Laboratory work

I've been working on creating a tool called rustsn that allows you to generate, compile, and test code using codeSpark. Initially, the idea was to automate the process of writing small pieces of code — the so—called snippets - for different programming languages based on explanations provided by the user. This tool began to evolve and acquire new features, such as generating complete code for applications and explaining existing code based on vector representations (embeddings). When I first started working on rustsn, the main task was to ensure that the user could, for example, simply describe in words what function he needed to write, and the system would automatically generate working code. I started with Rust, because this language has powerful features for working with types and testing, which makes it ideal for writing secure and productive code. Later, I added support for other languages such as JavaScript, Python, and TypeScript. This tool has become much more than just a code generator. For example, I added the ask command, which allows you to get an explanation to the existing code of your project. For this purpose, a special model is used that analyzes the source code and finds the most relevant files based on your question. In the near future, I plan to significantly expand the functionality of codeSpark.