External: Coursera Courses ↗ · Coursera

Open Course on External: Coursera

Free to audit · Opens on External: Coursera

Getting Started with Vector Search and Embeddings

Coursera · Beginner ·🔍 RAG & Vector Search ·5mo ago

Skills: Vector Stores80%RAG Basics70%

Key Takeaways

Using text embeddings and Vertex AI vector search to find similar documents

Original Description

This is a self-paced lab that takes place in the Google Cloud console. In this lab, you will use text embeddings and Vertex AI vector search to find similar documents based on their text content.

☆ Save to playlist Watch on External: Coursera ↗

AI explanation not available for this lesson yet

This lesson is still being prepared for the AI tutor. In the meantime, explore lessons that are ready.

Browse explainer-ready lessons →

More on: Vector Stores

View skill →

Build a RAG Agent in n8n | Vector DB Pinecone + WhatsApp + Gmail [2026]

Build a RAG Agent in n8n | Vector DB Pinecone + WhatsApp + Gmail [2026]

Journey 3: Optimize Your Vector Index for Scale

Journey 3: Optimize Your Vector Index for Scale

Microsoft Developer

Spin Up Weaviate

Spin Up Weaviate

Build your own Vector Store from Scratch: Vector Store/DB 101

Build your own Vector Store from Scratch: Vector Store/DB 101

Deploy Vector DBs Securely

Deploy Vector DBs Securely

Configuring Vector Search in Cloud SQL for PostgreSQL

Related Reads

Why High Vector Similarity Doesn’t Guarantee Correct Answers in RAG

High vector similarity doesn't guarantee correct answers in RAG, learn why and how to improve your models

Advanced RAG: Chunking, Hybrid Search and Reranking

Improve RAG systems by enhancing information retrieval with techniques like chunking, hybrid search, and reranking

Advanced RAG: Chunking, Hybrid Search and Reranking

Improve RAG system performance by enhancing information retrieval with chunking, hybrid search, and reranking techniques

Medium · Programming

Break Your Own RAG Pipeline Before Users Do

Learn to test your RAG pipeline with adversarial examples to catch retrieval failures before users do, improving overall system robustness

Towards Data Science

What exactly is retrieval augmented generation?