TastyLamps
Correcting LLM Hallucinations
Correcting Hallucinations in Large Language Models
At <10B parameters it's an LLM trained to provide optimal results for RAG and structured outputs. Although significantly smaller (and thus faster) than GPT-4 or Gemini-1.5 Pro, it performs at a comparable level for generation, citations, and structured outputs.
Mockingbird: A RAG-Focused LLM
Why Do Grapes Spark in the Microwave? (2019)
Show HN: Talk to YouTube – RAG for YouTube Videos
https://github.com/SulemanKazi/TtYT
Hi HN,I built this little application for setting up RAG on Youtube video transcripts. I haven't seen a lot of RAG for multimodal use-cases so I thought this was interesting. It uses YoutubeDL to get transcripts and Vectara to set up the RAG system. It's multilingual so other languages besides english work as well.The answer produced by the LLM has references with timestamps to where its...
GBoard Caps [video]
https://asknews.demo.vectara.com/
It defaults to a summarization-first view. To get a more search-like experience go to options > UX Mode > select Search (instead of summary).