From the course: LLM Foundations: Vector Databases for Caching and Retrieval Augmented Generation (RAG)

Course coverage and prerequisites

From the course: LLM Foundations: Vector Databases for Caching and Retrieval Augmented Generation (RAG)

Start my 1-month free trial Buy for my team

Course coverage and prerequisites

“

Before we begin this course, let's quickly review the topics covered in the course and prerequisite skills required for learners. What is the scope of this course? Vector databases are based on the concept of vectors. We will quickly review the concepts around vectors and vector search. If you are not familiar with these concepts, I would recommend additional learning as needed. As an example vector database, we will study Milvus in this course. We will discuss concepts around the Milvus database and then set it up using Docker. Then we will proceed to do data manipulation operations like inserts, updates, and deletes with Milvus. We will query and do vector searches on this data. We will use Python notebooks for this exploration. Then we get into use cases for vector databases. First, we will use Milvus as a cache for LLM prompts and responses. Then we will use Milvus as part of a retrieval-augmented generation or RAG system. What are the prerequisite skills for this course for the learners? The learner should be familiar with natural language processing concepts for machine learning. It's recommended to have prior experience in this area, especially around deep learning and transformers. Exposure to using large language models or LLMs by providing prompts and consuming responses is desired. Also, familiarity with text embeddings is helpful. The code for this course is in Python, so familiarity with Python and Jupyter Notebooks is required. Also, we will use Docker to set up Milvus locally, so that is also a prerequisite. We will use LangChain as part of some of the examples. Familiarity with LangChain's capabilities is also desired. Let's now get into the course and start learning about vector databases.

Contents