Collection of docker yaml configurations and Python programs to build RAG (Retrieval Augmented Generation) applications using LLMs (Large Language Models) and vector databases.
Contains docker files to create a RAG with OpenWebUI
A Python program to experiment with different chunking strategies for document ingestion into Qdrant vector database for RAG applications.4
Don't use Python v 3.14, fastembed works with 3.13 or lower.