This article originally appeared on LinkedIn on Feb 19th, 2024 by Rick Hightower
Rick Hightower Engineering Consultant focused on AI
February 19, 2023
JParse, is the most efficient JSON parser for the JVM yet.
JParse is the most efficient JSON parser for the JVM yet - it uses an index overlay to deliver lightning-fast parsing speeds.
This article originally appeared on LinkedIn.
Title: Using ChatGPT Chat Function Calls from Java
Original Publication Date: July 9, 2023
As artificial intelligence and chatbots become more popular, it is increasingly important to integrate functions into chat conversations. Functions are small pieces of code that can be reused and embedded into larger programs to perform a specific task. In this blog post, we will discuss how to implement and integrate functions into ChatGPT conversations using JAI, a Java OpenAI API client. This guide will cover how to define a function, handle function callbacks, and mix function results with the content and context returned from the function. We will also provide an example of a weather-related function and its integration into a larger program using a function map.
This article originally appeared on LinkedIn on July 11th, 2023.
Rick Hightower Engineering Consultant focused on AI
July 11, 2023
In today’s fast-paced business world, it is essential to stay ahead of the competition. An efficient search engine that can provide accurate information to your customers or employees can make a big difference. However, building and maintaining a robust search engine can be a challenge. In this dev notebook, we will explore how ChatGPT, Embeddings, and HyDE can help you improve your search results.
The world of artificial intelligence (AI) is constantly evolving, and the latest development is the release of Llama 2 by tech giant Meta. This open-source large language model has been trained on a massive 2 trillion tokens, making it a top contender to dominate the industry. In this blog post, we will delve into the implications of Llama 2’s release, its partnership with Microsoft, and the development of other generative AI technologies by Meta.
Author: Rick Hightower
We will look at a real-world use case that most developers and tech managers should understand. We will give ChatGPT a Java method and ask it to create a Mermaid sequence diagram.
Chain of Thought (CoT) prompting is a technique that improves the performance of Large Language Models (LLMs) on reasoning tasks. It uses few-shot learning. According to Toward Data Science, CoT helps LLMs handle complex tasks like common sense reasoning and arithmetic. It does this by breaking down multi-step requests into smaller steps. This creates a way to see and understand the process. It makes both the input and output easier to manage and tweak.
Large Language Models (LLMs) have become increasingly popular in recent years due to their ability to understand and generate human-like text across various domains (V7 Labs) (Scale AI). These models, such as OpenAI’s GPT-4 and Google’s PaLM 2, are trained on massive amounts of text data, allowing them to excel at tasks like text generation, summarization, translation, and sentiment analysis (Scale AI) (Moveworks). However, despite their impressive capabilities, LLMs must improve their reasoning and problem-solving tasks (Moveworks) to solve complex problems.
mindmap
root((Advanced SQL Techniques for ETL))
CASE Statements
Conditional Logic
Data Standardization
Conditional Aggregation
FILTER Alternative
GROUP BY Operations
Data Aggregation
Monthly Metrics
Handling Nulls
COALESCE Function
Window Functions
Partitioning
RANK
Rolling Aggregates
Duplicate Detection
SQL Functions
LEAD & LAG
ROW_NUMBER
DENSE_RANK
Cumulative Metrics
Table Partitioning
Performance Optimization
Date-Based Partitioning
Query Efficiency
Scalability
Advanced SQL Techniques for ETL
Ever wrestled with massive datasets using procedural scripts? You know that feeling—like moving a mountain with a teaspoon. Transform that struggle into power with advanced SQL techniques that turn hours into minutes.
This article originally appeared on August 7, 2023 on LinkedIn.
An IBM study shows product managers are early adopters of generative AI. They rank in the top-ten professions that use AI. The report states that 21% of product managers use AI daily. Product Managers are leading the AI charge.
As AI’s role in product management increases, product managers must learn how to use AI to stay competitive. Product managers using AI differ from their traditional counterparts by applying their technical expertise to harness AI’s potential in enhancing product management processes.
Author: Rick HightowerThis article was originally published on LinkedIn on July 30, 2023.
