-
     @override
     def list_jobs(self) -> List[JobInfo]:
         """List server-side jobs across the database's tables."""
         return LOOP.run(self._conn.list_jobs())
 
+    @override
+    def get_job(self, job_id: str) -> Optional[JobDescription]:
+        """Describe a single server-side job by id.
+
+        Returns None when the server has no such job.
+        """
+        return LOOP.run(self._conn.get_job(job_id))
+
     @override
     def cancel_job(self, job_id: str) -> bool:
         """Request cancellation of a server-side job by id.
@@ -1488,6 +1436,14 @@ class LanceDBConnection(DBConnection):
         """
         return LOOP.run(self._conn.cancel_job(job_id))
 
+    @override
+    def job_history(self, job_id: Optional[str] = None) -> List[pa.RecordBatch]:
+        """The lifecycle event history of a server-side job, as Arrow batches.
+
+        Lists history across all jobs when `job_id` is None.
+        """
+        return LOOP.run(self._conn.job_history(job_id))
+
     @override
     def namespace_client(self) -> LanceNamespace:
         """Get the equivalent namespace client for this connection.
@@ -2258,11 +2214,15 @@ class AsyncConnection(object):
             namespace_path = []
         await self._inner.drop_all_tables(namespace_path=namespace_path)
 
-    async def open_job(self, job_id: str) -> AsyncJob:
-        """Open a server-side job by id. See
-        [DBConnection.open_job][lancedb.db.DBConnection.open_job].
+    def job(self, job_id: str) -> AsyncJob:
+        """An [AsyncJob][lancedb.job.AsyncJob] handle for a server-side job
+        by id.
+
+        The handle is constructed without a server round trip; an unknown id
+        surfaces when the handle is used. Dropping the handle has no effect
+        on the job itself.
         """
-        return AsyncJob(await self._inner.open_job(job_id))
+        return AsyncJob(self._inner.job(job_id))
 
     async def create_function_async(
         self, definition: UdfDefinition
@@ -2283,25 +2243,17 @@ class AsyncConnection(object):
         """Open one exact immutable Function version from the remote catalog."""
         return FunctionVersion.from_json(await self._inner.get_function(name, version))
 
-    async def list_functions(self) -> List[FunctionVersion]:
-        """List every published immutable Function version.
-
-        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()
-        ]
-
-    async def drop_function(self, name: str, *, version: str) -> bool:
-        """Drop one exact immutable Function version from the remote catalog."""
-        return await self._inner.drop_function(name, version)
-
     async def list_jobs(self) -> List[JobInfo]:
         """List server-side jobs across the database's tables."""
         return await self._inner.list_jobs()
 
+    async def get_job(self, job_id: str) -> Optional[JobDescription]:
+        """Describe a single server-side job by id.
+
+        Returns None when the server has no such job.
+        """
+        return await self._inner.get_job(job_id)
+
     async def cancel_job(self, job_id: str) -> bool:
         """Request cancellation of a server-side job by id.
 
@@ -2311,46 +2263,12 @@ class AsyncConnection(object):
         """
         return await self._inner.cancel_job(job_id)
 
-    async def execute_query(
-        self,
-        query: str,
-        *,
-        default_namespace_path: Optional[List[str]] = None,
-    ) -> AsyncRecordBatchReader:
-        """Execute SQL and return an asynchronous Arrow reader.
+    async def job_history(self, job_id: Optional[str] = None) -> List[pa.RecordBatch]:
+        """The lifecycle event history of a server-side job, as Arrow batches.
 
-        This submits through :meth:`execute_query_async` and waits until the
-        initial result stream is readable. It does not wait for the full query
-        to finish.
+        Lists history across all jobs when `job_id` is None.
         """
-        submitted = await self.execute_query_async(
-            query,
-            default_namespace_path=default_namespace_path,
-        )
-        return await submitted.reader()
-
-    async def execute_query_async(
-        self,
-        query: str,
-        *,
-        default_namespace_path: Optional[List[str]] = None,
-    ) -> AsyncSqlQuery:
-        """Start executing SQL and return its query handle.
-
-        The database from ``connect_async`` is used for unqualified database
-        references. The namespace defaults to ``["public"]``. Local
-        connections raise ``NotImplementedError``.
-        """
-        return AsyncSqlQuery(
-            await self._inner.execute_query_async(
-                query,
-                default_namespace_path=default_namespace_path,
-            )
-        )
-
-    async def describe_query(self, query_id: UUID) -> QueryDescription:
-        """Describe a submitted SQL query by its connection-scoped id."""
-        return await self._inner.describe_query(query_id)
+        return await self._inner.job_history(job_id)
 
     async def namespace_client(self) -> LanceNamespace:
         """Get the equivalent namespace client for this connection.

python/python/lancedb/embeddings/gte.py

@@ -21,7 +21,7 @@ class GteEmbeddings(TextEmbeddingFunction):
     An embedding function that uses GTE-LARGE MLX format(for Apple silicon devices only)
     as well as the standard cpu/gpu version from: https://huggingface.co/thenlper/gte-large.
 
-    For Apple users, you will need the mlx package installed, which can be done with:
+    For Apple users, you will need the mlx package insalled, which can be done with:
         pip install mlx
 
     Parameters

python/python/lancedb/embeddings/instructor.py

@@ -60,7 +60,7 @@ class InstructorEmbeddingFunction(TextEmbeddingFunction):
 
     import lancedb
     from lancedb.pydantic import LanceModel, Vector
-    from lancedb.embeddings import get_registry, InstructorEmbeddingFunction
+    from lancedb.embeddings import get_registry, InstuctorEmbeddingFunction
 
     instructor = get_registry().get("instructor").create(
         source_instruction="represent the document for retrieval",

python/python/lancedb/exceptions.py

@@ -35,9 +35,3 @@ class JobCancelledError(RuntimeError):
     """Exception raised when an asynchronous job was cancelled."""
 
     pass
-
-
-class JobNotFoundError(ValueError):
-    """Exception raised when opening a job the server does not have."""
-
-    pass

python/python/lancedb/functions.py

@@ -470,7 +470,11 @@ class InputBinding(_RemoteValue):
 
 
 class OutputMapping(_RemoteValue):
-    """One stable result-field mapping."""
+    """One stable result-field mapping.
+
+    Assignment state is outside the Slice 1 client contract. During the NULL
+    transition Lance exposes no public cell-flag identifier to persist here.
+    """
 
     result_field: str
     output_name: str
@@ -480,13 +484,6 @@ class OutputMapping(_RemoteValue):
     nullable: bool
 
 
-class AssignmentMapping(_RemoteValue):
-    """Internal physical column preserving flattened struct validity."""
-
-    output_name: str
-    output_field_id: _Int32
-
-
 class FunctionBinding(_RemoteValue):
     """Immutable Function binding persisted by the Enterprise table service."""
 
@@ -494,7 +491,6 @@ class FunctionBinding(_RemoteValue):
     function: FunctionVersionRef
     inputs: tuple[InputBinding, ...]
     outputs: tuple[OutputMapping, ...]
-    assignment: Optional[AssignmentMapping] = None
     input_schema: Optional[Mapping[str, Any]] = None
     output_schema: Optional[Mapping[str, Any]] = None
 
@@ -525,12 +521,6 @@ class RefreshColumnResult(_RemoteValue):
 
 _FUNCTION_NAME = re.compile(r"^[A-Za-z_][A-Za-z0-9_.-]*$")
 _FUNCTION_BLOB_V2_TYPE = "blob_v2"
-_ARROW_EXTENSION_NAME_KEY = "ARROW:extension:name"
-_BLOB_V2_EXTENSION_NAME = "lance.blob.v2"
-_NESTED_BLOB_COLLECTION_ERROR = (
-    "unsupported Arrow type for Function signature: Blob v2 fields nested under "
-    "collection types are not supported"
-)
 
 
 _GRAMMAR_PRIMITIVES = (
@@ -601,19 +591,6 @@ def _validate_exact_arrow_field(field: pa.Field) -> None:
                 "unsupported Arrow type for Function signature: lance.blob.v2 "
                 f"requires a supported Blob storage layout, got {field}"
             )
-        metadata = {
-            (key.decode() if isinstance(key, bytes) else key): (
-                value.decode() if isinstance(value, bytes) else value
-            )
-            for key, value in (field.metadata or {}).items()
-        }
-        if metadata and metadata != {
-            _ARROW_EXTENSION_NAME_KEY: _BLOB_V2_EXTENSION_NAME
-        }:
-            raise TypeError(
-                "unsupported Arrow type for Function signature: lance.blob.v2 "
-                "field metadata must contain only its canonical extension marker"
-            )
     elif field.metadata:
         raise TypeError(
             "unsupported Arrow type for Function signature: field metadata "
@@ -678,84 +655,23 @@ def _canonical_arrow_field(field: pa.Field) -> str:
     return _canonical_arrow_type(field.type)
 
 
-def _blob_storage_type(field: pa.Field) -> pa.DataType:
-    data_type = field.type
-    if isinstance(data_type, pa.ExtensionType):
-        return data_type.storage_type
-    return data_type
-
-
-def _exact_blob_storage_type(field: pa.Field) -> dict[str, Any]:
-    storage = _blob_storage_type(field)
-    if not pa.types.is_struct(storage):
-        raise TypeError(
-            "unsupported Arrow type for Function signature: lance.blob.v2 "
-            "requires struct storage"
-        )
-    return {
-        "type": "struct",
-        "fields": [
-            {
-                "name": child.name,
-                "nullable": child.nullable,
-                "type": (
-                    {"type": "large_binary"}
-                    if pa.types.is_large_binary(child.type)
-                    else _exact_arrow_type(child.type)
-                ),
-            }
-            for child in storage
-        ],
-    }
-
-
-def _data_type_has_blob_v2(data_type: pa.DataType) -> bool:
-    if pa.types.is_struct(data_type):
-        return any(
-            _is_blob_v2_field(field) or _data_type_has_blob_v2(field.type)
-            for field in data_type
-        )
-    if (
-        pa.types.is_list(data_type)
-        or pa.types.is_large_list(data_type)
-        or pa.types.is_fixed_size_list(data_type)
-    ):
-        field = data_type.value_field
-        return _is_blob_v2_field(field) or _data_type_has_blob_v2(field.type)
-    if pa.types.is_map(data_type):
-        return any(
-            _is_blob_v2_field(field) or _data_type_has_blob_v2(field.type)
-            for field in (data_type.key_field, data_type.item_field)
-        )
-    return False
-
-
-def _exact_arrow_field(
-    field: pa.Field, *, inside_collection: bool = False
-) -> dict[str, Any]:
+def _exact_arrow_field(field: pa.Field) -> dict[str, Any]:
     _validate_exact_arrow_field(field)
     if _is_blob_v2_field(field):
-        if inside_collection:
-            raise TypeError(_NESTED_BLOB_COLLECTION_ERROR)
-        return {
-            "name": field.name,
-            "nullable": field.nullable,
-            "type": _exact_blob_storage_type(field),
-            "metadata": {
-                _ARROW_EXTENSION_NAME_KEY: _BLOB_V2_EXTENSION_NAME,
-            },
-        }
+        raise TypeError(
+            "unsupported Arrow type for Function signature: nested Blob v2 "
+            "fields are not supported; declare Blob parameters or named result "
+            "fields directly"
+        )
     value = {
         "name": field.name,
         "nullable": field.nullable,
-        "type": _exact_arrow_type(field.type, inside_collection=inside_collection),
+        "type": _exact_arrow_type(field.type),
     }
     return value
 
 
-def _exact_arrow_type(
-    data_type: pa.DataType, *, inside_collection: bool = False
-) -> dict[str, Any]:
+def _exact_arrow_type(data_type: pa.DataType) -> dict[str, Any]:
     for candidate, name in _GRAMMAR_PRIMITIVES:
         if data_type == candidate:
             return {"type": name}
@@ -769,10 +685,7 @@ def _exact_arrow_type(
             )
         return {
             "type": "struct",
-            "fields": [
-                _exact_arrow_field(field, inside_collection=inside_collection)
-                for field in fields
-            ],
+            "fields": [_exact_arrow_field(field) for field in fields],
         }
     if (
         pa.types.is_list(data_type)
@@ -797,15 +710,11 @@ def _exact_arrow_type(
                 if pa.types.is_large_list(data_type)
                 else "fixed_size_list"
             ),
-            "fields": [
-                _exact_arrow_field(data_type.value_field, inside_collection=True)
-            ],
+            "fields": [_exact_arrow_field(data_type.value_field)],
         }
         if pa.types.is_fixed_size_list(data_type):
             value["length"] = data_type.list_size
         return value
-    if pa.types.is_map(data_type) and _data_type_has_blob_v2(data_type):
-        raise TypeError(_NESTED_BLOB_COLLECTION_ERROR)
     raise TypeError(f"unsupported Arrow type for Function signature: {data_type}")
 
 
@@ -915,6 +824,8 @@ def _function_output(output: pa.DataType | pa.Field | pa.Schema) -> FunctionOutp
 
     if not fields:
         raise ValueError("named-struct Function output must contain at least one field")
+    if any(field.nullable for field in fields):
+        raise ValueError("Function output fields must be non-nullable")
     for field in fields:
         _validate_exact_arrow_field(field)
     names = [field.name for field in fields]
@@ -926,7 +837,7 @@ def _function_output(output: pa.DataType | pa.Field | pa.Schema) -> FunctionOutp
             FunctionResultField(
                 name=field.name,
                 arrow_type=_canonical_arrow_field(field),
-                nullable=field.nullable,
+                nullable=False,
             )
             for field in fields
         ),
@@ -1309,9 +1220,8 @@ def udf(
 
     Input and output signatures are inferred from supported annotations. For
     Arrow types annotations cannot express precisely, pass ``input_schema``
-    and ``output_schema`` together. Scalar outputs must be non-nullable. Every
-    named-struct field may be nullable; Enterprise preserves the struct's
-    validity when the result is expanded into sibling columns.
+    and ``output_schema`` together. Nullable outputs are rejected because V1
+    uses physical NULL to represent unassigned computed-column rows.
 
     Parameters
     ----------
@@ -1323,8 +1233,8 @@ def udf(
         Explicit input fields in the exact order of the callable parameters.
         Must be provided together with ``output_schema``.
     output_schema : pyarrow.DataType, pyarrow.Field, or pyarrow.Schema, optional
-        Explicit scalar or named-struct output. Scalar outputs must be
-        non-nullable. Must be provided together with ``input_schema``.
+        Explicit scalar or named-struct output. Must be non-nullable and be
+        provided together with ``input_schema``.
     pip : sequence of str, optional
         Pip requirements for the remote environment.
     conda : sequence of str, optional
@@ -1390,7 +1300,6 @@ def udf(
 
 
 __all__ = [
-    "AssignmentMapping",
     "ApplicationInput",
     "FunctionApplication",
     "FunctionArtifact",

python/python/lancedb/index.py

@@ -751,7 +751,7 @@ class IvfPq:
         This value controls how much the vector is compressed during the
         quantization step.  The more sub vectors there are the less the vector is
         compressed.  The default is the dimension of the vector divided by 16.  If
-        the dimension is not evenly divisible by 16 we use the dimension divided by
+        the dimension is not evenly divisible by 16 we use the dimension divded by
         8.
 
         The above two cases are highly preferred.  Having 8 or 16 values per

python/python/lancedb/job.py

@@ -4,27 +4,15 @@
 """Handles to operations a server may run asynchronously."""
 
 import asyncio
-import json
 from datetime import timedelta
 from typing import Any, Callable, Generic, Optional, TypeVar, cast
 
-import pyarrow as pa
-
 from lancedb.background_loop import LOOP
 
 from . import _lancedb
-from ._lancedb import JobDescription, JobFailureInfo, JobInfo
 
 T = TypeVar("T")
 
-__all__ = [
-    "AsyncJob",
-    "Job",
-    "JobDescription",
-    "JobFailureInfo",
-    "JobInfo",
-]
-
 
 class AsyncJob(Generic[T]):
     """A handle to an operation that may still be running.
@@ -90,149 +78,6 @@ class AsyncJob(Generic[T]):
             return
         await self._inner.cancel()
 
-    async def refresh(self) -> None:
-        """Ask the backend for this job's current state, and for a server-side
-        job its full record, then cache it for the properties below.
-
-        The properties are all `None` until this runs, because submitting an
-        operation returns only a job id. `status` fetches the whole record too;
-        `wait` records only the terminal state it establishes.
-        """
-        if self._inner is None:
-            return
-        await self._inner.refresh()
-
-    @property
-    def state(self) -> Optional[str]:
-        """The last observed lifecycle state, without contacting the backend.
-
-        `None` until the handle has talked to it. See :meth:`AsyncJob.refresh`.
-        """
-        if self._inner is None:
-            return "finished"
-        return self._inner._state
-
-    @property
-    def job_type(self) -> Optional[str]:
-        """The job's type, as the server names it.
-
-        `None` for an in-process job, which has no server-side record.
-        """
-        return self._field("job_type")
-
-    @property
-    def creation_ms(self) -> Optional[int]:
-        """When the job was created, in milliseconds since the epoch."""
-        return self._field("creation_ms")
-
-    @property
-    def spec(self) -> Optional[Any]:
-        """The job-type-specific specification it was submitted with."""
-        return self._field("spec")
-
-    @property
-    def result(self) -> Optional[Any]:
-        """The job-type-specific terminal result, as reported data rather than
-        the typed model :meth:`AsyncJob.wait` returns.
-
-        `None` until the job succeeds, so a job that never terminates reports
-        its progress through :meth:`AsyncJob.events` instead.
-        """
-        return self._field("result")
-
-    @property
-    def failure(self) -> Optional[JobFailureInfo]:
-        """Why the job failed, when it failed and the server reports a reason."""
-        return self._field("failure")
-
-    @property
-    def _spec_json(self) -> Optional[str]:
-        return self._field("_spec_json")
-
-    @property
-    def _result_json(self) -> Optional[str]:
-        return self._field("_result_json")
-
-    def _field(self, name: str) -> Optional[Any]:
-        description = self._inner._description if self._inner is not None else None
-        return getattr(description, name) if description is not None else None
-
-    async def events(
-        self,
-        *,
-        limit: Optional[int] = None,
-        filter: Optional[str] = None,
-    ) -> "pa.Table":
-        """This job's recorded lifecycle events.
-
-        Where the properties above report a terminal result only once the job
-        reaches one, events are written as the job runs and outlive the workers
-        that produced them. A distributed job records a `claim`/`claim_complete`
-        pair per unit of work, each carrying `rows_processed`, so a job that
-        never finishes still accounts for what it did.
-
-        Parameters
-        ----------
-        limit: int, optional
-            Maximum event rows to return. The server caps results at 1000 by
-            default and 10,000 at most, and truncates without saying so, so
-            pass this for a job that emits an event per fragment.
-        filter: str, optional
-            SQL-like expression over the `state`, `updated_by`, `emitted_from`,
-            `emitted_by`, and `claim_entity` columns, such as
-            ``state = 'claim_complete'``.
-        """
-        if self._inner is None:
-            raise NotImplementedError(
-                "job event history is only available for server-side jobs"
-            )
-        return await self._inner.events(limit=limit, filter=filter)
-
-    def __repr__(self) -> str:
-        return _job_repr("AsyncJob", self)
-
-
-_REPR_INDENT = " " * 4
-
-
-def _repr_payload(value: Any) -> str:
-    """Render a job payload as indented JSON, aligned under its field."""
-    try:
-        rendered = json.dumps(value, indent=4)
-    except TypeError:
-        return repr(value)
-    return rendered.replace("\n", "\n" + _REPR_INDENT)
-
-
-def _job_repr(kind: str, job: Any) -> str:
-    """Render every field the handle currently knows, omitting the rest.
-
-    One field per line, with the JSON payloads indented, because a refresh
-    job's spec and result are the point of printing it.
-    """
-    state = job.state
-    if state is None:
-        # Nothing has been fetched yet, so there is nothing to lay out.
-        known = f"id={job.id!r}, " if job.id is not None else ""
-        return f"{kind}({known}not refreshed)"
-
-    fields = []
-    if job.id is not None:
-        fields.append(f"id={job.id!r}")
-    fields.append(f"state={state!r}")
-    for name in ("job_type", "creation_ms"):
-        value = getattr(job, name)
-        if value is not None:
-            fields.append(f"{name}={value!r}")
-    for name in ("spec", "result"):
-        value = getattr(job, name)
-        if value is not None:
-            fields.append(f"{name}={_repr_payload(value)}")
-    if job.failure is not None:
-        fields.append(f"failure={job.failure!r}")
-    body = "".join(f"\n{_REPR_INDENT}{field}," for field in fields)
-    return f"{kind}({body}\n)"
-
 
 class Job(Generic[T]):
     """Synchronous counterpart of `AsyncJob` with the same result type."""
@@ -277,75 +122,6 @@ class Job(Generic[T]):
             return
         LOOP.run(self._inner.cancel())
 
