feat: add list_versions to typescript, rust and remote python sdks (#1850)

Will require update to lance dependency to bring in this change which
makes the version serializable
https://github.com/lancedb/lance/pull/3143
This commit is contained in:
Bert
2024-11-21 13:35:14 -05:00
committed by GitHub
parent 72af977a73
commit cb9a00a28d
9 changed files with 195 additions and 13 deletions

View File

@@ -4,7 +4,7 @@ name = "lancedb"
dependencies = [
"deprecation",
"nest-asyncio~=1.0",
"pylance==0.19.3b1",
"pylance==0.20.0b1",
"tqdm>=4.27.0",
"pydantic>=1.10",
"packaging",

View File

@@ -78,6 +78,10 @@ class RemoteTable(Table):
self.schema.metadata
)
def list_versions(self):
"""List all versions of the table"""
return self._loop.run_until_complete(self._table.list_versions())
def to_arrow(self) -> pa.Table:
"""to_arrow() is not yet supported on LanceDB cloud."""
raise NotImplementedError("to_arrow() is not yet supported on LanceDB cloud.")

View File

@@ -8,7 +8,7 @@ import inspect
import time
from abc import ABC, abstractmethod
from dataclasses import dataclass
from datetime import timedelta
from datetime import datetime, timedelta
from functools import cached_property
from typing import (
TYPE_CHECKING,
@@ -1041,6 +1041,10 @@ class Table(ABC):
It can also be used to undo a `[Self::checkout]` operation
"""
@abstractmethod
def list_versions(self):
"""List all versions of the table"""
@cached_property
def _dataset_uri(self) -> str:
return _table_uri(self._conn.uri, self.name)
@@ -2931,6 +2935,19 @@ class AsyncTable:
"""
return await self._inner.version()
async def list_versions(self):
"""
List all versions of the table
"""
versions = await self._inner.list_versions()
for v in versions:
ts_nanos = v["timestamp"]
v["timestamp"] = datetime.fromtimestamp(ts_nanos // 1e9) + timedelta(
microseconds=(ts_nanos % 1e9) // 1e3
)
return versions
async def checkout(self, version):
"""
Checks out a specific version of the Table

View File

@@ -8,7 +8,7 @@ use lancedb::table::{
use pyo3::{
exceptions::{PyRuntimeError, PyValueError},
pyclass, pymethods,
types::{PyDict, PyDictMethods, PyString},
types::{IntoPyDict, PyDict, PyDictMethods, PyString},
Bound, FromPyObject, PyAny, PyRef, PyResult, Python, ToPyObject,
};
use pyo3_asyncio_0_21::tokio::future_into_py;
@@ -246,6 +246,33 @@ impl Table {
)
}
pub fn list_versions(self_: PyRef<'_, Self>) -> PyResult<Bound<'_, PyAny>> {
let inner = self_.inner_ref()?.clone();
future_into_py(self_.py(), async move {
let versions = inner.list_versions().await.infer_error()?;
let versions_as_dict = Python::with_gil(|py| {
versions
.iter()
.map(|v| {
let dict = PyDict::new_bound(py);
dict.set_item("version", v.version).unwrap();
dict.set_item(
"timestamp",
v.timestamp.timestamp_nanos_opt().unwrap_or_default(),
)
.unwrap();
let tup: Vec<(&String, &String)> = v.metadata.iter().collect();
dict.set_item("metadata", tup.into_py_dict(py)).unwrap();
dict.to_object(py)
})
.collect::<Vec<_>>()
});
Ok(versions_as_dict)
})
}
pub fn checkout(self_: PyRef<'_, Self>, version: u64) -> PyResult<Bound<'_, PyAny>> {
let inner = self_.inner_ref()?.clone();
future_into_py(self_.py(), async move {