Determine how to build an end-to-end semantic search pipeline for Resume Book

We want to use S3 Vectors and Amazon Bedrock to build a semantic search pipeline on student profiles to make it easier for recruiters to find students that they want.

No repository files, tests, or entry points are identified in the issue. Start by reviewing the existing TypeScript application and documenting how student profiles are represented, then investigate the proposed S3 Vectors and Amazon Bedrock integration. Done means an agreed end-to-end pipeline design with clear inputs, outputs, and implementation boundaries.

索引モデルが issue の本文から書いたものです。