-    def refresh(self) -> None:
-        """Ask the backend for this job's current state and record.
-
-        See :meth:`AsyncJob.refresh`.
-        """
-        if self._inner is None:
-            return
-        LOOP.run(self._inner.refresh())
-
-    @property
-    def state(self) -> Optional[str]:
-        """The last observed lifecycle state. See :attr:`AsyncJob.state`."""
-        return self._inner.state if self._inner is not None else "finished"
-
-    @property
-    def job_type(self) -> Optional[str]:
-        """The job's type. See :attr:`AsyncJob.job_type`."""
-        return self._field("job_type")
-
-    @property
-    def creation_ms(self) -> Optional[int]:
-        """When the job was created. See :attr:`AsyncJob.creation_ms`."""
-        return self._field("creation_ms")
-
-    @property
-    def spec(self) -> Optional[Any]:
-        """The job's specification. See :attr:`AsyncJob.spec`."""
-        return self._field("spec")
-
-    @property
-    def result(self) -> Optional[Any]:
-        """The job's terminal result. See :attr:`AsyncJob.result`."""
-        return self._field("result")
-
-    @property
-    def failure(self) -> Optional[JobFailureInfo]:
-        """Why the job failed. See :attr:`AsyncJob.failure`."""
-        return self._field("failure")
-
-    @property
-    def _spec_json(self) -> Optional[str]:
-        return self._field("_spec_json")
-
-    @property
-    def _result_json(self) -> Optional[str]:
-        return self._field("_result_json")
-
-    def _field(self, name: str) -> Optional[Any]:
-        return getattr(self._inner, name) if self._inner is not None else None
-
-    def events(
-        self,
-        *,
-        limit: Optional[int] = None,
-        filter: Optional[str] = None,
-    ) -> "pa.Table":
-        """This job's recorded lifecycle events.
-
-        See :meth:`AsyncJob.events`.
-        """
-        if self._inner is None:
-            raise NotImplementedError(
-                "job event history is only available for server-side jobs"
-            )
-        return LOOP.run(self._inner.events(limit=limit, filter=filter))
-
-    def __repr__(self) -> str:
-        return _job_repr("Job", self)
-
 
 def _typed_job(
     inner: "_lancedb.Job", result_decoder: Callable[[str], T]

python/python/lancedb/materialized_view.py

@@ -42,8 +42,6 @@ class MaterializedViewDefinition:
     """Cap on the number of rows the view holds."""
     inputs: List[str] = field(default_factory=list)
     """Source columns the projections and filter read."""
-    source_namespace: List[str] = field(default_factory=list)
-    """Namespace holding the source table; empty is the root namespace."""
 
 
 def _definition_from_schema(
@@ -55,8 +53,7 @@ def _definition_from_schema(
         raise ValueError(f"Table '{name}' is not a materialized view")
     value = json.loads(raw)
     kind = value.get("kind")
-    # "namespaced_select" keeps older readers from resolving the source at root.
-    if kind not in ("select", "namespaced_select"):
+    if kind != "select":
         raise NotImplementedError(
             f"materialized view '{name}' is defined by '{kind}', which this "
             "version of lancedb cannot refresh"
@@ -69,7 +66,6 @@ def _definition_from_schema(
         filter=value.get("filter"),
         limit=value.get("limit"),
         inputs=value.get("inputs", []),
-        source_namespace=value.get("source_namespace", []),
     )
 
 

python/python/lancedb/namespace.py

@@ -12,7 +12,6 @@ from __future__ import annotations
 
 import sys
 from typing import TYPE_CHECKING, Any, Dict, Iterable, List, Optional, Union
-from uuid import UUID
 
 if sys.version_info >= (3, 12):
     from typing import override
@@ -49,11 +48,8 @@ from lancedb._lancedb import (
     connect_namespace_client as _connect_namespace_client,
 )
 from lancedb.background_loop import LOOP
-from lancedb.arrow import AsyncRecordBatchReader
 from lancedb.db import AsyncConnection, DBConnection
 from lancedb.job import AsyncJob, Job
-from lancedb.sql import AsyncQuery as AsyncSqlQuery
-from lancedb.sql import QueryDescription
 from lance_namespace import (
     LanceNamespace,
     connect as namespace_connect,
@@ -1451,37 +1447,6 @@ class AsyncLanceNamespaceDBConnection:
             namespace_path=namespace_path, page_token=page_token, limit=limit
         )
 
-    async def execute_query(
-        self,
-        query: str,
-        *,
-        default_namespace_path: Optional[List[str]] = None,
-    ) -> AsyncRecordBatchReader:
-        """Execute SQL when supported by the underlying connection."""
-        return await self._inner.execute_query(
-            query,
-            default_namespace_path=default_namespace_path,
-        )
-
-    async def execute_query_async(
-        self,
-        query: str,
-        *,
-        default_namespace_path: Optional[List[str]] = None,
-    ) -> AsyncSqlQuery:
-        """Start executing SQL when supported by the underlying connection.
-
-        Namespace-backed local connections do not support SQL.
-        """
-        return await self._inner.execute_query_async(
-            query,
-            default_namespace_path=default_namespace_path,
-        )
-
-    async def describe_query(self, query_id: UUID) -> QueryDescription:
-        """Describe a submitted SQL query when supported."""
-        return await self._inner.describe_query(query_id)
-
     async def namespace_client(self) -> LanceNamespace:
         """Get the namespace client for this connection.
 

python/python/lancedb/query.py

@@ -78,10 +78,6 @@ if TYPE_CHECKING:
 T = TypeVar("T", bound="LanceModel")
 AnalyzePlanDistributedMetrics = Literal["aggregate", "per_worker", "full"]
 
-# Number of rows a hybrid query returns when no limit was set on it. This
-# mirrors the default the Rust query builder applies to its sub-queries.
-DEFAULT_HYBRID_LIMIT = 10
-
 
 @runtime_checkable
 class _LanceScanner(Protocol):
@@ -113,7 +109,6 @@ def _query_is_plain_scan(query: Query) -> bool:
     return (
         query.vector is None
         and query.full_text_query is None
-        and query.take_offsets is None
         and not query.postfilter
         and not query.order_by
     )
@@ -809,10 +804,6 @@ class Query(pydantic.BaseModel):
     # offset to start fetching results from
     offset: Optional[int] = None
 
-    # Dataset offsets whose duplicate occurrences must be restored after lookup.
-    # This is populated when a take query is converted to this serializable form.
-    take_offsets: Optional[List[int]] = None
-
     # if true, will only search the indexed data
     fast_search: Optional[bool] = None
 
@@ -834,7 +825,6 @@ class Query(pydantic.BaseModel):
         query = cls()
         query.limit = req.limit
         query.offset = req.offset
-        query.take_offsets = req.take_offsets
         query.filter = req.filter
         query.full_text_query = req.full_text_search
         query.columns = req.select
@@ -863,7 +853,7 @@ class Query(pydantic.BaseModel):
         return query
 
     # This tells pydantic to allow custom types (needed for the `vector` query since
-    # pa.Array wouldn't be allowed otherwise)
+    # pa.Array wouln't be allowed otherwise)
     model_config = pydantic.ConfigDict(arbitrary_types_allowed=True)
 
 
@@ -3897,54 +3887,14 @@ class AsyncHybridQuery(AsyncStandardQuery, AsyncVectorQueryBase):
 
         return self
 
-    def _create_child_queries(
-        self,
-    ) -> Tuple["AsyncFTSQuery", "AsyncVectorQuery", int, int]:
-        """Build the sub-queries that make up this hybrid query.
-
-        Execution, `explain_plan` and `analyze_plan` all go through here so that
-        the plans that are reported are the plans that actually run.
-
-        Returns the two sub-queries along with the effective limit and offset of
-        the hybrid query itself.
-        """
-        fts_query = AsyncFTSQuery(self._inner.to_fts_query(), self._table)
-        vec_query = AsyncVectorQuery(self._inner.to_vector_query(), self._table)
-
-        fts_req = fts_query._inner.to_query_request()
-        vec_req = vec_query._inner.to_query_request()
-
-        # Only one of the two sub-queries carries the limit when it was never
-        # set explicitly: nearest_to()/nearest_to_text() build the sibling query
-        # from scratch, and that is where the default gets filled in. Which one
-        # that is depends on the order the hybrid query was built in, so look at
-        # both rather than at a single side.
-        limit = fts_req.limit if fts_req.limit is not None else vec_req.limit
-        if limit is None:
-            limit = DEFAULT_HYBRID_LIMIT
-        offset = fts_req.offset or vec_req.offset or 0
-
-        fts_query.with_row_id()
-        vec_query.with_row_id()
-
-        # offset() pushes the offset down into both sub-queries, which would make
-        # each of them skip its own first `offset` rows. The window has to be
-        # taken out of the combined, reranked results instead, so fetch the
-        # skipped prefix here too and slice it off afterwards.
-        fts_query.limit(limit + offset)
-        vec_query.limit(limit + offset)
-        fts_query.offset(0)
-        vec_query.offset(0)
-
-        return fts_query, vec_query, limit, offset
-
     async def to_batches(
         self,
         *,
         max_batch_length: Optional[int] = None,
         timeout: Optional[timedelta] = None,
     ) -> AsyncRecordBatchReader:
-        fts_query, vec_query, limit, offset = self._create_child_queries()
+        fts_query = AsyncFTSQuery(self._inner.to_fts_query(), self._table)
+        vec_query = AsyncVectorQuery(self._inner.to_vector_query(), self._table)
 
         req = fts_query._inner.to_query_request()
         blob_auto_row_id = False
@@ -3964,6 +3914,9 @@ class AsyncHybridQuery(AsyncStandardQuery, AsyncVectorQueryBase):
         self._blob_auto_row_id = blob_auto_row_id
         self._blob_paths = blob_paths
 
+        fts_query.with_row_id()
+        vec_query.with_row_id()
+
         fts_results, vector_results = await asyncio.gather(
             fts_query.to_arrow(timeout=timeout),
             vec_query.to_arrow(timeout=timeout),
@@ -3975,9 +3928,8 @@ class AsyncHybridQuery(AsyncStandardQuery, AsyncVectorQueryBase):
             norm=self._norm,
             fts_query=fts_query.get_query(),
             reranker=self._reranker,
-            limit=limit,
+            limit=self._inner.get_limit(),
             with_row_ids=True,
-            offset=offset,
         )
         if (
             not self._user_requested_row_id()
@@ -4006,14 +3958,14 @@ class AsyncHybridQuery(AsyncStandardQuery, AsyncVectorQueryBase):
         ...     print(plan)
         >>> asyncio.run(doctest_example()) # doctest: +ELLIPSIS, +NORMALIZE_WHITESPACE
         RRFReranker(K=60)
-            ProjectionExec: expr=[vector@0 as vector, text@3 as text, _distance@2 as _distance, _rowid@1 as _rowid]
+            ProjectionExec: expr=[vector@0 as vector, text@3 as text, _distance@2 as _distance]
               LanceRead: uri=..., projection=[text], source=stream(_rowid)
                 GlobalLimitExec: skip=0, fetch=10
                   FilterExec: _distance@2 IS NOT NULL
                     SortExec: TopK(fetch=10), expr=[_distance@2 ASC NULLS LAST, _rowid@1 ASC NULLS LAST], preserve_partitioning=[false]
                       KNNVectorDistance: metric=l2
                         LanceRead: uri=..., projection=[vector], ...
-            ProjectionExec: expr=[vector@2 as vector, text@3 as text, _score@1 as _score, _rowid@0 as _rowid]
+            ProjectionExec: expr=[vector@2 as vector, text@3 as text, _score@1 as _score]
               LanceRead: uri=..., projection=[vector, text], source=stream(_rowid)
                 GlobalLimitExec: skip=0, fetch=10
                   MatchQuery: column=text, query=[hello]
@@ -4028,9 +3980,8 @@ class AsyncHybridQuery(AsyncStandardQuery, AsyncVectorQueryBase):
         plan : str
         """  # noqa: E501
 
-        fts_query, vec_query, _, _ = self._create_child_queries()
-        vector_plan = await vec_query.explain_plan(verbose)
-        fts_plan = await fts_query.explain_plan(verbose)
+        vector_plan = await self._inner.to_vector_query().explain_plan(verbose)
+        fts_plan = await self._inner.to_fts_query().explain_plan(verbose)
         # Indent sub-plans under the reranker
         indented_vector = "\n".join("  " + line for line in vector_plan.splitlines())
         indented_fts = "\n".join("  " + line for line in fts_plan.splitlines())
@@ -4057,12 +4008,14 @@ class AsyncHybridQuery(AsyncStandardQuery, AsyncVectorQueryBase):
         -------
         plan : str
         """
-        fts_query, vec_query, _, _ = self._create_child_queries()
-
         results = ["Vector Search Query:"]
-        results.append(await vec_query.analyze_plan(distributed_metrics))
+        results.append(
+            await self._inner.to_vector_query().analyze_plan(distributed_metrics)
+        )
         results.append("FTS Search Query:")
-        results.append(await fts_query.analyze_plan(distributed_metrics))
+        results.append(
+            await self._inner.to_fts_query().analyze_plan(distributed_metrics)
+        )
 
         return "\n".join(results)
 

python/python/lancedb/remote/db.py

@@ -9,7 +9,6 @@ from concurrent.futures import ThreadPoolExecutor
 import sys
 from typing import TYPE_CHECKING, Any, Dict, Iterable, List, Optional, Union
 from urllib.parse import urlparse
-from uuid import UUID
 import warnings
 
 if sys.version_info >= (3, 12):
@@ -26,12 +25,10 @@ from ..common import DATA
 from ..db import DBConnection, LOOP
 from ..functions import FunctionVersion, UdfDefinition
 from ..job import AsyncJob, Job
-from ..sql import Query as SqlQuery
-from ..sql import QueryDescription
 from ..materialized_view import MaterializedView, SelectArg
 
 if TYPE_CHECKING:
-    from .._lancedb import JobInfo
+    from .._lancedb import JobDescription, JobInfo
 from ..embeddings import EmbeddingFunctionConfig
 from lance_namespace import (
     LanceNamespace,
@@ -119,7 +116,6 @@ class RemoteDBConnection(DBConnection):
         read_timeout: Optional[float] = None,
         storage_options: Optional[Dict[str, str]] = None,
         read_consistency_interval: Optional[timedelta] = None,
-        sql_host_override: Optional[str] = None,
     ):
         """Connect to a remote LanceDB database."""
         if isinstance(client_config, dict):
@@ -165,7 +161,6 @@ class RemoteDBConnection(DBConnection):
         self.api_key = api_key
         self.region = region
         self.host_override = host_override
-        self.sql_host_override = sql_host_override
         self.storage_options = storage_options
         self.db_name = parsed.netloc
 
@@ -180,7 +175,6 @@ class RemoteDBConnection(DBConnection):
                 api_key=api_key,
                 region=region,
                 host_override=host_override,
-                sql_host_override=sql_host_override,
                 client_config=client_config,
                 storage_options=storage_options,
                 read_consistency_interval=read_consistency_interval,
@@ -199,7 +193,6 @@ class RemoteDBConnection(DBConnection):
                 "api_key": self.api_key,
                 "region": self.region,
                 "host_override": self.host_override,
-                "sql_host_override": self.sql_host_override,
                 "client_config": _client_config_to_dict(self.client_config),
                 "storage_options": self.storage_options,
             }
@@ -739,11 +732,14 @@ class RemoteDBConnection(DBConnection):
         )
 
     @override
-    def open_job(self, job_id: str) -> Job:
-        """Open a server-side job by id. See
-        [DBConnection.open_job][lancedb.db.DBConnection.open_job].
+    def job(self, job_id: str) -> Job:
+        """A [Job][lancedb.job.Job] handle for a server-side job by id.
+
+        The handle is constructed without a server round trip; an unknown id
+        surfaces when the handle is used. Dropping the handle has no effect
+        on the job itself.
         """
-        return Job(LOOP.run(self._conn.open_job(job_id)))
+        return Job(self._conn.job(job_id))
 
     @override
     def create_function_async(self, definition: UdfDefinition) -> Job[FunctionVersion]:
@@ -753,19 +749,19 @@ class RemoteDBConnection(DBConnection):
     def get_function(self, name: str, *, version: str) -> FunctionVersion:
         return LOOP.run(self._conn.get_function(name, version=version))
 
-    @override
-    def list_functions(self) -> List[FunctionVersion]:
-        return LOOP.run(self._conn.list_functions())
-
-    @override
-    def drop_function(self, name: str, *, version: str) -> bool:
-        return LOOP.run(self._conn.drop_function(name, version=version))
-
     @override
     def list_jobs(self) -> List["JobInfo"]:
         """List server-side jobs across the database's tables."""
         return LOOP.run(self._conn.list_jobs())
 
+    @override
+    def get_job(self, job_id: str) -> Optional["JobDescription"]:
+        """Describe a single server-side job by id.
+
+        Returns None when the server has no such job.
+        """
+        return LOOP.run(self._conn.get_job(job_id))
+
     @override
     def cancel_job(self, job_id: str) -> bool:
         """Request cancellation of a server-side job by id.
@@ -777,35 +773,12 @@ class RemoteDBConnection(DBConnection):
         return LOOP.run(self._conn.cancel_job(job_id))
 
     @override
-    def execute_query_async(
-        self,
-        query: str,
-        *,
-        default_namespace_path: Optional[List[str]] = None,
-    ) -> SqlQuery:
-        """Start executing SQL through this remote connection.
+    def job_history(self, job_id: Optional[str] = None) -> List[pa.RecordBatch]:
+        """The lifecycle event history of a server-side job, as Arrow batches.
 
-        Unqualified tables use this connection's database and the
-        ``["public"]`` namespace by default. Fully qualified table names may
-        reference other databases available to the same deployment.
+        Lists history across all jobs when `job_id` is None.
         """
-        return SqlQuery(
-            LOOP.run(
-                self._conn.execute_query_async(
-                    query,
-                    default_namespace_path=default_namespace_path,
-                )
-            )
-        )
-
-    @override
-    def describe_query(self, query_id: UUID) -> QueryDescription:
-        """Describe a submitted SQL query by its connection-scoped id."""
-        return LOOP.run(
-            self._conn.describe_query(
-                query_id,
-            )
-        )
+        return LOOP.run(self._conn.job_history(job_id))
 
     @override
     def namespace_client(self) -> LanceNamespace:

python/python/lancedb/remote/header.py

@@ -177,7 +177,4 @@ class OAuthProvider(HeaderProvider):
         if not self._current_token:
             raise RuntimeError("Failed to obtain OAuth token")
 
-        return {
-            "Authorization": f"Bearer {self._current_token}",
-            "x-lancedb-credential-type": "oidc",
-        }
+        return {"Authorization": f"Bearer {self._current_token}"}

python/python/lancedb/remote/table.py

@@ -548,7 +548,6 @@ class RemoteTable(Table):
         LOOP.run(
             self._table.create_index(
                 column,
-                replace=replace,
                 config=config,
                 wait_timeout=wait_timeout,
                 name=name,
@@ -720,7 +719,7 @@ class RemoteTable(Table):
         Parameters
         ----------
         query: list/np.ndarray/str/PIL.Image.Image, default None
-            The targeted vector to search for.
+            The targetted vector to search for.
 
             - *default None*.
             Acceptable types are: list, np.ndarray, PIL.Image.Image

python/python/lancedb/rerankers/base.py

@@ -175,7 +175,7 @@ class Reranker(ABC):
             if the results haven't been executed yet or the results in arrow format.
         query : str or None,
             The input query. Some rerankers might not need the query to rerank.
-            In that case, it can be set to None explicitly. This is intended to
+            In that case, it can be set to None explicitly. This is inteded to
             be handled by the reranker implementations.
         deduplicate : bool, optional
             Whether to deduplicate the results based on the `_rowid` column,

python/python/lancedb/sql.py

@@ -1,88 +0,0 @@
-# SPDX-License-Identifier: Apache-2.0
-# SPDX-FileCopyrightText: Copyright The LanceDB Authors
-
-"""Handles to SQL queries running on a remote database."""
-
-from uuid import UUID
-
-import pyarrow as pa
-
-from lancedb.background_loop import LOOP
-
-from . import _lancedb
-from .arrow import AsyncRecordBatchReader
-
-QueryDescription = _lancedb.QueryDescription
-
-
-class AsyncQuery:
-    """A handle to a submitted SQL query on an asynchronous connection."""
-
-    def __init__(self, inner: "_lancedb.SqlQuery"):
-        self._inner = inner
-
-    @property
-    def id(self) -> UUID:
-        """The stable identifier scoped to the connection that submitted it."""
-        return self._inner.id
-
-    async def describe(self) -> QueryDescription:
-        """Get a point-in-time description of the query."""
-        return await self._inner.describe()
-
-    async def reader(self) -> AsyncRecordBatchReader:
-        """Wait for the initial result stream and return its Arrow reader.
-
-        Results are single-consumer. Calling this method more than once on the
-        same query raises an error. Later batches are streamed as they become
-        available without waiting for the full query to finish.
-        """
-        return AsyncRecordBatchReader(await self._inner.reader())
-
-    async def cancel(self) -> None:
-        """Request cancellation of the query."""
-        await self._inner.cancel()
-
-
-class Query:
-    """Synchronous counterpart of :class:`AsyncQuery`."""
-
-    def __init__(self, inner: AsyncQuery):
-        self._inner = inner
-
-    @property
-    def id(self) -> UUID:
-        """The stable identifier scoped to the connection that submitted it."""
-        return self._inner.id
-
-    def describe(self) -> QueryDescription:
-        """Get a point-in-time description of the query."""
-        return LOOP.run(self._inner.describe())
-
-    def reader(self) -> pa.RecordBatchReader:
-        """Wait for the initial result stream and return a blocking reader.
-
-        Results are single-consumer. Calling this method more than once on the
-        same query raises an error. Later batches block only until they become
-        available, without waiting for the full query to finish.
-        """
-        reader = LOOP.run(self._inner.reader())
-
-        def next_batch():
-            try:
-                return LOOP.run(reader.__anext__())
-            except StopAsyncIteration:
-                return None
-
-        def batches():
-            while (batch := next_batch()) is not None:
-                yield batch
-
-        return pa.RecordBatchReader.from_batches(reader.schema, batches())
-
-    def cancel(self) -> None:
-        """Request cancellation of the query."""
-        LOOP.run(self._inner.cancel())
-
-
-__all__ = ["AsyncQuery", "Query", "QueryDescription"]

python/python/lancedb/table.py

@@ -1547,9 +1547,7 @@ class Table(ABC):
         on: Union[str, Iterable[str]]
             A column (or columns) to join on.  This is how records from the
             source table and target table are matched.  Typically this is some
-            kind of key or id column.  Passing several columns matches on the
-            composite key: a source row updates a target row only when it
-            agrees on every one of them.
+            kind of key or id column.
 
