Question 1

How is storage size calculated?

Accepted Answer

Storage = total vectors × dimensions × bytes per float (4 for float32, 2 for float16). Results shown in MB and GB.

Question 2

Which embedding models are compared?

Accepted Answer

OpenAI ada-002 (1536), text-embedding-3-small (512/1536), text-embedding-3-large (256/3072), Cohere v3 (1024), BGE (1024), E5 (1024). Dimensions selectable where applicable.

Question 3

What cost estimates are included?

Accepted Answer

Pinecone/Weaviate storage cost (based on $0.10/GB/month), embedding API cost per 1K tokens, and relative query latency estimates.

🧠 Embedding Dimension Calculator

⚙️ Configuration

📊 Model comparison