A look at a few of the best retrieval models for Retrieval Augmented Generation (RAG) and how we use them. Covering OpenAI's text-embedding-ada-002, Cohere's new Embed v3, and a small but strong performing open source model called e5-base-v2.
📌 Code:
https://github.com/pinecone-io/examples/tree/master/learn/search/semantic-search/2311-embedding-examples
🌲 Subscribe for Latest Articles and Videos:
https://www.pinecone.io/newsletter-signup/
👋🏼 AI Dev:
https://aurelio.ai
👾 Discord:
https://discord.gg/c5QtDB9RAP
Twitter: https://twitter.com/jamescalam
LinkedIn: https://www.linkedin.com/in/jamescalam/
#artificialintelligence #nlp #openai #ai
00:45 MTEB Leaderboards
01:46 Starting with OpenAI, Cohere, and e5
04:35 Inference Speeds
06:06 Querying with Different Models
08:05 Results between models
09:35 Ada 002 vs Cohere v3
10:29 Another test for OpenAI, Cohere, and E5
15:23 More Questions and Final Thoughts
Choose to Build with AI
Matched to Hugging Face
AI Maker Residence 3
The third AI workshop taught by our legendary teacher, Nick Sarafa. This is a full-day hands-on training workshop for purposeful co-creation with AI using Claude Code.
Imagine having access to hundreds of billions of dollars of computing power and knowing exactly how to make it work for you through the power of super intelligence.
◆ Fri 09 Oct 2026◆ KOKO Cafe, London◆ With Nick Sarafa
