feat: SDK surface for functions, materialized views, jobs, refresh_column

Adds the derived-compute interface to the SDK:

- Database trait: create/list/drop_function, create/refresh/alter/
  drop/list_materialized_view, list_jobs -- default implementations
  return Error::NotSupported (NotImplementedError in python), so
  existing Database impls are unaffected; local single-node
  implementations are planned. BaseTable gains refresh_column with
  the same default.
- RemoteDatabase/RemoteTable implement them against the server REST
  routes (/v1/function/*, /v1/materialized_view/*, /v1/job/list,
  /v1/table/{id}/refresh_column), with mock-HTTP unit tests.
- Connection/Table public methods, pyo3 bindings (FunctionInfo,
  MaterializedViewInfo, JobInfo pyclasses), and python wrappers:
  sync on the DBConnection base (shared by local and remote
  connections), async on AsyncConnection; refresh_column on
  LanceTable, RemoteTable, and AsyncTable.

python/python/lancedb/db.py

@@ -563,6 +563,101 @@ class DBConnection(EnforceOverrides):
         raise NotImplementedError("serialize is not supported for this connection type")
 
 
+    # -- Derived compute: functions, materialized views, jobs -------------
+    # Server-backed features (LanceDB Enterprise / Cloud); local
+    # connections raise NotImplementedError for now.
+
+    def create_function(
+        self,
+        name: str,
+        language: str,
+        return_type: str,
+        body: str,
+        options: Optional[Dict[str, str]] = None,
+    ):
+        """Register a UDF (CREATE FUNCTION).
+
+        Parameters
+        ----------
+        name: str
+            Function name.
+        language: str
+            Implementation language (currently "python").
+        return_type: str
+            SQL return type, e.g. "FLOAT", "FLOAT[1536]",
+            "STRUCT(a FLOAT, b VARCHAR)", "TABLE(chunk VARCHAR, idx INT)".
+        body: str
+            Function body: source text, or base64 cloudpickle bytes when
+            options["body_format"] == "cloudpickle".
+        options: dict, optional
+            input_columns, pip, num_gpus, batch_size, timeout,
+            error_policy, docker_image, body_format, ...
+        """
+        LOOP.run(self._conn.create_function(name, language, return_type, body, options))
+
+    def list_functions(self):
+        """List registered functions (SHOW FUNCTIONS)."""
+        return LOOP.run(self._conn.list_functions())
+
+    def drop_function(self, name: str):
+        """Drop a registered function (DROP FUNCTION)."""
+        LOOP.run(self._conn.drop_function(name))
+
+    def create_materialized_view(
+        self,
+        name: str,
+        query: str,
+        *,
+        auto_refresh: bool = False,
+        with_no_data: bool = False,
+    ) -> Optional[str]:
+        """Create a materialized view (CREATE MATERIALIZED VIEW).
+
+        `query` is the view's SELECT statement, e.g.
+        "SELECT id, embed(body) AS vec FROM articles WHERE id > 1".
+        Returns the initial-population job id, or None when
+        with_no_data=True.
+        """
+        return LOOP.run(
+            self._conn.create_materialized_view(
+                name, query, auto_refresh=auto_refresh, with_no_data=with_no_data
+            )
+        )
+
+    def refresh_materialized_view(
+        self,
+        name: str,
+        *,
+        src_version: Optional[int] = None,
+        num_workers: Optional[int] = None,
+        max_workers: Optional[int] = None,
+    ) -> str:
+        """Refresh a materialized view; returns the refresh job id."""
+        return LOOP.run(
+            self._conn.refresh_materialized_view(
+                name,
+                src_version=src_version,
+                num_workers=num_workers,
+                max_workers=max_workers,
+            )
+        )
+
+    def alter_materialized_view(self, name: str, *, auto_refresh: bool):
+        """Update a materialized view's options (ALTER MATERIALIZED VIEW)."""
+        LOOP.run(self._conn.alter_materialized_view(name, auto_refresh=auto_refresh))
+
+    def drop_materialized_view(self, name: str):
+        """Drop a materialized view definition (DROP MATERIALIZED VIEW)."""
+        LOOP.run(self._conn.drop_materialized_view(name))
+
+    def list_materialized_views(self):
+        """List registered materialized view definitions."""
+        return LOOP.run(self._conn.list_materialized_views())
+
+    def list_jobs(self):
+        """List inflight server-side jobs across the database's tables."""
+        return LOOP.run(self._conn.list_jobs())
+
 class LanceDBConnection(DBConnection):
     """
     A connection to a LanceDB database.
@@ -1787,6 +1882,75 @@ class AsyncConnection(object):
         )
         return AsyncTable(table)
 
