Langchain4J musings
For example, I never bought into blockchain, the solution still searching for problems to solve, nor in microservices, the latest in the cargo cult IT trends. Despite my late arrival at the LLM party, I have been a regular user of LLMs. I use OpenAI for non-controversial questions outside my cone of knowledge, e.g., linguistics or legal; I use GitHub Copilot in my IDE to improve my code.
A plethora of LLMs is available at the moment. I mentioned OpenAI, but plenty of others beg for your attention: Google Gemini, Cohere, Amazon Bedrock, ad nauseam. Each has pros and cons, which are irrelevant to this introductory post.
My main requirement in the context of this post is that it needs to run locally. Besides, I want an abstraction layer over the LLM to learn the abstractions, not the specifics.
LangChain4j offers an abstraction API over the specifics of different LLMs. Here’s a focus on what we will use in this section:
