Bridging a Gap Between LLMs and Programming with TypeChat

At this time, large language models (LLMs) like OpenAI's ChatGPT are out of date. Although not perfect, they can help with all sorts of tasks such as creating effective Excel spreadsheets, writing cover letters, requesting music references, and creating working computer programs in a variety of languages. One thing these LLMs don't yet do is integrate well with existing application interfaces. However, that's where the TypeChat library comes in, bridging the gap between LLMs and programming.

TypeChat is an MIT-licensed experimental library from Microsoft that sits between a user and an LLM and formats AI responses that are type-safe so they can be easily rewired to the original interface. It does this by generating JSON responses based on user input, which makes it easy to take user input directly, run it through the LLM, and then use the output directly in another piece of code. It can be used for things like prototyping prompts, answer validation, and error handling. It is also not limited to a single LLM and can be modified quite easily to work with many existing models.

The software is still in its infancy, but hopes to make it a little easier to work between user inputs in existing software and LLMs that are quickly becoming fashionable in the IT world. We expect to see many more tools like this become available as more people start using these new tools, which have many applications beyond just writing code.