Uses hybrid semantic search (combination of dense embeddings and sparse vectors) to retrieve high quality answers across your documents.<p>Features<p>- Significantly faster than competition (Process a 200 page PDF in <5s)<p>- Much better answer quality<p>- Fast summarization tool<p>- Beta API for end to end extractive document QA (hello@dankgpt.com)<p>Try it out (no login)<p>- Llama 2 paper <a href="https://www.dankgpt.com/chat/346f444d-e286-4671-b157-540f4cb819ca" rel="nofollow noreferrer">https://www.dankgpt.com/chat/346f444d-e286-4671-b157-540f4cb...</a><p>- Scott Aaronson Quantum Information Science lectures <a href="https://www.dankgpt.com/chat/cc491d72-dc7b-4ace-8e26-60026ae29c02" rel="nofollow noreferrer">https://www.dankgpt.com/chat/cc491d72-dc7b-4ace-8e26-60026ae...</a><p>- Berkshire 2022 Annual Report <a href="https://www.dankgpt.com/chat/068bf85f-b372-46a4-a164-6096f8c4c5fd" rel="nofollow noreferrer">https://www.dankgpt.com/chat/068bf85f-b372-46a4-a164-6096f8c...</a><p>Why not host it yourself?<p>- You definitely can! DankGPT is intended as a quick way to ask questions about a research paper, or help students with answering questions from their lecture slides, with an easy way to share your chatbot.
I'm so confused. It seems like a joke (DankGPT and mentions of GPT5) but then it actually works. Is it just a tiny wrapper on top of langchain meant to poke fun at all the thin API-wrapper startups?