embedding model
A model that maps text to embedding vectors rather than generating text.
In more detail
Choose one on retrieval quality for your kind of text, its dimensions and maximum input length, cost and licence, then test the shortlist on your own labelled queries. Use one model per index: vectors from different models are not comparable, so record which model made each one.
Related terms
- embedding vector — A list of numbers that represents a piece of text, or an image, so that items with similar meaning lie close together.
- MTEB — The Massive Text Embedding Benchmark, a public set of tasks and a Hugging Face leaderboard for comparing embedding models.
- cross-encoder — A model that reads a query and a passage together and outputs one relevance score, instead of embedding each separately.
Taught in
- What An Embedding Is — AI Engineering: LLM Apps, RAG & Agents
- Embedding Models — AI Engineering: LLM Apps, RAG & Agents
- Keyword And Hybrid Search — AI Engineering: LLM Apps, RAG & Agents
- How RAG Works And When To Use It — AI Engineering: LLM Apps, RAG & Agents
- Chunking And Ingestion — AI Engineering: LLM Apps, RAG & Agents
References
- Hugging Face: sentence-transformers/all-MiniLM-L6-v2 model card
- Hugging Face: MTEB leaderboard
- OpenAI: Vector embeddings guide (dimensions parameter)