mirror of
https://github.com/lancedb/lancedb.git
synced 2026-10-13 07:12:27 +00:00
feat(sql): bind query parameters over Flight DoExchange (#4345)
`execute_query` / `execute_query_async` can now bind values to `$1` /
`$name` placeholders instead of splicing them into the SQL text. The
values travel as Arrow, so a float32 keeps its exact bits and type and a
vector stays a compact `FixedSizeList` (3 KB for 768 dims rather than ~9
KB of decimal literals parsed back as Float64).
```rust
db.execute_query_async("SELECT id FROM docs ORDER BY distance(vector, $vector) LIMIT $k")
.parameters(batch) // one-row RecordBatch
.execute()
.await?;
```
```python
db.execute_query(sql, parameters={"vector": np.float32_vector, "k": 10})
```
- A statement with parameters is sent on one `DoExchange`: the first
message carries the `CommandStatementQuery` descriptor and the parameter
schema, the second the one-row batch, and the result rows stream back on
the same call. Statements without parameters keep `PollFlightInfo` +
`DoGet` unchanged.
- Column `i` binds `$<i+1>`; a column whose name is not a number also
binds `$<name>`. Python accepts a list (positional), a dict (named), or
a one-row `RecordBatch` / `Table`; 1-D numpy / pyarrow arrays become a
`FixedSizeList` of their element type.
- A parameterized query runs on its call: `cancel()`, dropping the
handle before reading, or dropping the reader ends the call and stops
the server-side statement. It is still registered for `describe_query`.
- `Database::execute_query_async` now takes an `ExecuteQueryRequest`
options struct.
Server side: lancedb/sophon#8256.
This commit is contained in:
@@ -14,9 +14,10 @@ use crate::{
|
||||
table::Table,
|
||||
};
|
||||
use arrow::{
|
||||
array::RecordBatch,
|
||||
datatypes::Schema,
|
||||
ffi_stream::ArrowArrayStreamReader,
|
||||
pyarrow::{FromPyArrow, ToPyArrow},
|
||||
pyarrow::{FromPyArrow, PyArrowType, ToPyArrow},
|
||||
};
|
||||
use lancedb::{
|
||||
connection::Connection as LanceConnection,
|
||||
@@ -148,18 +149,22 @@ impl Connection {
|
||||
self.get_inner().map(|inner| inner.uri().to_string())
|
||||
}
|
||||
|
||||
#[pyo3(signature = (query, *, default_namespace_path=None))]
|
||||
#[pyo3(signature = (query, *, default_namespace_path=None, parameters=None))]
|
||||
pub fn execute_query_async<'a>(
|
||||
self_: PyRef<'a, Self>,
|
||||
query: String,
|
||||
default_namespace_path: Option<Bound<'_, PyAny>>,
|
||||
parameters: Option<PyArrowType<RecordBatch>>,
|
||||
) -> PyResult<Bound<'a, PyAny>> {
|
||||
let inner = self_.get_inner()?.clone();
|
||||
let default_namespace_path = parse_default_namespace_path(default_namespace_path)?;
|
||||
future_into_py(self_.py(), async move {
|
||||
let operation = inner
|
||||
let mut operation = inner
|
||||
.execute_query_async(query)
|
||||
.default_namespace_path(default_namespace_path);
|
||||
if let Some(PyArrowType(parameters)) = parameters {
|
||||
operation = operation.parameters(parameters);
|
||||
}
|
||||
operation
|
||||
.execute()
|
||||
.await
|
||||
|
||||
Reference in New Issue
Block a user