+    # -- Derived compute: functions, materialized views, jobs -------------
+    # Server-backed features (LanceDB Enterprise / Cloud); local
+    # connections raise NotImplementedError for now.
+
+    async def create_function(
+        self,
+        name: str,
+        language: str,
+        return_type: str,
+        body: str,
+        options: Optional[Dict[str, str]] = None,
+    ):
+        """Register a UDF (CREATE FUNCTION)."""
+        await self._inner.create_function(name, language, return_type, body, options)
+
+    async def list_functions(self):
+        """List registered functions (SHOW FUNCTIONS)."""
+        return await self._inner.list_functions()
+
+    async def drop_function(self, name: str):
+        """Drop a registered function (DROP FUNCTION)."""
+        await self._inner.drop_function(name)
+
+    async def create_materialized_view(
+        self,
+        name: str,
+        query: str,
+        *,
+        auto_refresh: bool = False,
+        with_no_data: bool = False,
+    ) -> Optional[str]:
+        """Create a materialized view; returns the initial-population
+        job id, or None when with_no_data=True."""
+        return await self._inner.create_materialized_view(
+            name, query, auto_refresh=auto_refresh, with_no_data=with_no_data
+        )
+
+    async def refresh_materialized_view(
+        self,
+        name: str,
+        *,
+        src_version: Optional[int] = None,
+        num_workers: Optional[int] = None,
+        max_workers: Optional[int] = None,
+    ) -> str:
+        """Refresh a materialized view; returns the refresh job id."""
+        return await self._inner.refresh_materialized_view(
+            name,
+            src_version=src_version,
+            num_workers=num_workers,
+            max_workers=max_workers,
+        )
+
+    async def alter_materialized_view(self, name: str, *, auto_refresh: bool):
+        """Update a materialized view's options."""
+        await self._inner.alter_materialized_view(name, auto_refresh)
+
+    async def drop_materialized_view(self, name: str):
+        """Drop a materialized view definition."""
+        await self._inner.drop_materialized_view(name)
+
+    async def list_materialized_views(self):
+        """List registered materialized view definitions."""
+        return await self._inner.list_materialized_views()
+
+    async def list_jobs(self):
+        """List inflight server-side jobs across the database's tables."""
+        return await self._inner.list_jobs()
+
     async def rename_table(
         self,
         cur_name: str,

python/python/lancedb/remote/table.py

@@ -887,6 +887,33 @@ class RemoteTable(Table):
     def add_columns(self, transforms: Dict[str, str]) -> AddColumnsResult:
         return LOOP.run(self._table.add_columns(transforms))
 
+    def refresh_column(
+        self,
+        columns,
+        *,
+        where: Optional[str] = None,
+        num_workers: Optional[int] = None,
+        max_workers: Optional[int] = None,
+    ) -> str:
+        """Trigger recompute of computed columns (REFRESH COLUMN).
+
+        The expression is resolved server-side from each column's stored
+        binding; columns bound to the same struct-returning function
+        refresh together. Returns the refresh job id. Server-backed
+        feature (LanceDB Enterprise / Cloud).
+        """
+        if isinstance(columns, str):
+            columns = [columns]
+        return LOOP.run(
+            self._table.refresh_column(
+                list(columns),
+                where=where,
+                num_workers=num_workers,
+                max_workers=max_workers,
+            )
+        )
+
+
     def alter_columns(
         self, *alterations: Iterable[Dict[str, str]]
     ) -> AlterColumnsResult:

python/python/lancedb/table.py

@@ -3714,6 +3714,33 @@ class LanceTable(Table):
     ) -> AddColumnsResult:
         return LOOP.run(self._table.add_columns(transforms))
 
+    def refresh_column(
+        self,
+        columns,
+        *,
+        where: Optional[str] = None,
+        num_workers: Optional[int] = None,
+        max_workers: Optional[int] = None,
+    ) -> str:
+        """Trigger recompute of computed columns (REFRESH COLUMN).
+
+        The expression is resolved server-side from each column's stored
+        binding; columns bound to the same struct-returning function
+        refresh together. Returns the refresh job id. Server-backed
+        feature (LanceDB Enterprise / Cloud).
+        """
+        if isinstance(columns, str):
+            columns = [columns]
+        return LOOP.run(
+            self._table.refresh_column(
+                list(columns),
+                where=where,
+                num_workers=num_workers,
+                max_workers=max_workers,
+            )
+        )
+
+
     def alter_columns(
         self, *alterations: Iterable[Dict[str, str]]
     ) -> AlterColumnsResult:
@@ -5390,6 +5417,25 @@ class AsyncTable:
 
         return await self._inner.update(updates_sql, where)
 
