fix(node): allow undefined/omitted values for nullable vector fields (#2656)

**Problem**: When a vector field is marked as nullable, users should be
able to omit it or pass `undefined`, but this was throwing an error:
"Table has embeddings: 'vector', but no embedding function was provided"

fixes: #2646

**Solution**: Modified `validateSchemaEmbeddings` to check
`field.nullable` before treating `undefined` values as missing embedding
fields.

**Changes**:
- Fixed validation logic in `nodejs/lancedb/arrow.ts`
- Enabled previously skipped test for nullable fields
- Added reproduction test case

**Behavior**:
-  `{ vector: undefined }` now works for nullable fields
-  `{}` (omitted field) now works for nullable fields  
-  `{ vector: null }` still works (unchanged)
-  Non-nullable fields still properly throw errors (unchanged)

---------

Co-authored-by: Will Jones <willjones127@gmail.com>
Co-authored-by: neha <neha@posthog.com>
This commit is contained in:
Neha Prasad
2025-10-02 23:23:05 +05:30
committed by GitHub
parent 1aa0fd16e7
commit 9e2a68541e
2 changed files with 84 additions and 16 deletions

View File

@@ -1285,19 +1285,36 @@ function validateSchemaEmbeddings(
if (isFixedSizeList(field.type)) {
field = sanitizeField(field);
if (data.length !== 0 && data?.[0]?.[field.name] === undefined) {
// Check if there's an embedding function registered for this field
let hasEmbeddingFunction = false;
// Check schema metadata for embedding functions
if (schema.metadata.has("embedding_functions")) {
const embeddings = JSON.parse(
schema.metadata.get("embedding_functions")!,
);
if (
// biome-ignore lint/suspicious/noExplicitAny: we don't know the type of `f`
embeddings.find((f: any) => f["vectorColumn"] === field.name) ===
undefined
) {
// biome-ignore lint/suspicious/noExplicitAny: we don't know the type of `f`
if (embeddings.find((f: any) => f["vectorColumn"] === field.name)) {
hasEmbeddingFunction = true;
}
}
// Check passed embedding function parameter
if (embeddings && embeddings.vectorColumn === field.name) {
hasEmbeddingFunction = true;
}
// If the field is nullable AND there's no embedding function, allow undefined/omitted values
if (field.nullable && !hasEmbeddingFunction) {
fields.push(field);
} else {
// Either not nullable OR has embedding function - require explicit values
if (hasEmbeddingFunction) {
// Don't add to missingEmbeddingFields since this is expected to be filled by embedding function
fields.push(field);
} else {
missingEmbeddingFields.push(field);
}
} else {
missingEmbeddingFields.push(field);
}
} else {
fields.push(field);