Posts

Show HN: Semantically search and ask your Gmail using Local LLMs https://ift.tt/1An7lh4

Show HN: Semantically search and ask your Gmail using Local LLMs https://ift.tt/GT9hYQw June 20, 2025 at 11:25PM

Show HN: Vpuna AI Search – A semantic search platform https://ift.tt/BmdcwTY

Show HN: Vpuna AI Search – A semantic search platform Dear HN Community, I am a long time fan and first-time contributor. I just launched a developer focused semantic search platform and wanted to share it with the community. The idea is simple: upload structured or unstructured documents, select the fields you want to index and tag as metadata, and instantly get a clean search API you can use in your own app. Here is what it currently supports: - Manage your own tenants and projects - Upload .json and .txt files (support for .pdf, .docx, .xlsx, .yml, etc. coming soon) - Expose 3 APIs: search, upload document (embeddings), and delete document - Manage your own API keys - Uses CPU based sentence-transformers/all-MiniLM-L6-v2 for embeddings ( support for other local and online models are coming soon) LLM summarization and Model Context Protocol (MCP) support are on the roadmap Why I built it: In my consulting work, I kept seeing client wanting to move beyond basic keyword search and inte...

Banning Plastic Bags Works to Limit Shoreline Litter, Study Finds

Image
By Christina Kelso from NYT Climate https://ift.tt/pZXFmni via IFTTT

Show HN: Simstack, SSH escape room for developers https://ift.tt/aSwolNU

Show HN: Simstack, SSH escape room for developers I built a realistic prod system under heavy pressure where you SSH in and solve real problems. You get your own server (real box) and have to fix various things up under fire. a friend told me it reminded them of DOOM for SREs, another called it a "flight simulator" because you can do anything (and reboot if you crash). someone else said it was like "an escape room for engineers", in that you have to find your own way around an unfamiliar box and solve puzzles. idk, maybe it's fun. try it! how it works: you get two Hetzner servers: a traffic generator (real traffic from NYC taxi data highly compressed to 12k rps) firing tons of requests at a user server, which has some (realistically) broken stuff trying to get that data to a chart. your job is to get it working and get the whole system latency down. You can use whatever tools or techniques you like to do so. so far I've seen people messing around in database...

Trump’s Base in Uproar Over His Openness to Joining Iran Fight

Image
By Jess Bidgood from NYT U.S. https://ift.tt/IPF1v7W via IFTTT

Show HN: Interactive Literature Reviews with Visual Knowledge Maps https://ift.tt/REdjDci

Show HN: Interactive Literature Reviews with Visual Knowledge Maps I built a tool for academics and practitioners that turns literature reviews into interactive, visual experiences. Upload PDFs and HTML sources, and AI creates a knowledge map showing how everything connects. What it does: - Upload research papers (PDFs) and web sources (HTML) - AI generates interactive knowledge maps from your sources - Skim read at a high level or read per-source/section summaries - Expand/build further specific sections of the map that interest you - Read original sources in context - Ask questions about the research and get contextual answers I have curated some reviews on LLMs, Diffusion Models, Vision Language Models, AI Agents, Robotics, and Text-to-Speech. Why I built this: I was constructing lit reviews with ChatGPT and getting lost in the walls of chat; I wanted to make a better experience for myself. Please give me feedback on the UX/anything else! https://ift.tt/t2XhpZJ June 18, 2025 at 11:2...