+    async def refresh_column(
+        self,
+        columns,
+        *,
+        where: Optional[str] = None,
+        num_workers: Optional[int] = None,
+        max_workers: Optional[int] = None,
+    ) -> str:
+        """Trigger recompute of computed columns (REFRESH COLUMN).
+        Returns the refresh job id. Server-backed feature."""
+        if isinstance(columns, str):
+            columns = [columns]
+        return await self._inner.refresh_column(
+            list(columns),
+            where_clause=where,
+            num_workers=num_workers,
+            max_workers=max_workers,
+        )
+
     async def add_columns(
         self, transforms: dict[str, str] | pa.field | List[pa.field] | pa.Schema
     ) -> AddColumnsResult:

python/src/connection.rs

@@ -18,7 +18,10 @@ use lancedb::{
     connection::Connection as LanceConnection,
     connection::NamespaceClientPushdownOperation,
     database::namespace::LanceNamespaceDatabase,
-    database::{CreateTableMode, Database, ReadConsistency},
+    database::{
+        CreateFunctionRequest, CreateMaterializedViewRequest, CreateTableMode, Database,
+        ReadConsistency, RefreshMaterializedViewRequest,
+    },
 };
 use pyo3::{
     Bound, FromPyObject, Py, PyAny, PyRef, PyResult, Python,
@@ -27,6 +30,46 @@ use pyo3::{
     types::{PyDict, PyDictMethods},
 };
 
+/// A registered function, as returned by `list_functions`.
+#[pyclass(get_all)]
+#[derive(Clone)]
+pub struct FunctionInfo {
+    pub name: String,
+    pub language: String,
+    pub return_type: String,
+    pub description: String,
+}
+
+/// A registered materialized view definition.
+#[pyclass(get_all)]
+#[derive(Clone)]
+pub struct MaterializedViewInfo {
+    pub name: String,
+    pub source_table: String,
+    pub projection: Vec<String>,
+    pub udf_columns: Vec<String>,
+    pub filter: Option<String>,
+    pub auto_refresh: bool,
+}
+
+/// One inflight server-side job.
+#[pyclass(get_all)]
+#[derive(Clone)]
+pub struct JobInfo {
+    pub table: String,
+    pub job_id: String,
+    pub job_type: String,
+    pub state: String,
+    pub column: Option<String>,
+    pub age_seconds: Option<i64>,
+    pub command: Option<String>,
+    pub units_done: Option<i64>,
+    pub units_total: Option<i64>,
+    pub committed: bool,
+    pub rows_skipped: u64,
+    pub error: Option<String>,
+}
+
 #[pyclass]
 pub struct Connection {
     inner: Option<LanceConnection>,
@@ -310,6 +353,163 @@ impl Connection {
         })
     }
 
