feat: add use_index parameter to merge insert operations (#2674)

## Summary

Exposes `use_index` Merge Insert parameter, which was created upstream
in https://github.com/lancedb/lance/pull/4688.

## API Examples

### Python
```python
# Force table scan
table.merge_insert(["id"]) \
    .when_not_matched_insert_all() \
    .use_index(False) \
    .execute(data)
```

### Node.js/TypeScript
```typescript
// Force table scan  
await table.mergeInsert("id")
    .whenNotMatchedInsertAll()
    .useIndex(false)
    .execute(data);
```

### Rust
```rust
// Force table scan
let mut builder = table.merge_insert(&["id"]);
builder.when_not_matched_insert_all()
       .use_index(false);
builder.execute(data).await?;
```

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-authored-by: Claude <noreply@anthropic.com>
This commit is contained in:
Will Jones
2025-09-24 12:50:21 -07:00
committed by GitHub
parent 356d7046fd
commit d617cdef4a
9 changed files with 132 additions and 0 deletions

View File

@@ -33,6 +33,7 @@ class LanceMergeInsertBuilder(object):
self._when_not_matched_by_source_delete = False
self._when_not_matched_by_source_condition = None
self._timeout = None
self._use_index = True
def when_matched_update_all(
self, *, where: Optional[str] = None
@@ -78,6 +79,23 @@ class LanceMergeInsertBuilder(object):
self._when_not_matched_by_source_condition = condition
return self
def use_index(self, use_index: bool) -> LanceMergeInsertBuilder:
"""
Controls whether to use indexes for the merge operation.
When set to `True` (the default), the operation will use an index if available
on the join key for improved performance. When set to `False`, it forces a full
table scan even if an index exists. This can be useful for benchmarking or when
the query optimizer chooses a suboptimal path.
Parameters
----------
use_index: bool
Whether to use indices for the merge operation. Defaults to `True`.
"""
self._use_index = use_index
return self
def execute(
self,
new_data: DATA,

View File

@@ -3920,6 +3920,7 @@ class AsyncTable:
when_not_matched_by_source_delete=merge._when_not_matched_by_source_delete,
when_not_matched_by_source_condition=merge._when_not_matched_by_source_condition,
timeout=merge._timeout,
use_index=merge._use_index,
),
)