         Examples
         --------
@@ -1619,7 +1617,7 @@ class Table(ABC):
         Parameters
         ----------
         query: list/np.ndarray/str/PIL.Image.Image, default None
-            The targeted vector to search for.
+            The targetted vector to search for.
 
             - *default None*.
             Acceptable types are: list, np.ndarray, PIL.Image.Image
@@ -1680,9 +1678,9 @@ class Table(ABC):
         Offsets are mostly useful for sampling as the set of all valid offsets is easily
         known in advance to be [0, len(table)).
 
-        No guarantees are made regarding the order in which results are returned.
-        Repeated offsets produce repeated rows, which makes this method suitable for
-        sampling with replacement.
+        No guarantees are made regarding the order in which results are returned.  If
+        you desire an output order that matches the order of the given offsets, you will
+        need to add the row offset column to the output and align it yourself.
 
         Parameters
         ----------
@@ -1793,9 +1791,6 @@ class Table(ABC):
         The result has the same length and order as ``row_ids``. Null blobs
         produce null slots; valid empty blobs produce ``b""``.
 
-        ``_rowid`` values stay valid after compaction when the table has stable
-        row ids.
-
         Convenience for small payloads. For large values use
         :meth:`fetch_blob_files`.
         """
@@ -1813,9 +1808,6 @@ class Table(ABC):
         The result has the same length and order as ``requests``; null blobs
         produce null slots and empty ranges on non-null blobs produce ``b""``.
 
-        ``_rowid`` values stay valid after compaction when the table has stable
-        row ids.
-
         Row IDs can be obtained from a query with ``with_row_id(True)``. This
         API is currently supported only by local tables.
         """
@@ -1831,9 +1823,6 @@ class Table(ABC):
         ``_rowid`` or a ``_lance_row_id`` field on the blob descriptor. Null
         rows are ``None``. Remote tables require LanceDB Cloud server 0.5.0 or
         newer.
-
-        ``_rowid`` values stay valid after compaction when the table has stable
-        row ids.
         """
 
     @abstractmethod
@@ -3841,7 +3830,7 @@ class LanceTable(Table):
         Parameters
         ----------
         query: list/np.ndarray/str/PIL.Image.Image, default None
-            The targeted vector to search for.
+            The targetted vector to search for.
 
             - *default None*.
             Acceptable types are: list, np.ndarray, PIL.Image.Image
@@ -4101,7 +4090,6 @@ class LanceTable(Table):
             )
             and not self._route_pushdown_to_rust
             and self.current_branch() is None
-            and query.take_offsets is None
         ):
             from lancedb.namespace import _execute_server_side_query
 
@@ -5638,7 +5626,7 @@ class AsyncTable:
         if fill_value is None:
             fill_value = 0.0
 
-        # _sanitize_data is an old code path, but we will use it until the
+        # _santitize_data is an old code path, but we will use it until the
         # new code path is ready.
         if mode == "overwrite":
             # For overwrite, apply the same preprocessing as create_table
@@ -5712,9 +5700,7 @@ class AsyncTable:
         on: Union[str, Iterable[str]]
             A column (or columns) to join on.  This is how records from the
             source table and target table are matched.  Typically this is some
-            kind of key or id column.  Passing several columns matches on the
-            composite key: a source row updates a target row only when it
-            agrees on every one of them.
+            kind of key or id column.
 
         Examples
         --------
@@ -5814,7 +5800,7 @@ class AsyncTable:
         Parameters
         ----------
         query: list/np.ndarray/str/PIL.Image.Image, default None
-            The targeted vector to search for.
+            The targetted vector to search for.
 
             - *default None*.
             Acceptable types are: list, np.ndarray, PIL.Image.Image
@@ -5997,23 +5983,7 @@ class AsyncTable:
 
     def _sync_query_to_async(
         self, query: Query
-    ) -> (
-        AsyncHybridQuery
-        | AsyncFTSQuery
-        | AsyncVectorQuery
-        | AsyncQuery
-        | AsyncTakeQuery
-    ):
-        if query.take_offsets is not None:
-            take_query = self.take_offsets(query.take_offsets)
-            if query.columns:
-                take_query = take_query.select(query.columns)
-            if query.use_lsm is not None:
-                take_query = take_query.use_lsm(query.use_lsm)
-            if query.with_row_id:
-                take_query = take_query.with_row_id()
-            return take_query
-
+    ) -> AsyncHybridQuery | AsyncFTSQuery | AsyncVectorQuery | AsyncQuery:
         async_query = self.query()
         if query.limit is not None:
             async_query = async_query.limit(query.limit)
@@ -6078,7 +6048,6 @@ class AsyncTable:
                 self._namespace_client, self._pushdown_operations
             )
             and not self._route_pushdown_to_rust
-            and query.take_offsets is None
         ):
             from lancedb.namespace import _execute_server_side_query
 
@@ -6576,9 +6545,6 @@ class AsyncTable:
         Offsets are mostly useful for sampling as the set of all valid offsets is easily
         known in advance to be [0, len(table)).
 
-        No guarantees are made regarding the order in which results are returned.
-        Repeated offsets produce repeated rows.
-
         Parameters
         ----------
         offsets: list[int]

python/python/tests/test_blob.py

@@ -66,25 +66,6 @@ def _row_ids_by_id(table):
     return dict(zip(hits["id"].to_pylist(), hits["_rowid"].to_pylist()))
 
 
-def _assert_missing_blob_row_ids(exc_info):
-    message = str(exc_info.value)
-    assert "row ids" in message
-    assert "rowaddr" not in message
-    assert "fragment" not in message
-
-
-def _assert_fetch_apis_reject_missing_row_ids(table, row_ids):
-    with pytest.raises(ValueError) as exc_info:
-        table.fetch_blobs("image", row_ids)
-    _assert_missing_blob_row_ids(exc_info)
-    with pytest.raises(ValueError) as exc_info:
-        table.fetch_blob_files("image", row_ids)
-    _assert_missing_blob_row_ids(exc_info)
-    with pytest.raises(ValueError) as exc_info:
-        table.fetch_blob_ranges("image", [(row_id, 0, 1) for row_id in row_ids])
-    _assert_missing_blob_row_ids(exc_info)
-
-
 def test_blob_factory_declares_v2_field():
     field = lancedb.blob("image")
     assert isinstance(field.type, pa.ExtensionType)
@@ -297,10 +278,7 @@ def test_blob_v2_projection_sources_use_typed_column_name():
 
 
 def _legacy_v1_table(name):
-    # Legacy v1 blob columns are only writable at file version <= 2.1.
-    db = lancedb.connect(
-        "memory:///", storage_options={"new_table_data_storage_version": "2.1"}
-    )
+    db = lancedb.connect("memory:///")
     schema = pa.schema(
         [
             pa.field("id", pa.int64()),
@@ -713,25 +691,6 @@ def test_fetch_blobs_accepts_query_result():
     assert {blobs[i].as_py() for i in range(len(blobs))} == {b"gamma"}
 
 
-def test_fetch_blobs_after_compact_with_stable_row_ids(tmp_path):
-    db = lancedb.connect(
-        tmp_path, storage_options={"new_table_enable_stable_row_ids": "true"}
-    )
-    schema = pa.schema([pa.field("id", pa.int64()), lancedb.blob("image")])
-    table = db.create_table("t", schema=schema)
-    table.add([{"id": 1, "image": b"frag-one"}])
-    table.add([{"id": 2, "image": b"frag-two"}])
-    by_id = _row_ids_by_id(table)
-    ids = [by_id[1], by_id[2]]
-
-    table.optimize()
-
-    blobs = table.fetch_blobs("image", ids)
-    assert blobs.to_pylist() == [b"frag-one", b"frag-two"]
-    ranges = table.fetch_blob_ranges("image", [(ids[0], 5, 3), (ids[1], 5, 3)])
-    assert ranges.to_pylist() == [b"one", b"two"]
-
-
 def test_fetch_blobs_preserves_null_and_empty_values():
     table = _blob_table(
         "nulls",
@@ -780,25 +739,8 @@ def test_fetch_blob_ranges_validates_requests():
     with pytest.raises(ValueError, match="offset \\+ length overflowed"):
         table.fetch_blob_ranges("image", [(row_id, 2**64 - 1, 1)])
 
-    with pytest.raises(ValueError) as exc_info:
+    with pytest.raises(ValueError, match="row IDs"):
         table.fetch_blob_ranges("image", [(2**64 - 1, 0, 1)])
-    _assert_missing_blob_row_ids(exc_info)
-
-
-def test_fetch_blob_apis_reject_missing_fragment_row_addr():
-    table = _blob_table("missing_frag", [{"id": 1, "image": b"x"}])
-    live = _row_ids_by_id(table)[1]
-    _assert_fetch_apis_reject_missing_row_ids(table, [1 << 32, live])
-
-
-def test_fetch_blob_apis_reject_deleted_row_ids():
-    table = _blob_table(
-        "deleted_rows",
-        [{"id": 1, "image": b"one"}, {"id": 2, "image": b"two"}],
-    )
-    by_id = _row_ids_by_id(table)
-    table.delete("id = 2")
-    _assert_fetch_apis_reject_missing_row_ids(table, [by_id[2], by_id[1]])
 
 
 def test_fetch_blob_ranges_empty_requests_returns_empty_array():

python/python/tests/test_embeddings.py

@@ -327,8 +327,8 @@ def test_embedding_function_with_pandas(tmp_path):
         ) -> List[np.array]:
             return [np.random.randn(self.ndims()).tolist() for _ in range(len(texts))]
 
-    registry = get_registry()
-    func = registry.get("mock-embedding").create()
+    registery = get_registry()
+    func = registery.get("mock-embedding").create()
 
     class TestSchema(LanceModel):
         text: str = func.SourceField()
@@ -394,9 +394,9 @@ def test_multiple_embeddings_for_pandas(tmp_path):
         ) -> List[np.array]:
             return [np.random.randn(self.ndims()).tolist() for _ in range(len(texts))]
 
-    registry = get_registry()
-    func1 = registry.get("mock-embedding").create()
-    func2 = registry.get("mock-embedding2").create()
+    registery = get_registry()
+    func1 = registery.get("mock-embedding").create()
+    func2 = registery.get("mock-embedding2").create()
 
     class TestSchema(LanceModel):
         text: str = func1.SourceField()

python/python/tests/test_first_class_function_slice2.py

@@ -12,8 +12,6 @@ from datetime import date
 import http.server
 import json
 from pathlib import Path
-import subprocess
-import sys
 import threading
 from typing import Optional
 
@@ -69,80 +67,6 @@ def test_scalar_udf_matches_shared_registration_golden_and_remains_callable():
     }
 
 
-def _main_udf_source(
-    *, threshold: int = 20, input_annotation: str = "int", comparison: str = ">="
-) -> str:
-    return (
-        "from __future__ import annotations\n"
-        "from lancedb.functions import udf\n"
-        f"THRESHOLD = {threshold}\n"
-        "\n"
-        "@udf\n"
-        f"def label(value: {input_annotation}) -> str:\n"
-        f"    return 'big' if value {comparison} THRESHOLD else 'small'\n"
-        "\n"
-        "assert label.__module__ == '__main__'\n"
-        "print(label.registration_request.to_canonical_json())\n"
-    )
-
-
-def _run_main_udf(path: Path, source: str) -> dict:
-    path.parent.mkdir(parents=True, exist_ok=True)
-    path.write_text(source)
-    result = subprocess.run(
-        [sys.executable, str(path)],
-        check=True,
-        capture_output=True,
-        text=True,
-    )
-    return json.loads(result.stdout)
-
-
-def test_main_udf_registration_identity_is_stable_across_processes_and_paths(
-    tmp_path,
-):
-    source = _main_udf_source()
-    original_path = tmp_path / "original" / "job.py"
-    moved_path = tmp_path / "moved" / "renamed_job.py"
-
-    original_runs = [_run_main_udf(original_path, source) for _ in range(2)]
-    moved_run = _run_main_udf(moved_path, source)
-
-    assert len({run["artifact"]["digest"] for run in [*original_runs, moved_run]}) == 1
-    assert all(
-        run["signature"] == original_runs[0]["signature"]
-        for run in [original_runs[1], moved_run]
-    )
-    assert original_runs[0] == original_runs[1] == moved_run
-
-    body_change = _run_main_udf(
-        tmp_path / "changes" / "body.py", _main_udf_source(comparison=">")
-    )
-    global_change = _run_main_udf(
-        tmp_path / "changes" / "global.py", _main_udf_source(threshold=21)
-    )
-    annotation_change = _run_main_udf(
-        tmp_path / "changes" / "annotation.py",
-        _main_udf_source(input_annotation="float"),
-    )
-
-    baseline = original_runs[0]
-    assert baseline["signature"] == body_change["signature"]
-    assert baseline["signature"] == global_change["signature"]
-    assert baseline["signature"] != annotation_change["signature"]
-    assert (
-        len(
-            {
-                baseline["artifact"]["digest"],
-                body_change["artifact"]["digest"],
-                global_change["artifact"]["digest"],
-                annotation_change["artifact"]["digest"],
-            }
-        )
-        == 4
-    )
-
-
 def _run_packaged(definition, *args):
     """Execute the shipped artifact in a fresh namespace, as a worker would."""
     source = base64.b64decode(definition.registration_request.artifact.content.data)
@@ -668,167 +592,6 @@ def test_blob_fields_use_the_scalar_function_semantic_type():
     assert signature.output.arrow_type == "blob_v2"
 
 
-def test_whole_named_struct_function_can_include_a_blob_result_field():
-    @udf(
-        input_schema=pa.schema([lancedb.blob("image", nullable=False)]),
-        output_schema=pa.field(
-            "payload",
-            pa.struct(
-                [
-                    pa.field("mime_type", pa.string(), nullable=False),
-                    lancedb.blob("image", nullable=False),
-                ]
-            ),
-            nullable=False,
-        ),
-    )
-    def inspect_blob(image):
-        return {"mime_type": "image/png", "image": image}
-
-    output = inspect_blob.registration_request.signature.output
-    assert output.kind == "named_struct"
-    assert [(field.name, field.arrow_type) for field in output.fields] == [
-        ("mime_type", "utf8"),
-        ("image", "blob_v2"),
-    ]
-
-
-def test_struct_blob_signature_fields_preserve_exact_metadata_and_nullability():
-    nested_input = pa.field(
-        "payload",
-        pa.struct(
-            [
-                pa.field("mime_type", pa.string(), nullable=False),
-                pa.field(
-                    "nested",
-                    pa.struct([lancedb.blob("image", nullable=True)]),
-                    nullable=True,
-                ),
-            ]
-        ),
-        nullable=True,
-    )
-    nested_output = pa.field(
-        "result",
-        pa.struct(
-            [
-                pa.field("mime_type", pa.string(), nullable=False),
-                pa.field(
-                    "nested",
-                    pa.struct([lancedb.blob("image", nullable=True)]),
-                    nullable=False,
-                ),
-            ]
-        ),
-        nullable=False,
-    )
-
-    @udf(input_schema=pa.schema([nested_input]), output_schema=nested_output)
-    def copy_payload(payload):
-        return payload
-
-    signature = copy_payload.registration_request.signature
-    input_type = json.loads(signature.inputs[0].arrow_type)
-    assert input_type["fields"][1]["nullable"] is True
-    input_blob = input_type["fields"][1]["type"]["fields"][0]
-    assert input_blob["nullable"] is True
-    assert input_blob["metadata"] == {"ARROW:extension:name": "lance.blob.v2"}
-
-    assert signature.output.kind == "named_struct"
-    nested_result = next(
-        field for field in signature.output.fields if field.name == "nested"
-    )
-    output_type = json.loads(nested_result.arrow_type)
-    output_blob = output_type["fields"][0]
-    assert output_blob["nullable"] is True
-    assert output_blob["metadata"] == {"ARROW:extension:name": "lance.blob.v2"}
-
-
-def test_struct_blob_signature_supports_multiple_struct_levels():
-    recursive = pa.field(
-        "value",
-        pa.struct(
-            [
-                pa.field(
-                    "level_1",
-                    pa.struct(
-                        [
-                            pa.field(
-                                "level_2",
-                                pa.struct([lancedb.blob("image", nullable=False)]),
-                                nullable=False,
-                            )
-                        ]
-                    ),
-                    nullable=False,
-                )
-            ]
-        ),
-        nullable=False,
-    )
-
-    @udf(
-        input_schema=pa.schema([recursive]),
-        output_schema=pa.field("size", pa.int64(), nullable=False),
-    )
-    def blob_size(value):
-        return len(value["level_1"]["level_2"]["image"])
-
-    encoded = json.loads(blob_size.registration_request.signature.inputs[0].arrow_type)
-    blob = encoded["fields"][0]["type"]["fields"][0]["type"]["fields"][0]
-    assert blob["metadata"]["ARROW:extension:name"] == "lance.blob.v2"
-
-
-@pytest.mark.parametrize(
-    "data_type",
-    [
-        pa.list_(lancedb.blob("item", nullable=False)),
-        pa.large_list(lancedb.blob("item", nullable=False)),
-        pa.list_(lancedb.blob("item", nullable=False), 2),
-        pa.map_(pa.string(), lancedb.blob("value", nullable=False).type),
-    ],
-)
-def test_blob_signature_rejects_collection_ancestors(data_type):
-    with pytest.raises(
-        TypeError,
-        match="Blob v2 fields nested under collection types are not supported",
-    ):
-
-        @udf(
-            input_schema=pa.schema([pa.field("value", data_type, nullable=False)]),
-            output_schema=pa.field("size", pa.int64(), nullable=False),
-        )
-        def blob_size(value):
-            return len(value)
-
-
-def test_blob_signature_rejects_collection_below_a_struct():
-    nested = pa.field(
-        "value",
-        pa.struct(
-            [
-                pa.field(
-                    "images",
-                    pa.list_(lancedb.blob("item", nullable=False)),
-                    nullable=False,
-                )
-            ]
-        ),
-        nullable=False,
-    )
-    with pytest.raises(
-        TypeError,
-        match="Blob v2 fields nested under collection types are not supported",
-    ):
-
-        @udf(
-            input_schema=pa.schema([nested]),
-            output_schema=pa.field("size", pa.int64(), nullable=False),
-        )
-        def blob_size(value):
-            return len(value["images"])
-
-
 def test_named_struct_function_can_include_a_blob_result_field():
     @udf(
         input_schema=pa.schema([lancedb.blob("image", nullable=False)]),
@@ -850,43 +613,6 @@ def test_named_struct_function_can_include_a_blob_result_field():
     ]
 
 
-def test_named_struct_function_preserves_nullable_result_fields():
-    @udf(
-        input_schema=pa.schema([pa.field("value", pa.int64(), nullable=False)]),
-        output_schema=pa.schema(
-            [
-                pa.field("result", pa.int64(), nullable=True),
-                pa.field("failure_code", pa.int32(), nullable=False),
-            ]
-        ),
-    )
-    def nullable_result(value):
-        return {"result": value, "failure_code": 0}
-
-    output = nullable_result.registration_request.signature.output
-    assert [(field.name, field.nullable) for field in output.fields] == [
-        ("result", True),
-        ("failure_code", False),
-    ]
-
-    @udf(
-        input_schema=pa.schema([pa.field("value", pa.int64(), nullable=False)]),
-        output_schema=pa.schema(
-            [
-                pa.field("result", pa.int64(), nullable=True),
-                pa.field("failure_code", pa.int32(), nullable=True),
-            ]
-        ),
-    )
-    def all_nullable(value):
-        return {"result": value, "failure_code": None}
-
-    assert all(
-        field.nullable
-        for field in all_nullable.registration_request.signature.output.fields
-    )
-
-
 def test_metadata_marked_blob_field_uses_the_semantic_type():
     extension = lancedb.blob("image", nullable=False).type
     storage = (
@@ -927,6 +653,22 @@ def test_blob_marker_rejects_invalid_storage_layout():
             return len(image)
 
