Hacker News with Generative AI: Question Answering

TeapotLLM- an open-source <1B model for hallucination-resistant Q&A on a CPU (huggingface.co)
Teapot is an open-source small language model (~800 million parameters) fine-tuned on synthetic data and optimized to run locally on resource-constrained devices such as smartphones and CPUs. Teapot is trained to only answer using context from documents, reducing hallucinations. Teapot can perform a variety of tasks, including hallucination-resistant Question Answering (QnA), Retrieval-Augmented Generation (RAG), and JSON extraction. Teapot is a model built by and for the community.
Open Source, Language Models, Question Answering, Generative AI, CPU
14 points by zakerytclarke 10 days ago | 2 comments
Show HN: Gurubase – AI-Powered Q&A Assistants for Any Topic (github.com/Gurubase)
Gurubase is an open-source RAG system that lets you create AI-powered Q&A assistants by indexing websites, PDF documents, YouTube videos, and GitHub code repositories.
Open Source, Artificial Intelligence, Question Answering, Knowledge Management, Software
13 points by fatihbaltaci 95 days ago | 0 comments
Ask HN: How are you reading (nonfiction) books/pdfs in 2025? (ycombinator.com)
Everytime I start reading a book, I feel like uploading it in NotebookLM/ChatGPT to get QA; but these don't let me read in their app, and its not easy to get digital copies of books. I also want to ask questions adjacent to what I'm reading easily; I wonder if there are great apps/hacks people have for this.
Reading, Technology, Artificial Intelligence, Books, Question Answering
10 points by kanodiaashu 106 days ago | 26 comments
KAG – Knowledge Graph RAG Framework (github.com/OpenSPG)
KAG is a logical reasoning and Q&A framework based on the OpenSPG engine and large language models, which is used to build logical reasoning and Q&A solutions for vertical domain knowledge bases.
Knowledge Graphs, Question Answering, Open Source
230 points by taikon 117 days ago | 80 comments
Knowledge Graph Based Agent for Complex, Knowledge-Intensive QA in Medicine (arxiv.org)
Biomedical knowledge is uniquely complex and structured, requiring distinct reasoning strategies compared to other scientific disciplines like physics or chemistry.
Knowledge Graphs, Artificial Intelligence, Medicine, Question Answering
3 points by rntn 194 days ago | 0 comments
Show HN: Airgapped Offline RAG – Run LLMs Locally with Llama, Mistral, & Gemini (github.com/vincentkoc)
This project by Vincent Koc implements a Retrieval-Augmented Generation (RAG) based Question-Answering system for documents. It uses Llama 3, Mistral, and Gemini models for local inference with LlaMa c++, langchain for orchestration, chromadb for vector storage, and Streamlit for the user interface.
Open Source, AI, Question Answering
9 points by koconder 197 days ago | 1 comments
Show HN: Quilt – Powerful RAG UI for Document QA (quilt.fly.dev)
Software, User Interfaces, Question Answering
63 points by andes314 206 days ago | 22 comments
OpenEQA: Embodied Question Answering in the Era of Foundation Models (open-eqa.github.io)
Artificial Intelligence, Foundation Models, Question Answering
42 points by beefman 378 days ago | 0 comments