Daniel Warfield

Senior Engineer
Daniel is a data scientist who leads engineer engagement for EyeLevel. He also writes extensively about AI at Towards Data Science.
Research

Do Vector Databases Lose Accuracy at Scale?

Research shows vector databases lose accuracy at just 10,000 pages, but there's a way out.

Read Article
Tutorials

The AI Engineer's Guide to Document Parsing in RAG Applications

Understanding and optimizing your parsing strategy is one of the keys to building high-performance RAG applications. There are several popular parsing strategies and tools out there, each with their own strengths and limitations.

Read Article
Tutorials

Multimodal RAG Explained: Integrating Text, Images, Audio, and More in AI

Multimodal Retrieval-Augmented Generation (RAG) has emerged as a unique approach to increase efficiency and reliability of AI systems. This concept extends traditional text-based RAG systems to incorporate various data types such as images, audio, and video, creating richer and more contextually accurate information retrieval and generation.

Read Article
Tutorials

Understanding CRAG: Meta's Comprehensive Benchmark for Retrieval Augmented Generation

CRAG, or the Comprehensive RAG Benchmark, is Meta’s newest benchmark to evaluate AI performance. We break the latest benchmark down and evaluate its importance for AI engineers.

Read Article
Research

World's Most Accurate RAG? Langchain/Pinecone, LlamaIndex and EyeLevel Duke it Out

Winner achieved 98% accuracy across 1,000+ pages of complex documents

Read Article