medium10 pts · first answer countsragembeddings
Forgetting the query prefix
Your E5-family embedding model expects "query: " before questions and "passage: " before documents. You embed both without prefixes. What is the likely effect?
Discussion 0
Join free to post in the discussion.
Related questions
- What text embeddings areAI Engineer (LLM & Generative AI)
- What RAG doesAI Engineer (LLM & Generative AI)
- Comparing two embeddingsAI Engineer (LLM & Generative AI)
- Dot product of two vectorsAI Engineer (LLM & Generative AI)
- What a vector database doesAI Engineer (LLM & Generative AI)
- What semantic search adds over keywordsAI Engineer (LLM & Generative AI)
- What an embedding dimension isAI Engineer (LLM & Generative AI)
- What top-k means in retrievalAI Engineer (LLM & Generative AI)