AI+Data Weekly ( AI, Data, Iceberg, Polaris, Streamlit, Flink, Kafka, Python, Java, NiFi )
#167 - 09-December-2024
https://bsky.app/profile/paasdev.bsky.social
Big Announcement Coming
Happy Krampusnacht to all those who celebrate.
AWS Updates
🧊 S3 Tables for Iceberg
☃️ AWS re:Invent 2024 Announcements
🧊 AWS Trainium Chips
The Coolness this week
❄️ Apache Polaris + Iceberg Quickstart
⚡️ How to extract tables from pdfs
🚀 Microsoft 1bit LLM BitNet
🐿️ Verifying Kafka Transactions Entry 2
🐿️ FLUSS: Streaming Storage
🐿️ Fluss -> Flow for Flink Real Time Analytics
🌐 TableFlow - iceberg / kafka
❄️ Snowflake Cortex AI + Slack
🐿️❄️ Door dash flink, kafka, snowflake
🧠 Prompt Stack -- all in one
🔌 SpaCY Layout for PDF
📱 Responsible AI Pathways
📼 Megaparse documents python
🔌 Time Series LLM
❄️ Generate Synthetic Data in Snowflake
🐿️ LLMs and GenAI - When to use them
🐿️ Flink Observability with Prometheus
📡 New SQL GUI
🍫 TDD for GenAI
🕵️
🎁 Open Source Agent Framework for Production
💻 Cedit command line editor
🏭 ServiceNow AgentLab
🎤 Snowflake Lessons Learned in Replication
🎄 Privastead
🔌 Backup Icloud with nodejs on linux
🔌 Backup Google with nodejs on linux
🎄 HuggingFace macos chat source code
🎁 Ollama working with structured output
🎁 dspy ai how to
🔌 Piazza updater
🔌 Building a financial report with langgraph
ColPali Notebook with QWEN 2 VL
New Models
📼 Open Source Video Foundation Model by Hunyuan
🌐 marco-o1
☁️ Amazon Foundation Models - Nova
❄️ Snowflake Arctic Instruct
🏫 Large Scale World Model Google
💻 PaliGemma Google SmOl Vision
💻 Ollama 3.3
Upcoming
💻 Dec 19: Conf42 IoT 2024: Virtual: https://www.conf42.com/Internet_of_Things_IoT_2024_Tim_Spann_opensource_build
Recent Tim Stuff
💻 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
CODE + COMMUNITY
© 2020-2024 Tim Spann https://www.youtube.com/@FLaNK-Stack
(AI + Vectors + LLM + Streaming + IoT)
Top comments (1)
Great weekly roundup! For those interested in vector search capabilities, it's worth noting that Astra DB with its vector capabilities is another solid option, especially when integrated with streaming data pipelines. Looking forward to more updates on this space!