 
+def test_nested_blob_signature_field_has_a_clear_error():
+    nested = pa.field(
+        "value",
+        pa.struct([lancedb.blob("image", nullable=False)]),
+        nullable=False,
+    )
+    with pytest.raises(TypeError, match="nested Blob v2 fields are not supported"):
+
+        @udf(
+            input_schema=pa.schema([nested]),
+            output_schema=pa.field("size", pa.int64(), nullable=False),
+        )
+        def blob_size(value):
+            return len(value["image"])
+
+
 def test_nested_non_blob_extension_is_not_silently_unwrapped():
     class TestExtension(pa.ExtensionType):
         def __init__(self):
@@ -1199,10 +941,6 @@ def test_local_function_catalog_operations_are_not_supported(tmp_path):
         db.create_function_async(normalize_score)
     with pytest.raises(NotImplementedError, match=message):
         db.get_function("normalize_score", version="fv_exact")
-    with pytest.raises(NotImplementedError, match=message):
-        db.list_functions()
-    with pytest.raises(NotImplementedError, match=message):
-        db.drop_function("normalize_score", version="fv_exact")
 
 
 @contextlib.contextmanager
@@ -1248,28 +986,6 @@ def _mock_remote_function_catalog():
                     "version": "fv_exact",
                 }
                 response = state["version"]
-            elif self.path == "/v1/functions/list":
-                assert body["include_definition"] is True
-                if "page_token" not in body:
-                    response = {
-                        "functions": [
-                            {
-                                "name": "normalize_score",
-                                "version": "fv_exact",
-                                "definition": state["version"],
-                            }
-                        ],
-                        "page_token": "next",
-                    }
-                else:
-                    assert body["page_token"] == "next"
-                    response = {"functions": []}
-            elif self.path == "/v1/functions/drop":
-                assert body == {
-                    "name": "normalize_score",
-                    "version": "fv_exact",
-                }
-                response = {"dropped": True}
             else:
                 status = 404
                 response = {"error": "not found"}
@@ -1328,83 +1044,3 @@ def test_blocking_remote_registration_returns_function_version():
         "/v1/functions/create",
         "/v1/jobs/describe",
     ]
-
-
-def test_remote_list_functions_paginates_and_returns_typed_versions():
-    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)
-        state["requests"].clear()
-        functions = db.list_functions()
-
-    assert functions == [created]
-    assert state["requests"] == [
-        ("/v1/functions/list", {"include_definition": True}),
-        (
-            "/v1/functions/list",
-            {"include_definition": True, "page_token": "next"},
-        ),
-    ]
-
-
-@pytest.mark.asyncio
-async def test_async_remote_list_functions_returns_typed_versions():
-    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)
-        created = await registration.wait()
-        state["requests"].clear()
-        functions = await db.list_functions()
-
-    assert functions == [created]
-    assert [path for path, _ in state["requests"]] == [
-        "/v1/functions/list",
-        "/v1/functions/list",
-    ]
-
-
-def test_remote_drop_function_sends_exact_version():
-    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}},
-        )
-        assert db.drop_function("normalize_score", version="fv_exact") is True
-
-    assert state["requests"] == [
-        (
-            "/v1/functions/drop",
-            {"name": "normalize_score", "version": "fv_exact"},
-        )
-    ]
-
-
-@pytest.mark.asyncio
-async def test_async_remote_drop_function_sends_exact_version():
-    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}},
-        )
-        assert await db.drop_function("normalize_score", version="fv_exact") is True
-
-    assert state["requests"] == [
-        (
-            "/v1/functions/drop",
-            {"name": "normalize_score", "version": "fv_exact"},
-        )
-    ]

python/python/tests/test_fts.py

@@ -1011,13 +1011,8 @@ def test_fts_ngram(mem_db: DBConnection):
     assert set(r["text"] for r in results) == {"lance database", "lance is cool"}
 
     results = (
-        table.search(
-            "nce",  # spellchecker:disable-line
-            query_type="fts",
-        )
-        .limit(10)
-        .to_list()
-    )
+        table.search("nce", query_type="fts").limit(10).to_list()
+    )  # spellchecker:disable-line
     assert len(results) == 2
     assert set(r["text"] for r in results) == {"lance database", "lance is cool"}
 
@@ -1039,13 +1034,8 @@ def test_fts_ngram(mem_db: DBConnection):
     assert set(r["text"] for r in results) == {"lance database", "lance is cool"}
 
     results = (
-        table.search(
-            "nce",  # spellchecker:disable-line
-            query_type="fts",
-        )
-        .limit(10)
-        .to_list()
-    )
+        table.search("nce", query_type="fts").limit(10).to_list()
+    )  # spellchecker:disable-line
     assert len(results) == 0
 
     results = table.search("la", query_type="fts").limit(10).to_list()

python/python/tests/test_header_provider.py

@@ -54,10 +54,7 @@ class TestOAuthProvider:
         provider = OAuthProvider(fetcher)
         headers = provider.get_headers()
 
-        assert headers == {
-            "Authorization": "Bearer token123",
-            "x-lancedb-credential-type": "oidc",
-        }
+        assert headers == {"Authorization": "Bearer token123"}
         assert provider._current_token == "token123"
         assert provider._token_expires_at is not None
 
@@ -76,20 +73,14 @@ class TestOAuthProvider:
 
         # First call
         headers1 = provider.get_headers()
-        assert headers1 == {
-            "Authorization": "Bearer token1",
-            "x-lancedb-credential-type": "oidc",
-        }
+        assert headers1 == {"Authorization": "Bearer token1"}
 
         # Wait for token to expire
         time.sleep(1.1)
 
         # Second call should refresh
         headers2 = provider.get_headers()
-        assert headers2 == {
-            "Authorization": "Bearer token2",
-            "x-lancedb-credential-type": "oidc",
-        }
+        assert headers2 == {"Authorization": "Bearer token2"}
         assert call_count == 2
 
     def test_no_expiry_info(self):
@@ -101,18 +92,12 @@ class TestOAuthProvider:
         provider = OAuthProvider(fetcher)
         headers = provider.get_headers()
 
-        assert headers == {
-            "Authorization": "Bearer permanent_token",
-            "x-lancedb-credential-type": "oidc",
-        }
+        assert headers == {"Authorization": "Bearer permanent_token"}
         assert provider._token_expires_at is None
 
         # Should not refresh on second call
         headers2 = provider.get_headers()
-        assert headers2 == {
-            "Authorization": "Bearer permanent_token",
-            "x-lancedb-credential-type": "oidc",
-        }
+        assert headers2 == {"Authorization": "Bearer permanent_token"}
 
     def test_missing_access_token(self):
         """Test error handling when access_token is missing."""
@@ -136,10 +121,7 @@ class TestOAuthProvider:
         provider = OAuthProvider(fetcher)
         headers = provider.get_headers()
 
-        assert headers == {
-            "Authorization": "Bearer sync_token",
-            "x-lancedb-credential-type": "oidc",
-        }
+        assert headers == {"Authorization": "Bearer sync_token"}
 
 
 class TestClientConfigIntegration:

python/python/tests/test_hybrid_query.py

@@ -203,93 +203,6 @@ async def test_async_hybrid_query_default_limit(table: AsyncTable):
     assert texts.count("a") == 1
 
 
-@pytest.mark.asyncio
-async def test_async_hybrid_query_offset(table: AsyncTable):
-    # The offset window of a hybrid query must be a suffix of the same query
-    # run without an offset. Skipping the first rows of each sub-query instead
-    # of the first rows of the fused result silently changes which rows land in
-    # the window.
-    full = await (
-        table.query()
-        .nearest_to([0.0, 0.4])
-        .nearest_to_text("dog")
-        .limit(4)
-        .with_row_id()
-        .to_arrow()
-    )
-    assert len(full) == 4
-
-    second_page = await (
-        table.query()
-        .nearest_to([0.0, 0.4])
-        .nearest_to_text("dog")
-        .offset(2)
-        .limit(2)
-        .with_row_id()
-        .to_arrow()
-    )
-    assert second_page["_rowid"].to_pylist() == full["_rowid"].to_pylist()[2:]
-
-    first_page = await (
-        table.query()
-        .nearest_to([0.0, 0.4])
-        .nearest_to_text("dog")
-        .limit(2)
-        .with_row_id()
-        .to_arrow()
-    )
-    # Paging through the result must visit every row exactly once: no row
-    # repeated from the previous page and none dropped between the two.
-    paged = first_page["_rowid"].to_pylist() + second_page["_rowid"].to_pylist()
-    assert sorted(paged) == sorted(full["_rowid"].to_pylist())
-
-
-@pytest.mark.asyncio
-async def test_async_hybrid_query_fts_first_default_limit(table: AsyncTable):
-    # nearest_to() and nearest_to_text() build their new sibling sub-query from
-    # scratch, and that is the sub-query the default limit ends up on. So the
-    # side that carries the limit depends on the order the hybrid query was
-    # built in, and looking at only one side loses the limit for half the ways
-    # a hybrid query can be written. Without a limit the combined results are
-    # not truncated at all and the whole union of both candidate lists is
-    # returned.
-    await table.add([{"text": "dog", "vector": [50.0 + i, 50.0]} for i in range(10)])
-
-    result = await (
-        table.query().nearest_to_text("dog").nearest_to([0.1, 0.1]).to_arrow()
-    )
-    assert len(result) == 10
-
-    offset_result = await (
-        table.query().nearest_to_text("dog").nearest_to([0.1, 0.1]).offset(2).to_arrow()
-    )
-    assert len(offset_result) == 10
-
-
-@pytest.mark.asyncio
-async def test_async_hybrid_query_explain_plan_matches_execution(table: AsyncTable):
-    # Paging rewrites the sub-queries: each one fetches limit + offset rows with
-    # no offset of its own, and the window is sliced out after fusion. The plans
-    # have to be built from those rewritten sub-queries, otherwise explain_plan
-    # and analyze_plan describe a query that is never run.
-    query = (
-        table.query().nearest_to([0.0, 0.4]).nearest_to_text("dog").offset(2).limit(2)
-    )
-    await query.to_arrow()
-
-    plan = await query.explain_plan()
-    assert [
-        line.strip() for line in plan.splitlines() if "GlobalLimitExec" in line
-    ] == [
-        "GlobalLimitExec: skip=0, fetch=4",
-        "GlobalLimitExec: skip=0, fetch=4",
-    ]
-
-    analyzed = await query.analyze_plan()
-    assert analyzed.count("skip=0, fetch=4") == 2
-    assert "skip=2" not in analyzed
-
-
 def test_hybrid_query_offset(sync_table: Table):
     # The offset window of a hybrid query must be a suffix of the same query
     # run without an offset -- it must not be silently ignored.

python/python/tests/test_materialized_views.py

@@ -266,38 +266,3 @@ async def test_async_namespace_connection_materialized_views(tmp_path):
             handle._route_pushdown_to_rust == through_namespace._route_pushdown_to_rust
         )
         assert handle._namespace_path == through_namespace._namespace_path
-
-
-def test_namespaced_select_kind_is_read_and_unknown_kinds_are_refused():
-    import json
-
-    import pyarrow as pa
-
-    from lancedb.materialized_view import _definition_from_schema
-
-    def schema_with(definition: dict) -> pa.Schema:
-        return pa.schema([pa.field("id", pa.int32())]).with_metadata(
-            {b"mv.definition": json.dumps(definition).encode()}
-        )
-
-    # "namespaced_select" is the namespaced form of "select": same shape,
-    # a separate kind so readers that predate it refuse instead of
-    # resolving the source at the root.
-    definition = _definition_from_schema(
-        schema_with(
-            {
-                "kind": "namespaced_select",
-                "source_table": "people",
-                "source_namespace": ["ns"],
-                "projections": [{"output": "name", "expression": "name"}],
-            }
-        ),
-        "v",
-    )
-    assert definition.source_table == "people"
-    assert definition.source_namespace == ["ns"]
-
-    with pytest.raises(NotImplementedError, match="cannot refresh"):
-        _definition_from_schema(
-            schema_with({"kind": "select_v3", "source_table": "people"}), "v"
-        )

python/python/tests/test_namespace.py

@@ -193,13 +193,7 @@ class TestNamespaceConnection:
             ),
         )
 
-        # Legacy v1 blob columns are only writable at file version <= 2.1.
-        table = db.create_table(
-            "blob_table",
-            data,
-            namespace_path=["test_ns"],
-            storage_options={"new_table_data_storage_version": "2.1"},
-        )
+        table = db.create_table("blob_table", data, namespace_path=["test_ns"])
         df = table.to_pandas(blob_mode="lazy").sort_values("id")
 
         blob = df["blob"].iloc[0]

python/python/tests/test_query.py

@@ -40,10 +40,6 @@ from utils import exception_output
 from importlib.util import find_spec
 
 
-# Legacy v1 blob columns are only writable at file version <= 2.1.
-LEGACY_BLOB_STORAGE_OPTIONS = {"new_table_data_storage_version": "2.1"}
-
-
 def _blob_query_data():
     return pa.table(
         {
@@ -123,17 +119,13 @@ def _assert_blob_bytes_projection(df):
 
 def _blob_query_table(db, name, blob_schema):
     if blob_schema == "v1":
-        return db.create_table(
-            name, _blob_query_data(), storage_options=LEGACY_BLOB_STORAGE_OPTIONS
-        )
+        return db.create_table(name, _blob_query_data())
     return _create_blob_v2_query_table(db, name)
 
 
 async def _blob_query_table_async(db, name, blob_schema):
     if blob_schema == "v1":
-        return await db.create_table(
-            name, _blob_query_data(), storage_options=LEGACY_BLOB_STORAGE_OPTIONS
-        )
+        return await db.create_table(name, _blob_query_data())
     return await _create_blob_v2_query_table_async(db, name)
 
 
@@ -283,9 +275,7 @@ async def test_query_to_pandas_kwargs(table, table_async):
 def test_plain_scan_query_to_pandas_blob_modes(tmp_db, blob_mode):
     pytest.importorskip("lance")
     table = tmp_db.create_table(
-        f"test_query_to_pandas_blob_{blob_mode}",
-        _blob_query_data(),
-        storage_options=LEGACY_BLOB_STORAGE_OPTIONS,
+        f"test_query_to_pandas_blob_{blob_mode}", _blob_query_data()
     )
 
     df = (
@@ -332,9 +322,7 @@ def test_plain_scan_query_to_pandas_blob_mode_does_not_collect_arrow(
 ):
     pytest.importorskip("lance")
     table = tmp_db.create_table(
-        "test_query_to_pandas_blob_no_arrow_collect",
-        _blob_query_data(),
-        storage_options=LEGACY_BLOB_STORAGE_OPTIONS,
+        "test_query_to_pandas_blob_no_arrow_collect", _blob_query_data()
     )
     query = table.search().where("id = 1").select(["id", "blob"])
 
@@ -359,9 +347,7 @@ def test_plain_scan_query_to_pandas_blob_descriptions_flatten_uses_scanner(
 ):
     pytest.importorskip("lance")
     table = tmp_db.create_table(
-        "test_query_to_pandas_blob_desc_flatten",
-        _blob_query_data(),
-        storage_options=LEGACY_BLOB_STORAGE_OPTIONS,
+        "test_query_to_pandas_blob_desc_flatten", _blob_query_data()
     )
     query = table.search().where("id = 1").select(["id", "blob"])
 
@@ -379,11 +365,7 @@ def test_plain_scan_query_to_pandas_blob_descriptions_flatten_uses_scanner(
 def test_plain_scan_query_to_pandas_scanner_state(tmp_db):
     pytest.importorskip("lance")
     data = _blob_query_data()
-    table = tmp_db.create_table(
-        "test_query_to_pandas_scanner_state",
-        data.slice(0, 2),
-        storage_options=LEGACY_BLOB_STORAGE_OPTIONS,
-    )
+    table = tmp_db.create_table("test_query_to_pandas_scanner_state", data.slice(0, 2))
     table.add(data.slice(2, 2))
 
     fragments = table.to_lance().get_fragments()
@@ -418,9 +400,7 @@ def test_plain_scan_query_to_pandas_scanner_state(tmp_db):
 async def test_async_plain_scan_query_to_pandas_blob_projection(tmp_db_async):
     pytest.importorskip("lance")
     table = await tmp_db_async.create_table(
-        "test_async_query_to_pandas_blob_projection",
-        _blob_query_data(),
-        storage_options=LEGACY_BLOB_STORAGE_OPTIONS,
+        "test_async_query_to_pandas_blob_projection", _blob_query_data()
     )
 
     lazy_df = await (
@@ -472,9 +452,7 @@ async def test_async_plain_scan_query_to_pandas_blob_mode_does_not_collect_arrow
 ):
     pytest.importorskip("lance")
     table = await tmp_db_async.create_table(
-        "test_async_query_to_pandas_blob_no_arrow_collect",
-        _blob_query_data(),
-        storage_options=LEGACY_BLOB_STORAGE_OPTIONS,
+        "test_async_query_to_pandas_blob_no_arrow_collect", _blob_query_data()
     )
     query = table.query().where("id = 1").select(["id", "blob"])
 
@@ -496,11 +474,7 @@ async def test_async_plain_scan_query_to_pandas_blob_mode_does_not_collect_arrow
 
 def test_vector_query_to_pandas_blob_mode_requires_native_path(tmp_db):
     pytest.importorskip("lance")
-    table = tmp_db.create_table(
-        "test_vector_query_blob_mode",
-        _blob_query_data(),
-        storage_options=LEGACY_BLOB_STORAGE_OPTIONS,
-    )
+    table = tmp_db.create_table("test_vector_query_blob_mode", _blob_query_data())
 
     with pytest.raises(RuntimeError, match="Lance native pandas conversion"):
         table.search([1.0, 0.0]).select(["blob", "vector"]).limit(1).to_pandas(
@@ -511,9 +485,7 @@ def test_vector_query_to_pandas_blob_mode_requires_native_path(tmp_db):
 def test_vector_query_to_pandas_blob_descriptions_requires_plain_scan(tmp_db):
     pytest.importorskip("lance")
     table = tmp_db.create_table(
-        "test_vector_query_blob_descriptions",
-        _blob_query_data(),
-        storage_options=LEGACY_BLOB_STORAGE_OPTIONS,
+        "test_vector_query_blob_descriptions", _blob_query_data()
     )
 
     with pytest.raises(RuntimeError, match="plain scan query"):
@@ -1951,21 +1923,6 @@ def test_take_queries(tmp_path):
         17,
     ]
 
-    # Duplicate offsets are occurrences, not set members. Ordering is unspecified.
-    assert sorted(table.take_offsets([5, 2, 5, 17]).to_pandas()["idx"].to_list()) == [
-        2,
-        5,
-        5,
-        17,
-    ]
-
-    # Converting a take builder to its serializable query representation must
-    # retain occurrence metadata and execute with the same multiplicity.
-    query = table.take_offsets([5, 2, 5, 17]).select(["idx"]).to_query_object()
-    assert query.take_offsets == [5, 2, 5, 17]
-    converted = table._execute_query(query).read_all()
-    assert sorted(converted["idx"].to_pylist()) == [2, 5, 5, 17]
-
     # Take by row id
     assert list(
         sorted(table.take_row_ids([5, 2, 17]).to_pandas()["idx"].to_list())

python/python/tests/test_remote_db.py

@@ -479,49 +479,24 @@ def test_remote_permutation_is_picklable():
                 match = re.search(
                     r"_rowoffset\s+in\s+\((.*?)\)", body["filter"], re.IGNORECASE
                 )
-                offsets = list(
-                    dict.fromkeys(int(o.strip()) for o in match.group(1).split(","))
-                )
+                offsets = [int(o.strip()) for o in match.group(1).split(",")]
             else:
                 offsets = list(range(len(rows)))
-            columns = body.get("columns") or ["a"]
-            table = pa.table(
-                {
-                    column: (
-                        [rows[offset] for offset in offsets]
-                        if column == "a"
-                        else offsets
-                    )
-                    for column in columns
-                }
-            )
+            table = pa.table({"a": [rows[offset] for offset in offsets]})
 
             request.send_response(200)
             request.send_header("Content-Type", "application/vnd.apache.arrow.file")
             request.end_headers()
             with pa.ipc.new_file(request.wfile, schema=table.schema) as writer:
-                writer.write_table(table, max_chunksize=2)
+                writer.write_table(table)
         else:
             request.send_response(404)
             request.end_headers()
 
     with mock_lancedb_connection(handler) as db:
-        table = db.open_table("test")
-        assert table.take_offsets([0, 2, 0, 4]).to_list() == [
-            {"a": 0},
-            {"a": 0},
-            {"a": 2},
-            {"a": 4},
-        ]
-
-        permutation = Permutation.identity(table)
+        permutation = Permutation.identity(db.open_table("test"))
         restored = pickle.loads(pickle.dumps(permutation))
-        assert restored.__getitems__([0, 2, 0, 4]) == [
-            {"a": 0},
-            {"a": 2},
-            {"a": 0},
-            {"a": 4},
-        ]
+        assert restored.__getitems__([0, 2, 4]) == [{"a": 0}, {"a": 2}, {"a": 4}]
 
 
 def test_create_table_exist_ok():
@@ -820,13 +795,11 @@ def test_table_create_indices():
         scalar_req = received_requests[0]
         assert "name" in scalar_req
         assert scalar_req["name"] == "custom_scalar_idx"
-        assert scalar_req["replace"] is False
 
