Explore a multilingual semantic search example using Cohere's new multilingual model and compare its performance against OpenAI's GPT 3.5 text-embedding-ada-002 model. Learn about the cost differences, implementation process, and performance metrics of both models. Dive into data preparation, embedding techniques, and vector indexing with Pinecone. Discover how to make multilingual queries and gain insights on the strengths and weaknesses of Cohere and OpenAI embeddings for multilingual search applications.
Overview
Syllabus
What are Cohere embeddings
Cohere v OpenAI on cost
Cohere v OpenAI on performance
Implementing Cohere multilingual model
Data prep and embedding
Creating a vector index with Pinecone
Embedding and indexing everything
Making multilingual queries
Final throughts on Cohere and OpenAI
Taught by
James Briggs
