Overview
This course teaches how to implement Retrieval Augmented Generation (RAG) using a Pinecone vector database, a Llama 2 13B chat model, and Hugging Face and LangChain code. The learning outcomes include keeping Large Language Models (LLMs) up to date, reducing hallucinations, and citing original information sources. The course covers Python prerequisites, creating embeddings, building a vector database, initializing Llama 2, and comparing Llama 2 with RAG Llama 2. The teaching method involves practical hands-on sessions and code implementation. This course is intended for individuals interested in artificial intelligence, natural language processing, and open-source technologies.
Syllabus
Retrieval Augmented Generation with Llama 2
Python Prerequisites and Llama 2 Access
Retrieval Augmented Generation 101
Creating Embeddings with Open Source
Building Pinecone Vector DB
Creating Embedding Dataset
Initializing Llama 2
Creating the RAG RetrievalQA Component
Comparing Llama 2 vs RAG Llama 2
Taught by
James Briggs
Reviews
4.0 rating, based on 1 Class Central review
Showing Class Central Sort
-
good for Developers. but helped semi techies too.
could clearly see diff after RAG addition.
lot of business use cases possible.
could clearly see diff after RAG addition.