How would you build a RAG system for thousands of portfolio documents?

How would you build a RAG system for thousands of portfolio documents?medium

Type: scenario
Topic: how-would-you-build-a-rag-system-for-thousands-of-portfoli
Frequency: common
Tags: rag, how, would, you, build

Answer

Explanation

Ingestion: parse PDF filings → extract structured sections (holdings, NAV, metadata) → semantic chunking → embed with Bedrock Titan → store in ChromaDB with metadata (fund_name, filing_date, section_type). Retrieval: filter by fund_name + date range, then ANN search. Generation: inject top-3 chunks into Strands agent prompt. Batch process new filings via Step Functions on S3 upload.

Follow-upCan you give a production example?