Bump version: 0.32.0-beta.1 → 0.32.0-beta.2

2026-08-28 08:58:41 +00:00 · 2026-07-14 23:28:16 +00:00
227 changed files with 3683 additions and 21656 deletions
@@ -1,20 +0,0 @@
-{
-  "name": "lancedb",
-  "interface": {
-    "displayName": "LanceDB"
-  },
-  "plugins": [
-    {
-      "name": "lancedb",
-      "source": {
-        "source": "local",
-        "path": "./plugins/lancedb"
-      },
-      "policy": {
-        "installation": "AVAILABLE",
-        "authentication": "ON_INSTALL"
-      },
-      "category": "Developer Tools"
-    }
-  ]
-}
@@ -5,7 +5,3 @@ This directory contains repo-scoped code agent skills for the LanceDB project.
 Each skill is a folder that contains a required `SKILL.md` and optional bundled resources.

 Codex discovers skills from `.agents/skills` in the current working directory and parent directories.
-
-The `lancedb` skill lives in the `plugins/lancedb` plugin (see `plugins/lancedb/skills/lancedb`)
-so it can be installed via the plugin marketplaces (`.claude-plugin/marketplace.json` and
-`.agents/plugins/marketplace.json`); the `lancedb` entry here is a symlink into that plugin.
@@ -1 +0,0 @@
-../../plugins/lancedb/skills/lancedb
@@ -0,0 +1,145 @@
+---
+name: lancedb-branch-ops
+description: >-
+  Manage LanceDB table branches through the REST API: list, create, and delete
+  branches; target schema reads, field-metadata updates, and index creation to a
+  named branch; and verify that branch changes remain isolated from main. Use
+  when a task involves branch lifecycle, an experimental or isolated table
+  version, directing an operation to a non-main branch, or confirming that a
+  mutation did not affect main. This skill also explains that LanceDB has no
+  checkout operation; each request selects its target branch in the request
+  body.
+---
+
+## Goal
+
+Manage branches on a LanceDB table: list what exists, create new ones, delete stale ones, and direct read/write operations at a specific branch without touching main.
+
+## Step 0: Establish the connection
+
+Use the `lancedb-connect` skill to resolve the base URL and auth headers (`x-api-key`, `x-lancedb-database`). Skip this only if the connection is already known from the current conversation.
+
+All examples below use `{base_url}` — substitute the resolved endpoint and include the auth headers on every request.
+
+## The branch model (important)
+
+LanceDB branches are named snapshots that diverge from the table's current state at creation time. There is **no checkout command** — you never switch the whole table to a branch. Instead, you **pass `"branch": "<name>"` in the request body** of any operation to target that branch. Omitting the key (or sending an empty body) always targets main.
+
+`branches/list` returns only non-main branches. Main always exists and is not listed.
+
+## List branches
+
+```http
+POST {base_url}/v1/table/{table_id}/branches/list
+Content-Type: application/json
+
+{}
+```
+
+Response:
+```json
+{
+  "branches": {
+    "experiment-reindex": {"parentVersion": 1, "createAt": 1782506085, "manifestSize": 1029}
+  }
+}
+```
+
+If `branches` is `{}`, the table has no branches besides main.
+
+## Create a branch
+
+```http
+POST {base_url}/v1/table/{table_id}/branches/create
+Content-Type: application/json
+
+{"name": "experiment-reindex"}
+```
+
+HTTP 200 with `{}` body = success. The branch is created off the table's current state on main.
+
+Verify by calling `branches/list` and confirming the new name appears.
+
+## Delete a branch
+
+```http
+POST {base_url}/v1/table/{table_id}/branches/delete
+Content-Type: application/json
+
+{"name": "stale-2024"}
+```
+
+HTTP 200 with `{}` body = success. Only the branch pointer is removed — main and all row data remain intact.
+
+Verify by calling `branches/list` (name gone) and `describe` with no branch param (main still responds).
+
+## Operate on a specific branch
+
+Pass `"branch": "<name>"` in the body of any operation to scope it to that branch:
+
+**Read schema on a branch:**
+```http
+POST {base_url}/v1/table/{table_id}/describe
+Content-Type: application/json
+
+{"branch": "wip-branch"}
+```
+
+**Write metadata to a branch (not main):**
+```http
+POST {base_url}/v1/table/{table_id}/update_field_metadata
+Content-Type: application/json
+
+{
+  "branch": "wip-branch",
+  "updates": [
+    {
+      "path": "category",
+      "metadata": {"lancedb:description": "Product category label."},
+      "replace": false
+    }
+  ]
+}
+```
+
+**Build an index on a branch:**
+```http
+POST {base_url}/v1/table/{table_id}/create_index
+Content-Type: application/json
+
+{
+  "branch": "wip-branch",
+  "column": "category",
+  "index_type": "BTREE"
+}
+```
+
+## Verifying isolation
+
+After writing to a branch, always confirm the change did NOT land on main:
+
+```bash
+# Should show the new metadata
+curl -s -X POST {base_url}/v1/table/{table_id}/describe \
+  -H "x-api-key: <key>" -H "x-lancedb-database: <db>" \
+  -H "content-type: application/json" \
+  -d '{"branch": "wip-branch"}'
+
+# Should NOT show the new metadata
+curl -s -X POST {base_url}/v1/table/{table_id}/describe \
+  -H "x-api-key: <key>" -H "x-lancedb-database: <db>" \
+  -H "content-type: application/json" \
+  -d '{}'
+```
+
+## Quick reference
+
+| Goal | Endpoint | Body |
+|------|----------|------|
+| List all branches | `branches/list` | `{}` |
+| Create a branch | `branches/create` | `{"name": "..."}` |
+| Delete a branch | `branches/delete` | `{"name": "..."}` |
+| Read schema on branch | `describe` | `{"branch": "..."}` |
+| Write metadata on branch | `update_field_metadata` | `{"branch": "...", "updates": [...]}` |
+| Build index on branch | `create_index` | `{"branch": "...", "column": ..., "index_type": ...}` |
+| Target main (default) | any endpoint | omit `"branch"` key |
@@ -0,0 +1,178 @@
+---
+name: lancedb-column-metadata
+description: Column metadata authoring for LanceDB tables via the REST API. This skill is required for tasks like writing field descriptions, setting tags on columns (field_type, model, project_id, version), classifying columns as embeddings vs labels vs eval metrics, or grouping versioned columns into logical families — because it has the API integration needed to read the schema and persist metadata back. Invoke whenever someone wants to document, annotate, tag, or classify what their table columns ARE. Trigger even without an explicit "LanceDB" mention, as long as the context is column-level documentation or tagging for an ML or vector database table.
+metadata:
+  short-description: Write column descriptions, tags, and logical groupings to a LanceDB table
+---
+
+## Overview
+
+This skill authors column-level metadata for a LanceDB table. It connects to a LanceDB deployment over its REST API, inspects the table schema, generates appropriate metadata, and writes it back.
+
+## Step 0: Establish the connection
+
+Use the `lancedb-connect` skill (invoke it via the Skill tool) to resolve the base URL and auth headers (`x-api-key`, `x-lancedb-database`) for whichever deployment the user is working against — enterprise/self-hosted or a local dev server. Skip it only if the connection details are already established in the conversation.
+
+All examples below use `{base_url}` — substitute the resolved endpoint and include the resolved headers on every request.
+
+## Metadata keys
+
+All metadata uses namespaced keys:
+
+| Key | Purpose | Example value |
+|-----|---------|---------------|
+| `lancedb:description` | Human-readable explanation of what the column contains | `"CLIP ViT-L/14 image embedding, L2-normalized (768-dim)"` |
+| `lancedb:tag:<name>` | Flexible key-value tag; the suffix names the tag category | `lancedb:tag:field_type: "embedding"`, `lancedb:tag:model: "clip"`, `lancedb:tag:project_id: "foo"` |
+| `lancedb:logical-column` | Logical group/family this column belongs to | `"clip_features"` |
+
+Tags are open-ended — use whatever key suffix and value make sense given the user's intent. The tag suffix should describe *what is being classified* (e.g., `field_type`, `model`, `project_id`) and the value describes *how*.
+
+## Step 1: Resolve the table identifier
+
+You need:
+- **Table name** (required) — e.g., `my_table` or `my_namespace.my_table`
+- **Database name** — ask if not provided and not inferable from context; it goes in the `x-lancedb-database` header, never in the URL path
+
+The table identifier in the URL path is typically `table_name` for a top-level table, or `namespace$table_name` if the table lives in a namespace. The API accepts a `delimiter` query parameter to parse compound identifiers (default `$`).
+
+## Step 2: Describe the table
+
+```http
+POST {base_url}/v1/table/{table_id}/describe
+Content-Type: application/json
+
+{}
+```
+
+The response contains `schema.fields` — an array of field objects:
+
+```json
+{
+  "schema": {
+    "fields": [
+      {
+        "name": "clip_embedding_v3",
+        "type": { "type": "FixedSizeList", "fields": [...], "listSize": 768 },
+        "nullable": true,
+        "metadata": { "lancedb:description": "..." }
+      }
+    ]
+  }
+}
+```
+
+Each field has:
+- `name` — field name
+- `type` — Arrow data type (check `type.type` for the type string)
+- `nullable` — boolean
+- `metadata` — existing key-value metadata (read this before writing to avoid redundant updates)
+
+For struct/nested fields, recurse into `type.fields` and represent them as dot-notation paths (e.g., `parent.child`).
+
+If the user hasn't specified which columns to update, work with all columns.
+
+## Step 3: Generate metadata
+
+Decide what to generate based on the user's request.
+
+### Writing descriptions (`lancedb:description`)
+
+Base descriptions on:
+- The column name and Arrow type (e.g., `FixedSizeList` of floats → likely an embedding)
+- User-supplied context (upstream pipeline, sample values, domain knowledge)
+- Name patterns: `_embedding`/`_vec`/`_embed` → vector; `_label`/`_class` → label; `_score`/`_eval`/`_metric` → evaluation metric
+
+Be specific and concise. Good: `"Sentence-BERT embedding of the query text (768-dim)."` Not: `"An embedding column."`
+
+### Tagging columns (`lancedb:tag:<name>`)
+
+Choose tag key names that match what the user asked to annotate. Common patterns:
+
+- Semantic field type → `lancedb:tag:field_type: "embedding"` / `"text"` / `"image"` / `"label"` / `"eval"` / `"id"` / `"metadata"`
+- Model or source → `lancedb:tag:model: "clip"` / `"bert"` / `"vit"`
+- Project affiliation → `lancedb:tag:project_id: "<name>"`
+- Version → `lancedb:tag:version: "v3"` (and `lancedb:tag:latest: "true"` for the newest)
+
+Use Arrow type as a hint: `FixedSizeList` + float → embedding; `Utf8`/`LargeUtf8` → text; `Binary` → image or blob.
+
+Multiple tags on the same column are fine — each is a separate key.
+
+### Grouping into logical columns (`lancedb:logical-column`)
+
+Look for naming patterns across columns:
+- `clip_v1`, `clip_v2`, `clip_v3` → logical column `"clip"`, latest is `v3`
+- `text_embed_20240101`, `text_embed_20240601` → logical column `"text_embed"`, latest is the most recent date suffix
+
+Write `lancedb:logical-column` on all members of a group. Mark the newest with `lancedb:tag:latest: "true"` (in addition to its version tag).
+
+## Step 4: Write the metadata
+
+```http
+POST {base_url}/v1/table/{table_id}/update_field_metadata
+Content-Type: application/json
+
+{
+  "updates": [
+    {
+      "path": "clip_v3",
+      "metadata": {
+        "lancedb:description": "CLIP ViT-L/14 image embedding, L2-normalized (1024-dim).",
+        "lancedb:tag:field_type": "embedding",
+        "lancedb:tag:model": "clip",
+        "lancedb:tag:version": "v3",
+        "lancedb:tag:latest": "true",
+        "lancedb:logical-column": "clip"
+      },
+      "replace": false
+    },
+    {
+      "path": "clip_v2",
+      "metadata": {
+        "lancedb:description": "CLIP ViT-B/32 image embedding (768-dim), superseded by v3.",
+        "lancedb:tag:field_type": "embedding",
+        "lancedb:tag:model": "clip",
+        "lancedb:tag:version": "v2",
+        "lancedb:logical-column": "clip"
+      },
+      "replace": false
+    }
+  ]
+}
+```
+
+Rules:
+- **Use `"replace": false`** (merge) by default — this preserves existing metadata the user didn't ask to change
+- Use `"replace": true` only if the user explicitly asks to overwrite all existing metadata on a column
+- Set a value to `null` to delete a specific key
+- Batch all updates in a single request when possible
+
+The response includes `version` (new table version) and `fields` (the updated metadata per field).
+
+## Step 5: Confirm
+
+Report back:
+- Which columns were updated and what was written
+- The new table version number
+- Any columns skipped (e.g., already had up-to-date metadata)
+
+---
+
+## Quick examples
+
+**"Write descriptions for all columns in the `product_embeddings` table"**
+1. POST `/v1/table/product_embeddings/describe` → get all fields
+2. Generate a `lancedb:description` for each column based on name + type
+3. POST `update_field_metadata` with descriptions
+4. Report
+
+**"Tag the columns in `model_outputs` with their field type and model"**
+1. Describe `model_outputs`
+2. For each field, classify by name + Arrow type → set `lancedb:tag:field_type` and `lancedb:tag:model` where applicable
+3. POST `update_field_metadata`
+4. Report
+
+**"Group the feature columns in `training_features` into logical families and mark the latest version"**
+1. Describe the table
+2. Find version patterns → assign `lancedb:logical-column` and `lancedb:tag:version`; mark newest with `lancedb:tag:latest: "true"`
+3. POST `update_field_metadata`
+4. Show the grouping
@@ -0,0 +1,42 @@
+---
+name: lancedb-connect
+description: Resolve how to connect to a LanceDB deployment over the REST API — figure out the base URL, API key, and database header. Use this before making any REST requests to a LanceDB table, whenever the endpoint or auth setup is not already known. Also useful on its own when someone asks how to connect, authenticate, or curl their LanceDB instance.
+metadata:
+  short-description: Resolve the base URL and auth headers for a LanceDB deployment
+---
+
+## Goal
+
+Produce two things every REST request needs:
+
+1. **Base URL** — the endpoint
+2. **Headers** — `x-api-key`, and usually `x-lancedb-database`
+
+## Resolution steps
+
+1. If the user already gave a URL and API key (or said which environment they're working against), use that.
+2. Otherwise, look for credentials already available in the environment:
+   - Env vars like `LANCEDB_URI` / `LANCEDB_HOST` / `LANCEDB_API_KEY`
+   - A LanceDB endpoint already running or port-forwarded locally (the REST default port is 2333, i.e. `http://localhost:2333`)
+3. If you didn't find both pieces, ask the user directly: **"What's your LanceDB endpoint's URL, and what's your API key?"** Also ask which database to use if it isn't obvious. Don't guess or probe further — the user knows their deployment.
+
+## Validating the connection
+
+Make a cheap authenticated request and check the status:
+
+```bash
+curl -s -w "\n%{http_code}" "{base_url}/v1/table/?limit=1" \
+  -H "x-api-key: <key>" \
+  -H "x-lancedb-database: <database>"
+```
+
+- `200` — connection, key, and database header all good
+- `401` — API key missing or wrong
+- `400` mentioning a database header — this deployment expects `x-lancedb-database`
+
+## Non-REST equivalents
+
+If the caller would rather use the SDK or CLI than raw REST, the same credentials work:
+
+- Python SDK: `lancedb.connect("db://<database>", api_key="<key>", host_override="<base_url>")`
+- `lancedb` CLI: a `[profiles.<name>]` entry in `~/.lancedb/config.toml` with `http_server_url`, `api_key`, `database`
@@ -1,6 +1,6 @@
 ---
 name: lancedb
-description: Use when writing, reviewing, debugging, or documenting LanceDB pipelines in Python or TypeScript, especially code that should work across local LanceDB OSS tables and remote LanceDB Enterprise/Cloud tables. Helps avoid non-portable full-table materialization, choose idiomatic query/search patterns, apply LanceDB performance defaults for ingestion, indexing, filtering, and diagnostics, and resolve connections to the remote server for Enterprise-only operations such as jobs.
+description: Use when writing, reviewing, debugging, or documenting LanceDB pipelines in Python or TypeScript, especially code that should work across local LanceDB OSS tables and remote LanceDB Enterprise/Cloud tables. Helps avoid non-portable full-table materialization, choose idiomatic query/search patterns, and apply LanceDB performance defaults for ingestion, indexing, filtering, and diagnostics.
 ---

 # Building LanceDB Pipelines
@@ -19,7 +19,7 @@ Do NOT assume local-only table helpers exist on remote tables. If the user asks
 ## Workflow

 1. Identify the SDK: Python, TypeScript, or both.
-2. Identify the table mode: local/embedded OSS, remote Enterprise/Cloud, or portable across both. If the user says "LanceDB Enterprise", choose the remote table path. If the task involves jobs in any way (listing, inspecting, creating, or canceling jobs), it is always the remote path and requires a remote server connection — see "Connecting to the LanceDB remote server" below before doing anything else.
+2. Identify the table mode: local/embedded OSS, remote Enterprise/Cloud, or portable across both. If the user says "LanceDB Enterprise", choose the remote table path.
 3. Read the matching language branch before writing or changing code:
   - Python patterns: `references/python/patterns.md`
   - Python API quick reference: `references/python/api_reference.md`
@@ -27,11 +27,7 @@ Do NOT assume local-only table helpers exist on remote tables. If the user asks
   - TypeScript patterns: `references/typescript/patterns.md`
   - TypeScript API quick reference: `references/typescript/api_reference.md`
   - TypeScript performance guidance: `references/typescript/performance.md`
-   - Column metadata authoring (both SDKs): `references/column_metadata.md`
-   - Branch operations (both SDKs): `references/branch_ops.md`
-   - Remote server connection resolution (jobs, raw REST): `references/remote_connect.md`
-   - Job operations REST API (list/describe/cancel/query_events): `references/remote_jobs.md`
-4. Start with `patterns.md` for the selected SDK. Read `api_reference.md` when choosing method names or return collectors. Read `performance.md` when the task involves ingestion, indexing, filtering, query tuning, diagnostics, or large datasets. Read `column_metadata.md` when the task is documenting, tagging, classifying, or grouping table columns (field descriptions, `lancedb:tag:*` tags, logical column families). Read `branch_ops.md` when the task involves branch lifecycle (list/create/delete), writing to a non-main branch, or verifying a change stayed off main. Read `remote_connect.md` when the task involves jobs or direct REST access to an Enterprise deployment, and `remote_jobs.md` for the job REST methods themselves (list, describe, cancel, query_events).
+4. Start with `patterns.md` for the selected SDK. Read `api_reference.md` when choosing method names or return collectors. Read `performance.md` when the task involves ingestion, indexing, filtering, query tuning, diagnostics, or large datasets.
 5. For Python schemas, favor Pydantic models and validate records before writing. Use PyArrow schemas when Arrow-native, streaming, or highly dynamic data makes them materially better suited.
 6. Prefer `search()` or `query()` builders with explicit `select()` and `limit()` for reads.
 7. Avoid table-level full materialization in remote or portable code. This is the main local-vs-remote read pitfall.
@@ -72,10 +68,6 @@ Rules for portable Enterprise ingestion:

 This is Enterprise/Cloud-specific. Local/OSS tables have no separate data plane, so `mode="overwrite"` and immediate same-name reuse are fine there.

-## Connecting to the LanceDB remote server
-
-LanceDB Enterprise/Cloud deployments are served by a server implementing the lance-namespace OpenAPI spec (<https://github.com/lance-format/lance-namespace/blob/main/docs/src/spec.yaml>). Every remote (`db://...`) connection talks to such a server, and some operations exist only there. In particular, **all operations around jobs (listing, inspecting, creating, or canceling jobs) run server-side** — there is no local/OSS equivalent. Before any job work, or any direct REST call to an Enterprise deployment, read `references/remote_connect.md` to resolve the base URL, credentials, and database header and to validate the connection. Then use the four job REST methods documented in `references/remote_jobs.md` (list, describe, cancel, query_events).
-
 ## Script

 Run the scanner when reviewing or modifying an existing codebase:
@@ -4,19 +4,12 @@ Quick method reference for Python LanceDB code. Cross-check source for non-trivi

 ## Connect

-If you're connecting to a remote database, use this:
 ```python
 import lancedb

-db = lancedb.connect("db://my-db", api_key=api_key, host_override=host_override) # remote
+db = lancedb.connect("./camelot-db")         # local/OSS
+db = lancedb.connect("db://my-db", api_key=api_key, region=region)  # remote
 ```
-(values may be found in LANCEDB_API_KEY and LANCEDB_HOST_OVERRIDE, either in env vars or a .env file)
-
-If you're connecting to a local table using OSS LanceDB, use this:
-```python
-db = lancedb.connect("./camelot-db") # local/OSS
-```
-If you're not sure which, or if you can't find the api_key or host_override params, ask the user.

 **Place the local database directory next to the script/entrypoint that opens it** (i.e. resolve the path relative to the script, `Path(__file__).parent / "camelot-db"`), not buried under a shared `data/` folder. The Lance dataset is the database, not a data file — keeping it beside its code makes ownership obvious and paths stable regardless of the working directory the script is launched from.

@@ -103,32 +96,6 @@ print(table.index_stats("vector_idx"))

 Use these before changing indexes or search tuning.

-## Column (Field) Metadata
-
-```python
-schema = table.schema                       # sync property; async: await table.schema()
-meta = schema.field("category").metadata    # dict[bytes, bytes] — Arrow metadata is bytes-keyed
-res = table.update_field_metadata(          # varargs: one dict per field; works local + remote
-    {"path": "category", "metadata": {"lancedb:description": "...", "lancedb:tag:field_type": "label"}}
-)
-res.version  # new table version
-```
-
-Merges by default; a `None` value deletes that key; `"replace": True` swaps the whole map. Nested fields use dot-paths (`"a.b.c"`). `replace_field_metadata` is deprecated. See `references/column_metadata.md` for key conventions (`lancedb:description`, `lancedb:tag:<name>`, `lancedb:logical-column`) and the authoring workflow.
-
-## Branches
-
-```python
-table.branches.list()                          # non-main branches; {} = only main
-exp = table.branches.create("exp")             # fork off main -> handle scoped to the branch
-wip = table.branches.checkout("wip")           # existing branch -> scoped handle (version= pins read-only)
-wip = db.open_table("t", branch="wip")         # or open scoped directly
-table.branches.delete("stale")                 # removes only the branch pointer
-table.current_branch()                         # None = main
-```
-
-There is no global switch — scoping is per table handle: any read/write on a branch handle lands on that branch; the original handle keeps targeting main. See `references/branch_ops.md` for the model and isolation checks.
-
 ## Maintenance

 ```python
@@ -69,33 +69,6 @@ console.log(await table.indexStats("vector_idx"));

 Use these before changing indexes or search tuning.

-## Column (Field) Metadata
-
-```typescript
-const schema = await table.schema();
-const meta = schema.fields.find((f) => f.name === "category")?.metadata; // Map<string, string>
-const res = await table.updateFieldMetadata([
-  { path: "category", metadata: { "lancedb:description": "...", "lancedb:tag:field_type": "label" } },
-]);
-res.version; // new table version
-```
-
-Merges by default; a `null` value deletes that key; `replace: true` swaps the whole map. Nested fields use dot-paths (`"a.b.c"`). See `references/column_metadata.md` for key conventions (`lancedb:description`, `lancedb:tag:<name>`, `lancedb:logical-column`) and the authoring workflow.
-
-## Branches
-
-```typescript
-const branches = await table.branches();       // async manager
-await branches.list();                         // non-main branches; {} = only main
-const exp = await branches.create("exp");      // fork off main -> Table scoped to the branch
-const wip = await branches.checkout("wip");    // existing branch -> scoped Table (version arg pins read-only)
-const wip2 = await db.openTable("t", { branch: "wip" }); // or open scoped directly
-await branches.delete("stale");                // removes only the branch pointer
-table.currentBranch();                         // null = main
-```
-
-There is no global switch — scoping is per table handle: any read/write on a branch handle lands on that branch; the original handle keeps targeting main. See `references/branch_ops.md` for the model and isolation checks.
-
 ## Maintenance

 ```typescript
@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.37.1-beta.1"
+current_version = "0.32.0-beta.2"
 parse = """(?x)
    (?P<major>0|[1-9]\\d*)\\.
    (?P<minor>0|[1-9]\\d*)\\.
@@ -75,13 +75,6 @@ filename = "nodejs/Cargo.toml"
 replace = "\nversion = \"{new_version}\""
 search = "\nversion = \"{current_version}\""

-# The Python package takes its version from here (pyproject.toml declares
-# `dynamic = ["version"]`, so maturin reads it out of the crate manifest).
-[[tool.bumpversion.files]]
-filename = "python/Cargo.toml"
-replace = "\nversion = \"{new_version}\""
-search = "\nversion = \"{current_version}\""
-
 # Java documentation
 [[tool.bumpversion.files]]
 filename = "docs/src/java/java.md"
@@ -1,19 +0,0 @@
-{
-  "name": "lancedb",
-  "owner": {
-    "name": "LanceDB"
-  },
-  "description": "LanceDB plugins for Claude Code.",
-  "plugins": [
-    {
-      "name": "lancedb",
-      "source": "./plugins/lancedb",
-      "description": "Write, review, debug, and document LanceDB pipelines in Python and TypeScript that work across local LanceDB OSS tables and remote LanceDB Enterprise/Cloud tables.",
-      "version": "0.1.0",
-      "author": {
-        "name": "LanceDB"
-      },
-      "category": "development"
-    }
-  ]
-}
@@ -27,31 +27,19 @@ runs:
          # Extract failed job names
          FAILED_JOBS=$(echo "$JOB_RESULTS" | jq -r 'to_entries | map(select(.value.result == "failure")) | map(.key) | join(", ")')

-          TITLE="$WORKFLOW_NAME Failed ($FAILED_JOBS)"
-
-          # This action now also runs on nightly schedules, so a breakage that
-          # persists for a few days would otherwise file one issue per night.
-          # Comment on the open report instead when one already exists.
-          EXISTING=$(gh issue list --state open --label ci --limit 100 --json number,title \
-            | jq -r --arg title "$TITLE" 'map(select(.title == $title)) | .[0].number // empty')
-
-          if [ -n "$EXISTING" ]; then
-            gh issue comment "$EXISTING" --body "Failed again: $RUN_URL"
-            echo "Commented on existing issue #$EXISTING"
-          else
-            gh issue create \
-              --title "$TITLE" \
-              --body "The workflow **$WORKFLOW_NAME** failed during execution.
+          # Create issue with workflow name, failed jobs, and run URL
+          gh issue create \
+            --title "$WORKFLOW_NAME Failed ($FAILED_JOBS)" \
+            --body "The workflow **$WORKFLOW_NAME** failed during execution.

