gemini-code-assist[bot] commented on code in PR #37651:
URL: https://github.com/apache/beam/pull/37651#discussion_r2829476782
##########
sdks/python/apache_beam/ml/rag/enrichment/bigquery_vector_search.py:
##########
@@ -241,7 +241,7 @@ def format_query(self, items: List[EmbeddableItem]) -> str:
ARRAY_AGG(
STRUCT({"distance, " if self.include_distance else ""}\
{base_columns_str})
- ) as embeddable_items
+ ) as chunks
Review Comment:
The alias `chunks` seems inconsistent with the ongoing effort to deprecate
the term `Chunk` in favor of `EmbeddableItem` throughout the RAG API (as seen
in `ingestion/bigquery.py` and `types.py`). This change introduces a potential
source of confusion for users of the API. To maintain consistency, could you
please consider reverting to `embeddable_items` or using another name that
aligns with the new terminology, such as `retrieved_items`?
```suggestion
) as embeddable_items
```
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