The Azure OpenAI Service has taken a major leap forward with the introduction of GPT-4, OpenAI’s most advanced language model to date. As of April 3, 2023, GPT-4 is available in preview, allowing customers and partners to experience the power of this cutting-edge AI model. Read more on Azure Blog
This article was originally published on November 7, 2023 on LinkedIn.
OpenAI’s Latest Developments: Reasons Why You Should Add These Points to Your Tech Radar
The technology landscape is rapidly evolving, with artificial intelligence (AI) at the forefront, and OpenAI is consistently at the helm of breakthroughs and innovations. With ChatGPT-4 Turbo, a soon-to-be-released GPT Builder, Assistant API with playground support, and a new text-to-speech model, OpenAI is revolutionizing the interaction between AI and users. Furthermore, OpenAI’s competitive stance is bolstered by reducing costs for companies and developers, adapting quickly to maintain its market lead, and responding to the developer community’s feedback. The anticipation of Grok, a potential competitor announced by Elon Musk, adds to the dynamism of the AI field. Here are the compelling reasons why OpenAI’s latest developments should be firmly on your tech radar.
On a sunny afternoon, Rick and Chris were walking and chatting about Streamlit, a popular Python library for creating web applications. Their conversation flowed naturally, covering various aspects of this intriguing tool.
(This article originally appeared on 10/25/2024 on LinkedIN.)
Rick:“Hey Chris, I’ve been hearing a lot of buzz about Streamlit lately. So, what’s the scoop on it, especially when it comes to UI stuff? I’m toying with the idea of whipping up a CRUD app PoC with a slick interface. You think Streamlit’s the way to go for that kind of thing?”"Chris:“Oh, Streamlit is fantastic for that kind of project, Rick! It’s become quite popular for data apps and prototypes. The beauty of it is how it turns Python scripts into interactive web apps with minimal effort.”Rick:“That sounds promising. I am looking for a quick and dirty solution as a proof of concept. Hmmmm.. I wonder…. What kind of UI elements does it offer?”Chris:“Quite a range, actually. You’ve got your basic text elements like titles and headers, data display options for tables and metrics, and a variety of input widgets - buttons, sliders, text inputs, you name it. It even integrates well with data visualization libraries like Matplotlib and Plotly.”Rick:“Interesting. Are there any alternatives I should consider?”Chris:“Well, there’s Dash, which is also Python-based but more focused on analytical web applications. Or you could go the traditional route with Flask or Django paired with a frontend library, but that’s more complex.”Rick:“Got it. What about other languages? Any similar frameworks that simplify web development?”Chris:“Absolutely! If you’re into R, there’s Shiny. For Java developers, Vaadin is a great option. And if you’re looking to build desktop apps, Tauri and Electron are worth checking out.”Rick:“Thanks, that’s helpful. I think I will stick with Python for now. Can you walk me through the basics of how Streamlit works?”Chris:“Sure thing! Streamlit apps are basically Python scripts. You start by importing Streamlit, then use its functions to add widgets and layout elements. It’s reactive, so whenever an input changes, the script reruns from top to bottom, updating the app dynamically.”Rick:“That sounds straightforward. What about working with databases?”Chris:“While Streamlit doesn’t directly connect to databases, you can easily use Python’s database libraries. You’d typically use something like SQLAlchemy to connect to your database, run queries, and then display the results using Streamlit’s functions.”Rick:“And deploying a Streamlit app? How does that work?”Chris:“You’ve got several options there. Streamlit Cloud is the simplest - it connects directly to your GitHub repo. But you can also use services like Heroku, AWS Elastic Beanstalk, or even Docker if you prefer containerization.”Rick:“This has been really informative, Chris. Thanks a lot!”Chris:“Happy to help, Rick! If you have any more questions as you dive into Streamlit, don’t hesitate to ask. Happy coding!”