        **Failed jobs:** $FAILED_JOBS

        **Run URL:** $RUN_URL

        Please investigate the failed jobs and address any issues." \
-              --label "ci"
+            --label "ci"

-            echo "Issue created successfully"
-          fi
+          echo "Issue created successfully"
        else
          echo "No job failures detected, skipping issue creation"
        fi
@@ -18,14 +18,6 @@ inputs:
    description: "The manylinux version to build for"
    required: false
    default: "2_17"
-  package-name:
-    description: "Override [project] name in python/pyproject.toml (e.g. 'lancedb-compat'). Default keeps 'lancedb'."
-    required: false
-    default: "lancedb"
-  rustflags:
-    description: "RUSTFLAGS for the build container, as a single whitespace-free token (e.g. '-Ctarget-cpu=x86-64-v2'). Empty leaves RUSTFLAGS unset, keeping the defaults from .cargo/config.toml."
-    required: false
-    default: ""
 runs:
  using: "composite"
  steps:
@@ -35,18 +27,6 @@ runs:
        ARM_BUILD: ${{ inputs.arm-build }}
      run: |
        echo "ARM BUILD: $ARM_BUILD"
-    - name: Patch package name for variant build
-      if: ${{ inputs.package-name != 'lancedb' }}
-      shell: bash
-      env:
-        PACKAGE_NAME: ${{ inputs.package-name }}
-      run: |
-        # Swap the [project] name so this build produces e.g. lancedb-compat
-        # wheels. The package still installs files under the lancedb/
-        # namespace -- import lancedb still works after pip install.
-        sed -i.bak 's/^name = "lancedb"$/name = "'"$PACKAGE_NAME"'"/' python/pyproject.toml
-        rm -f python/pyproject.toml.bak
-        grep '^name = ' python/pyproject.toml
    - name: Build x86_64 Manylinux wheel
      if: ${{ inputs.arm-build == 'false' }}
      uses: PyO3/maturin-action@v1
@@ -54,7 +34,7 @@ runs:
        maturin-version: "1.12.4"
        command: build
        working-directory: python
-        docker-options: "-e PIP_EXTRA_INDEX_URL='https://pypi.fury.io/lance-format/ https://pypi.fury.io/lancedb/' -e PROTOC=/usr/local/bin/protoc ${{ inputs.rustflags != '' && format('-e RUSTFLAGS={0}', inputs.rustflags) || '' }}"
+        docker-options: "-e PIP_EXTRA_INDEX_URL='https://pypi.fury.io/lance-format/ https://pypi.fury.io/lancedb/' -e PROTOC=/usr/local/bin/protoc"
        target: x86_64-unknown-linux-gnu
        manylinux: ${{ inputs.manylinux }}
        args: ${{ inputs.args }}
@@ -71,7 +51,7 @@ runs:
        maturin-version: "1.12.4"
        command: build
        working-directory: python
-        docker-options: "-e PIP_EXTRA_INDEX_URL='https://pypi.fury.io/lance-format/ https://pypi.fury.io/lancedb/' -e PROTOC=/usr/local/bin/protoc ${{ inputs.rustflags != '' && format('-e RUSTFLAGS={0}', inputs.rustflags) || '' }}"
+        docker-options: "-e PIP_EXTRA_INDEX_URL='https://pypi.fury.io/lance-format/ https://pypi.fury.io/lancedb/' -e PROTOC=/usr/local/bin/protoc"
        target: aarch64-unknown-linux-gnu
        manylinux: ${{ inputs.manylinux }}
        args: ${{ inputs.args }}
@@ -6,6 +6,7 @@ on:
      # We don't publish pre-releases for Rust. Crates.io is just a source
      # distribution, so we don't need to publish pre-releases.
      - "v*-beta*"
+      - "*-v*" # for example, python-vX.Y.Z

 env:
  # This env var is used by Swatinem/rust-cache@v2 for the cache
@@ -1,222 +0,0 @@
-name: Check doc links
-
-# Checking external links is inherently noisy: third-party sites rate-limit
-# automated clients, reject non-browser user agents, and go down temporarily.
-# Blocking pull requests on that trades a lot of false failures for very little
-# signal, so this runs on a schedule and reports findings in a single tracking
-# issue instead of failing anyone's build.
-on:
-  schedule:
-    - cron: "0 7 * * *"
-  workflow_dispatch:
-
-# The report lives in one repository-global issue, so runs must not overlap: a
-# lookup racing a create produces duplicate issues, and a healthy run closing
-# the issue while a failing run only rewrites its body would leave a broken
-# report closed. The group is deliberately ref-independent so that a manual
-# dispatch serializes against the scheduled run.
-concurrency:
-  group: docs-link-check
-  cancel-in-progress: false
-
-permissions: {}
-
-env:
-  REPORT_TITLE: "Docs link checker report"
-
-jobs:
-  scan:
-    name: Scan links
-    runs-on: ubuntu-24.04
-    # lychee-action is pinned by SHA, but its wrapper downloads the lychee
-    # release tarball at run time without verifying a digest, and hands the
-    # resulting binary a GitHub token. Release assets remain replaceable, so
-    # that binary is confined to a job whose token can only read public
-    # content; everything that writes runs in the report job below.
-    permissions:
-      contents: read
-    outputs:
-      exit_code: ${{ steps.lychee.outputs.exit_code }}
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v6
-        with:
-          # workflow_dispatch can run from any ref, but the report is
-          # repository-global. Always measure the default branch so a manual
-          # run from a topic branch cannot close a report that main warrants,
-          # or overwrite it with branch-only findings.
-          ref: ${{ github.event.repository.default_branch }}
-          persist-credentials: false
-
-      - name: Check links
-        id: lychee
-        uses: lycheeverse/lychee-action@e7477775783ea5526144ba13e8db5eec57747ce8 # v2.9.0
-        with:
-          # Restricted to http(s) on purpose. Much of docs/src is generated
-          # API reference (the js/ tree comes from `npm run docs` in nodejs)
-          # and the hand-written pages use mkdocstrings cross-references and
-          # nav-relative paths that only resolve in the site mkdocs builds,
-          # not in this checkout, so relative links would be reported as
-          # broken on every run.
-          args: >-
-            --scheme https
-            --scheme http
-            --no-progress
-            --max-retries 3
-            --timeout 20
-            'docs/src/**/*.md'
-          format: json
-          output: ./lychee/out.json
-          jobSummary: false
-          # The report, not a red build, is the signal for broken links. The
-          # validation step below still fails the run if the check itself
-          # breaks.
-          fail: false
-
-      - name: Validate report
-        # lychee does not reserve exit code 2 for broken links: its CLI
-        # parser also exits 2 on an invalid option, before any link was
-        # checked or any report written. Only a parseable report whose
-        # counts agree with the exit code counts as a link verdict; anything
-        # else fails here, and the report job below is skipped entirely, so
-        # the tracking issue is never touched. Exit 2 covers timeouts as
-        # well as errors, and a timed-out host is exactly the transient
-        # unavailability this report exists to surface, so both count as
-        # findings. Requiring total > 0 also catches a glob that silently
-        # stopped matching any file.
-        if: steps.lychee.outputs.exit_code == 0 || steps.lychee.outputs.exit_code == 2
-        env:
-          EXIT_CODE: ${{ steps.lychee.outputs.exit_code }}
-        run: |
-          jq -e --argjson code "$EXIT_CODE" '
-            (.total > 0) and
-            (if $code == 0
-             then .errors == 0 and .timeouts == 0
-               and (.error_map | length == 0) and (.timeout_map | length == 0)
-             else (.errors + .timeouts) > 0
-               and ((.error_map | length) + (.timeout_map | length)) > 0
-             end)
-          ' ./lychee/out.json
-
-      - name: Upload report
-        if: steps.lychee.outputs.exit_code == 2
-        uses: actions/upload-artifact@v7
-        with:
-          name: link-report
-          path: ./lychee/out.json
-          retention-days: 7
-
-  report:
-    name: Update report issue
-    needs: scan
-    runs-on: ubuntu-24.04
-    # Deliberately no checkout: this job needs the report artifact and the
-    # issues API, not the repository contents.
-    permissions:
-      issues: write
-    env:
-      EXIT_CODE: ${{ needs.scan.outputs.exit_code }}
-      GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-    steps:
-      - name: Classify checker result
-        # lychee exits 0 when every link resolves and 2 when links fail,
-        # both already cross-checked against the report by the scan job's
-        # validation step. Anything else (1 runtime, 3 bad config) means the
-        # check never produced a link verdict, which must surface as a failed
-        # run rather than be published as "broken documentation links".
-        run: |
-          case "$EXIT_CODE" in
-            0|2)
-              echo "lychee exit code $EXIT_CODE"
-              ;;
-            *)
-              echo "::error::lychee exited with '$EXIT_CODE': the link check did not complete. Leaving the report issue untouched."
-              exit 1
-              ;;
-          esac
-
-      - name: Find existing report issue
-        id: report
-        # Matched on title alone, and through search rather than a listing:
-        # the issue action applies labels in a separate call after creating the
-        # issue, so a label filter misses a half-created report, and this
-        # repository has far more open issues than one listing page holds.
-        # Closed issues are included because a healthy run closes the report:
-        # an open-only lookup would forget that identity and the next failing
-        # run would open a duplicate. The oldest match stays the canonical
-        # report and is reopened below when links break again.
-        run: |
-          match=$(gh issue list --repo "$GITHUB_REPOSITORY" --state all \
-            --search "in:title \"$REPORT_TITLE\" author:app/github-actions" \
-            --limit 50 --json number,title,state \
-            --jq "[.[] | select(.title == \"$REPORT_TITLE\")] | sort_by(.number) | first // empty")
-          echo "number=$(jq -r '.number // empty' <<<"$match")" >> "$GITHUB_OUTPUT"
-          echo "state=$(jq -r '.state // empty' <<<"$match")" >> "$GITHUB_OUTPUT"
-
-      - name: Download report
-        if: env.EXIT_CODE == 2
-        uses: actions/download-artifact@v8
-        with:
-          name: link-report
-          path: ./lychee
-
-      - name: Compose report
-        if: env.EXIT_CODE == 2
-        run: |
-          run_url="$GITHUB_SERVER_URL/$GITHUB_REPOSITORY/actions/runs/$GITHUB_RUN_ID"
-          {
-            echo "Broken documentation links found by [\`$GITHUB_WORKFLOW\`]($run_url)."
-            echo
-            echo "This issue is rewritten by every scheduled run and closed automatically once all links resolve."
-            echo
-            echo "Entries can be false positives: some sites rate-limit or block automated clients while working fine in a browser. Confirm before editing the docs, and add persistent offenders to \`--exclude\` in \`.github/workflows/docs-link-check.yml\`."
-            echo
-            # Timeouts are reported alongside errors: entries land in
-            # timeout_map with a status text instead of an HTTP code.
-            jq -r '
-              "\(.errors) of \(.total) links failed, \(.timeouts) timed out.",
-              "",
-              ([(.error_map | to_entries[]), (.timeout_map | to_entries[])]
-               | group_by(.key)[] |
-                "### Errors in \(.[0].key)",
-                "",
-                (map(.value[])[] | "* [\(.status.code // .status.text // "ERR")] <\(.url)> — \(.status.details // .status.text // "unknown error")"),
-                "")
-            ' ./lychee/out.json
-          } > ./lychee/issue.md
-
-      - name: Reopen report issue
-        # A healthy run closes the report, and the issue action below only
-        # rewrites the body of whatever number it is given. Without an
-        # explicit reopen, the 2 -> 0 -> 2 sequence would keep rewriting a
-        # closed issue while links are broken. A CLOSED state implies the
-        # lookup found a canonical issue, so no separate emptiness check.
-        if: env.EXIT_CODE == 2 && steps.report.outputs.state == 'CLOSED'
-        env:
-          ISSUE_NUMBER: ${{ steps.report.outputs.number }}
-        run: |
-          run_url="$GITHUB_SERVER_URL/$GITHUB_REPOSITORY/actions/runs/$GITHUB_RUN_ID"
-          gh issue reopen "$ISSUE_NUMBER" --repo "$GITHUB_REPOSITORY" \
-            --comment "Broken documentation links found again in [the latest run]($run_url)."
-
-      - name: Report broken links
-        if: env.EXIT_CODE == 2
-        uses: peter-evans/create-issue-from-file@fca9117c27cdc29c6c4db3b86c48e4115a786710 # v6.0.0
-        with:
-          # Empty on the first failing run, which creates the issue; afterwards
-          # the same issue is updated in place.
-          issue-number: ${{ steps.report.outputs.number }}
-          title: ${{ env.REPORT_TITLE }}
-          content-filepath: ./lychee/issue.md
-          labels: documentation
-
-      - name: Close report issue once links are healthy
-        # An OPEN state implies the lookup found a canonical issue; a report
-        # that is already closed needs nothing.
-        if: env.EXIT_CODE == 0 && steps.report.outputs.state == 'OPEN'
-        env:
-          ISSUE_NUMBER: ${{ steps.report.outputs.number }}
-        run: |
-          run_url="$GITHUB_SERVER_URL/$GITHUB_REPOSITORY/actions/runs/$GITHUB_RUN_ID"
-          gh issue close "$ISSUE_NUMBER" --repo "$GITHUB_REPOSITORY" \
-            --comment "All documentation links resolved in [the latest run]($run_url)."
@@ -1,85 +0,0 @@
-name: GitHub Release
-
-# All SDKs share one version, so a single `vX.Y.Z` tag produces a single GitHub
-# release covering all of them. The per-package publish workflows (PyPI, NPM,
-# Cargo, Maven) trigger off the same tag independently.
-
-on:
-  push:
-    tags:
-      - "v*"
-
-permissions:
-  contents: read
-
-jobs:
-  gh-release:
-    runs-on: ubuntu-latest
-    permissions:
-      contents: write
-    steps:
-      - uses: actions/checkout@v6
-        with:
-          fetch-depth: 0
-          lfs: true
-      - name: Extract version
-        id: extract_version
-        env:
-          GITHUB_REF: ${{ github.ref }}
-        run: |
-          set -e
-          echo "Extracting tag and version from $GITHUB_REF"
-          if [[ $GITHUB_REF =~ refs/tags/v(.*) ]]; then
-            VERSION=${BASH_REMATCH[1]}
-            TAG=v$VERSION
-            echo "tag=$TAG" >> $GITHUB_OUTPUT
-            echo "version=$VERSION" >> $GITHUB_OUTPUT
-          else
-            echo "Failed to extract version from $GITHUB_REF"
-            exit 1
-          fi
-          echo "Extracted version $VERSION from $GITHUB_REF"
-          if [[ $VERSION =~ beta ]]; then
-            echo "This is a beta release"
-            echo "prerelease=true" >> $GITHUB_OUTPUT
-
-            # Get last release (that is not this one)
-            FROM_TAG=$(git tag --sort='version:refname' \
-              | grep ^v \
-              | grep -vF "$TAG" \
-              | python ci/semver_sort.py v \
-              | tail -n 1)
-          else
-            echo "This is a stable release"
-            echo "prerelease=false" >> $GITHUB_OUTPUT
-            # Get last stable tag (ignore betas)
-            FROM_TAG=$(git tag --sort='version:refname' \
-              | grep ^v \
-              | grep -vF "$TAG" \
-              | grep -v beta \
-              | python ci/semver_sort.py v \
-              | tail -n 1)
-          fi
-          echo "Found from tag $FROM_TAG"
-          echo "from_tag=$FROM_TAG" >> $GITHUB_OUTPUT
-      - name: Create Release Notes
-        id: release_notes
-        uses: mikepenz/release-changelog-builder-action@v4
-        with:
-          configuration: .github/release_notes.json
-          toTag: ${{ steps.extract_version.outputs.tag }}
-          fromTag: ${{ steps.extract_version.outputs.from_tag }}
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-      - name: Create GH release
-        uses: softprops/action-gh-release@v2
-        with:
-          # Marking betas as pre-releases keeps them from taking the "Latest"
-          # badge on the releases page.
-          prerelease: ${{ steps.extract_version.outputs.prerelease }}
-          make_latest: ${{ steps.extract_version.outputs.prerelease == 'false' }}
-          tag_name: ${{ steps.extract_version.outputs.tag }}
-          token: ${{ secrets.GITHUB_TOKEN }}
-          generate_release_notes: false
-          name: LanceDB v${{ steps.extract_version.outputs.version }}
-          body: ${{ steps.release_notes.outputs.changelog }}
@@ -1,14 +1,13 @@
 name: Create release commit

-# This workflow increments the version, tags it, and pushes it. All SDKs share
-# a single version, so one tag releases all of them.
+# This workflow increments versions, tags the version, and pushes it.
 # When a tag is pushed, another workflow is triggered that creates a GH release
 # and uploads the binaries. This workflow is only for creating the tag.

 # This script will enforce that a minor version is incremented if there are any
-# breaking changes since the last minor increment. A breaking change in any SDK
-# bumps the minor version for all of them. If you wish to bypass this check, you
-# can manually increment the version and push the tag.
+# breaking changes since the last minor increment. However, it isn't able to
+# differentiate between breaking changes in Node versus Python. If you wish to
+# bypass this check, you can manually increment the version and push the tag.
 on:
  workflow_dispatch:
    inputs:
@@ -25,6 +24,16 @@ on:
        options:
          - preview
          - stable
+      python:
+        description: 'Make a Python release'
+        required: true
+        default: true
+        type: boolean
+      other:
+        description: 'Make a Node/Rust/Java release'
+        required: true
+        default: true
+        type: boolean
      bump-minor:
        description: 'Bump minor version'
        required: true
@@ -56,16 +65,29 @@ jobs:
        run: |
          git config user.name 'Lance Release'
          git config user.email 'lance-dev@lancedb.com'
-      - name: Bump version
+      - name: Bump Python version
+        if: ${{ inputs.python }}
+        working-directory: python
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        run: |
+          # Need to get the commit before bumping the version, so we can
+          # determine if there are breaking changes in the next step as well.
+          echo "COMMIT_BEFORE_BUMP=$(git rev-parse HEAD)" >> $GITHUB_ENV
+
+          pip install bump-my-version PyGithub packaging
+          bash ../ci/bump_version.sh ${{ inputs.type }} ${{ inputs.bump-minor }} python-v
+      - name: Bump Node/Rust version
+        if: ${{ inputs.other }}
        env:
          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
        run: |
          pip install bump-my-version PyGithub packaging
-          bash ci/bump_version.sh ${{ inputs.type }} ${{ inputs.bump-minor }}
+          bash ci/bump_version.sh ${{ inputs.type }} ${{ inputs.bump-minor }} v $COMMIT_BEFORE_BUMP
          bash ci/update_lockfiles.sh --amend
      - name: Push new version tag
        if: ${{ !inputs.dry_run }}
-        uses: ad-m/github-push-action@881a6320fdb16eb5318c5054f31c218aec2b324c # v1.3.0
+        uses: ad-m/github-push-action@master
        with:
          # Need to use PAT here too to trigger next workflow. See comment above.
          github_token: ${{ secrets.LANCEDB_RELEASE_TOKEN }}
@@ -61,11 +61,6 @@ jobs:
        sudo apt update
        sudo apt install -y protobuf-compiler libssl-dev
    - uses: Swatinem/rust-cache@v2
-      with:
-        # Restore everywhere, but only save from main. Per-PR saves are
-        # unreadable outside their own branch anyway, since GitHub scopes
-        # caches to the creating ref.
-        save-if: ${{ github.ref == 'refs/heads/main' }}
    - name: Format Rust
      run: cargo fmt --all -- --check
    - name: Lint Rust
@@ -108,11 +103,6 @@ jobs:
        cache: 'pnpm'
        cache-dependency-path: nodejs/pnpm-lock.yaml
    - uses: Swatinem/rust-cache@v2
-      with:
-        # Restore everywhere, but only save from main. Per-PR saves are
-        # unreadable outside their own branch anyway, since GitHub scopes
-        # caches to the creating ref.
-        save-if: ${{ github.ref == 'refs/heads/main' }}
    - name: Install dependencies
      run: |
        sudo apt update
@@ -192,11 +182,6 @@ jobs:
        cache-dependency-path: nodejs/pnpm-lock.yaml
    - uses: dtolnay/rust-toolchain@stable
    - uses: Swatinem/rust-cache@v2
-      with:
-        # Restore everywhere, but only save from main. Per-PR saves are
-        # unreadable outside their own branch anyway, since GitHub scopes
-        # caches to the creating ref.
-        save-if: ${{ github.ref == 'refs/heads/main' }}
    - name: Install dependencies
      run: |
        brew install protobuf
@@ -10,16 +10,10 @@ permissions:

 on:
  push:
+    branches:
+      - main
    tags:
      - "v*"
-  # The cross-compiled targets (musl especially) break from toolchain and
-  # dependency changes that nothing else in CI catches, and discovering that
-  # mid-release is expensive. A nightly run keeps that signal while dropping
-  # the full 8-target release matrix from all ~90 pushes to main each month.
-  # `report-failure` files an issue when a nightly breaks.
-  schedule:
-    - cron: "0 8 * * *"
-  workflow_dispatch:
  pull_request:
    # This should trigger a dry run (we skip the final publish step)
    paths:
@@ -32,6 +26,73 @@ concurrency:
  cancel-in-progress: true

