HomeCache: What If Your Home Could Actually Remember?

Описание и применение

HomeCache использует RAG‑архитектуру для хранения и поиска информации из домашних документов, позволяя пользователям задавать вопросы на естественном языке и получать ответы с указанием источника.

Задача

Household information is scattered across invoices, warranties, receipts, and manuals, making it hard to recall where specific details are stored.

Результат

HomeCache enables quick, trustworthy answers to household queries by leveraging user-uploaded documents and a RAG architecture.

Рабочий процесс

• Upload household documents
• Text extraction and chunking
• Generate embeddings for chunks
• Store chunks and embeddings in MongoDB Atlas Vector Search
• Ask a question in natural language
• Convert question to embedding
• Retrieve relevant memory chunks
• Feed question + memories to Gemma-2-2B-IT
• Generate grounded answer with source attribution
• Display answer and supporting document

Доказательства

I built HomeCache, an AI-powered memory for your home.

Источник

You can upload your household documents, and instead of digging through files one by one, you can simply ask questions about them in natural language.

Источник

HomeCache reads and processes it, breaks the information into smaller searchable pieces, and stores those memories in a vector database.

Источник

The relevant memories are then passed to Gemma-2-2B-IT, an open-weight model from Google.

Источник

HomeCache also keeps track of which documents were used to answer a question.

Источник