This is a working example of Frank Denneman's article RAG Architecture Deep Dive which defines the Load-Transform-Embed-Store workflow. For building RAG applications.
There are three examples. The open source example uses Ollama, llama2, and PostgeSQL with pgvector. The SaSS example uses OpenAI GPT3.5 and Pinecone. The RAG with Web Searcg demonstrates performing RAG with data from a search engine.
-
RAG Step-by-Step covers the SaSS example.
-
RAG Step-by-Step with Open Source covers the open source example.
Some examples use Ollama to serve open-source LLMs. You can use a standalone installation or Localstack AI, a containerized AI environment.