 jobs:
+  gh-release:
+    if: startsWith(github.ref, 'refs/tags/v')
+    runs-on: ubuntu-latest
+    permissions:
+      contents: write
+    steps:
+      - uses: actions/checkout@v6
+        with:
+          fetch-depth: 0
+          lfs: true
+      - name: Extract version
+        id: extract_version
+        env:
+          GITHUB_REF: ${{ github.ref }}
+        run: |
+          set -e
+          echo "Extracting tag and version from $GITHUB_REF"
+          if [[ $GITHUB_REF =~ refs/tags/v(.*) ]]; then
+            VERSION=${BASH_REMATCH[1]}
+            TAG=v$VERSION
+            echo "tag=$TAG" >> $GITHUB_OUTPUT
+            echo "version=$VERSION" >> $GITHUB_OUTPUT
+          else
+            echo "Failed to extract version from $GITHUB_REF"
+            exit 1
+          fi
+          echo "Extracted version $VERSION from $GITHUB_REF"
+          if [[ $VERSION =~ beta ]]; then
+            echo "This is a beta release"
+
+            # Get last release (that is not this one)
+            FROM_TAG=$(git tag --sort='version:refname' \
+              | grep ^v \
+              | grep -vF "$TAG" \
+              | python ci/semver_sort.py v \
+              | tail -n 1)
+          else
+            echo "This is a stable release"
+            # Get last stable tag (ignore betas)
+            FROM_TAG=$(git tag --sort='version:refname' \
+              | grep ^v \
+              | grep -vF "$TAG" \
+              | grep -v beta \
+              | python ci/semver_sort.py v \
+              | tail -n 1)
+          fi
+          echo "Found from tag $FROM_TAG"
+          echo "from_tag=$FROM_TAG" >> $GITHUB_OUTPUT
+      - name: Create Release Notes
+        id: release_notes
+        uses: mikepenz/release-changelog-builder-action@v4
+        with:
+          configuration: .github/release_notes.json
+          toTag: ${{ steps.extract_version.outputs.tag }}
+          fromTag: ${{ steps.extract_version.outputs.from_tag }}
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+      - name: Create GH release
+        uses: softprops/action-gh-release@v2
+        with:
+          prerelease: ${{ contains('beta', github.ref) }}
+          tag_name: ${{ steps.extract_version.outputs.tag }}
+          token: ${{ secrets.GITHUB_TOKEN }}
+          generate_release_notes: false
+          name: Node/Rust LanceDB v${{ steps.extract_version.outputs.version }}
+          body: ${{ steps.release_notes.outputs.changelog }}
+
  build-lancedb:
    strategy:
      fail-fast: false
@@ -40,18 +101,9 @@ jobs:
          - target: aarch64-apple-darwin
            host: macos-latest
            features: fp16kernels
-            pre_build: |-
-              brew install protobuf
-              # Fat LTO (the workspace default in .cargo/config.toml) is
-              # single-threaded and is the peak-memory step of the build. On
-              # this runner it accounted for ~111 of the job's ~113 minutes,
-              # making it the critical path of the entire publish pipeline.
-              # ThinLTO parallelizes it across the runner's cores, for a few
-              # percent of runtime performance.
-              export CARGO_PROFILE_RELEASE_LTO=thin
-              export CARGO_PROFILE_RELEASE_CODEGEN_UNITS=16
+            pre_build: brew install protobuf
          - target: x86_64-pc-windows-msvc
-            host: windows-2025
+            host: windows-2025-8x-x64
            features: ","
            pre_build: |-
              choco install --no-progress protoc ninja nasm
@@ -59,19 +111,19 @@ jobs:
              # There is an issue where choco doesn't add nasm to the path
              export PATH="$PATH:/c/Program Files/NASM"
              nasm -v
-              # See the ThinLTO note on aarch64-apple-darwin above. Keeping
-              # peak memory down is also what lets this run on the standard
-              # 4-core runner: the 8-core larger runner was only needed to
-              # stop fat LTO from OOMing rustc-LLVM.
+              # Fat LTO of the cdylib is single-threaded and the peak-memory
+              # step of the build, and had started hitting rustc-LLVM OOM on the
+              # Windows runners. ThinLTO parallelizes it across the runner's
+              # cores and keeps peak memory well under the limit.
              export CARGO_PROFILE_RELEASE_LTO=thin
              export CARGO_PROFILE_RELEASE_CODEGEN_UNITS=16
          - target: aarch64-pc-windows-msvc
-            host: windows-2025
+            host: windows-2025-8x-x64
            features: ","
            pre_build: |-
                choco install --no-progress protoc
                rustup target add aarch64-pc-windows-msvc
-                # See the ThinLTO note on aarch64-apple-darwin above.
+                # See ThinLTO note on the x86_64-pc-windows-msvc target above.
                export CARGO_PROFILE_RELEASE_LTO=thin
                export CARGO_PROFILE_RELEASE_CODEGEN_UNITS=16
          - target: x86_64-unknown-linux-gnu
@@ -146,49 +198,16 @@ jobs:
        with:
          toolchain: stable
          targets: ${{ matrix.settings.target }}
-      # These builds were entirely uncached: the old key was static, so
-      # `actions/cache` (which only writes on a miss) could never refresh it,
-      # and the multi-GB whole-`target/` copy it tried to store never fit the
-      # repo's cache budget, so no entry was ever saved. rust-cache prunes
-      # `target/` to dependency artifacts and keys on Cargo.lock plus the rustc
-      # version, which both fixes the key and keeps entries a sane size.
-      #
-      # This caches dependency *compilation* only. The LTO link of the cdylib
-      # re-runs regardless, since the local crate changes every time, so the
-      # win is larger on the non-LTO jobs than here.
-      - name: Cache cargo (native builds)
-        uses: Swatinem/rust-cache@v2
-        if: ${{ !matrix.settings.docker }}
+      - name: Cache cargo
+        uses: actions/cache@v5
        with:
-          # The release profile and per-target dirs differ from what the test
-          # workflows cache, so these need to be separate entries.
-          key: release-${{ matrix.settings.target }}
-          # Only the nightly run on main writes, so tag and PR runs restore a
-          # warm entry without every dependabot PR writing its own (which would
-          # be unreadable elsewhere anyway, since GitHub scopes caches to the
-          # creating ref). The nightly cadence also keeps entries inside
-          # GitHub's 7-day eviction window, which a tag-only trigger would not.
-          save-if: ${{ github.ref == 'refs/heads/main' }}
-      # Docker builds can use rust-cache too. `target/` already lives on the
-      # host because the whole workspace is bind-mounted into the container, and
-      # rust-cache's prune and save run host-side, so they can manage it -- which
-      # is what keeps the entry to dependency artifacts rather than a multi-GB
-      # copy of everything.
-      #
-      # Two differences from the native builds. The container's CARGO_HOME is
-      # bind-mounted from `.cargo-cache` rather than the host's ~/.cargo, so that
-      # has to be cached explicitly. And the key is derived from the *host* rustc
-      # version, which is not the compiler that produced these artifacts; that is
-      # safe because cargo fingerprints the real compiler and rebuilds on a
-      # mismatch, it just means a base-image toolchain bump costs one cold build
-      # instead of invalidating the key.
-      - name: Cache cargo (docker builds)
-        uses: Swatinem/rust-cache@v2
-        if: ${{ matrix.settings.docker }}
-        with:
-          key: docker-${{ matrix.settings.target }}
-          cache-directories: .cargo-cache
-          save-if: ${{ github.ref == 'refs/heads/main' }}
+          path: |
+            ~/.cargo/registry/index/
+            ~/.cargo/registry/cache/
+            ~/.cargo/git/db/
+            .cargo-cache
+            target/
+          key: nodejs-${{ matrix.settings.target }}-cargo-${{ matrix.settings.host }}
      - name: Install dependencies
        run: pnpm install --frozen-lockfile
      - name: Install Zig
@@ -206,13 +225,9 @@ jobs:
        if: ${{ matrix.settings.docker }}
        with:
          image: ${{ matrix.settings.docker }}
-          # All three mounts must live under `.cargo-cache`, which is what the
-          # cache step above saves. Previously the registry mounts pointed at
-          # `.cargo/...`, a path nothing cached, so the container re-downloaded
-          # the whole crate registry on every run.
          options: "--user 0:0 -v ${{ github.workspace }}/.cargo-cache/git/db:/usr/local/cargo/git/db \
-                    -v ${{ github.workspace }}/.cargo-cache/registry/cache:/usr/local/cargo/registry/cache \
-                    -v ${{ github.workspace }}/.cargo-cache/registry/index:/usr/local/cargo/registry/index \
+                    -v ${{ github.workspace }}/.cargo/registry/cache:/usr/local/cargo/registry/cache \
+                    -v ${{ github.workspace }}/.cargo/registry/index:/usr/local/cargo/registry/index \
                    -v ${{ github.workspace }}:/build -w /build/nodejs"
          run: |
            set -e
@@ -224,16 +239,6 @@ jobs:
              --js ../lancedb/native.js \
              --strip \
              --output-dir dist/
-      # The container runs as root (`--user 0:0`), so everything it wrote to the
-      # mounted cache dirs is root-owned. rust-cache's post step runs as the
-      # runner user and has to both read these and delete from them while
-      # pruning, so hand them back before it runs.
-      - name: Take ownership of docker build output
-        if: ${{ matrix.settings.docker }}
-        run: |
-          sudo chown -R "$(id -u):$(id -g)" \
-            "${{ github.workspace }}/.cargo-cache" \
-            "${{ github.workspace }}/target"
      - name: Build
        run: |
          ${{ matrix.settings.pre_build }}
@@ -247,15 +252,6 @@ jobs:
              --output-dir dist/
        if: ${{ !matrix.settings.docker }}
        shell: bash
-      # The standard Windows runners have ~14 GB free, and a release `target/`
-      # for this workspace is a large fraction of that. Report the remaining
-      # headroom so a build that only just fits is visible before a dependency
-      # bump turns it into a failed release. `always()` so the numbers are
-      # still there when the build is what ran out of space.
-      - name: Report disk headroom
-        if: always()
-        run: df -h
-        shell: bash
      - name: Upload artifact
        uses: actions/upload-artifact@v7
        with:
@@ -406,9 +402,7 @@ jobs:
    name: Report Workflow Failure
    runs-on: ubuntu-latest
    needs: [build-lancedb, test-lancedb, publish]
-    # Nightly runs are the only thing watching the cross-compiled targets now,
-    # so they have to report failures too or the signal is silently lost.
-    if: always() && failure() && (startsWith(github.ref, 'refs/tags/v') || github.event_name == 'schedule')
+    if: always() && failure() && startsWith(github.ref, 'refs/tags/v')
    permissions:
      contents: read
      issues: write
@@ -3,7 +3,7 @@ name: PyPI Publish
 on:
  push:
    tags:
-      - 'v*'
+      - 'python-v*'
  pull_request:
    # This should trigger a dry run (we skip the final publish step)
    paths:
@@ -20,15 +20,9 @@ env:
 permissions:
  contents: read

-# Without this, a force-push to a PR leaves the previous run going -- including
-# a ~74 minute Windows job and a billed arm64 wheel build.
-concurrency:
-  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
-  cancel-in-progress: true
-
 jobs:
  linux:
-    name: Python ${{ matrix.config.package_name }} ${{ matrix.config.platform }} manylinux${{ matrix.config.manylinux }}
+    name: Python ${{ matrix.config.platform }} manylinux${{ matrix.config.manylinux }}
    timeout-minutes: 60
    strategy:
      matrix:
@@ -37,28 +31,11 @@ jobs:
            manylinux: "2_28"
            extra_args: "--features fp16kernels"
            runner: ubuntu-22.04
-            package_name: "lancedb"
-            rustflags: ""
          # For successful fat LTO builds, we need a large runner to avoid OOM errors.
          - platform: aarch64
            manylinux: "2_28"
            extra_args: "--features fp16kernels"
            runner: ubuntu-2404-8x-arm64
-            package_name: "lancedb"
-            rustflags: ""
-          # `lancedb-compat`: pre-Haswell-friendly variant for x86_64 hosts
-          # without AVX2 (Sandy Bridge / Ivy Bridge / Westmere on Intel,
-          # Bulldozer / Piledriver / Steamroller on AMD). Compiled at the
-          # `x86-64-v2` baseline; runtime SIMD dispatch in lance-linalg
-          # picks the appropriate tier (scalar / AVX / AVX+FMA / AVX2+FMA
-          # / AVX-512) at load time. Same import as `lancedb` -- conflicts
-          # at install time, so users pick one.
-          - platform: x86_64
-            manylinux: "2_28"
-            extra_args: ""
-            runner: ubuntu-22.04
-            package_name: "lancedb-compat"
-            rustflags: "-Ctarget-cpu=x86-64-v2"
    runs-on: ${{ matrix.config.runner }}
    steps:
      - uses: actions/checkout@v6
@@ -75,13 +52,11 @@ jobs:
          args: "--release --strip ${{ matrix.config.extra_args }}"
          arm-build: ${{ matrix.config.platform == 'aarch64' }}
          manylinux: ${{ matrix.config.manylinux }}
-          package-name: ${{ matrix.config.package_name }}
-          rustflags: ${{ matrix.config.rustflags }}
      - uses: actions/upload-artifact@v7
-        if: startsWith(github.ref, 'refs/tags/v')
+        if: startsWith(github.ref, 'refs/tags/python-v')
        with:
-          name: wheels-linux-${{ matrix.config.package_name }}-${{ matrix.config.platform }}-${{ matrix.config.manylinux }}
-          path: target/wheels/*.whl
+          name: wheels-linux-${{ matrix.config.platform }}-${{ matrix.config.manylinux }}
+          path: target/wheels/lancedb-*.whl
          if-no-files-found: error
  mac:
    timeout-minutes: 90
@@ -107,7 +82,7 @@ jobs:
          python-minor-version: 10
          args: "--release --strip --target ${{ matrix.config.target }} --features fp16kernels"
      - uses: actions/upload-artifact@v7
-        if: startsWith(github.ref, 'refs/tags/v')
+        if: startsWith(github.ref, 'refs/tags/python-v')
        with:
          name: wheels-mac-${{ matrix.config.target }}
          path: target/wheels/lancedb-*.whl
@@ -128,26 +103,19 @@ jobs:
        uses: actions/setup-python@v6
        with:
          python-version: "3.13"
-      # NOTE: caching cargo here would be a no-op. This workflow only runs on
-      # tags and PRs, and GitHub only lets a run restore caches from its own ref
-      # or the default branch -- so with no run on main there is nothing that
-      # can populate an entry the release build would be allowed to read. Fixing
-      # this needs a main/nightly trigger (which would also catch wheel-build
-      # breakage before a release); the ~74 minutes here is otherwise dominated
-      # by the fat-LTO link, which no cache avoids.
      - uses: ./.github/workflows/build_windows_wheel
        with:
          python-minor-version: 10
          args: "--release --strip"
      - uses: actions/upload-artifact@v7
-        if: startsWith(github.ref, 'refs/tags/v')
+        if: startsWith(github.ref, 'refs/tags/python-v')
        with:
          name: wheels-windows
          path: target/wheels/lancedb-*.whl
          if-no-files-found: error
  publish:
    name: Publish wheels
-    if: startsWith(github.ref, 'refs/tags/v')
+    if: startsWith(github.ref, 'refs/tags/python-v')
    needs: [linux, mac, windows]
    runs-on: ubuntu-latest
    permissions:
@@ -177,7 +145,7 @@ jobs:
          FURY_TOKEN: ${{ secrets.FURY_TOKEN }}
        run: |
          shopt -s nullglob
-          WHEELS=(target/wheels/*.whl)
+          WHEELS=(target/wheels/lancedb-*.whl)
          if [[ ${#WHEELS[@]} -eq 0 ]]; then
            echo "No wheels found in target/wheels/" >&2
            exit 1
@@ -196,6 +164,72 @@ jobs:
        uses: pypa/gh-action-pypi-publish@release/v1
        with:
          packages-dir: target/wheels/
+  gh-release:
+    if: startsWith(github.ref, 'refs/tags/python-v')
+    runs-on: ubuntu-latest
+    permissions:
+      contents: write
+    steps:
+      - uses: actions/checkout@v6
+        with:
+          fetch-depth: 0
+          lfs: true
+      - name: Extract version
+        id: extract_version
+        env:
+          GITHUB_REF: ${{ github.ref }}
+        run: |
+          set -e
+          echo "Extracting tag and version from $GITHUB_REF"
+          if [[ $GITHUB_REF =~ refs/tags/python-v(.*) ]]; then
+            VERSION=${BASH_REMATCH[1]}
+            TAG=python-v$VERSION
+            echo "tag=$TAG" >> $GITHUB_OUTPUT
+            echo "version=$VERSION" >> $GITHUB_OUTPUT
+          else
+            echo "Failed to extract version from $GITHUB_REF"
+            exit 1
+          fi
+          echo "Extracted version $VERSION from $GITHUB_REF"
+          if [[ $VERSION =~ beta ]]; then
+            echo "This is a beta release"
+
+            # Get last release (that is not this one)
+            FROM_TAG=$(git tag --sort='version:refname' \
+              | grep ^python-v \
+              | grep -vF "$TAG" \
+              | python ci/semver_sort.py python-v \
+              | tail -n 1)
+          else
+            echo "This is a stable release"
+            # Get last stable tag (ignore betas)
+            FROM_TAG=$(git tag --sort='version:refname' \
+              | grep ^python-v \
+              | grep -vF "$TAG" \
+              | grep -v beta \
+              | python ci/semver_sort.py python-v \
+              | tail -n 1)
+          fi
+          echo "Found from tag $FROM_TAG"
+          echo "from_tag=$FROM_TAG" >> $GITHUB_OUTPUT
+      - name: Create Python Release Notes
+        id: python_release_notes
+        uses: mikepenz/release-changelog-builder-action@v4
+        with:
+          configuration: .github/release_notes.json
+          toTag: ${{ steps.extract_version.outputs.tag }}
+          fromTag: ${{ steps.extract_version.outputs.from_tag }}
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+      - name: Create Python GH release
+        uses: softprops/action-gh-release@v2
+        with:
+          prerelease: ${{ contains('beta', github.ref) }}
+          tag_name: ${{ steps.extract_version.outputs.tag }}
+          token: ${{ secrets.GITHUB_TOKEN }}
+          generate_release_notes: false
+          name: Python LanceDB v${{ steps.extract_version.outputs.version }}
+          body: ${{ steps.python_release_notes.outputs.changelog }}
  report-failure:
    name: Report Workflow Failure
    runs-on: ubuntu-latest
@@ -203,7 +237,7 @@ jobs:
    permissions:
      contents: read
      issues: write
-    if: always() && failure() && startsWith(github.ref, 'refs/tags/v')
+    if: always() && failure() && startsWith(github.ref, 'refs/tags/python-v')
    steps:
      - uses: actions/checkout@v6
      - uses: ./.github/actions/create-failure-issue
@@ -108,15 +108,6 @@ jobs:
        run: |
          sudo apt update
          sudo apt install -y protobuf-compiler
-      # `pip install -e .` builds the extension with maturin, which is most of
-      # this job's ~33 minutes. It had no Rust cache, so every dependency was
-      # recompiled from scratch on every run.
-      - uses: Swatinem/rust-cache@v2
-        with:
-          # Restore everywhere, but only save from main. Per-PR saves are
-          # unreadable outside their own branch anyway, since GitHub scopes
-          # caches to the creating ref.
-          save-if: ${{ github.ref == 'refs/heads/main' }}
      - name: Install
        run: |
          pip install --extra-index-url https://pypi.fury.io/lance-format/ --extra-index-url https://pypi.fury.io/lancedb/ -e .[tests,dev,embeddings]
@@ -177,14 +168,6 @@ jobs:
        uses: actions/setup-python@v6
        with:
          python-version: "3.13"
-      # maturin runs cargo natively on macOS (docker is Linux-only), so the host
-      # target dir is cacheable. This job had no Rust cache.
-      - uses: Swatinem/rust-cache@v2
-        with:
-          # Restore everywhere, but only save from main. Per-PR saves are
-          # unreadable outside their own branch anyway, since GitHub scopes
-          # caches to the creating ref.
-          save-if: ${{ github.ref == 'refs/heads/main' }}
      - uses: ./.github/workflows/build_mac_wheel
        with:
          args: --profile ci
@@ -214,14 +197,6 @@ jobs:
        uses: actions/setup-python@v6
        with:
          python-version: "3.13"
-      # maturin runs cargo natively on Windows (docker is Linux-only), so the
-      # host target dir is cacheable. This job had no Rust cache at all and so
-      # rebuilt every dependency from scratch on every run.
-      - uses: Swatinem/rust-cache@v2
-        with:
-          # Restore everywhere, but only save from main. The repo sits at
-          # GitHub's cache cap, so per-PR saves just evict main's entries.
-          save-if: ${{ github.ref == 'refs/heads/main' }}
      - uses: ./.github/workflows/build_windows_wheel
        with:
          args: --profile ci
@@ -249,14 +224,6 @@ jobs:
        uses: actions/setup-python@v6
        with:
          python-version: "3.10"
-      # As with Doctest, `pip install -e .` compiles the extension and this job
-      # had no Rust cache, which is most of its ~37 minutes.
-      - uses: Swatinem/rust-cache@v2
-        with:
-          # Restore everywhere, but only save from main. Per-PR saves are
-          # unreadable outside their own branch anyway, since GitHub scopes
-          # caches to the creating ref.
-          save-if: ${{ github.ref == 'refs/heads/main' }}
      - name: Install lancedb
        run: |
          pip install "pydantic<2"
@@ -48,11 +48,6 @@ jobs:
        with:
          components: rustfmt, clippy
      - uses: Swatinem/rust-cache@v2
-        with:
-          # Restore everywhere, but only save from main. Per-PR saves are
-          # unreadable outside their own branch anyway, since GitHub scopes
-          # caches to the creating ref.
-          save-if: ${{ github.ref == 'refs/heads/main' }}
      - name: Install dependencies
        run: |
          sudo apt update
@@ -94,11 +89,6 @@ jobs:
        run: rm -f Cargo.lock
      - uses: rui314/setup-mold@v1
      - uses: Swatinem/rust-cache@v2
-        with:
-          # Restore everywhere, but only save from main. Per-PR saves are
-          # unreadable outside their own branch anyway, since GitHub scopes
-          # caches to the creating ref.
-          save-if: ${{ github.ref == 'refs/heads/main' }}
      - name: Install dependencies
        run: |
          sudo apt update
@@ -108,7 +98,7 @@ jobs:
          cargo build --profile ci --benches --all-features --tests

  linux:
-    timeout-minutes: 60
+    timeout-minutes: 30
    # To build all features, we need more disk space than is available
    # on the free OSS github runner. This is mostly due to the the
    # sentence-transformers feature.
@@ -128,11 +118,6 @@ jobs:
          fetch-depth: 0
          lfs: true
      - uses: Swatinem/rust-cache@v2
-        with:
-          # Restore everywhere, but only save from main. Per-PR saves are
-          # unreadable outside their own branch anyway, since GitHub scopes
-          # caches to the creating ref.
-          save-if: ${{ github.ref == 'refs/heads/main' }}
      - name: Install dependencies
        run: |
          sudo apt update
@@ -173,7 +158,7 @@ jobs:
        run: CARGO_ARGS="--profile ci" make -C ./lancedb remote-tests

  macos:
-    timeout-minutes: 60
+    timeout-minutes: 30
    strategy:
      matrix:
        mac-runner: ["macos-14", "macos-15"]
@@ -190,11 +175,6 @@ jobs:
      - name: CPU features
        run: sysctl -a | grep cpu
      - uses: Swatinem/rust-cache@v2
-        with:
-          # Restore everywhere, but only save from main. Per-PR saves are
-          # unreadable outside their own branch anyway, since GitHub scopes
-          # caches to the creating ref.
-          save-if: ${{ github.ref == 'refs/heads/main' }}
      - name: Install dependencies
        run: brew install protobuf
      - name: Run tests
@@ -207,19 +187,12 @@ jobs:
          cargo test --profile ci --features $ALL_FEATURES --locked

