Most of the code we use to interact with LLMs (large language models) is hidden behind various APIs, and that's a good thing.
But if you're like me and want to understand the In and Departures There is still hope for you from these magical models. Currently, apart from researchers working on the development and training of new LLMs, there are mainly two types of people playing with these types of models:
- Users who interact through applications such as ChatGPT either Gemini.
- Data scientists and developers working with different libraries, such as chainlang, llama-index or even using Gemini either OpenAI APIs that simplify the process of building on these models.
The problem is, and you may have sensed this, that there is a fundamental knowledge in text mining and natural language processing that is completely hidden in consumer products or APIs. And don't get me wrong: they are great for developing interesting use cases around these technologies. But, if you want to have a deeper understanding to build complex use cases or manipulate LLMs a bit better, you will have to check the fundamentals, particularly when the models behave like you…
