Building a Personal Notes Assistant with RAG, Amazon Bedrock, and Pinecone

Description and use

A personal notes assistant built with RAG, Amazon Bedrock, and Pinecone enables quick, private retrieval of information from uploaded .txt files.

Problem

Users struggle to locate specific information within hundreds of personal notes, wasting time searching manually.

Outcome

The system provides a private, accurate, and efficient way to query personal notes using RAG, eliminating manual search and ensuring answers are grounded in the user's own documents.

Workflow

• Upload .txt file to /ingest endpoint
• Validate file type, size, encoding, and content
• Store original file in private S3 bucket with unique UUID key
• Chunk text into overlapping snippets
• Generate 512-dim embeddings with Amazon Titan
• Index embeddings and metadata in Pinecone
• Receive question at /ask endpoint
• Embed question with Amazon Titan
• Retrieve top 3 matching snippets from Pinecone
• Assemble prompt with question and snippets
• Generate answer with Amazon Nova Lite
• Return answer as JSON

Evidence

Project Goal: Upload plain text (.txt) notes and receive accurate answers strictly grounded in their content.

Source

Amazon Nova Lite generating the response.

Source