         # Check FTS index request has custom name
         fts_req = received_requests[1]
         assert "name" in fts_req
         assert fts_req["name"] == "custom_fts_idx"
-        assert fts_req["replace"] is False
         assert fts_req["block_size"] == 256
         assert fts_req["custom_stop_words"] == ["cloud"]
 
@@ -834,7 +807,6 @@ def test_table_create_indices():
         vector_req = received_requests[2]
         assert "name" in vector_req
         assert vector_req["name"] == "custom_vector_idx"
-        assert "replace" not in vector_req
 
         table.wait_for_index(["custom_scalar_idx"], timedelta(seconds=2))
         table.wait_for_index(
@@ -1107,9 +1079,6 @@ def test_remote_create_index_new_api():
             table.create_index("text", config=FTS(block_size=256))
             # IvfRq via new API
             table.create_index("vector", config=IvfRq(distance_type="l2"))
-            table.create_index(
-                "vector", config=IvfPq(distance_type="l2"), replace=False
-            )
 
         # Legacy index_type="IVF_RQ" routes to IvfRq config under the hood.
         with pytest.warns(DeprecationWarning, match="create_index"):
@@ -1119,17 +1088,15 @@ def test_remote_create_index_new_api():
                 num_partitions=8,
             )
 
-        assert len(received_requests) == 6
+        assert len(received_requests) == 5
         assert [req["column"] for req in received_requests] == [
             "vector",
             "category",
             "text",
             "vector",
             "vector",
-            "vector",
         ]
         assert received_requests[2]["block_size"] == 256
-        assert received_requests[4]["replace"] is False
 
 
 def test_table_wait_for_index_timeout():
@@ -2467,7 +2434,7 @@ def test_remote_blob_byte_apis_not_supported_on_old_server():
 
 
 def test_remote_connection_jobs_surface():
-    from lancedb.exceptions import JobFailedError, JobNotFoundError
+    from lancedb.exceptions import JobFailedError
 
     schema = pa.schema([("state", pa.string())])
     batch = pa.record_batch([pa.array(["created", "done"])], schema=schema)
@@ -2475,7 +2442,6 @@ def test_remote_connection_jobs_surface():
     with pa.ipc.new_stream(sink, schema) as writer:
         writer.write_batch(batch)
     events_body = sink.getvalue().to_pybytes()
-    query_events_payloads = []
 
     def handler(request):
         content_len = int(request.headers.get("Content-Length", 0))
@@ -2513,22 +2479,6 @@ def test_remote_connection_jobs_surface():
             request.end_headers()
             request.wfile.write(json.dumps(rsp).encode())
         elif request.path == "/v1/jobs/describe":
-            if payload["job_id"] == "job-2":
-                request.send_response(200)
-                request.send_header("Content-Type", "application/json")
-                request.end_headers()
-                request.wfile.write(
-                    json.dumps(
-                        dict(
-                            job_id="job-2",
-                            job_type="refresh_column",
-                            job_state="DONE",
-                            creation_ms=2000,
-                            result=dict(rows_assigned=1000000, rows_failed=0),
-                        )
-                    ).encode()
-                )
-                return
             if payload["job_id"] != "job-1":
                 request.send_response(404)
                 request.end_headers()
@@ -2560,7 +2510,7 @@ def test_remote_connection_jobs_surface():
             request.end_headers()
             request.wfile.write(b'{"job_id": "job-1"}')
         elif request.path == "/v1/jobs/query_events":
-            query_events_payloads.append(payload)
+            assert payload["job_id"] == "job-1"
             request.send_response(200)
             request.send_header("Content-Type", "application/vnd.apache.arrow.stream")
             request.end_headers()
@@ -2576,109 +2526,24 @@ def test_remote_connection_jobs_surface():
         assert jobs[0].table == "t1"
         assert jobs[1].state == "finished"
 
+        description = db.get_job("job-1")
+        assert description.job_type == "create_index"
+        assert description.state == "failed"
+        assert json.loads(description.spec_json) == {"column": "vec"}
+        assert description.failure.message == "worker died"
+        assert description.failure.retryable is True
+        assert db.get_job("missing") is None
+
         assert db.cancel_job("job-1") is True
         assert db.cancel_job("missing") is False
 
-        # Opening a job hands back a populated handle; a missing one fails.
-        with pytest.raises(JobNotFoundError, match="missing"):
-            db.open_job("missing")
-        finished = db.open_job("job-2")
-        assert finished.state == "finished"
-        assert finished.result == {"rows_assigned": 1000000, "rows_failed": 0}
+        batches = db.job_history("job-1")
+        assert len(batches) == 1
+        assert batches[0].num_rows == 2
+        assert batches[0].column("state").to_pylist() == ["created", "done"]
 
-        job = db.open_job("job-1")
+        job = db.job("job-1")
         assert job.id == "job-1"
-        # Opening already populated the handle.
-        assert job.state == "failed"
-        assert job.spec == {"column": "vec"}
-        assert job.failure.message == "worker died"
         assert job.status() == "failed"
         with pytest.raises(JobFailedError, match="worker died"):
             job.wait(timeout=timedelta(seconds=5))
-
-
-def test_remote_job_handle_reports_its_own_detail():
-    schema = pa.schema([("state", pa.string())])
-    batch = pa.record_batch([pa.array(["claim_complete"])], schema=schema)
-    sink = pa.BufferOutputStream()
-    with pa.ipc.new_stream(sink, schema) as writer:
-        writer.write_batch(batch)
-    events_body = sink.getvalue().to_pybytes()
-    event_payloads = []
-
-    def handler(request):
-        content_len = int(request.headers.get("Content-Length", 0))
-        body = request.rfile.read(content_len) if content_len > 0 else b""
-        payload = json.loads(body) if body else {}
-        if request.path == "/v1/jobs/describe":
-            request.send_response(200)
-            request.send_header("Content-Type", "application/json")
-            request.end_headers()
-            request.wfile.write(
-                json.dumps(
-                    dict(
-                        job_id="job-1",
-                        job_type="refresh_column",
-                        job_state="DONE",
-                        creation_ms=2000,
-                        spec=dict(column="vec"),
-                        result=dict(rows_assigned=1000000),
-                    )
-                ).encode()
-            )
-        elif request.path == "/v1/jobs/query_events":
-            event_payloads.append(payload)
-            request.send_response(200)
-            request.send_header("Content-Type", "application/vnd.apache.arrow.stream")
-            request.end_headers()
-            request.wfile.write(events_body)
-        else:
-            request.send_response(404)
-            request.end_headers()
-
-    with mock_lancedb_connection(handler) as db:
-        job = db.open_job("job-1")
-
-        # Opening populates the handle in the same round trip.
-        assert job.state == "finished"
-        job.refresh()
-        assert job.job_type == "refresh_column"
-        assert job.creation_ms == 2000
-        assert job.spec == {"column": "vec"}
-        assert job.result == {"rows_assigned": 1000000}
-        assert job.failure is None
-        # The JSON payloads stay reachable, but as internal APIs.
-        assert json.loads(job._spec_json) == {"column": "vec"}
-        assert json.loads(job._result_json) == {"rows_assigned": 1000000}
-
-        # print() shows everything the handle knows and nothing it does not.
-        # print() lays every known field out on its own line, with the JSON
-        # payloads indented rather than crammed onto one line.
-        assert repr(job) == "\n".join(
-            [
-                "Job(",
-                "    id='job-1',",
-                "    state='finished',",
-                "    job_type='refresh_column',",
-                "    creation_ms=2000,",
-                "    spec={",
-                '        "column": "vec"',
-                "    },",
-                "    result={",
-                '        "rows_assigned": 1000000',
-                "    },",
-                ")",
-            ]
-        )
-        # Nothing it does not know shows up.
-        assert "failure" not in repr(job)
-
-        events = job.events(filter="state = 'claim_complete'", limit=500)
-        assert isinstance(events, pa.Table)
-        assert events.column("state").to_pylist() == ["claim_complete"]
-        # The handle supplies job_id; the caller only narrows the query.
-        assert event_payloads[-1] == {
-            "job_id": "job-1",
-            "limit": 500,
-            "filter": "state = 'claim_complete'",
-        }

python/python/tests/test_rerankers.py

@@ -81,7 +81,7 @@ def get_test_table(tmp_path):
         "but his son was mortal",
         "there hasn't been a good battlefield game since 2142",
         "I wish they would make another one",
-        "campaigns are not as good as they used to be",
+        "campains are not as good as they used to be",
         "Multiplayer and open world games have destroyed the single player experience",
         "Maybe the future is console games",
         "I don't know",

python/python/tests/test_sql.py

@@ -1,162 +0,0 @@
-# SPDX-License-Identifier: Apache-2.0
-# SPDX-FileCopyrightText: Copyright The LanceDB Authors
-
-from uuid import UUID
-
-import pytest
-import pyarrow as pa
-
-import lancedb
-from lancedb import _lancedb
-from lancedb.arrow import AsyncRecordBatchReader
-from lancedb.db import AsyncConnection
-from lancedb.remote.db import RemoteDBConnection
-from lancedb.sql import AsyncQuery, Query
-
-NIL_QUERY_ID = UUID(int=0)
-
-
-class FakeNativeQuery:
-    id = UUID("0198f1b2-c3d4-7e5f-8123-456789abcdef")
-
-    async def reader(self):
-        return pa.table({"value": [1, 2]})
-
-
-class FakeNativeConnection:
-    async def execute_query_async(self, query, *, default_namespace_path=None):
-        return FakeNativeQuery()
-
-
-class FakeAsyncConnection:
-    async def execute_query_async(self, query, *, default_namespace_path=None):
-        return AsyncQuery(FakeNativeQuery())
-
-
-def remote_connection(sql_host_override=None):
-    return lancedb.connect(
-        "db://analytics",
-        api_key="test-key",
-        host_override="http://localhost:10024",
-        sql_host_override=sql_host_override,
-    )
-
-
-def test_sql_is_connection_scoped():
-    assert hasattr(lancedb, "sql")
-    assert not callable(lancedb.sql)
-    assert not hasattr(_lancedb, "sql")
-    assert not hasattr(remote_connection(), "sql")
-    assert hasattr(remote_connection(), "execute_query")
-    assert hasattr(remote_connection(), "execute_query_async")
-    assert hasattr(remote_connection(), "describe_query")
-
-
-def test_query_id_is_uuid():
-    query = AsyncQuery(FakeNativeQuery())
-    assert isinstance(query.id, UUID)
-    assert Query(query).id == query.id
-
-
-def test_connection_serializes_sql_host_override():
-    endpoint = "grpc+tls://sql.example.com:10026"
-    restored = lancedb.deserialize_conn(
-        remote_connection(sql_host_override=endpoint).serialize()
-    )
-    assert restored.sql_host_override == endpoint
-
-
-@pytest.mark.asyncio
-async def test_async_sql_reader_is_record_batch_stream():
-    reader = await AsyncQuery(FakeNativeQuery()).reader()
-    assert isinstance(reader, AsyncRecordBatchReader)
-    assert (await reader.read_all())[0].column(0).to_pylist() == [1, 2]
-
-
-def test_sync_sql_reader_is_record_batch_reader():
-    reader = Query(AsyncQuery(FakeNativeQuery())).reader()
-    assert isinstance(reader, pa.RecordBatchReader)
-    assert reader.read_all().column(0).to_pylist() == [1, 2]
-
-
-def test_execute_query_returns_blocking_reader():
-    connection = RemoteDBConnection.__new__(RemoteDBConnection)
-    connection._conn = FakeAsyncConnection()
-    reader = connection.execute_query("SELECT 1")
-    assert isinstance(reader, pa.RecordBatchReader)
-    assert reader.read_all().column(0).to_pylist() == [1, 2]
-
-
-@pytest.mark.asyncio
-async def test_async_execute_query_returns_async_reader():
-    connection = AsyncConnection(FakeNativeConnection())
-    reader = await connection.execute_query("SELECT 1")
-    assert isinstance(reader, AsyncRecordBatchReader)
-    assert (await reader.read_all())[0].column(0).to_pylist() == [1, 2]
-
-
-def test_local_connection_rejects_sql(tmp_path):
-    connection = lancedb.connect(tmp_path)
-    with pytest.raises(NotImplementedError, match="SQL"):
-        connection.execute_query("SELECT 1")
-    with pytest.raises(NotImplementedError, match="SQL"):
-        connection.execute_query_async("SELECT 1")
-    with pytest.raises(NotImplementedError, match="SQL"):
-        connection.describe_query(NIL_QUERY_ID)
-
-
-@pytest.mark.asyncio
-async def test_local_async_connection_rejects_sql(tmp_path):
-    connection = await lancedb.connect_async(tmp_path)
-    with pytest.raises(NotImplementedError, match="SQL"):
-        await connection.execute_query("SELECT 1")
-    with pytest.raises(NotImplementedError, match="SQL"):
-        await connection.execute_query_async("SELECT 1")
-    with pytest.raises(NotImplementedError, match="SQL"):
-        await connection.describe_query(NIL_QUERY_ID)
-
-
-@pytest.mark.asyncio
-async def test_async_namespace_connection_rejects_sql(tmp_path):
-    connection = lancedb.connect_namespace_async("dir", {"root": str(tmp_path)})
-    with pytest.raises(NotImplementedError, match="SQL"):
-        await connection.execute_query("SELECT 1")
-    with pytest.raises(NotImplementedError, match="SQL"):
-        await connection.execute_query_async("SELECT 1")
-    with pytest.raises(NotImplementedError, match="SQL"):
-        await connection.describe_query(NIL_QUERY_ID)
-
-
-def test_describe_query_requires_uuid():
-    with pytest.raises(TypeError, match="UUID"):
-        remote_connection().describe_query(str(NIL_QUERY_ID))
-
-
-@pytest.mark.parametrize(
-    "default_namespace_path",
-    ["public", ("public",), [1]],
-)
-def test_execute_query_async_requires_namespace_path_list(default_namespace_path):
-    with pytest.raises(ValueError, match="default_namespace_path"):
-        remote_connection().execute_query_async(
-            "SELECT 1", default_namespace_path=default_namespace_path
-        )
-
-
-def test_execute_query_async_rejects_invalid_endpoint():
-    connection = remote_connection(sql_host_override="invalid://localhost")
-    with pytest.raises(ValueError, match="sql_host_override"):
-        connection.execute_query_async("SELECT 1")
-
-
-@pytest.mark.parametrize(
-    "default_namespace_path",
-    [[""], ["café"], ["pub\tlic"], ["events$raw"]],
-)
-def test_execute_query_async_rejects_invalid_namespace_components(
-    default_namespace_path,
-):
-    with pytest.raises(ValueError, match="default_namespace_path"):
-        remote_connection().execute_query_async(
-            "SELECT 1", default_namespace_path=default_namespace_path
-        )

python/python/tests/test_table.py

@@ -64,23 +64,15 @@ async def _blob_v2_table_async(db: AsyncConnection, name: str):
     return table
 
 
-# Legacy v1 blob columns are only writable at file version <= 2.1.
-LEGACY_BLOB_STORAGE_OPTIONS = {"new_table_data_storage_version": "2.1"}
-
-
 def _blob_table(db: DBConnection, name: str, blob_schema: str):
     if blob_schema == "v1":
-        return db.create_table(
-            name, data=_blob_test_data(), storage_options=LEGACY_BLOB_STORAGE_OPTIONS
-        )
+        return db.create_table(name, data=_blob_test_data())
     return _blob_v2_table(db, name)
 
 
 async def _blob_table_async(db: AsyncConnection, name: str, blob_schema: str):
     if blob_schema == "v1":
-        return await db.create_table(
-            name, data=_blob_test_data(), storage_options=LEGACY_BLOB_STORAGE_OPTIONS
-        )
+        return await db.create_table(name, data=_blob_test_data())
     return await _blob_v2_table_async(db, name)
 
 
@@ -155,11 +147,7 @@ def test_table_to_pandas_invalid_blob_mode_non_blob_table(tmp_db: DBConnection):
 @pytest.mark.parametrize("blob_mode", ["lazy", "bytes", "descriptions"])
 def test_table_to_pandas_blob_modes(tmp_db: DBConnection, blob_mode):
     pytest.importorskip("lance")
-    table = tmp_db.create_table(
-        f"test_to_pandas_blob_{blob_mode}",
-        _blob_test_data(),
-        storage_options=LEGACY_BLOB_STORAGE_OPTIONS,
-    )
+    table = tmp_db.create_table(f"test_to_pandas_blob_{blob_mode}", _blob_test_data())
 
     df = table.to_pandas(blob_mode=blob_mode)
 
@@ -2694,43 +2682,6 @@ def test_merge_insert(mem_db: DBConnection):
         )
 
 
-def test_merge_insert_composite_key(mem_db: DBConnection):
-    table = mem_db.create_table(
-        "my_table",
-        data=pa.table(
-            {
-                "shard": ["a", "a", "b"],
-                "id": [1, 2, 1],
-                "val": ["x", "y", "z"],
-            }
-        ),
-    )
-
-    # ("a", 1) matches an existing row and updates it. ("b", 2) agrees with an
-    # existing row on each key column separately but on neither pair, so it is
-    # an insert.
-    new_data = pa.table({"shard": ["a", "b"], "id": [1, 2], "val": ["X", "W"]})
-    res = (
-        table.merge_insert(["shard", "id"])
-        .when_matched_update_all()
-        .when_not_matched_insert_all()
-        .execute(new_data)
-    )
-    assert res.num_updated_rows == 1
-    assert res.num_inserted_rows == 1
-
-    expected = pa.table(
-        {
-            "shard": ["a", "a", "b", "b"],
-            "id": [1, 2, 1, 2],
-            "val": ["X", "y", "z", "W"],
-        }
-    )
-    assert table.to_arrow().sort_by([("shard", "ascending"), ("id", "ascending")]) == (
-        expected
-    )
-
-
 def test_merge_insert_nullable_pandas_into_pydantic_schema(mem_db: DBConnection):
     # Regression test for https://github.com/lancedb/lancedb/issues/2366
     pd = pytest.importorskip("pandas")
@@ -3354,7 +3305,7 @@ def test_empty_query(mem_db: DBConnection):
     # None is the same as default
     df = table.search().select(["id"]).limit(None).to_arrow()
     assert df.num_rows == 100
-    # invalid limist is the same as None, which is the same as default
+    # invalid limist is the same as None, wihch is the same as default
     df = table.search().select(["id"]).limit(-1).to_arrow()
     assert df.num_rows == 100
     # valid limit should work
@@ -3971,7 +3922,7 @@ def test_stats(mem_db: DBConnection):
     print(f"{stats=}")
     assert stats == {
         # Full on-disk size of the data file, footer and metadata included.
-        "total_bytes": 637,
+        "total_bytes": 633,
         "num_rows": 2,
         "num_indices": 0,
         "fragment_stats": {

python/src/connection.rs

@@ -13,7 +13,11 @@ use crate::{
     runtime::future_into_py,
     table::Table,
 };
-use arrow::{datatypes::Schema, ffi_stream::ArrowArrayStreamReader, pyarrow::FromPyArrow};
+use arrow::{
+    datatypes::Schema,
+    ffi_stream::ArrowArrayStreamReader,
+    pyarrow::{FromPyArrow, ToPyArrow},
+};
 use lancedb::{
     connection::Connection as LanceConnection,
     connection::NamespaceClientPushdownOperation,
@@ -24,7 +28,7 @@ use pyo3::{
     Bound, FromPyObject, Py, PyAny, PyRef, PyResult, Python,
     exceptions::{PyRuntimeError, PyValueError},
     pyclass, pyfunction, pymethods,
-    types::{PyAnyMethods, PyDict, PyDictMethods, PyList},
+    types::{PyDict, PyDictMethods, PyList, PyListMethods},
 };
 
 #[pyclass]
@@ -82,24 +86,6 @@ impl Connection {
     }
 }
 
-fn parse_default_namespace_path(path: Option<Bound<'_, PyAny>>) -> PyResult<Vec<String>> {
-    match path {
-        Some(path) => {
-            if !path.is_instance_of::<PyList>() {
-                return Err(PyValueError::new_err(
-                    "Connection.execute_query_async default_namespace_path must be a list",
-                ));
-            }
-            path.extract::<Vec<String>>().map_err(|_| {
-                PyValueError::new_err(
-                    "Connection.execute_query_async default_namespace_path components must be strings",
-                )
-            })
-        }
-        None => Ok(vec!["public".to_string()]),
-    }
-}
-
 #[pymethods]
 impl Connection {
     fn __repr__(&self) -> String {
@@ -122,40 +108,6 @@ impl Connection {
         self.get_inner().map(|inner| inner.uri().to_string())
     }
 
