From f260d3bf127c00a475e1e77821d0a2db9f14534b Mon Sep 17 00:00:00 2001
From: devteamaegis <devteam.aegis@gmail.com>
Date: Tue, 9 Jun 2026 18:57:02 -0400
Subject: [PATCH] fix(util): convert numpy scalars in value_to_sql (#3522)

## What's broken

`Table.update(values={...})` raises `NotImplementedError: SQL conversion
is not implemented for this type` when a value is a numpy scalar such as
`np.int64`, `np.int32`, `np.float32`, or `np.bool_`. These arise
naturally from indexing an ndarray or a pandas int/bool column.
`np.float64` happens to work (it subclasses `float`), which makes the
failure inconsistent and surprising.

```python
df = pd.DataFrame({"id": np.array([10, 20], dtype="int32")})
t.update(where="id = 1", values={"id": df["id"].iloc[0]})   # np.int32
# -> NotImplementedError: SQL conversion is not implemented for this type
```

## Why it happens

`value_to_sql` is a `singledispatch` with handlers only for native
Python types and `np.ndarray`; numpy `integer`/`floating`/`bool_`
scalars aren't Python subclasses, so they fall through to the
`NotImplementedError` base.

## Fix

Register handlers for `np.bool_`, `np.integer`, and `np.floating` that
delegate to the existing native handlers.

## Test

`value_to_sql` on `np.int32/int64/float32/float64/bool_` all convert;
`np.int32` raised before.

Co-authored-by: Ishaan Samantray <ishaansamantray@Ishaans-MacBook-Pro.local>
---
 python/python/lancedb/util.py    | 15 +++++++++++++++
 python/python/tests/test_util.py | 15 +++++++++++++++
 2 files changed, 30 insertions(+)

diff --git a/python/python/lancedb/util.py b/python/python/lancedb/util.py
index b8e519933..e9d01407b 100644
--- a/python/python/lancedb/util.py
+++ b/python/python/lancedb/util.py
@@ -385,6 +385,21 @@ def _(value: np.ndarray):
     return value_to_sql(value.tolist())
 
 
+@value_to_sql.register(np.bool_)
+def _(value: np.bool_):
+    return value_to_sql(bool(value))
+
+
+@value_to_sql.register(np.integer)
+def _(value: np.integer):
+    return value_to_sql(int(value))
+
+
+@value_to_sql.register(np.floating)
+def _(value: np.floating):
+    return value_to_sql(float(value))
+
+
 def deprecated(func):
     """This is a decorator which can be used to mark functions
     as deprecated. It will result in a warning being emitted
diff --git a/python/python/tests/test_util.py b/python/python/tests/test_util.py
index b5ab159b7..f3051d45a 100644
--- a/python/python/tests/test_util.py
+++ b/python/python/tests/test_util.py
@@ -149,6 +149,21 @@ def test_value_to_sql_dict():
     assert value_to_sql({}) == "named_struct()"
 
 
+def test_value_to_sql_numpy_scalars():
+    # numpy scalars (e.g. pulled from an ndarray or a pandas column) must
+    # convert the same way as their native Python counterparts. np.float64
+    # already worked by virtue of subclassing float, but the integer / bool
+    # / float32 scalars previously raised NotImplementedError.
+    import numpy as np
+
+    assert value_to_sql(np.int32(5)) == "5"
+    assert value_to_sql(np.int64(5)) == "5"
+    assert value_to_sql(np.float32(1.5)) == "1.5"
+    assert value_to_sql(np.float64(1.5)) == "1.5"
+    assert value_to_sql(np.bool_(True)) == "TRUE"
+    assert value_to_sql(np.bool_(False)) == "FALSE"
+
+
 def test_append_vector_columns():
     registry = EmbeddingFunctionRegistry.get_instance()
     registry.register("test")(MockTextEmbeddingFunction)