In the dynamic world of AI development, PrivateGPT has emerged as a groundbreaking tool, offering a robust, private AI solution. Recently, I’ve integrated PrivateGPT into a project, enhancing it with custom jobs using LlamaIndex—a shortcut for implementing Retrieval Augmented Generation (RAG) support. PrivateGPT is remarkably easy to modify and extend. LlamaIndex serves as a shortcut for using LangChain to build RAG support, while PrivateGPT has been our go-to for building a backend tool for our GenAI needs. It allows us to effortlessly switch between vector stores and LLMs. This experience has been nothing short of transformative, highlighting the versatility and adaptability of PrivateGPT and LlamaIndex in real-world applications.
When integrating AI models with external tools, the details matter most. While OpenAI uses function calling and LiteLLM provides a universal interface, Anthropic’s Claude takes a distinctly different approach with its content-based message structure. This article explores how to integrate Claude with the Model Context Protocol (MCP). We reveal the unique patterns that make Anthropic’s implementation powerful and elegant.
Every journey into transformer models begins with a critical step: converting human language into a format machines can understand. Tokenization serves as this essential bridge, transforming raw text into structured numerical sequences that power today’s most advanced AI language models.
In this article, we will demystify tokenization, revealing its central role in NLP pipelines and showing why it matters for real-world applications. Whether you are building chatbots, analyzing documents, or training custom models, mastering tokenization unlocks the full potential of transformer architecture.
This article picks up where our last one left off, continuing our exploration of DuckDB by diving into the essential concepts you need to start working effectively with this powerful analytical database.
Think of DuckDB as your personal data chef, ready to transform raw data into delicious insights. Before any culinary magic happens, you need to establish your connection and learn to communicate your instructions clearly. In this article, we’ll explore how to connect to DuckDB, execute SQL queries, and define your data structures—fundamental skills for everything you’ll want to do with DuckDB.
You’ve built your first RAG system. Your embeddings are clean, your vector database is working well, and you’ve integrated a state-of-the-art LLM. Yet as your knowledge base grows past a few hundred documents, search quality degrades. Retrievals that once took milliseconds now crawl. Your LLM starts generating vague or inaccurate responses despite your careful engineering.
Imagine you’re a chef. Traditionally, analyzing your recipes’ ingredient costs meant sending them off to a separate accounting department - slow and cumbersome. DuckDB is like having a mini-accounting department right in your kitchen, instantly analyzing recipes as you create them. This embedded analytical database is changing how we work with data in Python by bringing analytical power directly into your applications.
Have you ever stared at your database schema and thought, “If I have to add one more column to this table, I’m going to lose it”? As you gaze into the abyss, wondering why you didn’t become a dentist, consider this: PostgreSQL can serve as both a document database and a relational database. We’ve all been there—trapped in migration hell, where each new business requirement sends us back to the drawing board. Maybe the requirements are a bit loose, and you’d rather not spend countless hours on schema migrations.
When DSPy’s programmatic optimization framework meets the Model Context Protocol (MCP), security becomes both more critical and more nuanced. While DSPy excels at transforming brittle prompts into reliable software components, connecting these self-optimizing agents to production MCP servers demands sophisticated security measures. This article demonstrates how to implement OAuth 2.1, JWT validation, and TLS encryption specifically for DSPy’s programmatic architecture.
When LangChain’s powerful agent framework meets the Model Context Protocol (MCP), security becomes both more critical and more complex. While LangChain excels at orchestrating multi-step AI workflows, connecting these agents to production MCP servers demands sophisticated security measures. This article demonstrates how to implement OAuth 2.1, JWT validation, and TLS encryption specifically for LangChain’s agent-based architecture.
Copyright © 2015 - 2025, Cloudurable™, all rights reserved.
Streamline your Cassandra Database, Apache Spark and Kafka DevOps in AWS.
SMACK/Lambda architecture consutling! Spark, Mesos, Akka, Cassandra and Kafka in AWS.
Apache Spark Training,
Kubernetes Security Training,
Akka Consulting,
AWS Cassandra Support,
Cassandra Training,
Kafka Training,
Cassandra Consulting,
Kafka Consulting,
Spark Training,
Spark Consulting,
Kafka Tutorial
Template by DevCows