Data Umbrella

Discover Polars, the high-performance DataFrame library revolutionizing data analysis in Python. Built on Rust, Polars offers unparalleled speed and efficiency, outperforming pandas, Dask, and even PySpark. Explore its innovative features like lazy evaluation, memory efficiency, and automatic multi-threading, designed to handle large datasets with ease.

In this session, you'll learn practical techniques for data manipulation and advanced transformations. We will demonstrate Polars' syntax and capabilities, making it accessible even if you’re new to Polars. Join us to elevate your Python data analysis to the next level.

This presentation covers:

• Section 1: What is Polars and how does it compare to pandas?
• Section 2: Getting Started with Polars in Python
• Section 3: Advanced Data Analysis with Polars
• Section 4: Should you switch to Polars?

One of the most popular embodiments of Generative AI are information retrieval (IR) augmented generation (RAG). Such systems use an information retrieval engine (based on semantic embeddings or keyword search) and then use a Large Language Model (LLM) to extract answers to a given query.

These systems require a large amount of computation and are usually implemented in the cloud which presents data privacy issues.

In this talk we will present The RAGged Edge Box project in which basic embedding systems and small local LLMs are packaged inside a multi-platform virtual machine (VirtualBox). The system provides a Web interface that runs locally and allows access to the RAG functionality in a completely private manner. The neural networks run on a ONNX runtime and do not require a GPU. RAG code is implemented in PHP and is easy to modify, requiring a much smaller execution environment than a Python alternative.

https://textualization.com/ragged/

Outline

• RAGged Edge Box demo
• AI Concepts (RAG, LLMs, Embeddings)
• RAG Concepts (IR, chunk, prompt)
• RAGged Edge Box (concept, advantages)
• RAGged Edge Box Architecture
• Enabling Technology Bits (ONNX, PHP Semantic Search)
• Extension Points
• VM Packaging
• RAGged Edge Box as a Platform