Microsoft's LUIS and Natural Language Processing
Explore Azure's LUIS for natural language processing, covering prebuilt domains, custom models, entity types, sentiment analysis, and command-line tools to enhance NLP capabilities.
Building an Advanced Agentic RAG System with Langchain, Ollama, and Milvus
Explore the cutting-edge world of Agentic Retrieval-Augmented Generation (RAG) systems in this 31-minute conference talk from Devoxx. Discover how to construct an advanced Agentic RAG system using open-source technologies like Langchain, Ollama, and Milv…
Easy RAG with LangChain4J and Docker - Implementing Retrieval-Augmented Generation
Explore the RAG (retrieval-augmented generation) pattern in this 31-minute conference talk from Devoxx. Learn the fundamental concepts behind RAG and gain hands-on experience setting up a practical RAG infrastructure using Docker. Discover how to configu…
Developing Cloud-Native Java AI Applications with DJL and LangChain4J
Explore the integration of Java with AI and large language models in this comprehensive conference talk. Learn how to consume, train/retrain, and infer various AI models, including LLMs like OpenAI, Llama, Gemma, and Mistral. Discover practical applicati…
From Naive to Advanced RAG: The Complete Guide - Lecture 1
Embark on a comprehensive deep-dive into Retrieval Augmented Generation (RAG) techniques, from basic implementations to advanced strategies. Learn how to overcome common challenges such as inaccurate or incomplete answers, outdated information, and ineff…
Automatic Image Captioning with Vision Transformer and GPT-2
Learn how to generate descriptive captions for images using Python and PyTorch in this 16-minute tutorial. Explore the process of automatic image captioning with the pre-trained 'nlpconnect/vit-gpt2-image-captioning' model from Hugging Face. Set up the V…
DuckDB's Search Capabilities for AI and LLM Stacks
Explore DuckDB's underrated search capabilities and its potential within an LLM stack in this 13-minute talk by Mehdi Ouazza, an experienced data engineer and developer relations lead at MotherDuck. Discover how DuckDB's versatile and efficient search me…
Synthetic Data Generation and Fine-tuning for OpenAI GPT-4 or Llama 3
Dive into an extensive tutorial on synthetic data generation and fine-tuning techniques for large language models like OpenAI GPT-4o and Llama 3. Learn how to create synthetic questions and answers, implement chain of thought reasoning, and augment data…
Jlama: A Native Java LLM Inference Engine
Explore JLama, a cutting-edge inference engine designed to empower Java developers with native AI capabilities. Discover how this innovative tool brings the power of large language models directly into the Java ecosystem without the need for GPUs. Learn…
Words as Weapons - The Dark Arts of Prompt Engineering
Explore the dark arts of Prompt Engineering in this eye-opening 43-minute conference talk from Devoxx. Delve into the evolving landscape of AI integration in organizations, focusing on the risks associated with Large Language Models (LLMs) and their appl…
Running Open Large Language Models in Production with Ollama and Serverless GPUs
Explore the deployment of open large language models in production environments using Ollama and serverless GPUs. Learn why companies are increasingly interested in running open models like Gemma and Llama, which offer full control over deployment, model…
Crafting Intelligent Applications with Quarkus and LangChain4j
Explore the evolution and capabilities of Quarkus/LangChain4j integration in this conference talk. Discover how Quarkus provides an ideal runtime for developing intelligent Java applications, leveraging LangChain4j's potential. Learn about seamless CDI i…
AI News Roundup: Latest Developments in Video Generation, Language Models, and Robotics
Explore cutting-edge AI advancements in video generation, language models, and robotics. Gain insights into open-source tools, updates from tech giants, and emerging technologies shaping the future of AI.
AI for Developers: Real Talk on AI Capabilities and Limitations
Explore AI's current capabilities, limitations, and practical applications with insights from an AI solopreneur. Learn about getting started, useful tools, and the role of open source in AI development.
Physics 4B: Electrostatics Multiple Choice Timed Assessment Demos - Lecture 3 and 4
Explore electrostatics through timed multiple-choice assessments, comparing results with and without AI assistance to enhance understanding and problem-solving skills.
Crafting Intelligent GitHub Bots
Develop AI-infused GitHub bots using Quarkus GitHub App Framework and LangChain4j to enhance workflows, automate tasks, and boost productivity in your development process.
Pushing LLMs over the Edge: Exploring the Limits of the Possible
Explore LLM limits through outrageous applications using LangChain4j and Quarkus. Witness complex tasks, potential havoc, and self-evaluating models in this thrilling journey of AI possibilities.
Practical LLM Inference in Modern Java
Implement efficient local LLM inference in Java, leveraging modern features for CPU-based performance without specialized hardware. Explore flexible frameworks adaptable to multiple architectures.
Oh No, Not Another Chatbot - Java and AI for Real Business Use Cases
Explore Java development with AI using LangChain4J and Spring AI. Learn to extract information from images for automatic form-filling using Azure OpenAI and Container Apps in a microservice architecture.
RAG: From Dumb Implementation to Serious Results - Optimizing Retrieval-Augmented Generation
Elevate RAG implementations using LangChain4j. Master advanced chunking, query refinement, metadata filtering, document reranking, data lifecycle management, and evaluation techniques for accurate, relevant results.
Avoid Common LLM Pitfalls - Techniques for Enhancing LLM Outputs
Explore techniques to overcome LLM limitations: response schemas, RAG, function calling, and grounding for improved outputs and real-world applications.