On this page
The problem
We need an embedding model for our RAG pipeline. The model determines retrieval quality, vector dimensions (affects storage), and API cost.
What we weighed
OpenAI text-embedding-3-small (1536d)
Pros
- +Cheapest OpenAI option ($0.02/1M tokens)
- +Good quality for general text
- +Configurable dimensions (shorten from the default 1536 with the dimensions parameter)
Cons
- −Not best-in-class on MTEB benchmarks
- −Vendor lock-in to OpenAI
OpenAI text-embedding-3-large (3072d)
Pros
- +Top-tier quality on MTEB
- +Configurable dimensions
Cons
- −6.5x more expensive than small variant
- −Higher storage cost (2x dimensions)
Cohere embed-v3
Pros
- +Strong multilingual support
- +Input type parameter (search_document vs search_query)
- +Competitive MTEB scores
Cons
- −Additional vendor dependency
- −Less ecosystem tooling
BGE-large-en-v1.5 (open source)
Pros
- +Free — self-hosted
- +Strong MTEB benchmarks
- +No vendor dependency
Cons
- −Must host GPU infrastructure
- −Operational overhead for scaling
What we chose
We chose OpenAI text-embedding-3-small. The cost is negligible at our scale (<$5/month), quality is sufficient for our document types (technical articles), and it integrates seamlessly with our existing OpenAI API key. We set the dimensions parameter to 1024 (down from the default 1536) to reduce storage while maintaining quality.
What it committed us to
- •Vector dimensions set to 1024 in pgvector schema
- •Locked to OpenAI for embeddings (acceptable — easy to migrate)
- •Must re-embed all documents if we switch models
- •Batch embedding for new content via background job