mirror of
https://github.com/lancedb/lancedb.git
synced 2025-12-25 14:29:56 +00:00
0b9924b432
It improves the UX as iterators can be of any type supported by the
table (plus recordbatch) & there is no separate requirement.
Also expands the test cases for pydantic & arrow schema.
If this is looks good I'll update the docs.
Example usage:
```
class Content(LanceModel):
vector: vector(2)
item: str
price: float
def make_batches():
for _ in range(5):
yield from [
# pandas
pd.DataFrame({
"vector": [[3.1, 4.1], [1, 1]],
"item": ["foo", "bar"],
"price": [10.0, 20.0],
}),
# pylist
[
{"vector": [3.1, 4.1], "item": "foo", "price": 10.0},
{"vector": [5.9, 26.5], "item": "bar", "price": 20.0},
],
# recordbatch
pa.RecordBatch.from_arrays(
[
pa.array([[3.1, 4.1], [5.9, 26.5]], pa.list_(pa.float32(), 2)),
pa.array(["foo", "bar"]),
pa.array([10.0, 20.0]),
],
["vector", "item", "price"],
),
# pydantic list
[
Content(vector=[3.1, 4.1], item="foo", price=10.0),
Content(vector=[5.9, 26.5], item="bar", price=20.0),
]]
db = lancedb.connect("db")
tbl = db.create_table("tabley", make_batches(), schema=Content, mode="overwrite")
tbl.add(make_batches())
```
Same should with arrow schema.
---------
Co-authored-by: Weston Pace <weston.pace@gmail.com>