Introduction

Retrieval Augmented Generation (RAG) has been a cornerstone in enhancing large language models (LLMs) for complex, knowledge-driven tasks. By pulling in relevant data from a vector database, RAG has empowered LLMs with factual grounding, significantly reducing instances of fabricated information. But is this the end of the road for RAG?

A new AI named Devin claiming the title of the world’s first AI software engineer. From coding entire projects to fixing GitHub issues, Devin seems to be the new topic. And with such sensational capabilities, the rumor mill is working overtime, sparking fears that the era of human software engineers might be coming to an end. But before you join the panic parade, let’s take a look and see why, despite these advancements, we’re not heading for the job market exit anytime soon.

After parsing the document, we can obtain structured or semi-structured data. The main task now is to break them down into smaller chunks to extract detailed features, and then embed these features to represent their semantics. Its position in RAG is shown in Figure 1.

In this tutorial we will create a personal local LLM assistant, that you can talk to. You will be able to record your voice using your microphone and send to the LLM. The LLM will return the answer with text AND speech.