  windows:
+    runs-on: windows-2022
    strategy:
-      fail-fast: false
      matrix:
-        include:
-          - target: x86_64-pc-windows-msvc
-            runner: windows-2022
-          # windows-11-arm is a standard runner, so it is free on public repos.
-          # Running natively lets the aarch64 tests actually execute -- this
-          # job used to cross-compile them and then skip the test step, paying
-          # full codegen and link cost for a compile check.
-          - target: aarch64-pc-windows-msvc
-            runner: windows-11-arm
-    runs-on: ${{ matrix.runner }}
+        target:
+          - x86_64-pc-windows-msvc
+          - aarch64-pc-windows-msvc
    defaults:
      run:
        working-directory: rust/lancedb
@@ -228,11 +201,6 @@ jobs:
      - name: Set target
        run: rustup target add ${{ matrix.target }}
      - uses: Swatinem/rust-cache@v2
-        with:
-          # Restore everywhere, but only save from main. Per-PR saves are
-          # unreadable outside their own branch anyway, since GitHub scopes
-          # caches to the creating ref.
-          save-if: ${{ github.ref == 'refs/heads/main' }}
      - name: Install Protoc v21.12
        run: choco install --no-progress protoc
      - name: Build
@@ -240,12 +208,11 @@ jobs:
          $env:VCPKG_ROOT = $env:VCPKG_INSTALLATION_ROOT
          cargo build --profile ci --features aws,remote --tests --locked --target ${{ matrix.target }}
      - name: Run tests
+        # Can only run tests when target matches host
+        if: ${{ matrix.target == 'x86_64-pc-windows-msvc' }}
        run: |
          $env:VCPKG_ROOT = $env:VCPKG_INSTALLATION_ROOT
-          # `--target` has to match the build step above. Without it cargo uses
-          # target/ci/ rather than target/<triple>/ci/ and rebuilds the entire
-          # dependency graph a second time.
-          cargo test --profile ci --features aws,remote --locked --target ${{ matrix.target }}
+          cargo test --profile ci --features aws,remote --locked

  msrv:
    # Check the minimum supported Rust version
@@ -271,11 +238,6 @@ jobs:
        with:
          toolchain: ${{ matrix.msrv }}
      - uses: Swatinem/rust-cache@v2
-        with:
-          # Restore everywhere, but only save from main. Per-PR saves are
-          # unreadable outside their own branch anyway, since GitHub scopes
-          # caches to the creating ref.
-          save-if: ${{ github.ref == 'refs/heads/main' }}
      - name: Downgrade  dependencies
        # These packages have newer requirements for MSRV
        run: |
@@ -296,18 +258,16 @@ jobs:
          cargo update -p aws-types --precise 1.3.9
          cargo update -p aws-sigv4 --precise 1.3.5
          cargo update -p aws-credential-types --precise 1.2.8
-          # aws-smithy-checksums must stay at or above 0.63.13: OpenDAL's S3
-          # service needs crc-fast ~1.9, and older releases pin it to ~1.3.
-          cargo update -p aws-smithy-checksums --precise 0.63.13
+          cargo update -p aws-smithy-checksums --precise 0.63.9
          cargo update -p aws-smithy-runtime --precise 1.9.3
-          cargo update -p aws-smithy-http --precise 0.62.6
-          cargo update -p aws-smithy-eventstream --precise 0.60.14
+          cargo update -p aws-smithy-http --precise 0.62.4
+          cargo update -p aws-smithy-eventstream --precise 0.60.12
          cargo update -p aws-smithy-http-client --precise 1.1.3
          cargo update -p aws-smithy-observability --precise 0.1.4
          cargo update -p aws-smithy-query --precise 0.60.8
-          cargo update -p aws-smithy-runtime-api --precise 1.9.3
-          cargo update -p aws-smithy-async --precise 1.2.7
-          cargo update -p aws-smithy-types --precise 1.3.6
+          cargo update -p aws-smithy-runtime-api --precise 1.9.1
+          cargo update -p aws-smithy-async --precise 1.2.6
+          cargo update -p aws-smithy-types --precise 1.3.5
          cargo update -p aws-smithy-xml --precise 0.60.11
          cargo update -p home --precise 0.5.9
      - name: cargo +${{ matrix.msrv }} check
@@ -92,8 +92,6 @@ Python bindings changes:
    * Should use `LOOP.run()` to call the corresponding `AsyncTable` method.
 6. Add concrete sync method to `RemoteTable` class in `python/python/lancedb/remote/table.py`.
 7. Add unit test in `python/tests/test_table.py`.
-8. If you added a new public class or module-level function (not just a method on an
-   existing class), expose it in the API reference. See "Python API reference" below.

 TypeScript bindings changes:

@@ -105,33 +103,6 @@ TypeScript bindings changes:
 5. Add test in `nodejs/__test__/table.test.ts`.
 6. Run `npm run docs` to generate TypeScript documentation.

-## Python API reference
-
-`docs/src/python/python.md` is the entire Python API reference. It is maintained by
-hand, and anything not listed there is not rendered at all, so new public classes and
-module-level functions have to be added explicitly. How depends on the module:
-
-* `lancedb.index`, `lancedb.embeddings`, `lancedb.remote`, and `lancedb.rerankers` are
-  rendered by a single directive each, driven by the module's `__all__`. Add the new
-  name to `__all__` and it appears; forget, and it is silently omitted.
-* Everything else (`lancedb`, `lancedb.table`, `lancedb.query`, `lancedb.db`, ...) is
-  listed symbol by symbol. Add a `::: lancedb.<module>.<Name>` line to the matching
-  section, and remember that the page separates synchronous and asynchronous APIs.
-
-Deliberately undocumented: concrete implementations reached through an abstract base
-(`LanceTable`, `LanceDBConnection`, `RemoteDBConnection`), query base classes already
-covered by `inherited_members`, and internal helpers.
-
-Cross-references in docstrings use mkdocstrings syntax, `[text][lancedb.table.Table]`.
-Plain relative links such as `[Table](Table)` do not resolve. To check your work:
-
-```shell
-pip install -r docs/requirements.txt
-cd docs && PYTHONPATH=. mkdocs build
-```
-
-The docs site only builds on pushes to `main`, so this is not covered by PR CI.
-
 ## Review Guidelines

 Please consider the following when reviewing code contributions.
@@ -13,20 +13,20 @@ categories = ["database-implementations"]
 rust-version = "1.91.0"

 [workspace.dependencies]
-lance = { "version" = "=11.0.0-beta.3", default-features = false, "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
-lance-core = { "version" = "=11.0.0-beta.3", "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
-lance-datagen = { "version" = "=11.0.0-beta.3", "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
-lance-file = { "version" = "=11.0.0-beta.3", "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
-lance-io = { "version" = "=11.0.0-beta.3", default-features = false, "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
-lance-index = { "version" = "=11.0.0-beta.3", "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
-lance-linalg = { "version" = "=11.0.0-beta.3", "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
-lance-namespace = { "version" = "=11.0.0-beta.3", "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
-lance-namespace-impls = { "version" = "=11.0.0-beta.3", default-features = false, "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
-lance-table = { "version" = "=11.0.0-beta.3", "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
-lance-testing = { "version" = "=11.0.0-beta.3", "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
-lance-datafusion = { "version" = "=11.0.0-beta.3", "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
-lance-encoding = { "version" = "=11.0.0-beta.3", "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
-lance-arrow = { "version" = "=11.0.0-beta.3", "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
+lance = { "version" = "=9.0.0-beta.23", default-features = false, "tag" = "v9.0.0-beta.23", "git" = "https://github.com/lance-format/lance.git" }
+lance-core = { "version" = "=9.0.0-beta.23", "tag" = "v9.0.0-beta.23", "git" = "https://github.com/lance-format/lance.git" }
+lance-datagen = { "version" = "=9.0.0-beta.23", "tag" = "v9.0.0-beta.23", "git" = "https://github.com/lance-format/lance.git" }
+lance-file = { "version" = "=9.0.0-beta.23", "tag" = "v9.0.0-beta.23", "git" = "https://github.com/lance-format/lance.git" }
+lance-io = { "version" = "=9.0.0-beta.23", default-features = false, "tag" = "v9.0.0-beta.23", "git" = "https://github.com/lance-format/lance.git" }
+lance-index = { "version" = "=9.0.0-beta.23", "tag" = "v9.0.0-beta.23", "git" = "https://github.com/lance-format/lance.git" }
+lance-linalg = { "version" = "=9.0.0-beta.23", "tag" = "v9.0.0-beta.23", "git" = "https://github.com/lance-format/lance.git" }
+lance-namespace = { "version" = "=9.0.0-beta.23", "tag" = "v9.0.0-beta.23", "git" = "https://github.com/lance-format/lance.git" }
+lance-namespace-impls = { "version" = "=9.0.0-beta.23", default-features = false, "tag" = "v9.0.0-beta.23", "git" = "https://github.com/lance-format/lance.git" }
+lance-table = { "version" = "=9.0.0-beta.23", "tag" = "v9.0.0-beta.23", "git" = "https://github.com/lance-format/lance.git" }
+lance-testing = { "version" = "=9.0.0-beta.23", "tag" = "v9.0.0-beta.23", "git" = "https://github.com/lance-format/lance.git" }
+lance-datafusion = { "version" = "=9.0.0-beta.23", "tag" = "v9.0.0-beta.23", "git" = "https://github.com/lance-format/lance.git" }
+lance-encoding = { "version" = "=9.0.0-beta.23", "tag" = "v9.0.0-beta.23", "git" = "https://github.com/lance-format/lance.git" }
+lance-arrow = { "version" = "=9.0.0-beta.23", "tag" = "v9.0.0-beta.23", "git" = "https://github.com/lance-format/lance.git" }
 ahash = "0.8"
 # Note that this one does not include pyarrow
 arrow = { version = "58.0.0", optional = false }
@@ -39,20 +39,20 @@ arrow-schema = "58.0.0"
 arrow-select = "58.0.0"
 arrow-cast = "58.0.0"
 async-trait = "0"
-datafusion = { version = "54.0.0", default-features = false }
-datafusion-catalog = "54.0.0"
-datafusion-common = { version = "54.0.0", default-features = false }
-datafusion-execution = "54.0.0"
-datafusion-expr = "54.0.0"
-datafusion-functions = "54.0.0"
-datafusion-physical-plan = "54.0.0"
-datafusion-physical-expr = "54.0.0"
-datafusion-sql = "54.0.0"
+datafusion = { version = "53.0.0", default-features = false }
+datafusion-catalog = "53.0.0"
+datafusion-common = { version = "53.0.0", default-features = false }
+datafusion-execution = "53.0.0"
+datafusion-expr = "53.0.0"
+datafusion-functions = "53.0.0"
+datafusion-physical-plan = "53.0.0"
+datafusion-physical-expr = "53.0.0"
+datafusion-sql = "53.0.0"
 env_logger = "0.11"
 half = { "version" = "2.7.1", default-features = false, features = [
    "num-traits",
 ] }
-futures = "0.3"
+futures = "0"
 log = "0.4"
 metrics = "0.24"
 metrics-util = "0.19"
@@ -64,6 +64,7 @@ snafu = "0.8"
 url = "2"
 num-traits = "0.2"
 regex = "1.10"
+lazy_static = "1"
 semver = "1.0.25"
 chrono = "0.4"

@@ -2,9 +2,9 @@ set -e

 RELEASE_TYPE=${1:-"stable"}
 BUMP_MINOR=${2:-false}
-HEAD_SHA=$(git rev-parse HEAD)
+TAG_PREFIX=${3:-"v"} # Such as "python-v"
+HEAD_SHA=${4:-$(git rev-parse HEAD)}

-readonly TAG_PREFIX="v"
 readonly SELF_DIR=$(cd "$( dirname "${BASH_SOURCE[0]}" )" && pwd )

 PREV_TAG=$(git tag --sort='version:refname' | grep ^$TAG_PREFIX | python $SELF_DIR/semver_sort.py $TAG_PREFIX | tail -n 1)
@@ -12,7 +12,7 @@ echo "Found previous tag $PREV_TAG"

 # Initially, we don't want to tag if we are doing stable, because we will bump
 # again later. See comment at end for why.
-if [[ "$RELEASE_TYPE" == 'stable' ]]; then
+if [[ "$RELEASE_TYPE" == 'stable' ]]; then 
  BUMP_ARGS="--no-tag"
 fi

@@ -51,11 +51,6 @@ plugins:
          paths: [../python/python]
          options:
            docstring_style: numpy
-            docstring_options:
-              # Attributes documented in a `Parameters` section, and pydantic
-              # dataclasses whose `__init__` griffe cannot see statically, both
-              # trip this check. It reports nothing actionable here.
-              warn_unknown_params: false
            heading_level: 3
            show_signature_annotations: true
            show_root_heading: true
@@ -453,16 +453,6 @@ paths:
                    The metric type to use for the index. l2, Cosine, Dot are supported.
                index_type:
                  type: string
-                custom_stop_words:
-                  type: [array, "null"]
-                  items:
-                    type: string
-                  description: |
-                    The custom stop-word list for an FTS index. A non-null
-                    array replaces the language's built-in stop-word list and is only
-                    applied when remove_stop_words is enabled. Null uses the built-in
-                    language list, while an empty array explicitly replaces it with no
-                    stop words.
      responses:
        "200":
          description: Index successfully created
@@ -520,4 +510,4 @@ paths:
        "401":
          $ref: "#/components/responses/unauthorized"
        "404":
-          $ref: "#/components/responses/not_found"
+          $ref: "#/components/responses/not_found"
@@ -14,7 +14,7 @@ Add the following dependency to your `pom.xml`:
 <dependency>
    <groupId>com.lancedb</groupId>
    <artifactId>lancedb-core</artifactId>
-    <version>0.37.1-beta.1</version>
+    <version>0.32.0-beta.2</version>
 </dependency>
 ```

@@ -249,57 +249,6 @@ try (BufferAllocator allocator = new RootAllocator();
 }
 ```

-### Creating an Empty Table
-
-To create an empty table, send an Arrow IPC stream that contains the table schema and no record batches.
-The schema in the IPC stream becomes the table schema, and rows can be inserted later.
-
-```java
-import org.lance.namespace.model.CreateTableRequest;
-import org.lance.namespace.model.CreateTableResponse;
-import org.apache.arrow.memory.BufferAllocator;
-import org.apache.arrow.memory.RootAllocator;
-import org.apache.arrow.vector.VectorSchemaRoot;
-import org.apache.arrow.vector.ipc.ArrowStreamWriter;
-import org.apache.arrow.vector.types.FloatingPointPrecision;
-import org.apache.arrow.vector.types.pojo.ArrowType;
-import org.apache.arrow.vector.types.pojo.Field;
-import org.apache.arrow.vector.types.pojo.FieldType;
-import org.apache.arrow.vector.types.pojo.Schema;
-
-import java.io.ByteArrayOutputStream;
-import java.nio.channels.Channels;
-import java.util.Arrays;
-
-Schema schema = new Schema(Arrays.asList(
-    new Field("id", FieldType.nullable(new ArrowType.Int(32, true)), null),
-    new Field("name", FieldType.nullable(new ArrowType.Utf8()), null),
-    new Field("embedding",
-        FieldType.nullable(new ArrowType.FixedSizeList(128)),
-        Arrays.asList(new Field("item",
-            FieldType.nullable(new ArrowType.FloatingPoint(FloatingPointPrecision.SINGLE)),
-            null)))
-));
-
-byte[] emptyTableData;
-try (BufferAllocator allocator = new RootAllocator();
-     VectorSchemaRoot root = VectorSchemaRoot.create(schema, allocator)) {
-    root.setRowCount(0);
-
-    ByteArrayOutputStream out = new ByteArrayOutputStream();
-    try (ArrowStreamWriter writer = new ArrowStreamWriter(root, null, Channels.newChannel(out))) {
-        writer.start();
-        writer.end();
-    }
-    emptyTableData = out.toByteArray();
-}
-
-CreateTableRequest request = new CreateTableRequest();
-request.setId(Arrays.asList("my_namespace", "empty_table"));
-
-CreateTableResponse response = namespaceClient.createTable(request, emptyTableData);
-```
-
 ### Insert

 ```java
@@ -482,88 +431,9 @@ query.setVector(vector);
 byte[] result = namespaceClient.queryTable(query);
 ```

-## Indexing
+### Reading Query Results

-The Java SDK exposes the REST namespace index operations through the same `LanceNamespace` client.
-Index creation runs asynchronously, so use `listTableIndices` or `describeTableIndexStats` to check progress.
-
-### Creating a Vector Index
-
-```java
-import org.lance.namespace.model.CreateTableIndexRequest;
-import org.lance.namespace.model.CreateTableIndexResponse;
-
-CreateTableIndexRequest request = new CreateTableIndexRequest();
-request.setId(Arrays.asList("my_namespace", "my_table"));
-request.setColumn("embedding");
-request.setIndexType("IVF_PQ");
-request.setDistanceType("cosine");
-request.setName("embedding_idx");
-
-CreateTableIndexResponse response = namespaceClient.createTableIndex(request);
-System.out.println("Index transaction: " + response.getTransactionId());
-```
-
-### Creating a Scalar Index
-
-```java
-import org.lance.namespace.model.CreateTableIndexRequest;
-import org.lance.namespace.model.CreateTableScalarIndexResponse;
-
-CreateTableIndexRequest request = new CreateTableIndexRequest();
-request.setId(Arrays.asList("my_namespace", "my_table"));
-request.setColumn("category");
-request.setIndexType("BTREE");
-request.setName("category_idx");
-
-CreateTableScalarIndexResponse response = namespaceClient.createTableScalarIndex(request);
-System.out.println("Index transaction: " + response.getTransactionId());
-```
-
-### Creating a Full Text Search Index
-
-```java
-import org.lance.namespace.model.CreateTableIndexRequest;
-import org.lance.namespace.model.CreateTableScalarIndexResponse;
-
-CreateTableIndexRequest request = new CreateTableIndexRequest();
-request.setId(Arrays.asList("my_namespace", "my_table"));
-request.setColumn("text_column");
-request.setIndexType("FTS");
-request.setName("text_idx");
-request.setBaseTokenizer("simple");
-request.setLowerCase(true);
-request.setWithPosition(true);
-
-CreateTableScalarIndexResponse response = namespaceClient.createTableScalarIndex(request);
-System.out.println("Index transaction: " + response.getTransactionId());
-```
-
-### Listing Indexes
-
-```java
-import org.lance.namespace.model.IndexContent;
-import org.lance.namespace.model.ListTableIndicesRequest;
-import org.lance.namespace.model.ListTableIndicesResponse;
-
-ListTableIndicesRequest request = new ListTableIndicesRequest();
-request.setId(Arrays.asList("my_namespace", "my_table"));
-
-ListTableIndicesResponse response = namespaceClient.listTableIndices(request);
-for (IndexContent index : response.getIndexes()) {
-    System.out.println(index.getIndexName() + ": " + index.getStatus());
-}
-```
-
-!!! note
-    The current Java namespace API exposes index type, index name, distance type, and full text search tokenizer options.
-    IVF training parameters such as `num_partitions` are not exposed by `CreateTableIndexRequest` yet.
-    To make those configurable from Java, the namespace API must add those fields first.
-
-## Reading Query Results
-
-Query results are returned as bytes in Apache Arrow IPC file format. Put the byte-channel
-adapter behind a small helper so query code can work with `ArrowFileReader` directly:
+Query results are returned in Apache Arrow IPC file format. Here's how to read them:

 ```java
 import org.apache.arrow.vector.ipc.ArrowFileReader;
@@ -571,50 +441,45 @@ import org.apache.arrow.vector.VectorSchemaRoot;
 import org.apache.arrow.memory.BufferAllocator;
 import org.apache.arrow.memory.RootAllocator;

-import java.io.IOException;
 import java.nio.ByteBuffer;
 import java.nio.channels.SeekableByteChannel;

-final class ArrowIpc {
-    static ArrowFileReader openFileReader(byte[] data, BufferAllocator allocator) throws IOException {
-        return new ArrowFileReader(new ByteArraySeekableByteChannel(data), allocator);
+// Helper class to read Arrow data from byte array
+class ByteArraySeekableByteChannel implements SeekableByteChannel {
+    private final byte[] data;
+    private long position = 0;
+    private boolean isOpen = true;
+
+    public ByteArraySeekableByteChannel(byte[] data) {
+        this.data = data;
    }

-    private static final class ByteArraySeekableByteChannel implements SeekableByteChannel {
-        private final byte[] data;
-        private long position = 0;
-        private boolean isOpen = true;
-
-        private ByteArraySeekableByteChannel(byte[] data) {
-            this.data = data;
-        }
-
-        @Override
-        public int read(ByteBuffer dst) {
-            int remaining = dst.remaining();
-            int available = (int) (data.length - position);
-            if (available <= 0) return -1;
-            int toRead = Math.min(remaining, available);
-            dst.put(data, (int) position, toRead);
-            position += toRead;
-            return toRead;
-        }
-
-        @Override public long position() { return position; }
-        @Override public SeekableByteChannel position(long newPosition) { position = newPosition; return this; }
-        @Override public long size() { return data.length; }
-        @Override public boolean isOpen() { return isOpen; }
-        @Override public void close() { isOpen = false; }
-        @Override public int write(ByteBuffer src) { throw new UnsupportedOperationException(); }
-        @Override public SeekableByteChannel truncate(long size) { throw new UnsupportedOperationException(); }
+    @Override
+    public int read(ByteBuffer dst) {
+        int remaining = dst.remaining();
+        int available = (int) (data.length - position);
+        if (available <= 0) return -1;
+        int toRead = Math.min(remaining, available);
+        dst.put(data, (int) position, toRead);
+        position += toRead;
+        return toRead;
    }
+
+    @Override public long position() { return position; }
+    @Override public SeekableByteChannel position(long newPosition) { position = newPosition; return this; }
+    @Override public long size() { return data.length; }
+    @Override public boolean isOpen() { return isOpen; }
+    @Override public void close() { isOpen = false; }
+    @Override public int write(ByteBuffer src) { throw new UnsupportedOperationException(); }
+    @Override public SeekableByteChannel truncate(long size) { throw new UnsupportedOperationException(); }
 }

 // Read query results
 byte[] queryResult = namespaceClient.queryTable(query);

 try (BufferAllocator allocator = new RootAllocator();
-     ArrowFileReader reader = ArrowIpc.openFileReader(queryResult, allocator)) {
+     ArrowFileReader reader = new ArrowFileReader(
+         new ByteArraySeekableByteChannel(queryResult), allocator)) {

    for (int i = 0; i < reader.getRecordBlocks().size(); i++) {
        reader.loadRecordBatch(reader.getRecordBlocks().get(i));
@@ -1,7 +1,7 @@
 # Contributing to LanceDB Typescript

 This document outlines the process for contributing to LanceDB Typescript.
-For general contribution guidelines, see [CONTRIBUTING.md](https://github.com/lancedb/lancedb/blob/main/CONTRIBUTING.md).
+For general contribution guidelines, see [CONTRIBUTING.md](../CONTRIBUTING.md).

 ## Project layout

@@ -83,24 +83,6 @@ Delete a branch.

 ***

-### diff()
-
-```ts
-diff(fromBranch): Promise<BranchDiff>
-```
-
-Compare a branch against main without modifying either branch.
-
-#### Parameters
-
-* **fromBranch**: `string`
-
-#### Returns
-
-`Promise`&lt;[`BranchDiff`](../interfaces/BranchDiff.md)&gt;
-
-***
-
 ### list()

 ```ts
@@ -112,28 +94,3 @@ List all branches, mapping name to branch metadata.
 #### Returns

 `Promise`&lt;`Record`&lt;`string`, [`BranchContents`](BranchContents.md)&gt;&gt;
-
-***
-
-### merge()
-
-```ts
-merge(fromBranch, dryRun): Promise<MergeBranchResult>
-```
-
-Merge a branch into main.
-
-Set `dryRun` to `true` to preview the merge. A rejected merge resolves
-with `status: "rejected"` instead of throwing.
-
-#### Parameters
-
-* **fromBranch**: `string`
-    Branch to merge from.
-
-* **dryRun**: `boolean` = `false`
-    When true, only preview the merge. Defaults to false.
-
-#### Returns
-
-`Promise`&lt;[`MergeBranchResult`](../interfaces/MergeBranchResult.md)&gt;
@@ -25,27 +25,6 @@ the underlying connection has been closed.

 ## Methods

-### cancelJob()
-
-```ts
-abstract cancelJob(jobId): Promise<boolean>
-```
-
-Request cancellation of a server-side job by id.
-
-Resolves to true if the server accepted the cancellation, false if no
-such job exists. Cancelling an already-terminal job is a no-op success.
-
-#### Parameters
-
-* **jobId**: `string`
-
-#### Returns
-
-`Promise`&lt;`boolean`&gt;
-
-***
-
 ### cloneTable()

 ```ts
@@ -386,26 +365,6 @@ Drop an existing table.

 ***

-### 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
@@ -420,62 +379,6 @@ 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
-abstract listJobs(): Promise<JobInfo[]>
-```
-
-List server-side jobs across the database's tables.
-
-#### Returns
-
-`Promise`&lt;[`JobInfo`](../interfaces/JobInfo.md)[]&gt;
-
-***
-
 ### listNamespaces()

 ```ts
@@ -1,83 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / Job
-
-# Class: Job
-
-A handle to an operation that may still be running.
-
-## Constructors
-
-### new Job()
-
-```ts
-new Job(): Job
-```
-
-#### Returns
-
-[`Job`](Job.md)
-
-## Accessors
-
-### 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.
-
-#### Returns
-
-`null` \| `string`
-
-## Methods
-
-### cancel()
-
-```ts
-cancel(): Promise<void>
-```
-
-Request cancellation. Cancelling a finished operation is a no-op.
-
-#### Returns
-
-`Promise`&lt;`void`&gt;
-
-***
-
-### status()
-
-```ts
-status(): Promise<string>
-```
-
-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. States a newer server reports that this
-client version does not know pass through as-is.
-
-#### Returns
-
-`Promise`&lt;`string`&gt;
-
-***
-
-### wait()
-
-```ts
-wait(): Promise<void>
-```
-
-Wait until the operation reaches a terminal state.
-
-#### Returns
-
-`Promise`&lt;`void`&gt;
@@ -76,23 +76,24 @@ the query optimizer chooses a suboptimal path.

 ***

-### useLsm()
+### useLsmWrite()

 ```ts
-useLsm(enable): MergeInsertBuilder
+useLsmWrite(useLsmWrite): MergeInsertBuilder
 ```

-Control MemWAL routing for this merge.
+Controls whether the merge uses the MemWAL LSM write path.

 By default (unset), a `mergeInsert` on a table with an LSM write spec is
-routed through Lance's MemWAL shard writer, and a table without one uses the
-standard path.
+routed through Lance's MemWAL shard writer, and a table without one uses
+the standard path. Pass `false` to force the standard path even when a
+spec is set. Pass `true` to require a spec — `mergeInsert` rejects if none
+is installed.

 #### Parameters

-* **enable**: `boolean`
-    `true` forces MemWAL routing and errors if the table has no
-    LSM write spec. `false` forces the standard write path even when a spec is set.
+* **useLsmWrite**: `boolean`
+    Whether to use the LSM write path.

 #### Returns

@@ -33,7 +33,7 @@ protected inner: Query | Promise<Query>;
 ### analyzePlan()

 ```ts
-analyzePlan(distributedMetrics?): Promise<string>
+analyzePlan(): Promise<string>
 ```

 Executes the query and returns the physical query plan annotated with runtime metrics.
@@ -41,12 +41,6 @@ Executes the query and returns the physical query plan annotated with runtime me
 This is useful for debugging and performance analysis, as it shows how the query was executed
 and includes metrics such as elapsed time, rows processed, and I/O statistics.

-#### Parameters
-
-* **distributedMetrics?**: [`AnalyzePlanDistributedMetrics`](../type-aliases/AnalyzePlanDistributedMetrics.md)
-    How distributed worker metrics are displayed for remote query plans.
-    Defaults to `"aggregate"`.
-
 #### Returns

 `Promise`&lt;`string`&gt;
@@ -497,42 +491,6 @@ ArrowTable.

 ***

-### useLsm()
-
-```ts
-useLsm(enable): this
-```
-
-Control MemWAL read routing for this query.
-
-By default (unset), when the table carries a MemWAL write spec (see
-[Table#setLsmWriteSpec](Table.md#setlsmwritespec)), reads are routed through the LSM scanner so
-they also return data written via the `mergeInsert` LSM path that has not yet
-been compacted into the base table (the active/frozen in-memory memtables and
-the flushed generations), deduplicated by primary key; a table without a spec
-reads the base table.
-
-#### Parameters
-
-* **enable**: `boolean`
-    `true` forces the LSM scanner and errors if the table has no
-    MemWAL write spec. `false` bypasses the MemWAL and reads the base table only,
-    even when a spec is present.
-    Note: the LSM scanner does not support every query shape (e.g. reranking,
-    hybrid search, `orderBy`). On a MemWAL table those shapes error unless
-    `useLsm(false)` is set, because a base-only read would silently exclude
-    un-compacted MemWAL data.
-
-#### Returns
-
-`this`
-
-#### Inherited from
-
-`StandardQueryBase.useLsm`
-
-***
-
 ### where()

 ```ts
@@ -38,7 +38,7 @@ protected inner: NativeQueryType | Promise<NativeQueryType>;
 ### analyzePlan()

 ```ts
-analyzePlan(distributedMetrics?): Promise<string>
+analyzePlan(): Promise<string>
 ```

 Executes the query and returns the physical query plan annotated with runtime metrics.
@@ -46,12 +46,6 @@ Executes the query and returns the physical query plan annotated with runtime me
 This is useful for debugging and performance analysis, as it shows how the query was executed
 and includes metrics such as elapsed time, rows processed, and I/O statistics.

-#### Parameters
-
-* **distributedMetrics?**: [`AnalyzePlanDistributedMetrics`](../type-aliases/AnalyzePlanDistributedMetrics.md)
-    How distributed worker metrics are displayed for remote query plans.
-    Defaults to `"aggregate"`.
-
 #### Returns

 `Promise`&lt;`string`&gt;
@@ -295,29 +295,6 @@ await table.createIndex("my_float_col");

 ***

-### createIndexAsync()
-
-```ts
-abstract createIndexAsync(column, options?): Promise<Job>
-```
-
-Create an index, returning a handle to the indexing job.
-
-The job may already be complete when returned; callers must not assume
-the index exists until [Job.wait](Job.md#wait) resolves.
-
-#### Parameters
-
-* **column**: `string`
-
-* **options?**: `Partial`&lt;[`IndexOptions`](../interfaces/IndexOptions.md)&gt;
-
-#### Returns
-
-`Promise`&lt;[`Job`](Job.md)&gt;
-
-***
-
 ### currentBranch()

 ```ts
@@ -431,10 +408,9 @@ Read the [LsmWriteSpec](../interfaces/LsmWriteSpec.md) currently installed on th

 Resolves to `undefined` when the MemWAL LSM write path is not enabled (no
 spec has been set, or it was removed with [Table#unsetLsmWriteSpec](Table.md#unsetlsmwritespec)).
-The returned spec mirrors what was passed to
-[Table#setLsmWriteSpec](Table.md#setlsmwritespec), except that `maintainedIndexes` always
-reports the concrete list resolved when the spec was set — `undefined`
-never round-trips.
+The returned spec — including its `maintainedIndexes` and
+`writerConfigDefaults` — mirrors what was passed to
+[Table#setLsmWriteSpec](Table.md#setlsmwritespec).

 #### Returns

@@ -807,11 +783,6 @@ All variants require the table to have an unenforced primary key
 ([Table#setUnenforcedPrimaryKey](Table.md#setunenforcedprimarykey)); bucket sharding additionally
 requires it to be the single column being bucketed.

-Omitting `maintainedIndexes` maintains every index on the table, resolved
-here, failing if one cannot be maintained — name them to install anyway.
-Naming them pins an exact set, and a still-building index is rejected
-rather than quietly omitted.
-
 #### Parameters

 * **spec**: [`LsmWriteSpec`](../interfaces/LsmWriteSpec.md)
@@ -29,7 +29,7 @@ protected inner: TakeQuery | Promise<TakeQuery>;
 ### analyzePlan()

 ```ts
-analyzePlan(distributedMetrics?): Promise<string>
+analyzePlan(): Promise<string>
 ```

 Executes the query and returns the physical query plan annotated with runtime metrics.
@@ -37,12 +37,6 @@ Executes the query and returns the physical query plan annotated with runtime me
 This is useful for debugging and performance analysis, as it shows how the query was executed
 and includes metrics such as elapsed time, rows processed, and I/O statistics.

-#### Parameters
-
-* **distributedMetrics?**: [`AnalyzePlanDistributedMetrics`](../type-aliases/AnalyzePlanDistributedMetrics.md)
-    How distributed worker metrics are displayed for remote query plans.
-    Defaults to `"aggregate"`.
-
 #### Returns

 `Promise`&lt;`string`&gt;
@@ -273,29 +267,6 @@ ArrowTable.

 ***

-### useLsm()
-
-```ts
-useLsm(enable): this
-```
-
-Control MemWAL read routing for this take query.
-
-`false` bypasses the MemWAL and reads the base table only — the escape hatch,
-since take-by-row-id/offset is not supported on the LSM scanner and, on a
-MemWAL table, auto-routes to it and errors otherwise.
-
-#### Parameters
-
-* **enable**: `boolean`
-    `false` reads the base table only.
-
-#### Returns
-
-`this`
-
-***
-
 ### withRowId()

 ```ts
@@ -51,7 +51,7 @@ addQueryVector(vector): VectorQuery
 ### analyzePlan()

 ```ts
-analyzePlan(distributedMetrics?): Promise<string>
+analyzePlan(): Promise<string>
 ```

 Executes the query and returns the physical query plan annotated with runtime metrics.
@@ -59,12 +59,6 @@ Executes the query and returns the physical query plan annotated with runtime me
 This is useful for debugging and performance analysis, as it shows how the query was executed
 and includes metrics such as elapsed time, rows processed, and I/O statistics.

-#### Parameters
-
-* **distributedMetrics?**: [`AnalyzePlanDistributedMetrics`](../type-aliases/AnalyzePlanDistributedMetrics.md)
-    How distributed worker metrics are displayed for remote query plans.
-    Defaults to `"aggregate"`.
-
 #### Returns

 `Promise`&lt;`string`&gt;
@@ -746,42 +740,6 @@ ArrowTable.

 ***

-### useLsm()
-
-```ts
-useLsm(enable): this
-```
-
-Control MemWAL read routing for this query.
-
-By default (unset), when the table carries a MemWAL write spec (see
-[Table#setLsmWriteSpec](Table.md#setlsmwritespec)), reads are routed through the LSM scanner so
-they also return data written via the `mergeInsert` LSM path that has not yet
-been compacted into the base table (the active/frozen in-memory memtables and
-the flushed generations), deduplicated by primary key; a table without a spec
-reads the base table.
-
-#### Parameters
-
-* **enable**: `boolean`
-    `true` forces the LSM scanner and errors if the table has no
-    MemWAL write spec. `false` bypasses the MemWAL and reads the base table only,
-    even when a spec is present.
-    Note: the LSM scanner does not support every query shape (e.g. reranking,
-    hybrid search, `orderBy`). On a MemWAL table those shapes error unless
-    `useLsm(false)` is set, because a base-only read would silently exclude
-    un-compacted MemWAL data.
-
-#### Returns
-
-`this`
-
-#### Inherited from
-
-`StandardQueryBase.useLsm`
-
-***
-
 ### where()

 ```ts
@@ -25,7 +25,6 @@
 - [Connection](classes/Connection.md)
 - [HeaderProvider](classes/HeaderProvider.md)
 - [Index](classes/Index.md)
- [Job](classes/Job.md)
 - [MakeArrowTableOptions](classes/MakeArrowTableOptions.md)
 - [MatchQuery](classes/MatchQuery.md)
 - [MergeInsertBuilder](classes/MergeInsertBuilder.md)
@@ -53,11 +52,6 @@
 - [AddDataOptions](interfaces/AddDataOptions.md)
 - [AddResult](interfaces/AddResult.md)
 - [AlterColumnsResult](interfaces/AlterColumnsResult.md)
- [BranchColumnChange](interfaces/BranchColumnChange.md)
- [BranchColumnSummary](interfaces/BranchColumnSummary.md)
- [BranchDiff](interfaces/BranchDiff.md)
- [BranchIndexSummary](interfaces/BranchIndexSummary.md)
- [BranchRowCountSummary](interfaces/BranchRowCountSummary.md)
 - [ClientConfig](interfaces/ClientConfig.md)
 - [ColumnAlteration](interfaces/ColumnAlteration.md)
 - [ColumnOrdering](interfaces/ColumnOrdering.md)
@@ -89,15 +83,9 @@
 - [IvfFlatOptions](interfaces/IvfFlatOptions.md)
 - [IvfPqOptions](interfaces/IvfPqOptions.md)
 - [IvfRqOptions](interfaces/IvfRqOptions.md)
- [JobDescription](interfaces/JobDescription.md)
- [JobFailureInfo](interfaces/JobFailureInfo.md)
- [JobInfo](interfaces/JobInfo.md)
 - [ListNamespacesOptions](interfaces/ListNamespacesOptions.md)
 - [ListNamespacesResponse](interfaces/ListNamespacesResponse.md)
 - [LsmWriteSpec](interfaces/LsmWriteSpec.md)
- [MergeBlocker](interfaces/MergeBlocker.md)
- [MergeBranchResult](interfaces/MergeBranchResult.md)
- [MergePreview](interfaces/MergePreview.md)
 - [MergeResult](interfaces/MergeResult.md)
 - [NativeOAuthConfig](interfaces/NativeOAuthConfig.md)
 - [OAuthConfig](interfaces/OAuthConfig.md)
@@ -130,7 +118,6 @@

 ## Type Aliases

- [AnalyzePlanDistributedMetrics](type-aliases/AnalyzePlanDistributedMetrics.md)
 - [BaseTokenizer](type-aliases/BaseTokenizer.md)
 - [Data](type-aliases/Data.md)
 - [DataLike](type-aliases/DataLike.md)
@@ -1,33 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / BranchColumnChange
-
-# Interface: BranchColumnChange
-
-A column whose definition differs between main and the branch.
-
-## Properties
-
-### branch
-
-```ts
-branch: BranchColumnSummary;
-```
-
-***
-
-### main
-
-```ts
-main: BranchColumnSummary;
-```
-
-***
-
-### name
-
-```ts
-name: string;
-```
@@ -1,33 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / BranchColumnSummary
-
-# Interface: BranchColumnSummary
-
-Summary of a column in a branch diff.
-
-## Properties
-
-### dataType
-
-```ts
-dataType: string;
-```
-
-***
-
-### name
-
-```ts
-name: string;
-```
-
-***
-
-### nullable
-
-```ts
-nullable: boolean;
-```
@@ -1,129 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / BranchDiff
-
-# Interface: BranchDiff
-
-Read-only comparison of a branch against main.
-
-## Properties
-
-### addedColumns
-
-```ts
-addedColumns: BranchColumnSummary[];
-```
-
-***
-
-### addedIndexes
-
-```ts
-addedIndexes: BranchIndexSummary[];
-```
-
-***
-
-### baseMoved
-
-```ts
-baseMoved: boolean;
-```
-
-***
-
-### branchVersion
-
-```ts
-branchVersion: number;
-```
-
-***
-
-### changedColumns
-
-```ts
-changedColumns: BranchColumnChange[];
-```
-
-***
-
-### fromBranch
-
-```ts
-fromBranch: string;
-```
-
-***
-
-### mainVersion
-
-```ts
-mainVersion: number;
-```
-
-***
-
-### mergeBlockers
-
-```ts
-mergeBlockers: MergeBlocker[];
-```
-
-***
-
-### mergeable
-
-```ts
-mergeable: boolean;
-```
-
-***
-
-### parentVersion
-
-```ts
-parentVersion: number;
-```
-
-***
-
-### removedColumns
-
-```ts
-removedColumns: BranchColumnSummary[];
-```
-
-***
-
-### removedIndexes
-
-```ts
-removedIndexes: BranchIndexSummary[];
-```
-
-***
-
-### rowCountBranch
-
-```ts
-rowCountBranch: number;
-```
-
-***
-
-### rowCountMain
-
-```ts
-rowCountMain: number;
-```
-
-***
-
-### rowSummary
-
-```ts
-rowSummary: BranchRowCountSummary;
-```
@@ -1,41 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / BranchIndexSummary
-
-# Interface: BranchIndexSummary
-
-Summary of an index in a branch diff.
-
-## Properties
-
-### columns
-
-```ts
-columns: string[];
-```
-
-***
-
-### indexName
-
-```ts
-indexName: string;
-```
-
-***
-
-### indexType?
-
-```ts
-optional indexType: string;
-```
-
-***
-
-### status
-
-```ts
-status: string;
-```
@@ -1,57 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / BranchRowCountSummary
-
-# Interface: BranchRowCountSummary
-
-Row-level comparison between main and the branch.
-
-## Properties
-
-### deltaAvailable
-
-```ts
-deltaAvailable: boolean;
-```
-
-***
-
-### inputsChanged
-
-```ts
-inputsChanged: number;
-```
-
-***
-
-### newOnBase
-
-```ts
-newOnBase: number;
-```
-
-***
-
-### newOnBranch
-
-```ts
-newOnBranch: number;
-```
-
-***
-
-### staleRecompute
-
-```ts
-staleRecompute: number;
-```
-
-***
-
-### unchanged
-
-```ts
-unchanged: number;
-```
@@ -43,34 +43,6 @@ The following tokenizers are available:

 ***

-### blockSize?
-
-```ts
-optional blockSize: 128 | 256;
-```
-
-Number of documents per compressed posting block.
-
-The default is 128. Supported values are 128 and 256. A value of 256 uses
-the experimental FTS V3 format and may introduce breaking changes.
-
-***
-
-### customStopWords?
-
-```ts
-optional customStopWords: string[];
-```
-
-Custom stop words that replace the built-in list for `language`.
-
-This option only affects tokenization when `removeStopWords` is true.
-
-`undefined` keeps the built-in language list. An empty array explicitly
-replaces it with no stop words.
-
-***
-
 ### language?

 ```ts
@@ -1,66 +0,0 @@
-[**@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".
@@ -1,33 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / JobFailureInfo
-
-# Interface: JobFailureInfo
-
-The server's account of why a job failed.
-
-## Properties
-
-### message?
-
-```ts
-optional message: string;
-```
-
-***
-
-### phase?
-
-```ts
-optional phase: string;
-```
-
-***
-
-### retryable?
-
-```ts
-optional retryable: boolean;
-```
@@ -1,58 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / JobInfo
-
-# Interface: JobInfo
-
-A row from `Connection.listJobs`: one server-side job.
-
-## Properties
-
-### createdAtMillis
-
-```ts
-createdAtMillis: number;
-```
-
-When the job was created, in milliseconds since the epoch.
-
-***
-
-### jobId
-
-```ts
-jobId: string;
-```
-
-The job id -- what `Connection.getJob` and `Connection.cancelJob`
-accept.
-
-***
-
-### jobType
-
-```ts
-jobType: string;
-```
-
-***
-
-### state
-
-```ts
-state: string;
-```
-
-Lifecycle state: "running", "finished", "failed", or "cancelled".
-
-***
-
-### table
-
-```ts
-table: string;
-```
-
-The table the job runs against, without URI or namespace.
@@ -34,9 +34,7 @@ Bucket and identity variants: the sharding column.
 optional maintainedIndexes: string[];
 ```

-Indexes the MemWAL keeps up to date. Omit to maintain every supported
-index, resolved on install — a snapshot, so indexes created later are not
-maintained. Pass `[]` for none.
+Names of indexes the MemWAL should keep up to date during writes.

 ***

@@ -1,25 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / MergeBlocker
-
-# Interface: MergeBlocker
-
-A reason why a branch cannot currently be merged.
-
-## Properties
-
-### code
-
-```ts
-code: string;
-```
-
-***
-
-### message
-
-```ts
-message: string;
-```
@@ -1,46 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / MergeBranchResult
-
-# Interface: MergeBranchResult
-
-Result of previewing or attempting a branch merge.
-
-## Properties
-
-### diff
-
-```ts
-diff: BranchDiff;
-```
-
-***
-
-### mainVersionAfter?
-
-```ts
-optional mainVersionAfter: number;
-```
-
-***
-
-### preview
-
-```ts
-preview: MergePreview;
-```
-
-***
-
-### status
-
-```ts
-status:
-  | "unknown"
-  | "rejected"
-  | "ready"
-  | "notImplemented"
-  | "merged";
-```
@@ -1,17 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / MergePreview
-
-# Interface: MergePreview
-
-Changes that would be, or were, promoted by a branch merge.
-
-## Properties
-
-### promotedColumns
-
-```ts
-promotedColumns: string[];
-```
@@ -44,7 +44,4 @@ The number of rows in the table
 totalBytes: number;
 ```

-The total size, in bytes, of the table's data files, index files, and
-overlay files
-
-Read from the manifest, so this excludes deletion files and manifests.
+The total number of bytes in the table
@@ -30,21 +30,6 @@ The tokenizer to use. The default is "simple".

 ***

-### customStopWords?
-
-```ts
-optional customStopWords: string[];
-```
-
-Custom stop words that replace the built-in list for `language`.
-
-This option only affects tokenization when `removeStopWords` is true.
-
-`undefined` keeps the built-in language list. An empty array explicitly
-replaces it with no stop words.
-
-***
-
 ### language?

 ```ts
@@ -1,11 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / AnalyzePlanDistributedMetrics
-
-# Type Alias: AnalyzePlanDistributedMetrics
-
-```ts
-type AnalyzePlanDistributedMetrics: "aggregate" | "per_worker" | "full";
-```
@@ -26,18 +26,6 @@ is also an [asynchronous API client](#connections-asynchronous).

 ::: lancedb.db.DBConnection

-::: lancedb.Session
-
-## Namespaces (Synchronous)
-
-A namespace-backed connection resolves tables through a
-[Lance namespace](https://lance-format.github.io/lance-namespace/) service instead of
-listing a storage directory.
-
-::: lancedb.connect_namespace
-
-::: lancedb.namespace.LanceNamespaceDBConnection
-
 ## Tables (Synchronous)

 ::: lancedb.table.Table
@@ -46,12 +34,8 @@ listing a storage directory.

 ::: lancedb.table.FragmentSummaryStats

-::: lancedb.table.TableStatistics
-
 ::: lancedb.table.Tags

-::: lancedb.table.Branches
-
 ## Expressions

 Type-safe expression builder for filters and projections. Use these instead
@@ -78,46 +62,29 @@ of raw SQL strings with [where][lancedb.query.LanceQueryBuilder.where] and

 ::: lancedb.query.LanceHybridQueryBuilder

-::: lancedb.query.LanceEmptyQueryBuilder
-
-::: lancedb.query.LanceTakeQueryBuilder
-
-## Full text queries
-
-Structured full text queries can be passed to
-[Table.search][lancedb.table.Table.search] or
-[AsyncTable.search][lancedb.table.AsyncTable.search] in place of a query string,
-and combined with [BooleanQuery][lancedb.query.BooleanQuery].
-
-::: lancedb.query.FullTextQuery
-
-::: lancedb.query.MatchQuery
-
-::: lancedb.query.PhraseQuery
-
-::: lancedb.query.BoostQuery
-
-::: lancedb.query.MultiMatchQuery
-
-::: lancedb.query.BooleanQuery
-
-::: lancedb.query.FullTextOperator
-
-::: lancedb.query.Occur
-
 ## Embeddings

-::: lancedb.embeddings
-    options:
-      show_root_heading: false
-      show_root_toc_entry: false
+::: lancedb.embeddings.registry.EmbeddingFunctionRegistry
+
+::: lancedb.embeddings.base.EmbeddingFunctionConfig
+
+::: lancedb.embeddings.base.EmbeddingFunction
+
+::: lancedb.embeddings.base.TextEmbeddingFunction
+
+::: lancedb.embeddings.sentence_transformers.SentenceTransformerEmbeddings
+
+::: lancedb.embeddings.openai.OpenAIEmbeddings
+
+::: lancedb.embeddings.open_clip.OpenClipEmbeddings

 ## Remote configuration

-::: lancedb.remote
-    options:
-      show_root_heading: false
-      show_root_toc_entry: false
+::: lancedb.remote.ClientConfig
+
+::: lancedb.remote.TimeoutConfig
+
+::: lancedb.remote.RetryConfig

 ## Context

@@ -127,50 +94,11 @@ and combined with [BooleanQuery][lancedb.query.BooleanQuery].

 ## Full text search

-Pass `custom_stop_words` to [lancedb.index.FTS][]:
+Use [lancedb.table.Table.create_fts_index][] for the synchronous API or
+[lancedb.table.AsyncTable.create_index][] with [lancedb.index.FTS][] for the
+asynchronous API.

-```python
-from lancedb.index import FTS
-
-table.create_index(
-    "text",
-    config=FTS(remove_stop_words=True, custom_stop_words=["acme", "internal"]),
-)
-```
-
-The list replaces the built-in stop words and is used only when
-`remove_stop_words=True`:
-
- `custom_stop_words=None` uses the built-in list for `language`.
- `custom_stop_words=[]` removes no words.
- Values are passed through without trimming, lowercasing, or other rewriting.
-
-The same option is available on `lancedb.tokenize(...)` and the deprecated
-[lancedb.table.Table.create_fts_index][] compatibility helper:
-
-```python
-import lancedb
-
-tokens = list(lancedb.tokenize("acme makes searchable data",
-                               custom_stop_words=["acme"]))
-```
-
-::: lancedb.tokenize
-
-::: lancedb.FtsToken
-
-## Blobs
-
-Blob columns store large binary values out of line so they can be read lazily
-instead of being materialized with the rest of the row.
-
-::: lancedb.blob
-
-::: lancedb.BlobType
-
-::: lancedb._blob.BlobFile
-    options:
-      show_root_full_path: false
+::: lancedb.index.FTS

 ## Utilities

@@ -178,14 +106,6 @@ instead of being materialized with the rest of the row.

 ::: lancedb.merge.LanceMergeInsertBuilder

-::: lancedb.otel.instrument_lancedb_metrics
-
-## Exceptions
-
-::: lancedb.exceptions.MissingValueError
-
-::: lancedb.exceptions.MissingColumnError
-
 ## Integrations

 ## Pydantic
@@ -194,30 +114,19 @@ instead of being materialized with the rest of the row.

 ::: lancedb.pydantic.vector

-::: lancedb.pydantic.Vector
-
-::: lancedb.pydantic.MultiVector
-
 ::: lancedb.pydantic.LanceModel

-## PyTorch
-
-::: lancedb.streaming.StreamingDataset
-
-::: lancedb.permutation.permutation_builder
-
-::: lancedb.permutation.PermutationBuilder
-
-::: lancedb.permutation.Permutation
-
-::: lancedb.permutation.Transforms
-
 ## Reranking

-::: lancedb.rerankers
-    options:
-      show_root_heading: false
-      show_root_toc_entry: false
+::: lancedb.rerankers.linear_combination.LinearCombinationReranker
+
+::: lancedb.rerankers.cohere.CohereReranker
+
+::: lancedb.rerankers.colbert.ColbertReranker
+
+::: lancedb.rerankers.cross_encoder.CrossEncoderReranker
+
+::: lancedb.rerankers.openai.OpenaiReranker

 ## Connections (Asynchronous)

@@ -228,12 +137,6 @@ can be used to create, list, or open tables.

 ::: lancedb.db.AsyncConnection

-## Namespaces (Asynchronous)
-
-::: lancedb.connect_namespace_async
-
-::: lancedb.namespace.AsyncLanceNamespaceDBConnection
-
 ## Tables (Asynchronous)

 Table hold your actual data as a collection of records / rows.
@@ -242,20 +145,32 @@ Table hold your actual data as a collection of records / rows.

 ::: lancedb.table.AsyncTags

-::: lancedb.table.AsyncBranches
-
 ## Indices (Asynchronous)

 Indices can be created on a table to speed up queries. This section
 lists the indices that LanceDb supports.

-::: lancedb.index
-    options:
-      show_root_heading: false
-      show_root_toc_entry: false
-      # `lang_mapping` is defined in the module rather than imported, so it is
-      # picked up despite not being in `__all__`. It is an internal lookup table.
-      filters: ["!^_", "!^lang_mapping$"]
+::: lancedb.index.BTree
+
+::: lancedb.index.Bitmap
+
+::: lancedb.index.LabelList
+
+::: lancedb.index.FTS
+
+::: lancedb.index.IvfPq
+
+::: lancedb.index.HnswPq
+
+::: lancedb.index.HnswSq
+
+::: lancedb.index.IvfFlat
+
+::: lancedb.index.IvfSq
+
+::: lancedb.index.IvfRq
+
+::: lancedb.index.HnswFlat

 ::: lancedb.table.IndexStatistics

@@ -283,7 +198,3 @@ rows nearest to a query vector and can be created with the
 ::: lancedb.query.AsyncHybridQuery
    options:
      inherited_members: true
-
-::: lancedb.query.AsyncTakeQuery
-    options:
-      inherited_members: true
@@ -8,7 +8,7 @@
    <parent>
      <groupId>com.lancedb</groupId>
      <artifactId>lancedb-parent</artifactId>
-      <version>0.37.1-beta.1</version>
+      <version>0.32.0-beta.2</version>
      <relativePath>../pom.xml</relativePath>
    </parent>

@@ -6,7 +6,7 @@

    <groupId>com.lancedb</groupId>
    <artifactId>lancedb-parent</artifactId>
-    <version>0.37.1-beta.1</version>
+    <version>0.32.0-beta.2</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>11.0.0-beta.3</lance-core.version>
+        <lance-core.version>9.0.0-beta.23</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>
@@ -1,7 +1,7 @@
 # Contributing to LanceDB Typescript

 This document outlines the process for contributing to LanceDB Typescript.
-For general contribution guidelines, see [CONTRIBUTING.md](https://github.com/lancedb/lancedb/blob/main/CONTRIBUTING.md).
+For general contribution guidelines, see [CONTRIBUTING.md](../CONTRIBUTING.md).

 ## Project layout

@@ -1,7 +1,7 @@
 [package]
 name = "lancedb-nodejs"
 edition.workspace = true
-version = "0.37.1-beta.1"
+version = "0.32.0-beta.2"
 publish = false
 license.workspace = true
 description.workspace = true
@@ -52,7 +52,6 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
      Float64,
      Struct,
      List,
-      Map_,
      Int16,
      Int32,
      Int64,
@@ -70,30 +69,6 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
    type Schema = ApacheArrow["Schema"];
    type Table = ApacheArrow["Table"];

-    function expectValidMapField(
-      // biome-ignore lint/suspicious/noExplicitAny: Arrow Field types vary across supported versions
-      field: any,
-    ): void {
-      expect(DataType.isMap(field.type)).toBe(true);
-      expect(field.type.keysSorted).toBe(true);
-      expect(field.type.children).toHaveLength(1);
-
-      const entries = field.type.children[0];
-      expect(entries.name).toBe("entries");
-      expect(entries.nullable).toBe(false);
-      expect(DataType.isStruct(entries.type)).toBe(true);
-      expect(entries.type.children).toHaveLength(2);
-
-      const [key, value] = entries.type.children;
-      expect([key.name, value.name]).toEqual(["key", "value"]);
-      expect(key.nullable).toBe(false);
-      expect(DataType.isUtf8(key.type)).toBe(true);
-      expect(value.nullable).toBe(true);
-      expect(DataType.isInt(value.type)).toBe(true);
-      expect(value.type.bitWidth).toBe(32);
-      expect(value.type.isSigned).toBe(true);
-    }
-
    // Helper method to verify various ways to create a table
    async function checkTableCreation(
      tableCreationMethod: (
@@ -197,35 +172,6 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
        expect(table.getChild("d")?.toJSON()).toEqual([9n, 10n, null]);
      });

-      it("will use a provided FixedSizeList schema with typed array values", function () {
-        const schema = new Schema([
-          new Field("text", new Utf8(), false),
-          new Field(
-            "vector",
-            new FixedSizeList(3, new Field("item", new Float32(), false)),
-            false,
-          ),
-        ]);
-
-        const table = makeArrowTable(
-          [
-            {
-              text: "foo",
-              vector: new Float32Array([1, 2, 3]),
-            },
-          ],
-          { schema },
-        );
-
-        expect(table.getChild("text")?.toJSON()).toEqual(["foo"]);
-        expect(
-          table
-            .getChild("vector")
-            ?.toJSON()
-            .map((value) => value.toJSON()),
-        ).toEqual([[1, 2, 3]]);
-      });
-
      it("will assume the column `vector` is FixedSizeList<Float32> by default", async function () {
        const schema = new Schema([
          new Field("a", new Float(Precision.DOUBLE), true),
@@ -992,65 +938,6 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
          false,
        );
      });
-
-      it("will make an empty table with a Map field", async function () {
-        const schema = new Schema([
-          new Field(
-            "attributes",
-            new Map_(
-              new Field(
-                "entries",
-                new Struct([
-                  new Field("key", new Utf8(), false),
-                  new Field("value", new Int32(), true),
-                ]),
-                false,
-              ),
-              true,
-            ),
-          ),
-        ]);
-
-        const table = makeEmptyTable(schema);
-
-        expectValidMapField(table.schema.fields[0]);
-
-        const buffer = await fromTableToBuffer(table);
-        const roundTripped = tableFromIPC(buffer);
-
-        expectValidMapField(roundTripped.schema.fields[0]);
-      });
-
-      it("preserves string schema metadata", function () {
-        const metadata = new Map([["source", "fixture"]]);
-        const schema = new Schema(
-          [new Field("value", new Int32(), true)],
-          metadata,
-        );
-
-        expect(makeEmptyTable(schema).schema.metadata.get("source")).toBe(
-          "fixture",
-        );
-      });
-
-      it.each([
-        ["non-string keys", new Map<unknown, unknown>([[42, "fixture"]])],
-        ["non-string values", new Map<unknown, unknown>([["source", 42]])],
-        [
-          "non-string keys and values",
-          new Map<unknown, unknown>([[42, false]]),
-        ],
-      ])("rejects schema metadata with %s", function (_, metadataLike) {
-        const metadata = metadataLike as unknown as Map<string, string>;
-        const schema = new Schema(
-          [new Field("value", new Int32(), true)],
-          metadata,
-        );
-
-        expect(() => makeEmptyTable(schema)).toThrow(
-          "Expected metadata, if present, to be a Map<string, string> but it had non-string keys or values",
-        );
-      });
    });

    describe("when using two versions of arrow", function () {
@@ -69,33 +69,6 @@ describe("given a connection", () => {
    await expect(tbl.countRows()).resolves.toBe(1);
  });

-  it("should isolate object-form table creation across databases", async () => {
-    const otherTmpDir = tmp.dirSync({ unsafeCleanup: true });
-    const otherDb = await connect(otherTmpDir.name);
-
-    try {
-      const firstTable = await db.createTable({
-        name: "defaultTable",
-        data: [{ rowId: "id1", vector: Array(384).fill(0) }],
-      });
-      const secondTable = await otherDb.createTable({
-        name: "defaultTable",
-        data: [{ rowId: "id2", vector: Array(384).fill(0) }],
-      });
-
-      await expect(db.tableNames()).resolves.toEqual(["defaultTable"]);
-      await expect(otherDb.tableNames()).resolves.toEqual(["defaultTable"]);
-
-      const firstRows = await firstTable.query().select(["rowId"]).toArray();
-      const secondRows = await secondTable.query().select(["rowId"]).toArray();
-      expect(firstRows.map((row) => row.rowId)).toEqual(["id1"]);
-      expect(secondRows.map((row) => row.rowId)).toEqual(["id2"]);
-    } finally {
-      otherDb.close();
-      otherTmpDir.removeCallback();
-    }
-  });
-
  it("should be able to drop tables`", async () => {
    await db.createTable("test", [{ id: 1 }, { id: 2 }]);
    await db.createTable("test2", [{ id: 1 }, { id: 2 }]);
@@ -11,11 +11,8 @@ import {
  Float16,
  Float32,
  Float64,
-  Int32,
  Schema,
  Utf8,
-  fromDataToBuffer,
-  tableFromIPC,
 } from "../lancedb/arrow";
 import { EmbeddingFunction, LanceSchema } from "../lancedb/embedding";
 import { getRegistry, register } from "../lancedb/embedding/registry";
@@ -187,63 +184,6 @@ describe("embedding functions", () => {
    const vector0 = JSON.parse(JSON.stringify(arr[0].vector));
    expect(vector0).toEqual([1, 2, 3]);
  });
-
-  it("should append generated vectors to a non-nullable schema", async () => {
-    @register("non_nullable_schema_test")
-    class MockEmbeddingFunction extends EmbeddingFunction<string> {
-      ndims() {
-        return 3;
-      }
-      embeddingDataType(): Float {
-        return new Float64();
-      }
-      async computeSourceEmbeddings(data: string[]) {
-        return data.map(() => [1, 2, 3]);
-      }
-    }
-
-    const schema = new Schema([
-      new Field("id", new Int32()),
-      new Field("text", new Utf8()),
-      new Field("type", new Utf8()),
-      new Field(
-        "vector",
-        new FixedSizeList(3, new Field("item", new Float64())),
-      ),
-    ]);
-    const func = new MockEmbeddingFunction();
-    const db = await connect(tmpDir.name);
-    const table = await db.createEmptyTable("test_non_nullable", schema, {
-      embeddingFunction: {
-        function: func,
-        sourceColumn: "text",
-      },
-    });
-
-    const data = [
-      { id: 1, text: "Carrot", type: "vegetable" },
-      { id: 2, text: "Apple", type: "fruit" },
-    ];
-    const buffer = await fromDataToBuffer(
-      data,
-      undefined,
-      await table.schema(),
-    );
-    const generatedTable = tableFromIPC(buffer);
-    const vectorField = generatedTable.schema.fields.find(
-      (field) => field.name === "vector",
-    );
-    expect(vectorField?.nullable).toBe(false);
-
-    await table.add(data);
-
-    const rows = await table.query().toArray();
-    expect(rows).toHaveLength(2);
-    for (const row of rows) {
-      expect([...row.vector]).toEqual([1, 2, 3]);
-    }
-  });
-
  it("should error when appending to a table with an unregistered embedding function", async () => {
    @register("mock")
    class MockEmbeddingFunction extends EmbeddingFunction<string> {
@@ -1,14 +0,0 @@
-// SPDX-License-Identifier: Apache-2.0
-// SPDX-FileCopyrightText: Copyright The LanceDB Authors
-
-import packageJson = require("../package.json");
-
-describe("package metadata", () => {
-  it("requires Node.js type declarations compatible with the runtime", () => {
-    expect(packageJson.engines.node).toBe(">= 18");
-    expect(packageJson.peerDependencies["@types/node"]).toBe(">=18");
-    expect(packageJson.peerDependenciesMeta["@types/node"]).toEqual({
-      optional: true,
-    });
-  });
-});
@@ -110,81 +110,6 @@ describe("Query outputSchema", () => {
  });
 });

-describe("Search pagination", () => {
-  let tmpDir: tmp.DirResult;
-  let table: Table;
-
-  beforeEach(async () => {
-    tmpDir = tmp.dirSync({ unsafeCleanup: true });
-    const db = await connect(tmpDir.name);
-    const schema = new Schema([
-      new Field("id", new Int64(), false),
-      new Field("text", new Utf8(), false),
-      new Field(
-        "vector",
-        new FixedSizeList(2, new Field("item", new Float32())),
-        false,
-      ),
-    ]);
-    const data = makeArrowTable(
-      [
-        { id: 1n, text: "common", vector: [0, 0] },
-        { id: 2n, text: "common common", vector: [1, 1] },
-        { id: 3n, text: "common common common", vector: [2, 2] },
-        { id: 4n, text: "common common common common", vector: [3, 3] },
-      ],
-      { schema },
-    );
-    table = await db.createTable("test", data);
-  });
-
-  afterEach(() => {
-    tmpDir.removeCallback();
-  });
-
-  it("applies offset after the vector search limit", async () => {
-    const allResults = await table
-      .vectorSearch([0, 0])
-      .select(["id"])
-      .limit(4)
-      .toArray();
-    const secondPage = await table
-      .vectorSearch([0, 0])
-      .select(["id"])
-      .limit(2)
-      .offset(2)
-      .toArray();
-
-    expect(allResults).toHaveLength(4);
-    expect(secondPage).toHaveLength(2);
-    expect(secondPage.map((row) => row.id)).toEqual(
-      allResults.slice(2, 4).map((row) => row.id),
-    );
-  });
-
-  it("applies offset after the full-text search limit", async () => {
-    await table.createIndex("text", { config: Index.fts() });
-
-    const allResults = await table
-      .search("common", "fts")
-      .select(["id"])
-      .limit(4)
-      .toArray();
-    const secondPage = await table
-      .search("common", "fts")
-      .select(["id"])
-      .limit(2)
-      .offset(2)
-      .toArray();
-
-    expect(allResults).toHaveLength(4);
-    expect(secondPage).toHaveLength(2);
-    expect(secondPage.map((row) => row.id)).toEqual(
-      allResults.slice(2, 4).map((row) => row.id),
-    );
-  });
-});
-
 describe("Query orderBy", () => {
  let tmpDir: tmp.DirResult;
  let table: Table;
@@ -15,7 +15,6 @@ import {
  OAuthHeaderProvider,
  StaticHeaderProvider,
 } from "../lancedb/header";
-import { Index } from "../lancedb/indices";

 // Test-only header providers
 class CustomProvider extends HeaderProvider {
@@ -170,38 +169,6 @@ describe("remote connection", () => {
    );
  });

-  it("surfaces JSON server errors from remote table operations", async () => {
-    await withMockDatabase(
-      (req, res) => {
-        const path = req.url ?? "";
-        if (path.endsWith("/describe/")) {
-          res.writeHead(200, { "Content-Type": "application/json" }).end(
-            JSON.stringify({
-              name: "broken_table",
-              version: 1,
-              schema: { fields: [] },
-            }),
-          );
-          return;
-        }
-
-        if (path.endsWith("/count_rows/")) {
-          res
-            .writeHead(400, { "Content-Type": "application/json" })
-            .end(JSON.stringify({ error: "count rows failed" }));
-          return;
-        }
-
-        res.writeHead(404).end();
-      },
-      async (db) => {
-        const table = await db.openTable("broken_table");
-
-        await expect(table.countRows()).rejects.toThrow("count rows failed");
-      },
-    );
-  });
-
  it("should pass on requested extra headers", async () => {
    await withMockDatabase(
      (req, res) => {
@@ -258,166 +225,6 @@ describe("remote connection", () => {
    );
  });

-  it("sends FTS options to remote tables", async () => {
-    let createIndexBody: Record<string, unknown> | undefined;
-
-    await withMockDatabase(
-      (req, res) => {
-        const path = req.url ?? "";
-        if (path.endsWith("/describe/")) {
-          res.writeHead(200, { "Content-Type": "application/json" }).end(
-            JSON.stringify({
-              name: "t",
-              version: 1,
-              schema: {
-                fields: [
-                  { name: "text", type: { type: "string" }, nullable: false },
-                ],
-              },
-            }),
-          );
-          return;
-        }
-
-        if (path.endsWith("/create_index/")) {
-          let raw = "";
-          req.on("data", (chunk) => {
-            raw += chunk;
-          });
-          req.on("end", () => {
-            createIndexBody = JSON.parse(raw);
-            res.writeHead(200).end();
-          });
-          return;
-        }
-
-        res.writeHead(404).end();
-      },
-      async (db) => {
-        const table = await db.openTable("t");
-        await table.createIndex("text", {
-          config: Index.fts({
-            blockSize: 256,
-            removeStopWords: true,
-            customStopWords: ["the"],
-          }),
-        });
-      },
-    );
-
-    expect(createIndexBody?.["column"]).toBe("text");
-    expect(createIndexBody?.["index_type"]).toBe("FTS");
-    expect(createIndexBody?.["block_size"]).toBe(256);
-    expect(createIndexBody?.["custom_stop_words"]).toEqual(["the"]);
-  });
-
-  it("diffs and merges remote branches", async () => {
-    const sampleDiff = {
-      fromBranch: "exp",
-      parentVersion: 1,
-      mainVersion: 2,
-      branchVersion: 3,
-      baseMoved: false,
-      rowCountMain: 3,
-      rowCountBranch: 3,
-      rowSummary: {
-        unchanged: 3,
-        newOnBase: 0,
-        newOnBranch: 0,
-        staleRecompute: 0,
-        inputsChanged: 0,
-        deltaAvailable: false,
-      },
-      addedColumns: [{ name: "tag", dataType: "utf8", nullable: true }],
-      removedColumns: [],
-      changedColumns: [],
-      addedIndexes: [],
-      removedIndexes: [],
-      mergeable: true,
-      mergeBlockers: [],
-    };
-    const mergeBodies: Record<string, unknown>[] = [];
-
-    await withMockDatabase(
-      (req, res) => {
-        const path = req.url ?? "";
-        if (path.endsWith("/describe/")) {
-          res.writeHead(200, { "Content-Type": "application/json" }).end(
-            JSON.stringify({
-              name: "t",
-              version: 2,
-              schema: { fields: [] },
-            }),
-          );
-          return;
-        }
-
-        let raw = "";
-        req.on("data", (chunk) => {
-          raw += chunk;
-        });
-        req.on("end", () => {
-          const body = raw ? JSON.parse(raw) : {};
-          if (path.endsWith("/branches/diff/")) {
-            // biome-ignore lint/style/useNamingConvention: snake_case mandated by the server wire format
-            expect(body).toEqual({ from_branch: "exp" });
-            res
-              .writeHead(200, { "Content-Type": "application/json" })
-              .end(JSON.stringify(sampleDiff));
-            return;
-          }
-          if (path.endsWith("/branches/merge/")) {
-            mergeBodies.push(body);
-            const dryRun = body["dry_run"] === true;
-            const response = {
-              status: dryRun ? "ready" : "rejected",
-              diff: dryRun
-                ? sampleDiff
-                : {
-                    ...sampleDiff,
-                    mergeable: false,
-                    mergeBlockers: [
-                      { code: "baseMoved", message: "main has advanced" },
-                    ],
-                  },
-              preview: { promotedColumns: dryRun ? ["tag"] : [] },
-            };
-            res
-              .writeHead(dryRun ? 200 : 409, {
-                "Content-Type": "application/json",
-              })
-              .end(JSON.stringify(response));
-            return;
-          }
-          res.writeHead(404).end();
-        });
-      },
-      async (db) => {
-        const table = await db.openTable("t");
-        const branches = await table.branches();
-
-        await expect(branches.diff("exp")).resolves.toEqual(sampleDiff);
-
-        const rejected = await branches.merge("exp");
-        expect(rejected.status).toBe("rejected");
-        expect(rejected.diff.mergeBlockers).toEqual([
-          { code: "baseMoved", message: "main has advanced" },
-        ]);
-
-        const preview = await branches.merge("exp", true);
-        expect(preview.status).toBe("ready");
-        expect(preview.preview.promotedColumns).toEqual(["tag"]);
-      },
-    );
-
-    expect(mergeBodies).toEqual([
-      // biome-ignore lint/style/useNamingConvention: snake_case mandated by the server wire format
-      { from_branch: "exp", dry_run: false },
-      // biome-ignore lint/style/useNamingConvention: snake_case mandated by the server wire format
-      { from_branch: "exp", dry_run: true },
-    ]);
-  });
-
  describe("TlsConfig", () => {
    it("should create TlsConfig with all fields", () => {
      const tlsConfig: TlsConfig = {
@@ -909,96 +716,3 @@ describe("remote connection", () => {
    });
  });
 });
-
-describe("remote connection jobs surface", () => {
-  it("lists, describes, cancels, and reads history", async () => {
-    const { tableFromArrays, tableToIPC } = await import("apache-arrow");
-    const eventsTable = tableFromArrays({ state: ["created", "succeeded"] });
-    const eventsBody = Buffer.from(tableToIPC(eventsTable, "stream"));
-
-    await withMockDatabase(
-      (req, res) => {
-        let body = "";
-        req.on("data", (chunk) => {
-          body += chunk;
-        });
-        req.on("end", () => {
-          const payload = body.length > 0 ? JSON.parse(body) : {};
-          if (req.url === "/v1/jobs/list") {
-            if (payload["page_token"] === undefined) {
-              res
-                .writeHead(200, { "Content-Type": "application/json" })
-                .end(
-                  '{"jobs": [{"job_id": "job-1", "table": "t1", ' +
-                    '"job_type": "create_index", "state": "in_progress", ' +
-                    '"created_at_millis": 1000}], "page_token": "next"}',
-                );
-            } else {
-              res
-                .writeHead(200, { "Content-Type": "application/json" })
-                .end(
-                  '{"jobs": [{"job_id": "job-2", "table": "t2", ' +
-                    '"job_type": "create_index", "state": "succeeded", ' +
-                    '"created_at_millis": 2000}]}',
-                );
-            }
-          } else if (req.url === "/v1/jobs/describe") {
-            if (payload["job_id"] !== "job-1") {
-              res.writeHead(404).end("no such job");
-              return;
-            }
-            res
-              .writeHead(200, { "Content-Type": "application/json" })
-              .end(
-                '{"job_id": "job-1", "job_type": "create_index", ' +
-                  '"job_state": "FAILED", "creation_ms": 1000, ' +
-                  '"spec": {"column": "vec"}, "failure": {"phase": "execute", ' +
-                  '"message": "worker died", "retryable": true}}',
-              );
-          } else if (req.url === "/v1/jobs/cancel") {
-            if (payload["job_id"] !== "job-1") {
-              res.writeHead(404).end("no such job");
-              return;
-            }
-            res
-              .writeHead(200, { "Content-Type": "application/json" })
-              .end('{"job_id": "job-1"}');
-          } else if (req.url === "/v1/jobs/query_events") {
-            res
-              .writeHead(200, {
-                "Content-Type": "application/vnd.apache.arrow.stream",
-              })
-              .end(eventsBody);
-          } else {
-            res.writeHead(404).end();
-          }
-        });
-      },
-      async (db) => {
-        const jobs = await db.listJobs();
-        expect(jobs.map((job) => job.jobId)).toEqual(["job-1", "job-2"]);
-        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);
-
-        const history = await db.jobHistory("job-1");
-        expect(history.numRows).toEqual(2);
-
-        const job = db.job("job-1");
-        expect(job.id).toEqual("job-1");
-        expect(await job.status()).toEqual("failed");
-        await expect(job.wait()).rejects.toThrow("worker died");
-      },
-    );
-  });
-});
@@ -2,7 +2,7 @@
 // SPDX-FileCopyrightText: Copyright The LanceDB Authors

 import * as arrow from "../lancedb/arrow";
-import { sanitizeField, sanitizeMap, sanitizeType } from "../lancedb/sanitize";
+import { sanitizeField, sanitizeType } from "../lancedb/sanitize";

 describe("sanitize", function () {
  describe("sanitizeType function", function () {
@@ -181,15 +181,4 @@ describe("sanitize", function () {
      );
    });
  });
-
-  describe("sanitizeMap function", function () {
-    it.each([
-      ["no children", []],
-      ["two children", [{}, {}]],
-    ])("should reject a Map type with %s", function (_, children) {
-      expect(() => sanitizeMap({ children, keysSorted: false })).toThrow(
-        "Expected a Map type to have exactly one child",
-      );
-    });
-  });
 });
@@ -86,44 +86,6 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
      await expect(table.countRows()).resolves.toBe(3);
    });

