by Joche Ojeda | Feb 24, 2025 | Linux, Postgres, SyncFrameworkV2, Ubuntu, WSL
After a problematic Windows update on my Surface computer that prevented me from compiling .NET applications, I spent days trying various fixes without success. Eventually, I had to format my computer and start fresh. This meant setting up everything again – Visual Studio, testing databases, and all the other development tools.To make future setups easier, I created a collection of WSL 2 scripts that automate the installation of tools I frequently use, like PostgreSQL and MySQL for testing purposes. While these scripts contain some practices that wouldn’t be recommended for production (like hardcoded passwords), they’re specifically designed for testing environments. The passwords used are already present in the sync framework source code, so there’s no additional security risk.I decided to share these scripts not as a perfect solution, but as a starting point for others who might need to set up similar testing environments. You can use them as inspiration for your own scripts or modify the default passwords to match your needs.
Note that these are specifically for testing purposes – particularly for working with the sync framework – and the hardcoded credentials should never be used in a production environment.
https://github.com/egarim/MyWslScripts
LDAP Scripts
MyWslScripts/ldap-setup.sh at master · egarim/MyWslScripts
MyWslScripts/add-ldap-user.sh at master · egarim/MyWslScripts
MySQL
MyWslScripts/install_mysql.sh at master · egarim/MyWslScripts
Postgres
MyWslScripts/install_postgres.sh at master · egarim/MyWslScripts
Redis
MyWslScripts/redis-install.sh at master · egarim/MyWslScripts
Let me know if you’d like me to share the actual scripts in a follow-up post!
by Joche Ojeda | Feb 23, 2025 | A.I
I’ve been thinking about this topic for a while and have collected numerous notes and ideas about how to present abstractions that allow large language models (LLMs) to interact with various systems – whether that’s your database, operating system, word documents, or other applications.
Before diving deeper, let’s review some fundamental concepts:
Key Concepts
First, let’s talk about APIs (Application Programming Interface). In simple terms, an API is a way to expose methods, functions, and procedures from your application, independent of the programming language being used.
Next is the REST API concept, which is a method of exposing your API using HTTP verbs. As IT professionals, we hear these terms – HTTP, REST, API – almost daily, but we might not fully grasp their core concepts. Let me explain how they relate to software automation using AI.
HTTP (Hypertext Transfer Protocol) is fundamentally a way for two applications to communicate using text. This is its beauty – text serves as the basic layer of understanding between systems, meaning almost any system or programming language can produce a client or server that can interact via HTTP.
REST (Representational State Transfer) is a methodology for systems to communicate and either change or read the state of another system.
Levels of System Interaction
When implementing LLMs for system automation, we first need to determine our desired level of interaction. Here are several approaches:
- Human-like Interaction: An LLM can interact with your operating system using mouse and keyboard inputs, effectively mimicking human behavior.
- REST API Integration: Your application can communicate using HTTP verbs and the REST protocol.
- SDK Implementation: You can create a software development kit that describes your application’s functionality and expose this to the LLM.
The connection method will vary depending on your chosen technology. For instance:
- Microsoft Semantic Kernel allows you to create plugins that interact with your system through REST API, database, or SDK.
- Microsoft AI extensions require you to decide on your preferred interaction level before implementation.
- The Model Context Protocol is a newer approach that enables application exposure for LLM agents, with Claude from Anthropic being a notable example.
Implementation Considerations
When automating your system, you need to consider:
- Available Integration Options: Not all systems provide an SDK or API, which can limit automation possibilities.
- Interaction Protocol Choice: You’ll need to decide between REST API, HTTP, or Model Context Protocol.
This overview should help you understand the various levels of resolution needed to automate your application. What’s your preferred method for integrating LLMs with your applications? I’d love to hear your thoughts and experiences.
by Joche Ojeda | Jun 10, 2024 | Blockchain, C#, Smart contracts, Stratis
Introduction
Blockchain technology has revolutionized various industries by providing a decentralized and secure way to manage data and transactions. At the heart of this innovation are smart contracts—self-executing contracts with the terms directly written into code. My journey into blockchain development began with the excitement of these possibilities, but it also came with challenges, particularly with the Solidity programming language. However, everything changed when I discovered the Stratis platform, which supports smart contracts using C#, making development much more accessible for me. In this article, I’ll share my experiences, challenges, and the eventual breakthrough that came with Stratis.
Challenges with Solidity
Solidity is the most popular language for writing smart contracts on Ethereum, but it has a steep learning curve. My background in programming didn’t include a lot of JavaScript-like languages, so adapting to Solidity’s syntax and concepts was daunting. The process of writing, testing, and deploying smart contracts often felt cumbersome. Debugging was a particular pain point, with cryptic error messages and a lack of mature tooling compared to more established programming environments.
The complexity and frustration of dealing with these issues made me seek an alternative that could leverage my existing programming skills. I wanted a platform that was easier to work with and more aligned with languages I was already comfortable with. This search led me to discover Stratis.
Introduction to Stratis
Stratis is a blockchain development platform designed to meet the needs of enterprises and developers by offering a simpler and more efficient way to build blockchain solutions. What caught my attention was its support for C#—a language I was already proficient in. Stratis allows developers to create smart contracts using C#, integrating seamlessly with the .NET ecosystem.
This discovery was a game-changer for me. The prospect of using a familiar language in a robust development environment like Visual Studio, combined with the powerful features of Stratis, promised a much smoother and more productive development experience.
Why Stratis Stood Out
The primary benefit of using C# over Solidity is the familiarity and maturity of the development tools. With C#, I could leverage the rich ecosystem of libraries, tools, and frameworks available in the .NET environment. This not only sped up the development process but also reduced the time spent on debugging and testing.
Stratis offers a comprehensive suite of tools designed to simplify blockchain development. The Stratis Full Node, for instance, provides a fully functional blockchain node that can be easily integrated into existing applications. Additionally, Stratis offers a smart contract template for Visual Studio, making it straightforward to start building and deploying smart contracts.
Another significant advantage is the support and community around Stratis. The documentation is thorough, and the community is active, providing a wealth of resources and assistance for developers at all levels.
Conclusion
Transitioning from Solidity to Stratis was a pivotal moment in my blockchain development journey. The challenges I faced with Solidity were mitigated by the ease and familiarity of C#. Stratis provided a robust and efficient platform that significantly improved my development workflow.
In the next article, I will dive into the practical steps of setting up the Stratis development environment. We’ll cover everything you need to get started, from installing the necessary tools to configuring your first Stratis Full Node. Stay tuned for a detailed guide that will set the foundation for your journey into C# smart contract development.
