Llms
-
Retrieval-Augmented Generation (RAG) is a powerful technique that enhances language models by incorporating external information…
7 min read -
From Theory to practice: understanding RAG, agents, fine-tuning, and more
16 min read -
No Baseline? No Benchmarks? No Biggie! An Experimental Approach to Agile Chatbot Development
InnovationLessons learned bringing LLM-based products to production
15 min read -
A toy example of bulk inference on commodity hardware using Python.
6 min read