-    it("should support a foreign Float64 vector schema end to end", async () => {
-      const conn = await connect(tmpDir.name);
-      const schema = new arrow.Schema([
-        new arrow.Field("resource_id", new arrow.Int32(), false),
-        new arrow.Field(
-          "vector",
-          new arrow.FixedSizeList(
-            3,
-            new arrow.Field("value", new arrow.Float64(), true),
-          ),
-          false,
-        ),
-      ]);
-      const data = [
-        {
-          // biome-ignore lint/style/useNamingConvention: matches the reported schema
-          resource_id: 0,
-          vector: [0.1, 0.1, 0.1],
-        },
-      ];
-
-      const resources = await conn.createTable("resources", data, { schema });
-
-      const existing = await resources
-        .query()
-        .where("resource_id = 0")
-        .limit(1)
-        .toArray();
-      expect(existing).toHaveLength(1);
-
-      const matched = await resources
-        .search(Float64Array.from(data[0].vector))
-        .limit(1)
-        .toArray();
-      expect(matched).toHaveLength(1);
-      expect(matched[0]["resource_id"]).toBe(0);
-    });
-
    it("should support branches", async () => {
      await table.add([{ id: 1 }]);
      expect(await table.countRows()).toBe(1);
@@ -277,16 +239,8 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
        },
        numIndices: 0,
        numRows: 3,
-        // Full on-disk size of the two data files, footers and metadata included.
-        totalBytes: 684,
+        totalBytes: 44,
      });
-
-      // Index files count toward totalBytes too (only deletion files and
-      // manifests are excluded).
-      await table.createIndex("id", { config: Index.btree() });
-      const statsWithIndex = await table.stats();
-      expect(statsWithIndex.numIndices).toBe(1);
-      expect(statsWithIndex.totalBytes).toBeGreaterThan(684);
    });

    it("should overwrite data if asked", async () => {
@@ -573,14 +527,6 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
      );
    });

-    it("should expose useLsm on takeRowIds as the base-only escape hatch", async () => {
-      await table.add([{ id: 1 }, { id: 2 }, { id: 3 }]);
-      // useLsm(false) is reachable on TakeQuery (the escape hatch for MemWAL tables,
-      // where take-by-row-id auto-routes to the LSM scanner and is rejected).
-      const res = await table.takeRowIds([0, 2]).useLsm(false).toArray();
-      expect(res.map((r) => r.id)).toEqual([1, 3]);
-    });
-
    it("should throw for negative number in takeRowIds", () => {
      expect(() => table.takeRowIds([-1])).toThrow("Row id cannot be negative");
      expect(() => table.takeRowIds([0, -5, 2])).toThrow(
@@ -897,11 +843,7 @@ describe("When creating an index", () => {
  afterEach(() => tmpDir.removeCallback());

  it("should create a vector index on vector columns", async () => {
-    const job = await tbl.createIndexAsync("vec");
-    expect(job.id).toBeNull();
-    await job.wait();
-    // Cancelling a job that already finished succeeds and does nothing.
-    await job.cancel();
+    await tbl.createIndex("vec");

    // check index directory
    const indexDir = path.join(tmpDir.name, "test.lance", "_indices");
@@ -2585,35 +2527,6 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
      expect(results3.length).toBe(1);
    });

-    test("full text search with custom posting block size", async () => {
-      const db = await connect(tmpDir.name);
-      const data = [
-        { text: "hello world", vector: [0.1, 0.2, 0.3] },
-        { text: "goodbye world", vector: [0.4, 0.5, 0.6] },
-      ];
-      const table = await db.createTable("test", data);
-      await table.createIndex("text", {
-        config: Index.fts({ blockSize: 256 }),
-      });
-
-      const index = (await table.listIndices()).find(
-        (index) => index.indexType === "FTS",
-      );
-      expect(index?.indexVersion).toBe(3);
-      expect(
-        (index?.indexDetails as Record<string, unknown>)["block_size"],
-      ).toBe(256);
-
-      const results = await table.search("hello").toArray();
-      expect(results[0].text).toBe(data[0].text);
-    });
-
-    test("rejects invalid full text posting block size", () => {
-      expect(() => Index.fts({ blockSize: 129 as 128 | 256 })).toThrow(
-        "128 or 256",
-      );
-    });
-
    test("full text search without lowercase", async () => {
      const db = await connect(tmpDir.name);
      const data = [
@@ -2819,15 +2732,6 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
  },
 );

-test("tokenize supports custom stop words", async () => {
-  const tokens = await tokenize("the lance data", {
-    stem: false,
-    removeStopWords: true,
-    customStopWords: ["lance"],
-  });
-  expect(tokens.map((token) => token.text)).toEqual(["the", "data"]);
-});
-
 describe("when calling explainPlan", () => {
  let tmpDir: tmp.DirResult;
  let table: Table;
@@ -2871,13 +2775,8 @@ describe("when calling analyzePlan", () => {
      .fill(1)
      .map(() => Math.random());
    const plan = await table.query().nearestTo(queryVec).analyzePlan();
+    console.log("Query Plan:\n", plan); // <--- Print the plan
    expect(plan).toMatch("AnalyzeExec");
-
-    const fullPlan = await table
-      .query()
-      .nearestTo(queryVec)
-      .analyzePlan("full");
-    expect(fullPlan).toMatch("AnalyzeExec");
  });
 });

@@ -3266,14 +3165,14 @@ describe("LSM merge insert", () => {
    await table.closeLsmWriters();
  });

-  it("falls back to the standard path with useLsm(false)", async () => {
+  it("falls back to the standard path with useLsmWrite(false)", async () => {
    const conn = await connect(tmpDir.name);
    const table = await bucketTable(conn);

    const res = await table
      .mergeInsert("id")
      .whenNotMatchedInsertAll()
-      .useLsm(false)
+      .useLsmWrite(false)
      .execute([
        { id: "b", value: 9 },
        { id: "e", value: 5 },
@@ -3307,36 +3206,4 @@ describe("LSM merge insert", () => {
        .execute([{ id: "g", value: 7 }]),
    ).rejects.toThrow();
  });
-
-  it("auto-routes reads through the MemWAL scanner", async () => {
-    const conn = await connect(tmpDir.name);
-    const table = await bucketTable(conn); // base ids "a", "b"
-
-    await table
-      .mergeInsert("id")
-      .whenMatchedUpdateAll()
-      .whenNotMatchedInsertAll()
-      .execute([{ id: "c", value: 3 }]);
-
-    // Default read auto-routes and includes the active memtable row.
-    const lsm = await table.query().toArray();
-    expect(lsm.map((r) => r.id).sort()).toEqual(["a", "b", "c"]);
-
-    // useLsm(false) bypasses the MemWAL and reads the base table only.
-    const baseOnly = await table.query().useLsm(false).toArray();
-    expect(baseOnly.map((r) => r.id).sort()).toEqual(["a", "b"]);
-  });
-
-  it("reads the base table when no LSM spec is installed", async () => {
-    const conn = await connect(tmpDir.name);
-    const table = await conn.createEmptyTable(
-      "plain",
-      new arrow.Schema([new arrow.Field("id", new arrow.Utf8(), false)]),
-    );
-    // No spec: default read and useLsm(false) both succeed against the base table.
-    await expect(table.query().toArray()).resolves.toBeDefined();
-    await expect(table.query().useLsm(false).toArray()).resolves.toBeDefined();
-    // useLsm(true) demands MemWAL routing; without a spec it errors.
-    await expect(table.query().useLsm(true).toArray()).rejects.toThrow();
-  });
 });
@@ -29,14 +29,8 @@ test("full text search", async () => {
    const tbl = await db.createTable("myVectors", data, { mode: "overwrite" });

    await tbl.createIndex("doc", {
-      config: lancedb.Index.fts({
-        stem: false,
-        removeStopWords: true,
-        customStopWords: ["banana"],
-      }),
+      config: lancedb.Index.fts(),
    });
-    const tokens = await tbl.tokenize("apple banana", { column: "doc" });
-    expect(tokens.map((token) => token.text)).toEqual(["apple"]);

    // --8<-- [start:full_text_search]
    const result = await tbl
@@ -1,7 +1,6 @@
 // SPDX-License-Identifier: Apache-2.0
 // SPDX-FileCopyrightText: Copyright The LanceDB Authors

-import { tableFromIPC } from "apache-arrow";
 import {
  Data,
  SchemaLike,
@@ -21,9 +20,6 @@ import type {
  CreateNamespaceResponse,
  DescribeNamespaceResponse,
  DropNamespaceResponse,
-  Job,
-  JobDescription,
-  JobInfo,
  ListNamespacesResponse,
 } from "./native";
 export type {
@@ -440,40 +436,6 @@ export abstract class Connection {
    newName: string,
    options?: RenameTableOptions,
  ): Promise<void>;
-
-  /**
-   * A {@link 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.
-   */
-  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.
-   *
-   * Resolves to true if the server accepted the cancellation, false if no
-   * 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 */
@@ -760,30 +722,6 @@ export class LocalConnection extends Connection {
      options?.newNamespacePath,
    );
  }
-
-  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);
-  }
 }

 /**
@@ -85,13 +85,7 @@ export {
  RenameTableOptions,
 } from "./connection";

-export {
-  Job,
-  JobDescription,
-  JobFailureInfo,
-  JobInfo,
-  Session,
-} from "./native.js";
+export { Session } from "./native.js";

 export {
  ExecutableQuery,
@@ -99,7 +93,6 @@ export {
  QueryBase,
  VectorQuery,
  TakeQuery,
-  AnalyzePlanDistributedMetrics,
  QueryExecutionOptions,
  ColumnOrdering,
  FullTextSearchOptions,
@@ -130,14 +123,6 @@ export {
 export {
  Table,
  Branches,
-  BranchColumnSummary,
-  BranchColumnChange,
-  BranchIndexSummary,
-  BranchRowCountSummary,
-  MergeBlocker,
-  BranchDiff,
-  MergePreview,
-  MergeBranchResult,
  AddDataOptions,
  UpdateOptions,
  OptimizeOptions,
@@ -200,16 +185,6 @@ export interface TokenizeOptions {
  /** Whether to remove stop words. */
  removeStopWords?: boolean;

-  /**
-   * Custom stop words that replace the built-in list for `language`.
-   *
-   * This option only affects tokenization when `removeStopWords` is true.
-   *
-   * `undefined` keeps the built-in language list. An empty array explicitly
-   * replaces it with no stop words.
-   */
-  customStopWords?: string[];
-
  /** Whether to fold ASCII characters. */
  asciiFolding?: boolean;

@@ -241,7 +216,6 @@ export async function tokenize(
    options?.lowercase,
    options?.stem,
    options?.removeStopWords,
-    options?.customStopWords,
    options?.asciiFolding,
    options?.ngramMinLength,
    options?.ngramMaxLength,
@@ -553,16 +553,6 @@ export interface FtsOptions {
   */
  removeStopWords?: boolean;

-  /**
-   * Custom stop words that replace the built-in list for `language`.
-   *
-   * This option only affects tokenization when `removeStopWords` is true.
-   *
-   * `undefined` keeps the built-in language list. An empty array explicitly
-   * replaces it with no stop words.
-   */
-  customStopWords?: string[];
-
  /**
   * whether to remove punctuation
   */
@@ -582,14 +572,6 @@ export interface FtsOptions {
   * whether to only index the prefix of the token for ngram tokenizer
   */
  prefixOnly?: boolean;
-
-  /**
-   * Number of documents per compressed posting block.
-   *
-   * The default is 128. Supported values are 128 and 256. A value of 256 uses
-   * the experimental FTS V3 format and may introduce breaking changes.
-   */
-  blockSize?: 128 | 256;
 }

 export class Index {
@@ -765,12 +747,10 @@ export class Index {
        options?.lowercase,
        options?.stem,
        options?.removeStopWords,
-        options?.customStopWords,
        options?.asciiFolding,
        options?.ngramMinLength,
        options?.ngramMaxLength,
        options?.prefixOnly,
-        options?.blockSize,
      ),
    );
  }
@@ -88,17 +88,21 @@ export class MergeInsertBuilder {
    );
  }
  /**
-   * Control MemWAL routing for this merge.
+   * Controls whether the merge uses the MemWAL LSM write path.
   *
   * By default (unset), a `mergeInsert` on a table with an LSM write spec is
-   * routed through Lance's MemWAL shard writer, and a table without one uses the
-   * standard path.
+   * routed through Lance's MemWAL shard writer, and a table without one uses
+   * the standard path. Pass `false` to force the standard path even when a
+   * spec is set. Pass `true` to require a spec — `mergeInsert` rejects if none
+   * is installed.
   *
-   * @param enable - `true` forces MemWAL routing and errors if the table has no
-   * LSM write spec. `false` forces the standard write path even when a spec is set.
+   * @param useLsmWrite - Whether to use the LSM write path.
   */
-  useLsm(enable: boolean): MergeInsertBuilder {
-    return new MergeInsertBuilder(this.#native.useLsm(enable), this.#schema);
+  useLsmWrite(useLsmWrite: boolean): MergeInsertBuilder {
+    return new MergeInsertBuilder(
+      this.#native.useLsmWrite(useLsmWrite),
+      this.#schema,
+    );
  }
  /**
   * Controls how an LSM merge checks that its input targets a single shard.
@@ -79,8 +79,6 @@ export interface QueryExecutionOptions {
  timeoutMs?: number;
 }

-export type AnalyzePlanDistributedMetrics = "aggregate" | "per_worker" | "full";
-
 export interface ColumnOrdering {
  columnName: string;
  ascending?: boolean;
@@ -313,20 +311,13 @@ export class QueryBase<
   *        KNNVectorDistance: metric=l2, metrics=[output_rows=1, elapsed_compute=114.333µs, output_batches=1]
   *         LanceScan: uri=/path/to/data, projection=[vector], row_id=true, row_addr=false, ordered=false, metrics=[output_rows=1, elapsed_compute=103.626µs, bytes_read=549, iops=2, requests=2]
   *
-   * @param distributedMetrics - How distributed worker metrics are displayed for remote query plans.
-   * Defaults to `"aggregate"`.
   * @returns A query execution plan with runtime metrics for each step.
   */
-  async analyzePlan(
-    distributedMetrics?: AnalyzePlanDistributedMetrics,
-  ): Promise<string> {
-    const distributedMetricsMode = distributedMetrics ?? "aggregate";
+  async analyzePlan(): Promise<string> {
    if (this.inner instanceof Promise) {
-      return this.inner.then((inner) =>
-        inner.analyzePlan(distributedMetricsMode),
-      );
+      return this.inner.then((inner) => inner.analyzePlan());
    } else {
-      return this.inner.analyzePlan(distributedMetricsMode);
+      return this.inner.analyzePlan();
    }
  }

@@ -460,30 +451,6 @@ export class StandardQueryBase<
    this.doCall((inner: NativeQueryType) => inner.fastSearch());
    return this;
  }
-
-  /**
-   * Control MemWAL read routing for this query.
-   *
-   * By default (unset), when the table carries a MemWAL write spec (see
-   * {@link Table#setLsmWriteSpec}), reads are routed through the LSM scanner so
-   * they also return data written via the `mergeInsert` LSM path that has not yet
-   * been compacted into the base table (the active/frozen in-memory memtables and
-   * the flushed generations), deduplicated by primary key; a table without a spec
-   * reads the base table.
-   *
-   * @param enable - `true` forces the LSM scanner and errors if the table has no
-   * MemWAL write spec. `false` bypasses the MemWAL and reads the base table only,
-   * even when a spec is present.
-   *
-   * Note: the LSM scanner does not support every query shape (e.g. reranking,
-   * hybrid search, `orderBy`). On a MemWAL table those shapes error unless
-   * `useLsm(false)` is set, because a base-only read would silently exclude
-   * un-compacted MemWAL data.
-   */
-  useLsm(enable: boolean): this {
-    this.doCall((inner: NativeQueryType) => inner.useLsm(enable));
-    return this;
-  }
 }

 /**
@@ -772,20 +739,6 @@ export class TakeQuery extends QueryBase<NativeTakeQuery> {
  constructor(inner: NativeTakeQuery) {
    super(inner);
  }
-
-  /**
-   * Control MemWAL read routing for this take query.
-   *
-   * `false` bypasses the MemWAL and reads the base table only — the escape hatch,
-   * since take-by-row-id/offset is not supported on the LSM scanner and, on a
-   * MemWAL table, auto-routes to it and errors otherwise.
-   *
-   * @param enable - `false` reads the base table only.
-   */
-  useLsm(enable: boolean): this {
-    this.doCall((inner: NativeTakeQuery) => inner.useLsm(enable));
-    return this;
-  }
 }

 /** A builder for LanceDB queries.
@@ -84,7 +84,7 @@ export function sanitizeMetadata(
    throw Error("Expected metadata, if present, to be a Map<string, string>");
  }
  for (const item of metadataLike) {
-    if (typeof item[0] !== "string" || typeof item[1] !== "string") {
+    if (!(typeof item[0] === "string" || !(typeof item[1] === "string"))) {
      throw Error(
        "Expected metadata, if present, to be a Map<string, string> but it had non-string keys or values",
      );
@@ -288,11 +288,12 @@ export function sanitizeMap(typeLike: object) {
  if (!("keysSorted" in typeLike) || typeof typeLike.keysSorted !== "boolean") {
    throw Error("Expected a Map type to have a `keysSorted` property");
  }
-  if (typeLike.children.length !== 1) {
-    throw Error("Expected a Map type to have exactly one child");
-  }

-  return new Map_(sanitizeField(typeLike.children[0]), typeLike.keysSorted);
+  return new Map_(
+    // biome-ignore lint/suspicious/noExplicitAny: skip
+    typeLike.children.map((field) => sanitizeField(field)) as any,
+    typeLike.keysSorted,
+  );
 }

 export function sanitizeDuration(typeLike: object) {
@@ -30,7 +30,6 @@ import {
  DropColumnsResult,
  IndexConfig,
  IndexStatistics,
-  Job,
  Branches as NativeBranches,
  OptimizeStats,
  TableStatistics,
@@ -197,11 +196,7 @@ export interface LsmWriteSpec {
  column?: string;
  /** Bucket variant: the number of buckets, in `[1, 1024]`. */
  numBuckets?: number;
-  /**
-   * Indexes the MemWAL keeps up to date. Omit to maintain every supported
-   * index, resolved on install — a snapshot, so indexes created later are not
-   * maintained. Pass `[]` for none.
-   */
+  /** Names of indexes the MemWAL should keep up to date during writes. */
  maintainedIndexes?: string[];
  /** Default `ShardWriter` configuration recorded in the MemWAL index. */
  writerConfigDefaults?: Record<string, string>;
@@ -363,17 +358,6 @@ export abstract class Table {
    options?: Partial<IndexOptions>,
  ): Promise<void>;

-  /**
-   * Create an index, returning a handle to the indexing job.
-   *
-   * The job may already be complete when returned; callers must not assume
-   * the index exists until {@link Job.wait} resolves.
-   */
-  abstract createIndexAsync(
-    column: string,
-    options?: Partial<IndexOptions>,
-  ): Promise<Job>;
-
  /**
   * Drop an index from the table.
   *
@@ -599,11 +583,6 @@ export abstract class Table {
   * All variants require the table to have an unenforced primary key
   * ({@link Table#setUnenforcedPrimaryKey}); bucket sharding additionally
   * requires it to be the single column being bucketed.
-   *
-   * Omitting `maintainedIndexes` maintains every index on the table, resolved
-   * here, failing if one cannot be maintained — name them to install anyway.
-   * Naming them pins an exact set, and a still-building index is rejected
-   * rather than quietly omitted.
   * @param {LsmWriteSpec} spec The sharding spec to install.
   * @returns {Promise<void>}
   * @example
@@ -631,10 +610,9 @@ export abstract class Table {
   *
   * Resolves to `undefined` when the MemWAL LSM write path is not enabled (no
   * spec has been set, or it was removed with {@link Table#unsetLsmWriteSpec}).
-   * The returned spec mirrors what was passed to
-   * {@link Table#setLsmWriteSpec}, except that `maintainedIndexes` always
-   * reports the concrete list resolved when the spec was set — `undefined`
-   * never round-trips.
+   * The returned spec — including its `maintainedIndexes` and
+   * `writerConfigDefaults` — mirrors what was passed to
+   * {@link Table#setLsmWriteSpec}.
   * @returns {Promise<LsmWriteSpec | undefined>}
   */
  abstract getLsmWriteSpec(): Promise<LsmWriteSpec | undefined>;
@@ -962,22 +940,6 @@ export class LocalTable extends Table {
    );
  }

-  async createIndexAsync(
-    column: string,
-    options?: Partial<IndexOptions>,
-  ): Promise<Job> {
-    // biome-ignore lint/suspicious/noExplicitAny: skip
-    const nativeIndex = (options?.config as any)?.inner;
-    return await this.inner.createIndexAsync(
-      nativeIndex,
-      column,
-      options?.replace,
-      options?.waitTimeoutSeconds,
-      options?.name,
-      options?.train,
-    );
-  }
-
  async dropIndex(name: string): Promise<void> {
    await this.inner.dropIndex(name);
  }
@@ -1367,76 +1329,6 @@ export interface FieldMetadataUpdate {
  replace?: boolean;
 }

