sm-joe/localrag ? reverse-engineered prompt
Reverse engineered prompt
Build me a private local chat app for my own documents that runs fully in Docker.
I want a clean dark UI where I can upload PDF, DOCX, TXT, and Markdown files, ask questions about them, and get answers that are grounded in the uploaded content with citations showing where the answer came from. If the answer is not in the documents, it should say so clearly instead of making things up.
Please make it use a local LLM through Ollama, store document embeddings in Qdrant, and keep the whole thing portable so I can run it on my machine without sending files to any cloud service. I also want conversation history saved so I can come back to old chats, rename or delete them, and continue a previous thread. Keep it secure and practical, with sensible upload limits and validation. If you need to check current docs for any of the tools, feel free to look them up online first.
Are you gonna build this?
make sure you review the code using coderabbit