I am trying to create a vector data using AWS Bedrock. I am passing a CSV file(stored in S3). While ingesting data, some of the data is randomly dropped by AWS. The csv file has 1000 rows while the vector database has only 850 rows of data. I have tried using vector data in Opensearch, Aurora and Pinecone. But the issue stays same. Can anyone help? CSV file is less than 7MB

Thank you!

Entire data ingested into DB