-/** Summary of a column in a branch diff. */
-export interface BranchColumnSummary {
-  name: string;
-  dataType: string;
-  nullable: boolean;
-}
-
-/** A column whose definition differs between main and the branch. */
-export interface BranchColumnChange {
-  name: string;
-  main: BranchColumnSummary;
-  branch: BranchColumnSummary;
-}
-
-/** Summary of an index in a branch diff. */
-export interface BranchIndexSummary {
-  indexName: string;
-  columns: string[];
-  indexType?: string;
-  status: string;
-}
-
-/** Row-level comparison between main and the branch. */
-export interface BranchRowCountSummary {
-  unchanged: number;
-  newOnBase: number;
-  newOnBranch: number;
-  staleRecompute: number;
-  inputsChanged: number;
-  deltaAvailable: boolean;
-}
-
-/** A reason why a branch cannot currently be merged. */
-export interface MergeBlocker {
-  code: string;
-  message: string;
-}
-
-/** Read-only comparison of a branch against main. */
-export interface BranchDiff {
-  fromBranch: string;
-  parentVersion: number;
-  mainVersion: number;
-  branchVersion: number;
-  baseMoved: boolean;
-  rowCountMain: number;
-  rowCountBranch: number;
-  rowSummary: BranchRowCountSummary;
-  addedColumns: BranchColumnSummary[];
-  removedColumns: BranchColumnSummary[];
-  changedColumns: BranchColumnChange[];
-  addedIndexes: BranchIndexSummary[];
-  removedIndexes: BranchIndexSummary[];
-  mergeable: boolean;
-  mergeBlockers: MergeBlocker[];
-}
-
-/** Changes that would be, or were, promoted by a branch merge. */
-export interface MergePreview {
-  promotedColumns: string[];
-}
-
-/** Result of previewing or attempting a branch merge. */
-export interface MergeBranchResult {
-  status: "ready" | "rejected" | "notImplemented" | "merged" | "unknown";
-  diff: BranchDiff;
-  preview: MergePreview;
-  mainVersionAfter?: number;
-}
-
 /**
 * Branch manager for a {@link Table}.
 *
@@ -1489,28 +1381,4 @@ export class Branches {
  async delete(name: string): Promise<void> {
    return await this.#inner.delete(name);
  }
-
-  /** Compare a branch against main without modifying either branch. */
-  async diff(fromBranch: string): Promise<BranchDiff> {
-    return (await this.#inner.diff(fromBranch)) as unknown as BranchDiff;
-  }
-
-  /**
-   * Merge a branch into main.
-   *
-   * Set `dryRun` to `true` to preview the merge. A rejected merge resolves
-   * with `status: "rejected"` instead of throwing.
-   *
-   * @param fromBranch Branch to merge from.
-   * @param dryRun When true, only preview the merge. Defaults to false.
-   */
-  async merge(
-    fromBranch: string,
-    dryRun: boolean = false,
-  ): Promise<MergeBranchResult> {
-    return (await this.#inner.merge(
-      fromBranch,
-      dryRun,
-    )) as unknown as MergeBranchResult;
-  }
 }
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-darwin-arm64",
-	"version": "0.37.1-beta.1",
+	"version": "0.32.0-beta.2",
 	"os": ["darwin"],
 	"cpu": ["arm64"],
 	"main": "lancedb.darwin-arm64.node",
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-arm64-gnu",
-	"version": "0.37.1-beta.1",
+	"version": "0.32.0-beta.2",
 	"os": ["linux"],
 	"cpu": ["arm64"],
 	"main": "lancedb.linux-arm64-gnu.node",
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-arm64-musl",
-	"version": "0.37.1-beta.1",
+	"version": "0.32.0-beta.2",
 	"os": ["linux"],
 	"cpu": ["arm64"],
 	"main": "lancedb.linux-arm64-musl.node",
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-x64-gnu",
-	"version": "0.37.1-beta.1",
+	"version": "0.32.0-beta.2",
 	"os": ["linux"],
 	"cpu": ["x64"],
 	"main": "lancedb.linux-x64-gnu.node",
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-x64-musl",
-	"version": "0.37.1-beta.1",
+	"version": "0.32.0-beta.2",
 	"os": ["linux"],
 	"cpu": ["x64"],
 	"main": "lancedb.linux-x64-musl.node",
@@ -1,6 +1,6 @@
 {
  "name": "@lancedb/lancedb-win32-arm64-msvc",
-  "version": "0.37.1-beta.1",
+  "version": "0.32.0-beta.2",
  "os": [
    "win32"
  ],
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-win32-x64-msvc",
-	"version": "0.37.1-beta.1",
+	"version": "0.32.0-beta.2",
 	"os": ["win32"],
 	"cpu": ["x64"],
 	"main": "lancedb.win32-x64-msvc.node",
@@ -1,12 +1,12 @@
 {
  "name": "@lancedb/lancedb",
-  "version": "0.37.1-beta.1",
+  "version": "0.32.0-beta.1",
  "lockfileVersion": 3,
  "requires": true,
  "packages": {
    "": {
      "name": "@lancedb/lancedb",
-      "version": "0.37.1-beta.1",
+      "version": "0.32.0-beta.1",
      "cpu": [
        "x64",
        "arm64"
@@ -55,13 +55,7 @@
        "openai": "4.29.2"
      },
      "peerDependencies": {
-        "@types/node": ">=18",
        "apache-arrow": ">=15.0.0 <=18.1.0"
-      },
-      "peerDependenciesMeta": {
-        "@types/node": {
-          "optional": true
-        }
      }
    },
    "node_modules/@aws-crypto/crc32": {
@@ -11,7 +11,7 @@
    "ann"
  ],
  "private": false,
-  "version": "0.37.1-beta.1",
+  "version": "0.32.0-beta.2",
  "main": "dist/index.js",
  "exports": {
    ".": "./dist/index.js",
@@ -101,12 +101,6 @@
    "openai": "4.29.2"
  },
  "peerDependencies": {
-    "@types/node": ">=18",
    "apache-arrow": ">=15.0.0 <=18.1.0"
-  },
-  "peerDependenciesMeta": {
-    "@types/node": {
-      "optional": true
-    }
  }
 }
@@ -340,69 +340,6 @@ impl Connection {
        self.get_inner()?.drop_all_tables(&ns).await.default_error()
    }

-    /// A `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.
-    #[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))
-    }
-
-    /// List server-side jobs across the database's tables.
-    #[napi(catch_unwind)]
-    pub async fn list_jobs(&self) -> napi::Result<Vec<crate::job::JobInfo>> {
-        let jobs = self.get_inner()?.list_jobs().await.default_error()?;
-        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)]
-    pub async fn cancel_job(&self, job_id: String) -> napi::Result<bool> {
-        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(
@@ -43,7 +43,6 @@ pub fn tokenize(
    lower_case: Option<bool>,
    stem: Option<bool>,
    remove_stop_words: Option<bool>,
-    custom_stop_words: Option<Vec<String>>,
    ascii_folding: Option<bool>,
    ngram_min_length: Option<u32>,
    ngram_max_length: Option<u32>,
@@ -73,7 +72,6 @@ pub fn tokenize(
    if let Some(remove_stop_words) = remove_stop_words {
        opts = opts.remove_stop_words(remove_stop_words);
    }
-    opts = opts.custom_stop_words(custom_stop_words);
    if let Some(ascii_folding) = ascii_folding {
        opts = opts.ascii_folding(ascii_folding);
    }
@@ -224,13 +222,11 @@ impl Index {
        lower_case: Option<bool>,
        stem: Option<bool>,
        remove_stop_words: Option<bool>,
-        custom_stop_words: Option<Vec<String>>,
        ascii_folding: Option<bool>,
        ngram_min_length: Option<u32>,
        ngram_max_length: Option<u32>,
        prefix_only: Option<bool>,
-        block_size: Option<u32>,
-    ) -> napi::Result<Self> {
+    ) -> Self {
        let mut opts = FtsIndexBuilder::default();
        if let Some(with_position) = with_position {
            opts = opts.with_position(with_position);
@@ -253,7 +249,6 @@ impl Index {
        if let Some(remove_stop_words) = remove_stop_words {
            opts = opts.remove_stop_words(remove_stop_words);
        }
-        opts = opts.custom_stop_words(custom_stop_words);
        if let Some(ascii_folding) = ascii_folding {
            opts = opts.ascii_folding(ascii_folding);
        }
@@ -266,15 +261,10 @@ impl Index {
        if let Some(prefix_only) = prefix_only {
            opts = opts.ngram_prefix_only(prefix_only);
        }
-        if let Some(block_size) = block_size {
-            opts = opts
-                .block_size(block_size as usize)
-                .map_err(|err| napi::Error::from_reason(err.to_string()))?;
-        }

-        Ok(Self {
+        Self {
            inner: Mutex::new(Some(LanceDbIndex::FTS(opts))),
-        })
+        }
    }

    #[napi(factory)]
@@ -1,123 +0,0 @@
-// SPDX-License-Identifier: Apache-2.0
-// SPDX-FileCopyrightText: Copyright The LanceDB Authors
-
-use std::sync::Arc;
-
-use napi_derive::napi;
-
-use crate::error::NapiErrorExt;
-
-/// A handle to an operation that may still be running.
-#[napi]
-pub struct Job {
-    inner: Arc<lancedb::Job>,
-}
-
-impl Job {
-    pub(crate) fn new(inner: lancedb::Job) -> Self {
-        Self {
-            inner: Arc::new(inner),
-        }
-    }
-}
-
-#[napi]
-impl Job {
-    /// Identifies the operation on the server that is running it. Operations
-    /// that run in this process have no server id. The value is opaque.
-    #[napi(getter)]
-    pub fn id(&self) -> Option<String> {
-        self.inner.id().map(str::to_string)
-    }
-
-    /// 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. States a newer server reports that this
-    /// client version does not know pass through as-is.
-    #[napi(catch_unwind)]
-    pub async fn status(&self) -> napi::Result<String> {
-        self.inner.status().await.default_error()
-    }
-
-    /// Wait until the operation reaches a terminal state.
-    #[napi(catch_unwind)]
-    pub async fn wait(&self) -> napi::Result<()> {
-        self.inner.wait().await.default_error()
-    }
-
-    /// Request cancellation. Cancelling a finished operation is a no-op.
-    #[napi(catch_unwind)]
-    pub async fn cancel(&self) -> napi::Result<()> {
-        self.inner.cancel().await.default_error()
-    }
-}
-
-/// A row from `Connection.listJobs`: one server-side job.
-#[napi(object)]
-pub struct JobInfo {
-    /// The job id -- what `Connection.getJob` and `Connection.cancelJob`
-    /// accept.
-    pub job_id: String,
-    /// The table the job runs against, without URI or namespace.
-    pub table: 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 created_at_millis: i64,
-}
-
-impl From<lancedb::database::JobInfo> for JobInfo {
-    fn from(info: lancedb::database::JobInfo) -> Self {
-        Self {
-            job_id: info.job_id,
-            table: info.table,
-            job_type: info.job_type,
-            state: info.state,
-            created_at_millis: info.created_at_millis,
-        }
-    }
-}
-
-/// The server's account of why a job failed.
-#[napi(object)]
-pub struct JobFailureInfo {
-    pub phase: Option<String>,
-    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,
-            }),
-        }
-    }
-}
@@ -11,7 +11,6 @@ mod error;
 mod header;
 mod index;
 mod iterator;
-mod job;
 pub mod merge;
 pub mod otel;
 pub mod permutation;
@@ -51,9 +51,9 @@ impl NativeMergeInsertBuilder {
    }

    #[napi]
-    pub fn use_lsm(&self, enable: bool) -> Self {
+    pub fn use_lsm_write(&self, use_lsm_write: bool) -> Self {
        let mut this = self.clone();
-        this.inner.use_lsm(enable);
+        this.inner.use_lsm_write(use_lsm_write);
        this
    }

@@ -19,7 +19,6 @@ use lancedb::index::scalar::{
    BooleanQuery, BoostQuery, FtsQuery, FullTextSearchQuery, MatchQuery, MultiMatchQuery, Occur,
    Operator, PhraseQuery,
 };
-use lancedb::query::AnalyzePlanDistributedMetrics;
 use lancedb::query::ExecutableQuery;
 use lancedb::query::Query as LanceDbQuery;
 use lancedb::query::QueryBase;
@@ -48,28 +47,6 @@ impl From<ColumnOrdering> for LanceDbColumnOrdering {
    }
 }

-fn analyze_plan_options(
-    distributed_metrics: Option<String>,
-) -> napi::Result<QueryExecutionOptions> {
-    let analyze_plan_distributed_metrics =
-        match distributed_metrics.as_deref().unwrap_or("aggregate") {
-            "aggregate" => AnalyzePlanDistributedMetrics::Aggregate,
-            "per_worker" => AnalyzePlanDistributedMetrics::PerWorker,
-            "full" => AnalyzePlanDistributedMetrics::Full,
-            mode => {
-                return Err(napi::Error::from_reason(format!(
-                    "Invalid distributedMetrics value '{}'. Expected one of: \
-                 'aggregate', 'per_worker', 'full'",
-                    mode
-                )));
-            }
-        };
-
-    let mut options = QueryExecutionOptions::default();
-    options.analyze_plan_distributed_metrics = analyze_plan_distributed_metrics;
-    Ok(options)
-}
-
 fn bytes_to_arrow_array(data: Uint8Array, dtype: String) -> napi::Result<Arc<dyn Array>> {
    let buf = arrow_buffer::Buffer::from(data.to_vec());
    let num_bytes = buf.len();
@@ -168,11 +145,6 @@ impl Query {
        self.inner = self.inner.clone().with_row_id();
    }

-    #[napi]
-    pub fn use_lsm(&mut self, enable: bool) {
-        self.inner = self.inner.clone().use_lsm(enable);
-    }
-
    #[napi]
    pub fn order_by(&mut self, ordering: Option<Vec<ColumnOrdering>>) -> napi::Result<()> {
        let ordering = ordering.map(|ordering| {
@@ -228,17 +200,13 @@ impl Query {
    }

    #[napi(catch_unwind)]
-    pub async fn analyze_plan(&self, distributed_metrics: Option<String>) -> napi::Result<String> {
-        let options = analyze_plan_options(distributed_metrics)?;
-        self.inner
-            .analyze_plan_with_options(options)
-            .await
-            .map_err(|e| {
-                napi::Error::from_reason(format!(
-                    "Failed to execute analyze plan: {}",
-                    convert_error(&e)
-                ))
-            })
+    pub async fn analyze_plan(&self) -> napi::Result<String> {
+        self.inner.analyze_plan().await.map_err(|e| {
+            napi::Error::from_reason(format!(
+                "Failed to execute analyze plan: {}",
+                convert_error(&e)
+            ))
+        })
    }
 }

@@ -379,11 +347,6 @@ impl VectorQuery {
        self.inner = self.inner.clone().with_row_id();
    }

-    #[napi]
-    pub fn use_lsm(&mut self, enable: bool) {
-        self.inner = self.inner.clone().use_lsm(enable);
-    }
-
    #[napi]
    pub fn rerank(
        &mut self,
@@ -449,17 +412,13 @@ impl VectorQuery {
    }

    #[napi(catch_unwind)]
-    pub async fn analyze_plan(&self, distributed_metrics: Option<String>) -> napi::Result<String> {
-        let options = analyze_plan_options(distributed_metrics)?;
-        self.inner
-            .analyze_plan_with_options(options)
-            .await
-            .map_err(|e| {
-                napi::Error::from_reason(format!(
-                    "Failed to execute analyze plan: {}",
-                    convert_error(&e)
-                ))
-            })
+    pub async fn analyze_plan(&self) -> napi::Result<String> {
+        self.inner.analyze_plan().await.map_err(|e| {
+            napi::Error::from_reason(format!(
+                "Failed to execute analyze plan: {}",
+                convert_error(&e)
+            ))
+        })
    }
 }

@@ -489,11 +448,6 @@ impl TakeQuery {
        self.inner = self.inner.clone().with_row_id();
    }

-    #[napi]
-    pub fn use_lsm(&mut self, enable: bool) {
-        self.inner = self.inner.clone().use_lsm(enable);
-    }
-
    #[napi(catch_unwind)]
    pub async fn output_schema(&self) -> napi::Result<Buffer> {
        let schema = self.inner.output_schema().await.default_error()?;
@@ -537,17 +491,13 @@ impl TakeQuery {
    }

    #[napi(catch_unwind)]
-    pub async fn analyze_plan(&self, distributed_metrics: Option<String>) -> napi::Result<String> {
-        let options = analyze_plan_options(distributed_metrics)?;
-        self.inner
-            .analyze_plan_with_options(options)
-            .await
-            .map_err(|e| {
-                napi::Error::from_reason(format!(
-                    "Failed to execute analyze plan: {}",
-                    convert_error(&e)
-                ))
-            })
+    pub async fn analyze_plan(&self) -> napi::Result<String> {
+        self.inner.analyze_plan().await.map_err(|e| {
+            napi::Error::from_reason(format!(
+                "Failed to execute analyze plan: {}",
+                convert_error(&e)
+            ))
+        })
    }
 }

@@ -232,10 +232,6 @@ impl From<ClientConfig> for lancedb::remote::ClientConfig {
            tls_config: config.tls_config.map(Into::into),
            header_provider: None, // the header provider is set separately later
            user_id: config.user_id,
-            // Resolved from LANCE_CLIENT_MAX_BYTES_PER_REQUEST or the default.
-            max_bytes_per_request: None,
-            // Resolved from LANCE_CLIENT_MAX_REQUEST_DURATION or the read timeout.
-            max_request_duration: None,
        }
    }
 }
@@ -168,39 +168,6 @@ impl Table {
        builder.execute().await.default_error()
    }

-    #[napi(catch_unwind)]
-    pub async fn create_index_async(
-        &self,
-        index: Option<&Index>,
-        column: String,
-        replace: Option<bool>,
-        wait_timeout_s: Option<i64>,
-        name: Option<String>,
-        train: Option<bool>,
-    ) -> napi::Result<crate::job::Job> {
-        let lancedb_index = if let Some(index) = index {
-            index.consume()?
-        } else {
-            lancedb::index::Index::Auto
-        };
-        let mut builder = self.inner_ref()?.create_index(&[column], lancedb_index);
-        if let Some(replace) = replace {
-            builder = builder.replace(replace);
-        }
-        if let Some(timeout) = wait_timeout_s {
-            builder =
-                builder.wait_timeout(std::time::Duration::from_secs(timeout.try_into().unwrap()));
-        }
-        if let Some(name) = name {
-            builder = builder.name(name);
-        }
-        if let Some(train) = train {
-            builder = builder.train(train);
-        }
-        let job = builder.execute_async().await.default_error()?;
-        Ok(crate::job::Job::new(job))
-    }
-
    #[napi(catch_unwind)]
    pub async fn drop_index(&self, index_name: String) -> napi::Result<()> {
        self.inner_ref()?
@@ -339,9 +306,7 @@ impl Table {
        let transforms = NewColumnTransform::SqlExpressions(transforms);
        let res = self
            .inner_ref()?
-            .add_columns()
-            .transform(transforms)
-            .execute()
+            .add_columns(transforms, None)
            .await
            .default_error()?;
        Ok(res.into())
@@ -358,9 +323,7 @@ impl Table {
        let transforms = NewColumnTransform::AllNulls(schema);
        let res = self
            .inner_ref()?
-            .add_columns()
-            .transform(transforms)
-            .execute()
+            .add_columns(transforms, None)
            .await
            .default_error()?;
        Ok(res.into())
@@ -772,8 +735,7 @@ pub struct LsmWriteSpec {
    pub column: Option<String>,
    /// Bucket variant: the number of buckets, in `[1, 1024]`.
    pub num_buckets: Option<u32>,
-    /// Indexes the MemWAL keeps up to date. Omitted resolves every
-    /// maintainable index on install; an empty array means none.
+    /// Names of indexes the MemWAL should keep up to date during writes.
    pub maintained_indexes: Option<Vec<String>>,
    /// Default `ShardWriter` configuration recorded in the MemWAL index.
    pub writer_config_defaults: Option<HashMap<String, String>>,
@@ -783,6 +745,7 @@ impl TryFrom<LsmWriteSpec> for lancedb::table::LsmWriteSpec {
    type Error = napi::Error;

    fn try_from(value: LsmWriteSpec) -> napi::Result<Self> {
+        let maintained = value.maintained_indexes.unwrap_or_default();
        let writer_config_defaults = value.writer_config_defaults.unwrap_or_default();
        let spec = match value.spec_type.as_str() {
            "bucket" => {
@@ -809,7 +772,7 @@ impl TryFrom<LsmWriteSpec> for lancedb::table::LsmWriteSpec {
            }
        };
        Ok(spec
-            .with_maintained_indexes(value.maintained_indexes)
+            .with_maintained_indexes(maintained)
            .with_writer_config_defaults(writer_config_defaults))
    }
 }
@@ -827,7 +790,7 @@ impl From<lancedb::table::LsmWriteSpec> for LsmWriteSpec {
                spec_type: "bucket".to_string(),
                column: Some(column),
                num_buckets: Some(num_buckets),
-                maintained_indexes,
+                maintained_indexes: Some(maintained_indexes),
                writer_config_defaults: Some(writer_config_defaults),
            },
            Native::Identity {
@@ -838,7 +801,7 @@ impl From<lancedb::table::LsmWriteSpec> for LsmWriteSpec {
                spec_type: "identity".to_string(),
                column: Some(column),
                num_buckets: None,
-                maintained_indexes,
+                maintained_indexes: Some(maintained_indexes),
                writer_config_defaults: Some(writer_config_defaults),
            },
            Native::Unsharded {
@@ -848,7 +811,7 @@ impl From<lancedb::table::LsmWriteSpec> for LsmWriteSpec {
                spec_type: "unsharded".to_string(),
                column: None,
                num_buckets: None,
-                maintained_indexes,
+                maintained_indexes: Some(maintained_indexes),
                writer_config_defaults: Some(writer_config_defaults),
            },
        }
@@ -1043,10 +1006,7 @@ impl From<lancedb::index::IndexStatistics> for IndexStatistics {

 #[napi(object)]
 pub struct TableStatistics {
-    /// The total size, in bytes, of the table's data files, index files, and
-    /// overlay files
-    ///
-    /// Read from the manifest, so this excludes deletion files and manifests.
+    /// The total number of bytes in the table
    pub total_bytes: i64,

    /// The number of rows in the table
@@ -1395,28 +1355,4 @@ impl Branches {
    pub async fn delete(&self, name: String) -> napi::Result<()> {
        self.inner.delete_branch(&name).await.default_error()
    }
-
-    #[napi(ts_return_type = "Promise<Record<string, unknown>>")]
-    pub async fn diff(&self, from_branch: String) -> napi::Result<serde_json::Value> {
-        let diff = self.inner.diff_branch(&from_branch).await.default_error()?;
-        serde_json::to_value(diff).map_err(|err| {
-            napi::Error::from_reason(format!("failed to serialize branch diff: {err}"))
-        })
-    }
-
-    #[napi(ts_return_type = "Promise<Record<string, unknown>>")]
-    pub async fn merge(
-        &self,
-        from_branch: String,
-        dry_run: Option<bool>,
-    ) -> napi::Result<serde_json::Value> {
-        let result = self
-            .inner
-            .merge_branch(&from_branch, dry_run.unwrap_or(false))
-            .await
-            .default_error()?;
-        serde_json::to_value(result).map_err(|err| {
-            napi::Error::from_reason(format!("failed to serialize branch merge result: {err}"))
-        })
-    }
 }
@@ -1,21 +0,0 @@
-{
-  "name": "lancedb",
-  "description": "Write, review, debug, and document LanceDB pipelines in Python and TypeScript that work across local LanceDB OSS tables and remote LanceDB Enterprise/Cloud tables, with idiomatic query/search patterns and performance defaults for ingestion, indexing, filtering, and diagnostics.",
-  "version": "0.1.0",
-  "author": {
-    "name": "LanceDB"
-  },
-  "homepage": "https://www.lancedb.com",
-  "keywords": [
-    "lancedb",
-    "vector-search",
-    "full-text-search",
-    "hybrid-search",
-    "python",
-    "typescript",
-    "pipelines",
-    "ingestion",
-    "indexing",
-    "performance"
-  ]
-}
--- a/Show More
+++ b/Show More