Yisz··on Launch HN: Human Layer (YC F24) – Human-in-the-Loop API for AI SystemsHow does it compare with the built-in human-in-the-loop feature from langgraph? Or CrewAI allows humaninput as well right?
Yisz··on Show HN: Search Bar for YouTube TranscriptsVery cool. Does this also generate the transcripts or only add search for videos with existing transcripts?
Yisz··on Seeking Datasets for Evaluating File Chunking Strategies for RAG/LLMWe have a number of production RAG datasets (human-verified) and have custom generated evaluation datasets for a variety of companies.Feel free to reach out if you are interested: yi@relari.ai
Yisz··on What I Learned from Building Google Search and How It Inspires RAG DevelopmentVery interesting comparison of RAG to traditional search development. I'm curious how large an evaluation dataset is usually necessary to compare results from different experiments of Google search?