-    #[pyo3(signature = (query, *, default_namespace_path=None))]
-    pub fn execute_query_async<'a>(
-        self_: PyRef<'a, Self>,
-        query: String,
-        default_namespace_path: Option<Bound<'_, PyAny>>,
-    ) -> PyResult<Bound<'a, PyAny>> {
-        let inner = self_.get_inner()?.clone();
-        let default_namespace_path = parse_default_namespace_path(default_namespace_path)?;
-        future_into_py(self_.py(), async move {
-            let operation = inner
-                .execute_query_async(query)
-                .default_namespace_path(default_namespace_path);
-            operation
-                .execute()
-                .await
-                .map(crate::sql::Query::new)
-                .infer_error()
-        })
-    }
-
-    pub fn describe_query<'a>(
-        self_: PyRef<'a, Self>,
-        query_id: uuid::Uuid,
-    ) -> PyResult<Bound<'a, PyAny>> {
-        let inner = self_.get_inner()?.clone();
-        future_into_py(self_.py(), async move {
-            inner
-                .describe_query(query_id)
-                .await
-                .map(crate::sql::QueryDescription::from)
-                .infer_error()
-        })
-    }
-
     #[pyo3(signature = ())]
     pub fn get_read_consistency_interval(self_: PyRef<'_, Self>) -> PyResult<Bound<'_, PyAny>> {
         let inner = self_.get_inner()?.clone();
@@ -640,12 +592,9 @@ impl Connection {
         })
     }
 
-    pub fn open_job(self_: PyRef<'_, Self>, job_id: String) -> PyResult<Bound<'_, PyAny>> {
-        let inner = self_.get_inner()?.clone();
-        future_into_py(self_.py(), async move {
-            let job = inner.open_job(&job_id).await.infer_error()?;
-            Ok(crate::job::Job::new(job))
-        })
+    pub fn job(&self, job_id: String) -> PyResult<crate::job::Job> {
+        let inner = self.get_inner()?.clone();
+        Ok(crate::job::Job::new(inner.job(job_id).infer_error()?))
     }
 
     pub fn create_function_async(
@@ -680,30 +629,6 @@ impl Connection {
         })
     }
 
-    pub fn list_functions(self_: PyRef<'_, Self>) -> PyResult<Bound<'_, PyAny>> {
-        let inner = self_.get_inner()?.clone();
-        future_into_py(self_.py(), async move {
-            inner
-                .list_functions()
-                .await
-                .infer_error()?
-                .into_iter()
-                .map(|function| function.to_canonical_json().infer_error())
-                .collect::<PyResult<Vec<_>>>()
-        })
-    }
-
-    pub fn drop_function(
-        self_: PyRef<'_, Self>,
-        name: String,
-        version: String,
-    ) -> PyResult<Bound<'_, PyAny>> {
-        let inner = self_.get_inner()?.clone();
-        future_into_py(self_.py(), async move {
-            inner.drop_function(name, version).await.infer_error()
-        })
-    }
-
     pub fn list_jobs(self_: PyRef<'_, Self>) -> PyResult<Bound<'_, PyAny>> {
         let inner = self_.get_inner()?.clone();
         future_into_py(self_.py(), async move {
@@ -715,16 +640,42 @@ impl Connection {
         })
     }
 
+    pub fn get_job(self_: PyRef<'_, Self>, job_id: String) -> PyResult<Bound<'_, PyAny>> {
+        let inner = self_.get_inner()?.clone();
+        future_into_py(self_.py(), async move {
+            let description = inner.get_job(&job_id).await.infer_error()?;
+            Ok(description.map(crate::job::JobDescription::from))
+        })
+    }
+
     pub fn cancel_job(self_: PyRef<'_, Self>, job_id: String) -> PyResult<Bound<'_, PyAny>> {
         let inner = self_.get_inner()?.clone();
         future_into_py(self_.py(), async move {
             inner.cancel_job(&job_id).await.infer_error()
         })
     }
+
+    #[pyo3(signature = (job_id=None))]
+    pub fn job_history(
+        self_: PyRef<'_, Self>,
+        job_id: Option<String>,
+    ) -> PyResult<Bound<'_, PyAny>> {
+        let inner = self_.get_inner()?.clone();
+        future_into_py(self_.py(), async move {
+            let batches = inner.job_history(job_id.as_deref()).await.infer_error()?;
+            Python::attach(|py| {
+                let list = PyList::empty(py);
+                for batch in batches {
+                    list.append(batch.to_pyarrow(py)?)?;
+                }
+                Ok(list.unbind())
+            })
+        })
+    }
 }
 
 #[pyfunction]
-#[pyo3(signature = (uri, api_key=None, region=None, host_override=None, sql_host_override=None, read_consistency_interval=None, client_config=None, storage_options=None, session=None, manifest_enabled=false, namespace_client_properties=None, oauth_config=None))]
+#[pyo3(signature = (uri, api_key=None, region=None, host_override=None, read_consistency_interval=None, client_config=None, storage_options=None, session=None, manifest_enabled=false, namespace_client_properties=None, oauth_config=None))]
 #[allow(clippy::too_many_arguments)]
 pub fn connect(
     py: Python<'_>,
@@ -732,7 +683,6 @@ pub fn connect(
     api_key: Option<String>,
     region: Option<String>,
     host_override: Option<String>,
-    sql_host_override: Option<String>,
     read_consistency_interval: Option<f64>,
     client_config: Option<PyClientConfig>,
     storage_options: Option<HashMap<String, String>>,
@@ -752,12 +702,6 @@ pub fn connect(
         if let Some(host_override) = host_override {
             builder = builder.host_override(&host_override);
         }
-        #[cfg(feature = "remote")]
-        if let Some(sql_host_override) = sql_host_override {
-            builder = builder.sql_host_override(&sql_host_override);
-        }
-        #[cfg(not(feature = "remote"))]
-        let _ = sql_host_override;
         if let Some(read_consistency_interval) = read_consistency_interval {
             let read_consistency_interval = Duration::from_secs_f64(read_consistency_interval);
             builder = builder.read_consistency_interval(read_consistency_interval);

python/src/error.rs

@@ -114,12 +114,6 @@ impl<T> PythonErrorExt<T> for std::result::Result<T, LanceError> {
                         .getattr(intern!(py, "JobCancelledError"))?;
                     Err(PyErr::from_value(cls.call1((err.to_string(),))?))
                 }),
-                LanceError::JobNotFound { .. } => Python::attach(|py| {
-                    let cls = py
-                        .import(intern!(py, "lancedb.exceptions"))?
-                        .getattr(intern!(py, "JobNotFoundError"))?;
-                    Err(PyErr::from_value(cls.call1((err.to_string(),))?))
-                }),
                 _ => self.runtime_error(),
             },
         }

python/src/job.rs

@@ -4,50 +4,11 @@
 use std::sync::Arc;
 
 use crate::runtime::future_into_py;
-use arrow::{
-    datatypes::Schema,
-    pyarrow::{IntoPyArrow, Table as PyArrowTable},
-};
-use lancedb::job::JobEventsRequest;
-use pyo3::{
-    Bound, PyAny, PyRef, PyResult, Python,
-    exceptions::PyValueError,
-    pyclass, pymethods,
-    types::{PyAnyMethods, PyDict, PyDictMethods},
-};
+use pyo3::{Bound, PyAny, PyRef, PyResult, pyclass, pymethods};
 use serde::Serialize;
 
 use crate::error::PythonErrorExt;
 
-const REPR_INDENT: &str = "    ";
-
-/// Parse a stored JSON payload into Python data. The bindings carry these as
-/// strings because that is what crosses the boundary cheaply; the public
-/// Python surface is the parsed form.
-fn parse_json_payload<'py>(
-    py: Python<'py>,
-    raw: Option<&str>,
-) -> PyResult<Option<Bound<'py, PyAny>>> {
-    match raw {
-        None => Ok(None),
-        Some(raw) => Ok(Some(py.import("json")?.call_method1("loads", (raw,))?)),
-    }
-}
-
-/// A payload rendered as indented JSON, aligned under the field that holds it.
-fn pretty_json_payload(py: Python<'_>, raw: Option<&str>) -> PyResult<Option<String>> {
-    let Some(parsed) = parse_json_payload(py, raw)? else {
-        return Ok(None);
-    };
-    let kwargs = PyDict::new(py);
-    kwargs.set_item("indent", 4)?;
-    let rendered: String = py
-        .import("json")?
-        .call_method("dumps", (parsed,), Some(&kwargs))?
-        .extract()?;
-    Ok(Some(rendered.replace('\n', &format!("\n{REPR_INDENT}"))))
-}
-
 #[pyclass]
 pub struct Job {
     inner: Arc<lancedb::Job<std::result::Result<Option<String>, String>>>,
@@ -106,48 +67,6 @@ impl Job {
             Ok(())
         })
     }
-
-    pub fn refresh(self_: PyRef<'_, Self>) -> PyResult<Bound<'_, PyAny>> {
-        let inner = self_.inner.clone();
-        future_into_py(self_.py(), async move {
-            inner.refresh().await.infer_error()?;
-            Ok(())
-        })
-    }
-
-    /// The last observed lifecycle state, without contacting the backend.
-    #[getter]
-    pub fn _state(&self) -> Option<String> {
-        self.inner.state()
-    }
-
-    /// The last observed server-side record. `None` for an in-process job.
-    #[getter]
-    pub fn _description(&self) -> Option<JobDescription> {
-        self.inner.description().map(JobDescription::from)
-    }
-
-    #[pyo3(signature = (*, limit=None, filter=None))]
-    pub fn events(
-        self_: PyRef<'_, Self>,
-        limit: Option<u32>,
-        filter: Option<String>,
-    ) -> PyResult<Bound<'_, PyAny>> {
-        let inner = self_.inner.clone();
-        let request = JobEventsRequest { limit, filter };
-        future_into_py(self_.py(), async move {
-            let batches = inner.events(request).await.infer_error()?;
-            Python::attach(|py| {
-                let schema = batches
-                    .first()
-                    .map(|batch| batch.schema())
-                    .unwrap_or_else(|| Arc::new(Schema::empty()));
-                let table = PyArrowTable::try_new(batches, schema)
-                    .map_err(|err| PyValueError::new_err(err.to_string()))?;
-                table.into_pyarrow(py).map(|table| table.unbind())
-            })
-        })
-    }
 }
 
 /// A row from `Connection.list_jobs`: one server-side job.
@@ -202,7 +121,7 @@ impl JobFailureInfo {
     }
 }
 
-/// The server-side record behind a `Job` handle.
+/// A described job from `Connection.get_job`.
 #[pyclass(get_all, skip_from_py_object)]
 #[derive(Clone)]
 pub struct JobDescription {
@@ -210,49 +129,17 @@ pub struct JobDescription {
     job_type: String,
     state: String,
     creation_ms: i64,
-    /// Internal: the wire form behind the `spec` property.
-    _spec_json: Option<String>,
-    /// Internal: the wire form behind the `result` property.
-    _result_json: Option<String>,
+    spec_json: Option<String>,
     failure: Option<JobFailureInfo>,
 }
 
 #[pymethods]
 impl JobDescription {
-    /// The job-type-specific specification it was submitted with.
-    #[getter]
-    fn spec<'py>(&self, py: Python<'py>) -> PyResult<Option<Bound<'py, PyAny>>> {
-        parse_json_payload(py, self._spec_json.as_deref())
-    }
-
-    /// The job-type-specific terminal result. `None` until the job succeeds.
-    #[getter]
-    fn result<'py>(&self, py: Python<'py>) -> PyResult<Option<Bound<'py, PyAny>>> {
-        parse_json_payload(py, self._result_json.as_deref())
-    }
-
-    fn __repr__(&self, py: Python<'_>) -> PyResult<String> {
-        let mut fields = vec![
-            format!("job_id={:?}", self.job_id),
-            format!("job_type={:?}", self.job_type),
-            format!("state={:?}", self.state),
-            format!("creation_ms={}", self.creation_ms),
-        ];
-        // Lay the payloads out as indented JSON, the same way the `Job` repr
-        // does, so the two agree on how the same data looks.
-        for (name, payload) in [("spec", &self._spec_json), ("result", &self._result_json)] {
-            if let Some(rendered) = pretty_json_payload(py, payload.as_deref())? {
-                fields.push(format!("{name}={rendered}"));
-            }
-        }
-        if let Some(failure) = &self.failure {
-            fields.push(format!("failure={}", failure.__repr__()));
-        }
-        let body = fields
-            .iter()
-            .map(|field| format!("\n{REPR_INDENT}{field},"))
-            .collect::<String>();
-        Ok(format!("JobDescription({body}\n)"))
+    fn __repr__(&self) -> String {
+        format!(
+            "JobDescription(job_id={:?}, job_type={:?}, state={:?}, creation_ms={})",
+            self.job_id, self.job_type, self.state, self.creation_ms
+        )
     }
 }
 
@@ -263,11 +150,7 @@ impl From<lancedb::database::JobDescription> for JobDescription {
             job_type: description.job_type,
             state: description.state,
             creation_ms: description.creation_ms,
-            _spec_json: (!description.spec.is_null()).then(|| description.spec.to_string()),
-            _result_json: description
-                .result
-                .filter(|result| !result.is_null())
-                .map(|result| result.to_string()),
+            spec_json: (!description.spec.is_null()).then(|| description.spec.to_string()),
             failure: description.failure.map(|failure| JobFailureInfo {
                 phase: failure.phase,
                 message: failure.message,

python/src/lib.rs

@@ -34,7 +34,6 @@ pub mod permutation;
 pub mod query;
 pub mod runtime;
 pub mod session;
-pub mod sql;
 pub mod table;
 pub mod util;
 
@@ -51,8 +50,6 @@ pub fn _lancedb(_py: Python, m: &Bound<'_, PyModule>) -> PyResult<()> {
     m.add_class::<crate::job::JobInfo>()?;
     m.add_class::<crate::job::JobDescription>()?;
     m.add_class::<crate::job::JobFailureInfo>()?;
-    m.add_class::<crate::sql::Query>()?;
-    m.add_class::<crate::sql::QueryDescription>()?;
     m.add_class::<PyBlobFile>()?;
     m.add_class::<IndexConfig>()?;
     m.add_class::<Query>()?;

python/src/query.rs

@@ -323,7 +323,6 @@ impl<'py> IntoPyObject<'py> for PyQueryVectors {
 pub struct PyQueryRequest {
     pub limit: Option<usize>,
     pub offset: Option<usize>,
-    pub take_offsets: Option<Vec<u64>>,
     pub filter: Option<PyQueryFilter>,
     pub full_text_search: Option<PyLanceDB<FtsQuery>>,
     pub select: PySelect,
@@ -334,7 +333,7 @@ pub struct PyQueryRequest {
     pub column: Option<String>,
     pub query_vector: Option<PyQueryVectors>,
     pub minimum_nprobes: Option<usize>,
-    // None means user did not set it and default should be used (currently 20)
+    // None means user did not set it and default shoud be used (currenty 20)
     // Some(0) means user set it to None and there is no limit
     pub maximum_nprobes: Option<usize>,
     pub lower_bound: Option<f32>,
@@ -354,7 +353,6 @@ impl From<AnyQuery> for PyQueryRequest {
             AnyQuery::Query(query_request) => Self {
                 limit: query_request.limit,
                 offset: query_request.offset,
-                take_offsets: query_request.take_offsets,
                 filter: query_request.filter.map(PyQueryFilter),
                 full_text_search: query_request
                     .full_text_search
@@ -383,7 +381,6 @@ impl From<AnyQuery> for PyQueryRequest {
             AnyQuery::VectorQuery(vector_query) => Self {
                 limit: vector_query.base.limit,
                 offset: vector_query.base.offset,
-                take_offsets: vector_query.base.take_offsets,
                 filter: vector_query.base.filter.map(PyQueryFilter),
                 full_text_search: None,
                 select_source_columns: PySelect::source_columns(&vector_query.base.select),

python/src/sql.rs

@@ -1,90 +0,0 @@
-// SPDX-License-Identifier: Apache-2.0
-// SPDX-FileCopyrightText: Copyright The LanceDB Authors
-
-use std::sync::Arc;
-
-use chrono::{DateTime, Utc};
-use pyo3::{Bound, PyAny, PyRef, PyResult, pyclass, pymethods};
-use uuid::Uuid;
-
-use crate::arrow::RecordBatchStream;
-use crate::error::PythonErrorExt;
-use crate::runtime::future_into_py;
-
-#[pyclass(name = "SqlQuery")]
-pub struct Query {
-    inner: Arc<lancedb::sql::Query>,
-}
-
-impl Query {
-    pub(crate) fn new(inner: lancedb::sql::Query) -> Self {
-        Self {
-            inner: Arc::new(inner),
-        }
-    }
-}
-
-#[pymethods]
-impl Query {
-    #[getter]
-    pub fn id(&self) -> Uuid {
-        self.inner.id()
-    }
-
-    pub fn describe(self_: PyRef<'_, Self>) -> PyResult<Bound<'_, PyAny>> {
-        let inner = self_.inner.clone();
-        future_into_py(self_.py(), async move {
-            inner
-                .describe()
-                .await
-                .map(QueryDescription::from)
-                .infer_error()
-        })
-    }
-
-    pub fn reader(self_: PyRef<'_, Self>) -> PyResult<Bound<'_, PyAny>> {
-        let inner = self_.inner.clone();
-        future_into_py(self_.py(), async move {
-            let stream = inner.reader().await.infer_error()?;
-            Ok(RecordBatchStream::new(stream))
-        })
-    }
-
-    pub fn cancel(self_: PyRef<'_, Self>) -> PyResult<Bound<'_, PyAny>> {
-        let inner = self_.inner.clone();
-        future_into_py(self_.py(), async move {
-            inner.cancel().await.infer_error()?;
-            Ok(())
-        })
-    }
-}
-
-#[pyclass(get_all, skip_from_py_object)]
-#[derive(Clone)]
-pub struct QueryDescription {
-    id: Uuid,
-    status: String,
-    progress: Option<f64>,
-    expires_at: Option<DateTime<Utc>>,
-}
-
-#[pymethods]
-impl QueryDescription {
-    fn __repr__(&self) -> String {
-        format!(
-            "QueryDescription(id={:?}, status={:?}, progress={:?}, expires_at={:?})",
-            self.id, self.status, self.progress, self.expires_at
-        )
-    }
-}
-
-impl From<lancedb::sql::QueryDescription> for QueryDescription {
-    fn from(description: lancedb::sql::QueryDescription) -> Self {
-        Self {
-            id: description.id,
-            status: description.status.to_string(),
-            progress: description.progress,
-            expires_at: description.expires_at,
-        }
-    }
-}

rust/lancedb/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "lancedb"
-version = "0.39.0-beta.6"
+version = "0.38.0"
 edition.workspace = true
 description = "LanceDB: A serverless, low-latency vector database for AI applications"
 license.workspace = true
@@ -21,8 +21,6 @@ arrow-select = { workspace = true }
 arrow-ord = { workspace = true }
 arrow-cast = { workspace = true }
 arrow-ipc.workspace = true
-arrow-flight = { workspace = true, optional = true }
-prost = { version = "0.14", optional = true }
 chrono = { workspace = true }
 datafusion-catalog.workspace = true
 datafusion-common.workspace = true
@@ -79,7 +77,6 @@ reqwest = { version = "0.12.0", default-features = false, features = [
     "rustls-tls-native-roots",
     "stream",
 ], optional = true }
-tonic = { workspace = true, optional = true }
 http = { version = "1", optional = true } # Matching what is in reqwest
 urlencoding = { version = "2", optional = true }
 uuid = { workspace = true, features = ["v5"] }
@@ -148,11 +145,8 @@ huggingface = [
 ]
 dynamodb = ["lance/dynamodb", "aws"]
 remote = [
-    "dep:arrow-flight",
-    "dep:prost",
     "dep:reqwest",
     "dep:http",
-    "dep:tonic",
     "dep:urlencoding",
     "lance-namespace-impls/rest",
     "lance-namespace-impls/rest-adapter",

rust/lancedb/src/arrow.rs

@@ -163,7 +163,7 @@ pub struct PolarsDataFrameRecordBatchReader {
 impl PolarsDataFrameRecordBatchReader {
     /// Creates a new `PolarsDataFrameRecordBatchReader` from a given Polars DataFrame.
     /// If the input dataframe does not have aligned chunks, this function undergoes
-    /// the costly operation of reallocating each series as a single contiguous chunk.
+    /// the costly operation of reallocating each series as a single contigous chunk.
     pub fn new(mut df: DataFrame) -> Result<Self> {
         df.align_chunks();
         let arrow_schema =

rust/lancedb/src/blob.rs

@@ -7,9 +7,7 @@
 //! raw `Binary` / `LargeBinary` into the blob struct layout. Queries return
 //! small descriptors, not bytes.
 //!
-//! Blob tables require Lance file format >= 2.2. `_rowid` values stay valid
-//! after compaction when the table has stable row ids. Overwrite is a new
-//! create and does not keep the previous table's stable row id setting.
+//! Blob tables require Lance file format >= 2.2 and stable row ids at create.
 
 use std::ops::Range;
 use std::sync::Arc;
@@ -326,7 +324,6 @@ pub(crate) fn blob_column_names(schema: &Schema) -> Vec<String> {
 }
 
 /// Bumps storage format to at least [`LanceFileVersion::V2_2`] for blob schemas.
-/// Leaves `enable_stable_row_ids` unchanged.
 pub(crate) fn ensure_blob_storage_version(schema: &Schema, params: &mut WriteParams) {
     if !has_blob_columns(schema) {
         return;
@@ -388,30 +385,6 @@ fn ensure_all_row_ids_resolved(column: &str, requested: usize, resolved: usize)
     }
 }
 
