AI and All Data Weekly for 16 December 2024

AI+Data Weekly ( AI, Data, Iceberg, Polaris, Streamlit, Flink, Kafka, Python, Java, NiFi )

#168 - 16-December-2024

https://bsky.app/profile/paasdev.bsky.social

Big Announcement

I have joined Snowflake and will be working with the open source stack of Apache Polaris, Apache Iceberg, Apache NiFi and Streamlit. I will also be working with the amazing AI Data Cloud.

The Coolness this week

❄️ Apache Polaris + Iceberg Quickstart
⚡️ How to extract tables from pdfs
🚀 Microsoft 1bit LLM BitNet
🌐 TableFlow - iceberg / kafka
❄️ Snowflake Cortex AI + Slack
🚀 Ultralytics Heatmaps
🚀 Spring AI MCP
🚀 Maya Multimodal
🚀 Checkmate
🚀 Taming LLMS
🚀 Legend Studio
🚀 Build a Generative AI Synthetic Pipeline
🚀 Money Printer
❄️ Snowflake JDBC
⚡️ ColPali Notebook with QWEN 2 VL
❄️ Snowflake Streams and Tasks - Best Practices
⚡️ Place 3D
⚡️ Google AI Studio Live
⚡️ Google AI Studio Gemini 2.0 Prompts Chat
⚡️ Himalaya CLI
🚀 Step by Step Building REST API to HuggingFace mODELS
🚀 Surfer Org Protocol

New Models

❄️ Snowflake Arctic Instruct
💻 Ollama 3.3
🚀 Microsoft PHI-4 (Small)
🚀 Google Gemini 2
🚀 AI Safeguard Ivy VL Llava

Upcoming

💻 Dec 19: Conf42 IoT 2024: Virtual: https://www.conf42.com/Internet_of_Things_IoT_2024_Tim_Spann_opensource_build

Recent Tim Stuff

🐍 Unstructured Data and LLM: What, Why and How with Timothy Spann
💻 Conf42 IoT Building IoT
💻 XTremePython 2024 - LLM
💻 PyData NYC
💻 Advanced RAG Techniques @ All Things Open Raleigh 2024
💻 Building Real Time LLM Models
💻 Big Data Conference EU Talk on Open Source Real-Time AI
💻 CloudX AI Real-Time
💻 BuildStuff - Adding Generative AI
🐈‍⬛ Conf42 Prompt Engineering
🥑 06 Nov 2024 AI Alliance Talk in Manhattan
💻 08 Nov 2024 PyData NYC slides

Apps, Demos, Examples, Models, Notebooks and Projects

🐍 RAG 101
🐦 Milvus Knowledgebase
👻 AIM Ghosts
🚕 Unstructured Data - Ghosts - Part 1
🤖 Multimodal RAG is not Scary Ghosts
✍🏼 Advanced RAG Techniques

Technologies

Python Java Snowflake Streamlit AWS Google Cloud Azure

CODE + COMMUNITY

© 2020-2024 Tim Spann https://www.youtube.com/@FLaNK-Stack (AI + Vectors + LLM + Streaming + IoT)