Train a linear layer to increase your RAG system [Technical Report] [pdf] (research.phospho.ai)

Key highlights: - Uses a simple linear transformation on existing embeddings - Boosts hit rate from 89% to 95% on real-world examples - Minor increase on latency (less than 10ms) - Works on top of blackbox embedding models (Mistral AI, OpenAI, Cohere,...) - No dataset needed (just your documents) - Train easily on CPU