+    #[pyo3(signature = (name, language, return_type, body, options=None))]
+    pub fn create_function(
+        self_: PyRef<'_, Self>,
+        name: String,
+        language: String,
+        return_type: String,
+        body: String,
+        options: Option<HashMap<String, String>>,
+    ) -> PyResult<Bound<'_, PyAny>> {
+        let inner = self_.get_inner()?.clone();
+        future_into_py(self_.py(), async move {
+            inner
+                .create_function(CreateFunctionRequest {
+                    name,
+                    language,
+                    return_type,
+                    body,
+                    options: options.unwrap_or_default(),
+                })
+                .await
+                .infer_error()
+        })
+    }
+
+    pub fn list_functions(self_: PyRef<'_, Self>) -> PyResult<Bound<'_, PyAny>> {
+        let inner = self_.get_inner()?.clone();
+        future_into_py(self_.py(), async move {
+            let functions = inner.list_functions().await.infer_error()?;
+            Ok(functions
+                .into_iter()
+                .map(|f| FunctionInfo {
+                    name: f.name,
+                    language: f.language,
+                    return_type: f.return_type,
+                    description: f.description,
+                })
+                .collect::<Vec<_>>())
+        })
+    }
+
+    pub fn drop_function(self_: PyRef<'_, Self>, name: String) -> PyResult<Bound<'_, PyAny>> {
+        let inner = self_.get_inner()?.clone();
+        future_into_py(self_.py(), async move {
+            inner.drop_function(&name).await.infer_error()
+        })
+    }
+
+    #[pyo3(signature = (name, query, auto_refresh=false, with_no_data=false))]
+    pub fn create_materialized_view(
+        self_: PyRef<'_, Self>,
+        name: String,
+        query: String,
+        auto_refresh: bool,
+        with_no_data: bool,
+    ) -> PyResult<Bound<'_, PyAny>> {
+        let inner = self_.get_inner()?.clone();
+        future_into_py(self_.py(), async move {
+            inner
+                .create_materialized_view(CreateMaterializedViewRequest {
+                    name,
+                    query,
+                    auto_refresh,
+                    with_no_data,
+                })
+                .await
+                .infer_error()
+        })
+    }
+
+    #[pyo3(signature = (name, src_version=None, num_workers=None, max_workers=None))]
+    pub fn refresh_materialized_view(
+        self_: PyRef<'_, Self>,
+        name: String,
+        src_version: Option<u64>,
+        num_workers: Option<u32>,
+        max_workers: Option<u32>,
+    ) -> PyResult<Bound<'_, PyAny>> {
+        let inner = self_.get_inner()?.clone();
+        future_into_py(self_.py(), async move {
+            inner
+                .refresh_materialized_view(RefreshMaterializedViewRequest {
+                    name,
+                    src_version,
+                    num_workers,
+                    max_workers,
+                })
+                .await
+                .infer_error()
+        })
+    }
+
+    pub fn alter_materialized_view(
+        self_: PyRef<'_, Self>,
+        name: String,
+        auto_refresh: bool,
+    ) -> PyResult<Bound<'_, PyAny>> {
+        let inner = self_.get_inner()?.clone();
+        future_into_py(self_.py(), async move {
+            inner
+                .alter_materialized_view(&name, auto_refresh)
+                .await
+                .infer_error()
+        })
+    }
+
+    pub fn drop_materialized_view(
+        self_: PyRef<'_, Self>,
+        name: String,
+    ) -> PyResult<Bound<'_, PyAny>> {
+        let inner = self_.get_inner()?.clone();
+        future_into_py(self_.py(), async move {
+            inner.drop_materialized_view(&name).await.infer_error()
+        })
+    }
+
+    pub fn list_materialized_views(self_: PyRef<'_, Self>) -> PyResult<Bound<'_, PyAny>> {
+        let inner = self_.get_inner()?.clone();
+        future_into_py(self_.py(), async move {
+            let views = inner.list_materialized_views().await.infer_error()?;
+            Ok(views
+                .into_iter()
+                .map(|v| MaterializedViewInfo {
+                    name: v.name,
+                    source_table: v.source_table,
+                    projection: v.projection,
+                    udf_columns: v.udf_columns,
+                    filter: v.filter,
+                    auto_refresh: v.auto_refresh,
+                })
+                .collect::<Vec<_>>())
+        })
+    }
+
+    pub fn list_jobs(self_: PyRef<'_, Self>) -> PyResult<Bound<'_, PyAny>> {
+        let inner = self_.get_inner()?.clone();
+        future_into_py(self_.py(), async move {
+            let jobs = inner.list_jobs().await.infer_error()?;
+            Ok(jobs
+                .into_iter()
+                .map(|j| JobInfo {
+                    table: j.table,
+                    job_id: j.job_id,
+                    job_type: j.job_type,
+                    state: j.state,
+                    column: j.column,
+                    age_seconds: j.age_seconds,
+                    command: j.command,
+                    units_done: j.units_done,
+                    units_total: j.units_total,
+                    committed: j.committed,
+                    rows_skipped: j.rows_skipped,
+                    error: j.error,
+                })
+                .collect::<Vec<_>>())
+        })
+    }
+
     #[pyo3(signature = (cur_name, new_name, cur_namespace_path=None, new_namespace_path=None))]
     pub fn rename_table(
         self_: PyRef<'_, Self>,

python/src/lib.rs

@@ -41,6 +41,9 @@ pub fn _lancedb(_py: Python, m: &Bound<'_, PyModule>) -> PyResult<()> {
         .write_style("LANCEDB_LOG_STYLE");
     env_logger::init_from_env(env);
     m.add_class::<Connection>()?;
+    m.add_class::<connection::FunctionInfo>()?;
+    m.add_class::<connection::MaterializedViewInfo>()?;
+    m.add_class::<connection::JobInfo>()?;
     m.add_class::<Session>()?;
     m.add_class::<Table>()?;
     m.add_class::<IndexConfig>()?;

python/src/table.rs

@@ -1060,6 +1060,23 @@ impl Table {
         })
     }
 
+    #[pyo3(signature = (columns, where_clause=None, num_workers=None, max_workers=None))]
+    pub fn refresh_column(
+        self_: PyRef<'_, Self>,
+        columns: Vec<String>,
+        where_clause: Option<String>,
+        num_workers: Option<u32>,
+        max_workers: Option<u32>,
+    ) -> PyResult<Bound<'_, PyAny>> {
+        let inner = self_.inner_ref()?.clone();
+        future_into_py(self_.py(), async move {
+            inner
+                .refresh_column(&columns, where_clause, num_workers, max_workers)
+                .await
+                .infer_error()
+        })
+    }
+
     pub fn add_columns(
         self_: PyRef<'_, Self>,
         definitions: Vec<(String, String)>,