A Crash Course on Building RAG Systems – Part 9 (With Implementation)
A deep dive into ColPali for building vision-driven RAG systems (with implementation).
A collection of 90 posts
A deep dive into ColPali for building vision-driven RAG systems (with implementation).
A deep dive into ColBERT and ColBERTv2 for improving RAG systems (with implementation).
...using Llama-3.2 Vision and Chainlit.
A deep dive into Graph RAG and how it improves traditional RAG systems (with implementation).
...explained visually
...using Cohere’s Command R7B and CrewAI.
Predictable ↔ Random.
From 350 GB to 25 MB.
...for fine-tuning other LLMs.
A deep dive into building multimodal RAG systems on real-world data (with implementation).
Meta's latest LLM (100% Local).
...and building one with Dynamiq.
...using Llama-3.2-vision model and Streamlit.
A deep dive into key components of multimodal systems—CLIP embeddings, multimodal prompting, and tool calling.
...using Microsoft's Autogen and Llama3-70B.
...explained visually.
A deep dive into making RAG systems faster (with implementations).
Your own PerplexityAI (100% local).
A step-by-step hands-on guide.
Beginner-friendly and with implementation.
Which one is best for you?
Scale model training with 4 small changes.
Key techniques, explained in simple terms.
A practical and beginner-friendly crash course on building RAG apps (with implementations).
...explained in a single frame.
40 most used methods.
Understanding the tradeoffs between RAG and Fine-tuning, and owning the model vs. using a third-party host.
A powerful LoRA-variant explained in a beginner-friendly way and implemented in PyTorch.
LoRA-variants explained in a beginner-friendly way.
Understanding the challenges of traditional fine-tuning and addressing them with LoRA.