-/// Lance take reports a missing physical row address as NotSupported or InvalidInput.
-fn map_blob_take_error(column: &str, requested: usize, err: lance::Error) -> Error {
-    let missing_row_addr = match &err {
-        lance::Error::NotSupported { source, .. } => {
-            source.to_string().contains("must not target deleted rows")
-        }
-        lance::Error::InvalidInput { source, .. } => source
-            .to_string()
-            .contains("belongs to non-existent fragment"),
-        _ => false,
-    };
-
-    if missing_row_addr {
-        Error::InvalidInput {
-            message: format!(
-                "blob read for column '{column}' requested {requested} row ids but some \
-                 do not exist in the table; pass row ids collected from this table"
-            ),
-        }
-    } else {
-        err.into()
-    }
-}
-
 /// Materialize blob-local ranges (same length and order as `requests`, nulls preserved).
 pub(crate) async fn take_blob_ranges_aligned(
     dataset: &Arc<Dataset>,
@@ -432,8 +405,7 @@ pub(crate) async fn take_blob_ranges_aligned(
         .with_row_ids(lance_requests)
         .preserve_order(true)
         .execute()
-        .await
-        .map_err(|err| map_blob_take_error(column, requests.len(), err))?;
+        .await?;
     ensure_all_row_ids_resolved(column, requests.len(), payloads.len())?;
 
     let mut builder = LargeBinaryBuilder::new();
@@ -462,8 +434,7 @@ pub(crate) async fn take_blobs_aligned(
         .with_row_ids(row_ids.to_vec())
         .preserve_order(true)
         .execute()
-        .await
-        .map_err(|err| map_blob_take_error(column, row_ids.len(), err))?;
+        .await?;
     ensure_all_row_ids_resolved(column, row_ids.len(), payloads.len())?;
 
     let mut builder = LargeBinaryBuilder::new();
@@ -487,10 +458,7 @@ pub(crate) async fn take_blob_files_aligned(
         return Ok(Vec::new());
     }
 
-    let handles = dataset
-        .take_blobs(row_ids, column)
-        .await
-        .map_err(|err| map_blob_take_error(column, row_ids.len(), err))?;
+    let handles = dataset.take_blobs(row_ids, column).await?;
     ensure_all_row_ids_resolved(column, row_ids.len(), handles.len())?;
     Ok(handles
         .into_iter()
@@ -532,27 +500,10 @@ mod tests {
     fn storage_version_bumps_to_v2_2() {
         let mut params = WriteParams::default();
         ensure_blob_storage_version(&blob_schema(), &mut params);
-        let resolved = params
-            .data_storage_version
-            .unwrap_or(LanceFileVersion::Stable)
-            .resolve();
-        assert_eq!(resolved, ConcreteFileVersion::V2_2);
-        assert!(!params.enable_stable_row_ids);
-    }
-
-    #[test]
-    fn storage_version_leaves_stable_row_ids_enabled() {
-        let mut params = WriteParams {
-            enable_stable_row_ids: true,
-            ..Default::default()
-        };
-        ensure_blob_storage_version(&blob_schema(), &mut params);
-        assert!(params.enable_stable_row_ids);
-        let resolved = params
-            .data_storage_version
-            .unwrap_or(LanceFileVersion::Stable)
-            .resolve();
-        assert_eq!(resolved, ConcreteFileVersion::V2_2);
+        assert_eq!(
+            params.data_storage_version.unwrap().resolve(),
+            ConcreteFileVersion::V2_2
+        );
     }
 
     #[test]
@@ -625,6 +576,5 @@ mod tests {
         let mut params = WriteParams::default();
         ensure_blob_storage_version(&schema, &mut params);
         assert!(params.data_storage_version.is_none());
-        assert!(!params.enable_stable_row_ids);
     }
 }

rust/lancedb/src/connection.rs

@@ -23,18 +23,15 @@ use crate::connection::create_table::CreateTableBuilder;
 use crate::data::scannable::Scannable;
 use crate::database::listing::ListingDatabase;
 use crate::database::{
-    CloneTableRequest, Database, DatabaseOptions, JobInfo, OpenTableRequest, ReadConsistency,
-    TableNamesRequest,
+    CloneTableRequest, Database, DatabaseOptions, JobDescription, JobInfo, OpenTableRequest,
+    ReadConsistency, TableNamesRequest,
 };
 use crate::embeddings::{EmbeddingRegistry, MemoryRegistry};
 use crate::error::{Error, Result};
 #[cfg(feature = "remote")]
 use crate::remote::{
     client::ClientConfig,
-    db::{
-        OPT_REMOTE_API_KEY, OPT_REMOTE_HOST_OVERRIDE, OPT_REMOTE_REGION,
-        OPT_REMOTE_SQL_HOST_OVERRIDE,
-    },
+    db::{OPT_REMOTE_API_KEY, OPT_REMOTE_HOST_OVERRIDE, OPT_REMOTE_REGION},
 };
 use lance::io::ObjectStoreParams;
 pub use lance_file::version::LanceFileVersion;
@@ -325,43 +322,6 @@ pub struct CloneTableBuilder {
     request: CloneTableRequest,
 }
 
-/// Builder for asynchronously executing a SQL statement on a remote database.
-pub struct ExecuteQueryAsyncBuilder {
-    parent: Arc<dyn Database>,
-    query: String,
-    default_namespace_path: Vec<String>,
-}
-
-impl ExecuteQueryAsyncBuilder {
-    fn new(parent: Arc<dyn Database>, query: String) -> Self {
-        Self {
-            parent,
-            query,
-            default_namespace_path: vec!["public".to_string()],
-        }
-    }
-
-    /// Set the namespace used for unqualified table names.
-    ///
-    /// An empty path is treated as `public`, which is the SQL name for the
-    /// root Lance namespace.
-    pub fn default_namespace_path<I, S>(mut self, path: I) -> Self
-    where
-        I: IntoIterator<Item = S>,
-        S: Into<String>,
-    {
-        self.default_namespace_path = path.into_iter().map(Into::into).collect();
-        self
-    }
-
-    /// Start the statement and return its asynchronous query handle.
-    pub async fn execute(self) -> Result<crate::sql::Query> {
-        self.parent
-            .execute_query_async(&self.query, &self.default_namespace_path)
-            .await
-    }
-}
-
 impl CloneTableBuilder {
     fn new(parent: Arc<dyn Database>, target_table_name: String, source_uri: String) -> Self {
         Self {
@@ -445,51 +405,6 @@ impl Connection {
         &self.internal
     }
 
-    /// Start executing SQL on a remote LanceDB database.
-    ///
-    /// The query can reference tables in other databases with SQL dot notation.
-    /// Use [`ExecuteQueryAsyncBuilder::default_namespace_path`] to avoid qualifying
-    /// tables in the default namespace. Local connections return
-    /// [`Error::NotSupported`].
-    ///
-    /// # Example
-    ///
-    /// ```no_run
-    /// # async fn query(db: &lancedb::Connection) -> lancedb::Result<()> {
-    /// use futures::TryStreamExt;
-    ///
-    /// let query = db
-    ///     .execute_query_async("SELECT * FROM events LIMIT 10")
-    ///     .default_namespace_path(["public"])
-    ///     .execute()
-    ///     .await?;
-    /// println!("query id: {}", query.id());
-    /// let mut batches = query.reader().await?;
-    /// while let Some(batch) = batches.try_next().await? {
-    ///     println!("received {} rows", batch.num_rows());
-    /// }
-    /// # Ok(())
-    /// # }
-    /// ```
-    pub fn execute_query_async(&self, query: impl Into<String>) -> ExecuteQueryAsyncBuilder {
-        ExecuteQueryAsyncBuilder::new(self.internal.clone(), query.into())
-    }
-
-    /// Describe a submitted SQL query by its connection-scoped id.
-    ///
-    /// This performs one bounded status poll using state retained by this
-    /// connection. Running state with a live query handle is not evicted;
-    /// abandoned state has bounded retention, and server expiration is
-    /// honored. Terminal state is retained briefly.
-    /// Query ids are not portable to another connection. Local connections
-    /// return [`Error::NotSupported`].
-    pub async fn describe_query(
-        &self,
-        query_id: uuid::Uuid,
-    ) -> Result<crate::sql::QueryDescription> {
-        self.internal.describe_query(query_id).await
-    }
-
     /// Get the names of all tables in the database
     ///
     /// The names will be returned in lexicographical order (ascending)
@@ -608,43 +523,6 @@ impl Connection {
             .await
     }
 
-    /// List every published immutable Function version in the remote catalog.
-    ///
-    /// Results are ordered by Function name then version. The client walks all
-    /// server pages before returning. Local databases return
-    /// [`Error::NotSupported`].
-    ///
-    /// # Example
-    ///
-    /// ```no_run
-    /// # async fn list_functions(
-    /// #     connection: &lancedb::Connection,
-    /// # ) -> Result<(), Box<dyn std::error::Error>> {
-    /// 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
-    }
-
-    /// Drop one exact immutable Function version from the remote catalog.
-    ///
-    /// Returns `true` when the server appended a Dropped transition and
-    /// `false` for an idempotent replay. Local databases return
-    /// [`Error::NotSupported`].
-    pub async fn drop_function(
-        &self,
-        name: impl AsRef<str>,
-        version: impl AsRef<str>,
-    ) -> Result<bool> {
-        self.internal
-            .drop_function(name.as_ref(), version.as_ref())
-            .await
-    }
-
     /// Rename a table in the database.
     ///
     /// This is only supported in LanceDB Cloud.
@@ -670,34 +548,14 @@ impl Connection {
         self.internal.read_consistency().await
     }
 
-    /// Open a server-side job by id, returning a handle with its record
-    /// already populated. Fails with [`crate::Error::JobNotFound`] when the
-    /// server has no such job, the way [`Connection::open_table`] does for a
-    /// missing table.
+    /// A [`crate::job::Job`] handle for a server-side job by id, suitable for
+    /// waiting on or cancelling the job.
     ///
-    /// This is the one way in: the returned [`crate::job::Job`] answers for
-    /// its own state, specification, result, failure and event history, so
-    /// there is no separate connection-level call for any of them.
-    ///
-    /// # Example
-    ///
-    /// ```no_run
-    /// # use lancedb::job::JobEventsRequest;
-    /// # async fn open_job(
-    /// #     connection: &lancedb::Connection,
-    /// #     job_id: &str,
-    /// # ) -> Result<(), Box<dyn std::error::Error>> {
-    /// let job = connection.open_job(job_id).await?;
-    /// println!("{:?} {:?}", job.state(), job.result());
-    /// let done = job
-    ///     .events(JobEventsRequest::default().filter("state = 'claim_complete'"))
-    ///     .await?;
-    /// println!("{} completions", done.iter().map(|b| b.num_rows()).sum::<usize>());
-    /// # Ok(())
-    /// # }
-    /// ```
-    pub async fn open_job(&self, job_id: impl AsRef<str>) -> Result<crate::job::Job> {
-        self.internal.open_job(job_id.as_ref()).await
+    /// The handle is constructed without a server round trip; an unknown id
+    /// surfaces when the handle is used. Only server-backed databases support
+    /// job handles by id.
+    pub fn job(&self, job_id: impl AsRef<str>) -> Result<crate::job::Job> {
+        self.internal.job(job_id.as_ref())
     }
 
     /// List server-side jobs across the database's tables.
@@ -705,12 +563,24 @@ impl Connection {
         self.internal.list_jobs().await
     }
 
+    /// Describe a single server-side job by id. `None` when the server has no
+    /// such job.
+    pub async fn get_job(&self, job_id: impl AsRef<str>) -> Result<Option<JobDescription>> {
+        self.internal.get_job(job_id.as_ref()).await
+    }
+
     /// Request cancellation of a server-side job by id. Returns true if the
     /// server accepted the cancellation, false if no such job exists.
     pub async fn cancel_job(&self, job_id: impl AsRef<str>) -> Result<bool> {
         self.internal.cancel_job(job_id.as_ref()).await
     }
 
+    /// The lifecycle event history of a server-side job (all jobs when
+    /// `job_id` is `None`), as recorded Arrow batches.
+    pub async fn job_history(&self, job_id: Option<&str>) -> Result<Vec<RecordBatch>> {
+        self.internal.job_history(job_id).await
+    }
+
     /// Drop a table in the database.
     ///
     /// # Arguments
@@ -827,7 +697,7 @@ impl Connection {
 pub struct ConnectRequest {
     /// Database URI
     ///
-    /// ### Accepted URI formats
+    /// ### Accpeted URI formats
     ///
     /// - `/path/to/database` - local database on file system.
     /// - `s3://bucket/path/to/database` or `gs://bucket/path/to/database` - database on cloud object store
@@ -957,19 +827,6 @@ impl ConnectBuilder {
         self
     }
 
-    /// Set the SQL service host override for a remote connection.
-    ///
-    /// The SQL client is initialized lazily when the connection first executes
-    /// SQL and is retained for the connection's lifetime.
-    #[cfg(feature = "remote")]
-    pub fn sql_host_override(mut self, sql_host_override: &str) -> Self {
-        self.request.options.insert(
-            OPT_REMOTE_SQL_HOST_OVERRIDE.to_string(),
-            sql_host_override.to_string(),
-        );
-        self
-    }
-
     /// Set the database specific options
     ///
     /// See [crate::database::listing::ListingDatabaseOptions] for the options available for
@@ -1159,7 +1016,6 @@ impl ConnectBuilder {
 
         let mut merged_options = self.request.options.clone();
         Self::apply_env_defaults(&ENV_VARS_TO_STORAGE_OPTS, &mut merged_options);
-        let sql_host_override = merged_options.get(OPT_REMOTE_SQL_HOST_OVERRIDE).cloned();
         let options = RemoteDatabaseOptions::parse_from_map(&merged_options)?;
 
         let region = options.region.ok_or_else(|| Error::InvalidInput {
@@ -1201,15 +1057,11 @@ impl ConnectBuilder {
         }
 
         let storage_options = StorageOptions(options.storage_options.clone());
-        let host_overrides = crate::remote::db::RemoteHostOverrides {
-            rest: options.host_override,
-            sql: sql_host_override,
-        };
         let internal = Arc::new(crate::remote::db::RemoteDatabase::try_new(
             &self.request.uri,
             &api_key,
             &region,
-            host_overrides,
+            options.host_override,
             client_config,
             storage_options.into(),
             self.request.read_consistency_interval,
@@ -1503,23 +1355,6 @@ mod tests {
         assert_eq!(tc.connection.uri(), tc.uri);
     }
 
-    #[tokio::test]
-    async fn test_local_connection_rejects_sql_queries() {
-        let directory = tempdir().unwrap();
-        let connection = connect(directory.path().to_str().unwrap())
-            .execute()
-            .await
-            .unwrap();
-        assert!(matches!(
-            connection.execute_query_async("SELECT 1").execute().await,
-            Err(Error::NotSupported { .. })
-        ));
-        assert!(matches!(
-            connection.describe_query(uuid::Uuid::nil()).await,
-            Err(Error::NotSupported { .. })
-        ));
-    }
-
     #[cfg(feature = "remote")]
     #[test]
     fn test_apply_env_defaults() {

rust/lancedb/src/database.rs

@@ -18,6 +18,8 @@ use std::collections::HashMap;
 use std::sync::Arc;
 use std::time::Duration;
 
+use arrow_array::RecordBatch;
+
 use lance::dataset::ReadParams;
 use lance_namespace::LanceNamespace;
 use lance_namespace::models::{
@@ -204,8 +206,8 @@ pub enum ReadConsistency {
 /// compaction, column refresh, ...).
 #[derive(Debug, Clone)]
 pub struct JobInfo {
-    /// The job id -- what [`Database::open_job`] and
-    /// [`Database::cancel_job`] accept.
+    /// The job id -- what [`Database::get_job`] and [`Database::cancel_job`]
+    /// accept.
     pub job_id: String,
     /// The table the job runs against, without URI or namespace.
     pub table: String,
@@ -216,8 +218,8 @@ pub struct JobInfo {
     pub created_at_millis: i64,
 }
 
-/// The server-side record behind a [`crate::job::Job`] handle: lifecycle
-/// state plus the job-type-specific specification and result.
+/// A described job from [`Database::get_job`]: lifecycle state plus the
+/// job-type-specific specification.
 #[derive(Debug, Clone)]
 pub struct JobDescription {
     pub job_id: String,
@@ -228,10 +230,6 @@ pub struct JobDescription {
     pub creation_ms: i64,
     /// The job-type-specific specification. Null when the server omits it.
     pub spec: serde_json::Value,
-    /// The job-type-specific terminal result, for job types that define one.
-    /// `None` until the job succeeds, so a job that never terminates reports
-    /// its progress through [`crate::job::Job::events`] instead.
-    pub result: Option<serde_json::Value>,
     /// Why the job failed, when the job is failed and the server reports a
     /// reason.
     pub failure: Option<crate::error::JobFailure>,
@@ -309,45 +307,30 @@ pub trait Database:
     ) -> 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>> {
-        function_catalog_not_supported()
-    }
-    /// Drop one exact immutable Function version from the remote catalog.
-    async fn drop_function(&self, _name: &str, _version: &str) -> Result<bool> {
-        function_catalog_not_supported()
-    }
-    /// Open a job by id, returning a handle with its record already
-    /// populated. Fails with [`crate::Error::JobNotFound`] when the server has
-    /// no such job.
-    async fn open_job(&self, _job_id: &str) -> Result<crate::job::Job> {
-        job_op_not_supported("open_job")
+    /// A [`crate::job::Job`] handle for a server-side job by id, suitable for
+    /// waiting on or cancelling the job. The handle is constructed without a
+    /// server round trip; an unknown id surfaces when the handle is used.
+    fn job(&self, _job_id: &str) -> Result<crate::job::Job> {
+        job_op_not_supported("job")
     }
     /// List server-side jobs across the database's tables.
     async fn list_jobs(&self) -> Result<Vec<JobInfo>> {
         job_op_not_supported("list_jobs")
     }
+    /// Describe a single job by id. `None` when the server has no such job.
+    async fn get_job(&self, _job_id: &str) -> Result<Option<JobDescription>> {
+        job_op_not_supported("get_job")
+    }
     /// Request cancellation of a job by id. Returns true if the server
     /// accepted the cancellation, false if no such job exists. Cancelling an
     /// already-terminal job is a no-op success.
     async fn cancel_job(&self, _job_id: &str) -> Result<bool> {
         job_op_not_supported("cancel_job")
     }
-    /// Start executing a SQL statement on a remote database.
-    async fn execute_query_async(
-        &self,
-        _query: &str,
-        _default_namespace_path: &[String],
-    ) -> Result<crate::sql::Query> {
-        Err(crate::error::Error::NotSupported {
-            message: "SQL is not supported by this database".to_string(),
-        })
-    }
-    /// Describe a submitted SQL query by its connection-scoped id.
-    async fn describe_query(&self, _query_id: uuid::Uuid) -> Result<crate::sql::QueryDescription> {
-        Err(crate::error::Error::NotSupported {
-            message: "SQL is not supported by this database".to_string(),
-        })
+    /// The lifecycle event history of a job (all jobs when `job_id` is
+    /// `None`), as recorded Arrow batches.
+    async fn job_history(&self, _job_id: Option<&str>) -> Result<Vec<RecordBatch>> {
+        job_op_not_supported("job_history")
     }
     /// Open a table in the database
     async fn open_table(&self, request: OpenTableRequest) -> Result<Arc<dyn BaseTable>>;

rust/lancedb/src/database/listing.rs

@@ -13,12 +13,12 @@ use lance::dataset::{ReadParams, WriteMode, builder::DatasetBuilder};
 use lance::io::{ObjectStore, ObjectStoreParams, WrappingObjectStore};
 use lance_datafusion::utils::StreamingWriteSource;
 use lance_file::version::LanceFileVersion;
-use lance_io::object_store::{ReadDirOptions, StorageOptionsAccessor, StorageOptionsProvider};
+use lance_io::object_store::{StorageOptionsAccessor, StorageOptionsProvider};
 use lance_table::io::commit::commit_handler_from_url;
 use object_store::local::LocalFileSystem;
 use snafu::ResultExt;
 
-use crate::blob::ensure_blob_storage_version;
+use crate::blob::{ensure_blob_storage_version, has_blob_columns};
 use crate::connection::ConnectRequest;
 use crate::database::ReadConsistency;
 use crate::database::namespace::LanceNamespaceDatabase;
@@ -282,14 +282,11 @@ impl std::fmt::Display for ListingDatabase {
 
 const LANCE_EXTENSION: &str = "lance";
 
