diff --git a/module_4_rag/batch_score_documents.py b/module_4_rag/batch_score_documents.py index 6a39c25..34757f9 100644 --- a/module_4_rag/batch_score_documents.py +++ b/module_4_rag/batch_score_documents.py @@ -69,6 +69,9 @@ def score_data() -> None: print("...data exported. Job complete") else: print("Scored data found... skipping generating embeddings.") + + print("preview of data:") + print(df.head().T) if __name__ == "__main__": diff --git a/module_4_rag/feature_repo/data/city_wikipedia_summaries_with_embeddings.parquet b/module_4_rag/feature_repo/data/city_wikipedia_summaries_with_embeddings.parquet index 42c56eb..4a4883e 100644 Binary files a/module_4_rag/feature_repo/data/city_wikipedia_summaries_with_embeddings.parquet and b/module_4_rag/feature_repo/data/city_wikipedia_summaries_with_embeddings.parquet differ