AI/ML

Learn how `sqlite-vec` turns SQLite into a fast, embedded vector search engine. With support for float32, int8, and bit vectors, optimized distance metrics, and native SQL integration, it's ideal for offline AI, semantic search, and lightweight ML apps. This post walks through how it works and why it's surprisingly powerful.

archived 20 May 2025 12:46:56 UTC

Looking for the best open-source embedding model for your RAG app? We share a comparison workflow so you can stop paying the OpenAI tax.

I used AI in my plasma physics research and it didn’t go the way I expected.

Vector databases are kind of everywhere these days. There is a big pool of VC's that are pouring money into the ecosystem too. But while all of that is happening, sqlite has also gotten support for it. In this episode we talk the Alex Garcia, the maintainer of this project, and discuss how the project got created on what the future has in store. 00:00 Introduction 00:40 Dataviz 04:39 Chromebook matters 10:30 Why sqlite rocks 17:32 Facebook and VR stuff 26:19 Datasette & Simon 38:31 Towards sqlite-vec 46:46 Getting attention 52:38 Current work Sqlite-vec Github repo: https://github.com/asg017/sqlite-vec Alex Garcia blog: https://alexgarcia.xyz/blog/2024/sqlite-vec-hybrid-search/index.html Datasette discord: https://discord.com/invite/ktd74dm5mw Sqlite-vec channel on Mozilla Discord: https://discord.gg/Ve7WeCJFXk We have a Discord these days, feel free to discuss the podcast with us there! https://discord.probabl.ai You can follow the podcast on most podcast players including apple podcasts, spotify and rss.com. - https://podcasts.apple.com/us/podcast/sample-space/id1739598572 - https://open.spotify.com/show/0BnwEHuyOlHgeZfselpn1n - https://rss.com/podcasts/sample-space/ This podcast is part of the open efforts over at probabl. To learn more you can check out website or reach out to us on social media. Website: https://probabl.ai/ Bluesky: https://bsky.app/profile/probabl.bsky.social LinkedIn: https://www.linkedin.com/company/probabl Twitter: https://x.com/probabl_ai #probabl

Vector search has become a foundational tool for modern applications — from powering recommendation engines to enabling semantic search in…

OCR with Ollama - Using Local Vision Models to OCR an Image - ocr_ollama.py

Julius is a powerful AI data analyst that helps you analyze and visualize your data. Chat with your data, create graphs, build forecasting models, and more.

Mem0 enables AI apps to continuously learn from past user interactions, enhancing their intelligence and personalization.

c/ua is the Docker Container for Computer-Use AI Agents (CUA).

c/ua is the Docker Container for Computer-Use AI Agents. - trycua/cua

Last week I participated in a panel discussion on AI as part of a private event in New Zealand.

OpenMemory is a passport powered by Mem0 that lets you carry your memory across any AI app. It provides a unified memory layer that stays with you, enabling agents and assistants to remember what matters across applications.

If you liked Brooklyn Bridge Claude, you'll love White Genocide Grok

A lawyer representing Anthropic used Claude to generate citations in a court filing, then it hallucinated.

CocoIndex now supports knowledge graph with incremental processing. Build live knowledge for agents is super easy with CocoIndex!

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

DeerFlow is a community-driven framework for deep research, combining language models with tools like web search, crawling, and Python execution, while contributing back to the open-source communit...

🎬 Ever wondered how AI could turn your life into a documentary? Watch as I create a seemingly professional documentary about myself in minutes using Gemma 3, Ollama, and ElevenLabs - no film crew needed! 🎯 In this video, you'll learn: • How to use Gemma 3's multimodal capabilities with multiple images • Building a simple CLI app with Deno/TypeScript for image processing • Working with n8n workflows for AI integration • Creating convincing AI-generated narratives with Ollama • Complete workflow from capture to final video production ⏱️ Timestamps: 00:00 - Start 00:28 - I'm in a Documentary 01:56 - Gemma3 02:13 - Whats new in Gemma3 with Ollama 02:26 - Tell a story with many images 03:54 - Creating the app with Windsurf 04:49 - It's not in x language 05:19 - Let's look at the code 08:32 - The backend in n8n 🛠️ Tools & Resources Mentioned: • Gemma 3 27b • Ollama (https://ollama.com) • ElevenLabs (https://try.elevenlabs.io/tvlst) • n8n • Deno/TypeScript Want to create your own AI-powered content? Drop a comment below with your ideas or questions! #AIContent #TechTutorial #AIDocumentary My Links 🔗 👉🏻 Subscribe (free): https://www.youtube.com/technovangelist 👉🏻 Join and Support: https://www.youtube.com/channel/UCHaF9kM2wn8C3CLRwLkC2GQ/join 👉🏻 Newsletter: https://technovangelist.substack.com/subscribe 👉🏻 Twitter: https://www.twitter.com/technovangelist 👉🏻 Discord: https://discord.gg/uS4gJMCRH2 👉🏻 Patreon: https://patreon.com/technovangelist 👉🏻 Instagram: https://www.instagram.com/technovangelist/ 👉🏻 Threads: https://www.threads.net/@technovangelist?xmt=AQGzoMzVWwEq8qrkEGV8xEpbZ1FIcTl8Dhx9VpF1bkSBQp4 👉🏻 LinkedIn: https://www.linkedin.com/in/technovangelist/ 👉🏻 All Source Code: https://github.com/technovangelist/videoprojects Want to sponsor this channel? Let me know what your plans are here: https://www.technovangelist.com/sponsor

Once errors creep into the AI knowledge base, they can be very hard to get out.

Contribute to asgeirtj/system_prompts_leaks development by creating an account on GitHub.

A couple days ago, Ásgeir Thor Johnson convinced Claude to give up its system prompt. The prompt is a good reminder that chatbots are more than just their model. They’re tools and instructions that accrue and are honed, through user feedback and design.

Have a natural, spoken conversation with AI! Contribute to KoljaB/RealtimeVoiceChat development by creating an account on GitHub.

Minimal AI agent framework that just works with only seven tools. - aperoc/toolkami

Interesting release from Google, as a follow-up [to Gemma 3](https://simonwillison.net/2025/Mar/12/gemma-3/) from last month: To make Gemma 3 even more accessible, we are announcing new versions optimized with Quantization-Aware Training …

Therapeutics Commons (TDC): Multimodal Foundation for Therapeutic Science - mims-harvard/TDC

Give local LLMs superpowers with Open WebUI Tools. Use & build tools for function calling, API access (email/calendar) & real actions.

Contribute to asgeirtj/system_prompts_leaks development by creating an account on GitHub.

The simplest, fastest repository for training/finetuning small-sized VLMs. - huggingface/nanoVLM