-/// The table a listed child of the database names, or `None` if the child is not a table.
+/// The table a listed child directory holds, or `None` if it is not a table at all.
 ///
 /// A table is the directory `<name>.lance`; a loose file or any other directory under the
 /// database prefix belongs to something else. `dir_suffix` is `.lance`, built once by the
 /// caller rather than per child.
-/// The table a listed child directory holds, or `None` if it is not a table at all.
-///
-/// Only directories are considered, so a loose object named like a table is not one.
 fn table_name(location: &object_store::path::Path, dir_suffix: &str) -> Option<String> {
     location
         .filename()?
@@ -297,6 +294,75 @@ fn table_name(location: &object_store::path::Path, dir_suffix: &str) -> Option<S
         .map(String::from)
         .filter(|name| !name.is_empty())
 }
+
+/// One page of the table directories under the database directory, in key order.
+struct DirPage {
+    /// The table directories the page holds, as the store lists them.
+    common_prefixes: Vec<object_store::path::Path>,
+    /// Resumes after this page, or `None` when the page reached the end of the level.
+    page_token: Option<String>,
+}
+
+/// Where a listed location sits inside the database directory — the space page tokens live
+/// in — or `None` if it is not a child of that directory at all. Matching both halves of the
+/// prefix drops a location that merely starts with the directory's name (`dbx/y` against
+/// `db/`) as well as the marker object some stores keep for the directory itself.
+fn relative_key<'a>(prefix: Option<&str>, location: &'a str) -> Option<&'a str> {
+    let relative = match prefix {
+        Some(prefix) => location.strip_prefix(prefix)?,
+        None => location,
+    };
+    (!relative.is_empty()).then_some(relative)
+}
+
+/// One page of the table directories under `base_path`, one directory level deep.
+///
+/// Lance 11 exposes no paginated directory listing, so the level is listed in full and paged
+/// locally: table directories go into key order (a directory's key keeps its trailing `/`,
+/// so a token is never a table name), the page is the smallest `limit` of them past
+/// `page_token`, and the token handed back is the key of the last directory the page took —
+/// so a page that took nothing ends the listing rather than resuming from a position no page
+/// ever reached. Only `<name>.lance/` directories enter the page: loose objects, other
+/// directories, and a bare `.lance/` never take a page slot or name a token, which keeps a
+/// page to exactly one listing of the level. Correct on every store, at the cost of that one
+/// full-level listing per page.
+async fn read_dir_page(
+    object_store: &ObjectStore,
+    base_path: &object_store::path::Path,
+    page_token: Option<String>,
+    limit: Option<usize>,
+) -> Result<DirPage> {
+    let listed = object_store.list_with_delimiter(Some(base_path)).await?;
+    let prefix = {
+        let base = base_path.as_ref();
+        (!base.is_empty()).then(|| format!("{base}/"))
+    };
+    let table_dir_suffix = format!(".{LANCE_EXTENSION}/");
+    let mut children: Vec<(String, object_store::path::Path)> = listed
+        .common_prefixes
+        .into_iter()
+        .filter_map(|location| {
+            let key = format!("{}/", relative_key(prefix.as_deref(), location.as_ref())?);
+            (key.len() > table_dir_suffix.len() && key.ends_with(&table_dir_suffix))
+                .then_some((key, location))
+        })
+        .collect();
+    children.sort_unstable_by(|(left, _), (right, _)| left.cmp(right));
+    if let Some(resume) = &page_token {
+        children.retain(|(key, _)| key > resume);
+    }
+    let total = children.len();
+    children.truncate(limit.unwrap_or(total).min(total));
+    let page_token = match children.last() {
+        Some((last, _)) if children.len() < total => Some(last.clone()),
+        _ => None,
+    };
+    Ok(DirPage {
+        common_prefixes: children.into_iter().map(|(_, location)| location).collect(),
+        page_token,
+    })
+}
+
 const ENGINE: &str = "engine";
 const MIRRORED_STORE: &str = "mirroredStore";
 
@@ -512,7 +578,7 @@ impl ListingDatabase {
                 // iter thru the query params and extract the commit store param
                 let mut engine = None;
                 let mut mirrored_store = None;
-                let mut filtered_queries = vec![];
+                let mut filtered_querys = vec![];
 
                 // WARNING: specifying engine is NOT a publicly supported feature in lancedb yet
                 // THE API WILL CHANGE
@@ -528,13 +594,13 @@ impl ListingDatabase {
                         mirrored_store = Some(value.to_string());
                     } else {
                         // to owned so we can modify the url
-                        filtered_queries.push((key.to_string(), value.to_string()));
+                        filtered_querys.push((key.to_string(), value.to_string()));
                     }
                 }
 
                 // Filter out the commit store query param -- it's a lancedb param
                 url.query_pairs_mut().clear();
-                url.query_pairs_mut().extend_pairs(filtered_queries);
+                url.query_pairs_mut().extend_pairs(filtered_querys);
                 // Take a copy of the query string so we can propagate it to lance.
                 // `query_pairs_mut()` leaves the URL with `Some("")` even when no
                 // pairs survive (or none existed in the first place), so an empty
@@ -827,6 +893,7 @@ impl ListingDatabase {
         if let Some(enable_stable_row_ids) = overrides
             .enable_stable_row_ids
             .or(self.new_table_config.enable_stable_row_ids)
+            .or(has_blob_columns(&data_schema).then_some(true))
         {
             write_params.enable_stable_row_ids = enable_stable_row_ids;
         }
@@ -896,11 +963,11 @@ impl Database for ListingDatabase {
     }
 
     async fn read_consistency(&self) -> Result<ReadConsistency> {
-        if let Some(interval) = self.read_consistency_interval {
-            if interval.is_zero() {
+        if let Some(read_consistency_inverval) = self.read_consistency_interval {
+            if read_consistency_inverval.is_zero() {
                 Ok(ReadConsistency::Strong)
             } else {
-                Ok(ReadConsistency::Eventual(interval))
+                Ok(ReadConsistency::Eventual(read_consistency_inverval))
             }
         } else {
             Ok(ReadConsistency::Manual)
@@ -981,8 +1048,7 @@ impl Database for ListingDatabase {
         let mut tables = Vec::new();
         let mut page_token = request.page_token.filter(|token| !token.is_empty());
 
-        // A page of nothing: the store rejects a limit of zero, and no table was handed over
-        // for a token to resume after.
+        // A page of nothing: no table was handed over for a token to resume after.
         if limit == Some(0) {
             return Ok(ListTablesResponse {
                 context: None,
@@ -991,35 +1057,21 @@ impl Database for ListingDatabase {
             });
         }
 
-        loop {
-            // Ask only for what the page still has room for, so a database holding more
-            // than one page costs one request per page rather than one per table.
-            let listing = self
-                .object_store
-                .read_dir_page(
-                    self.base_path.clone(),
-                    ReadDirOptions {
-                        page_token: page_token.take(),
-                        limit: limit.map(|limit| limit - tables.len()),
-                    },
-                )
-                .await?;
-            page_token = listing.page_token;
-            // Only child directories can be tables, and the store already separates them
-            // out, so the objects in the page are not looked at.
-            tables.extend(
-                listing
-                    .result
-                    .common_prefixes
-                    .iter()
-                    .filter_map(|location| table_name(location, &dir_suffix)),
-            );
-            // Children that are not tables leave the page short of the limit, so keep
-            // going until the page is full or the database runs out.
-            if page_token.is_none() || limit.is_none_or(|limit| tables.len() >= limit) {
-                break;
-            }
-        }
+        // The page holds only table directories, so one call — and the one full-level
+        // listing behind it — fills it.
+        let page = read_dir_page(
+            &self.object_store,
+            &self.base_path,
+            page_token.take(),
+            limit,
+        )
+        .await?;
+        page_token = page.page_token;
+        tables.extend(
+            page.common_prefixes
+                .iter()
+                .filter_map(|location| table_name(location, &dir_suffix)),
+        );
 
         Ok(ListTablesResponse {
             context: None,
@@ -1665,8 +1717,8 @@ mod tests {
     }
 
     /// Only directories named `<name>.lance` are tables; loose files and other directories
-    /// under the database prefix are not. A page spent on them is filled from the next one,
-    /// so a page holding only non-tables does not read as an empty database.
+    /// under the database prefix are not. They never take a page slot, so even a `limit`
+    /// smaller than the clutter ahead of the first table returns that table.
     #[tokio::test]
     async fn test_listing_ignores_non_table_children() {
         let (tempdir, db) = setup_database().await;
@@ -1685,6 +1737,37 @@ mod tests {
         assert_eq!(page.tables, vec!["real"]);
     }
 
+    /// The Lance 11 fallback pages locally over one full-level listing, so a bounded page
+    /// costs exactly one listing call — clutter ahead of the first table must not buy extra
+    /// round trips.
+    #[tokio::test]
+    async fn test_one_full_listing_per_public_page() {
+        use crate::io::object_store::io_tracking::IoStatsHolder;
+        use lance_io::object_store::WrappingObjectStore;
+
+        let (tempdir, mut db) = setup_database().await;
+        create_tables(&db, &["real"]).await;
+        std::fs::write(tempdir.path().join("aaa-loose.lance"), b"not a table").unwrap();
+        create_dir_all(tempdir.path().join("aaa-scratch")).unwrap();
+
+        let io_stats = IoStatsHolder::default();
+        let mut tracked_store = (*db.object_store).clone();
+        tracked_store.inner =
+            io_stats.wrap(&tracked_store.store_prefix, tracked_store.inner.clone());
+        db.object_store = Arc::new(tracked_store);
+
+        let page = db
+            .list_tables(ListTablesRequest {
+                limit: Some(1),
+                ..Default::default()
+            })
+            .await
+            .unwrap();
+
+        assert_eq!(page.tables, vec!["real"]);
+        assert_eq!(io_stats.incremental_stats().read_iops, 1);
+    }
+
     #[tokio::test]
     async fn listing_ignores_empty_table_name() {
         let (tempdir, db) = setup_database().await;
@@ -3043,15 +3126,15 @@ mod tests {
     /// across platforms — see the `file://` test below).
     fn capture_query_like_connect(input_uri: &str) -> Option<String> {
         let mut url = url::Url::parse(input_uri).unwrap();
-        let mut filtered_queries = Vec::new();
+        let mut filtered_querys = Vec::new();
         for (key, value) in url.query_pairs() {
             if key == ENGINE || key == MIRRORED_STORE {
                 continue;
             }
-            filtered_queries.push((key.to_string(), value.to_string()));
+            filtered_querys.push((key.to_string(), value.to_string()));
         }
         url.query_pairs_mut().clear();
-        url.query_pairs_mut().extend_pairs(filtered_queries);
+        url.query_pairs_mut().extend_pairs(filtered_querys);
         url.query().filter(|q| !q.is_empty()).map(|s| s.to_string())
     }
 

rust/lancedb/src/database/namespace.rs

@@ -3,7 +3,6 @@
 
 //! Namespace-based database implementation that delegates table management to lance-namespace
 
-use lance_datafusion::utils::StreamingWriteSource;
 use std::collections::{HashMap, HashSet};
 use std::sync::{Arc, Mutex};
 
@@ -24,7 +23,7 @@ use lance_namespace_impls::ConnectBuilder;
 use lance_table::io::commit::CommitHandler;
 use lance_table::io::commit::external_manifest::ExternalManifestCommitHandler;
 
-use crate::blob::ensure_blob_storage_version;
+use crate::blob::{ensure_blob_storage_version, has_blob_columns};
 use crate::connection::NamespaceClientPushdownOperation;
 use crate::database::ReadConsistency;
 use crate::database::listing::{NewTableConfig, take_request_creation_overrides};
@@ -218,6 +217,7 @@ impl LanceNamespaceDatabase {
         if let Some(enable_stable_row_ids) = overrides
             .enable_stable_row_ids
             .or(self.new_table_config.enable_stable_row_ids)
+            .or(has_blob_columns(data_schema.as_ref()).then_some(true))
         {
             params.enable_stable_row_ids = enable_stable_row_ids;
         }
@@ -251,11 +251,11 @@ impl Database for LanceNamespaceDatabase {
     }
 
     async fn read_consistency(&self) -> Result<ReadConsistency> {
-        if let Some(interval) = self.read_consistency_interval {
-            if interval.is_zero() {
+        if let Some(read_consistency_inverval) = self.read_consistency_interval {
+            if read_consistency_inverval.is_zero() {
                 Ok(ReadConsistency::Strong)
             } else {
-                Ok(ReadConsistency::Eventual(interval))
+                Ok(ReadConsistency::Eventual(read_consistency_inverval))
             }
         } else {
             Ok(ReadConsistency::Manual)
@@ -305,10 +305,6 @@ impl Database for LanceNamespaceDatabase {
     }
 
     async fn create_table(&self, request: DbCreateTableRequest) -> Result<Arc<dyn BaseTable>> {
-        // Refuse a bad declaration before the namespace records a table.
-        crate::table::computed_columns::ensure_declarations_are_planned(
-            &request.data.arrow_schema(),
-        )?;
         let mut table_id = request.namespace_path.clone();
         table_id.push(request.name.clone());
         let mut existing_table = None;
@@ -543,7 +539,9 @@ impl Database for LanceNamespaceDatabase {
         self.namespace
             .drop_table(drop_request)
             .await
-            .map_err(|e| map_namespace_lance_error(e, name))?;
+            .map_err(|e| Error::Runtime {
+                message: format!("Failed to drop table: {}", e),
+            })?;
 
         Ok(())
     }
@@ -1497,15 +1495,6 @@ mod tests {
             .expect("Failed to list tables");
         assert!(!table_names_after.contains(&"drop_test".to_string()));
 
-        let error = conn
-            .drop_table("drop_test", &["test_ns".into()])
-            .await
-            .expect_err("dropping a missing table should fail");
-        assert!(
-            matches!(error, Error::TableNotFound { ref name, .. } if name == "drop_test"),
-            "expected TableNotFound, got: {error:?}"
-        );
-
         // Verify: Cannot open dropped table
         let open_result = conn.open_table("drop_test").execute().await;
         assert!(open_result.is_err());

rust/lancedb/src/dataloader/permutation/reader.rs

@@ -31,7 +31,7 @@ use lance::io::RecordBatchStream;
 use lance_arrow::RecordBatchExt;
 use lance_core::ROW_ID;
 use lance_core::error::LanceOptionExt;
-use std::collections::{HashMap, HashSet};
+use std::collections::HashMap;
 use std::sync::Arc;
 
 /// Reads a permutation of a source table based on row IDs stored in a separate table
@@ -234,14 +234,7 @@ impl PermutationReader {
             .expect_ok()?
             .values();
 
-        let mut unique_row_ids = HashSet::with_capacity(num_rows);
-        let in_list: Vec<Expr> = row_ids
-            .iter()
-            .copied()
-            .filter(|row_id| unique_row_ids.insert(*row_id))
-            .map(lit)
-            .collect();
-        let num_unique_row_ids = unique_row_ids.len();
+        let in_list: Vec<Expr> = row_ids.iter().map(|id| lit(*id)).collect();
 
         let base_query = QueryRequest {
             filter: Some(QueryFilter::Datafusion(col(ROW_ID).in_list(in_list, false))),
@@ -254,7 +247,7 @@ impl PermutationReader {
             .query(
                 &AnyQuery::Query(base_query),
                 QueryExecutionOptions {
-                    max_batch_length: num_unique_row_ids as u32,
+                    max_batch_length: num_rows as u32,
                     ..Default::default()
                 },
             )
@@ -269,9 +262,9 @@ impl PermutationReader {
             });
         }
 
-        if batches.iter().map(|b| b.num_rows()).sum::<usize>() != num_unique_row_ids {
+        if batches.iter().map(|b| b.num_rows()).sum::<usize>() != num_rows {
             return Err(Error::InvalidInput {
-                message: "Base table returned a different number of rows than the number of unique row IDs"
+                message: "Base table returned different number of rows than the number of row IDs"
                     .to_string(),
             });
         }
@@ -511,7 +504,6 @@ impl PermutationReader {
             let table = Table::from(self.base_table.clone());
             let batches = table
                 .take_offsets(offsets.to_vec())
-                .preserve_order()
                 .select(selection.clone())
                 .execute()
                 .await?
@@ -811,10 +803,10 @@ mod tests {
         .unwrap();
 
         // Take offsets in reverse order and verify returned rows match that order
-        let offsets = vec![5, 3, 5, 1, 0];
+        let offsets = vec![5, 3, 1, 0];
         let batch = reader.take_offsets(&offsets, Select::All).await.unwrap();
 
-        assert_eq!(batch.num_rows(), 5);
+        assert_eq!(batch.num_rows(), 4);
 
         let idx_values = batch
             .column(0)
@@ -828,52 +820,6 @@ mod tests {
         assert_eq!(idx_values, expected);
     }
 
-    #[tokio::test]
-    async fn test_take_offsets_preserves_repeated_rows_in_permutation() {
-        let base_table = lance_datagen::gen_batch()
-            .col("idx", lance_datagen::array::step::<Int32Type>())
-            .into_mem_table("tbl", RowCount::from(5), BatchCount::from(1))
-            .await;
-        let base_row_ids = collect_column::<UInt64Type>(&base_table, "_rowid").await;
-        let permutation_row_ids = vec![
-            base_row_ids[3],
-            base_row_ids[1],
-            base_row_ids[3],
-            base_row_ids[2],
-        ];
-        let permutation_batch = RecordBatch::try_new(
-            Arc::new(Schema::new(vec![
-                Field::new("row_id", DataType::UInt64, false),
-                Field::new(SPLIT_ID_COLUMN, DataType::UInt64, false),
-            ])),
-            vec![
-                Arc::new(UInt64Array::from(permutation_row_ids)),
-                Arc::new(UInt64Array::from(vec![0; 4])),
-            ],
-        )
-        .unwrap();
-        let permutation_table = virtual_table("row_ids", &permutation_batch).await;
-        let reader = PermutationReader::try_from_tables(
-            base_table.base_table().clone(),
-            permutation_table.base_table().clone(),
-            0,
-        )
-        .await
-        .unwrap();
-
-        let batch = reader
-            .take_offsets(&[0, 1, 2, 3], Select::All)
-            .await
-            .unwrap();
-        let idx_values = batch
-            .column(0)
-            .as_primitive::<Int32Type>()
-            .values()
-            .to_vec();
-
-        assert_eq!(idx_values, vec![3, 1, 3, 2]);
-    }
-
     #[tokio::test]
     async fn test_take_offsets_with_column_selection() {
         let (base_table, row_ids_table, row_ids) = setup_permutation_tables(10).await;
@@ -937,17 +883,17 @@ mod tests {
             .unwrap();
 
         // With no permutation table, take_offsets uses the base table directly
-        let offsets = vec![0, 2, 0, 4, 6];
+        let offsets = vec![0, 2, 4, 6];
         let batch = reader.take_offsets(&offsets, Select::All).await.unwrap();
 
-        assert_eq!(batch.num_rows(), 5);
+        assert_eq!(batch.num_rows(), 4);
 
         let idx_values = batch
             .column(0)
             .as_primitive::<Int32Type>()
             .values()
             .to_vec();
-        assert_eq!(idx_values, vec![0, 2, 0, 4, 6]);
+        assert_eq!(idx_values, vec![0, 2, 4, 6]);
     }
 
     #[tokio::test]

rust/lancedb/src/error.rs

@@ -102,8 +102,6 @@ pub enum Error {
     },
     #[snafu(display("Job{} was cancelled", job_id.as_ref().map(|id| format!(" {id}")).unwrap_or_default()))]
     JobCancelled { job_id: Option<String> },
-    #[snafu(display("Job '{job_id}' was not found"))]
-    JobNotFound { job_id: String },
 
     // 3rd party / external errors
     #[snafu(display("object_store error: {source}"))]

rust/lancedb/src/function.rs

@@ -582,8 +582,8 @@ pub struct InputBinding {
 
 /// Ordered result-field to table-field mapping for a Function binding.
 ///
-/// `nullable` describes the logical Function result. Physical computed-column
-/// fields remain nullable while unassigned.
+/// Assignment state is not part of the Slice 1 client contract. During the
+/// NULL transition there is no public Lance cell-flag identifier to persist.
 #[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
 pub struct OutputMapping {
     pub result_field: String,
@@ -594,14 +594,6 @@ pub struct OutputMapping {
     pub nullable: bool,
 }
 
-/// Internal physical column preserving the parent validity of a flattened
-/// named-struct result.
-#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
-pub struct AssignmentMapping {
-    pub output_name: String,
-    pub output_field_id: i32,
-}
-
 /// Immutable Function binding persisted by the Enterprise table service.
 #[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
 pub struct FunctionBinding {
@@ -609,8 +601,6 @@ pub struct FunctionBinding {
     function: FunctionVersionRef,
     inputs: Vec<InputBinding>,
     outputs: Vec<OutputMapping>,
-    #[serde(default, skip_serializing_if = "Option::is_none")]
-    assignment: Option<AssignmentMapping>,
     /// Exact Arrow schema presented to the Function, encoded with the Lance
     /// Namespace Arrow JSON representation.
     #[serde(default, skip_serializing_if = "Option::is_none")]
@@ -637,10 +627,6 @@ impl FunctionBinding {
         &self.outputs
     }
 
-    pub fn assignment(&self) -> Option<&AssignmentMapping> {
-        self.assignment.as_ref()
-    }
-
     pub fn input_schema(&self) -> Option<&Value> {
         self.input_schema.as_ref()
     }

rust/lancedb/src/index/vector.rs

@@ -125,7 +125,7 @@ macro_rules! impl_pq_params_setter {
         /// This value controls how much the vector is compressed during the quantization step.
         /// The more sub vectors there are the less the vector is compressed.  The default is
         /// the dimension of the vector divided by 16.  If the dimension is not evenly divisible
-        /// by 16 we use the dimension divided by 8.
+        /// by 16 we use the dimension divded by 8.
         ///
         /// The above two cases are highly preferred.  Having 8 or 16 values per subvector allows
         /// us to use efficient SIMD instructions.