Personal RAG with memory
Drop your PDFs and notes into a folder, chat with them in natural language. Memory of past conversations, the assistant gets smarter over time. You end with something you actually use every day.
03, Personal RAG Assistant with Memory Difficulty: Medium Time: 5-8 hours What it does: A chatbot that knows your documents. Upload PDFs, notes, or any text and chat with them. It remembers past conversations so context builds over time. Why build this You have knowledge scattered everywhere: PDFs, notes, bookmarks, docs. A RAG assistant lets you ask questions across all of it in natural language. The memory layer means it gets better the more you use it. What you need Python 3.10+ LangChain ChromaDB (local vector database, no account needed) An Anthropic API key or OpenAI API key Your documents (PDFs, markdown files, text files) Setup (15 minutes) Create your project Install dependencies Set your API key Create the starter script Save this as rag.py: Try it Add your…
Part of 5 weekend projects: Excalidraw, RAG, agents (batch2) · Back to the pack