Learn: RAG and search

1. What is retrieval-augmented generation?Pinecone · Why a model answers better with your documents at hand.Mark done
2. EmbeddingsOpenAI · Turning text into vectors you can search by meaning.Mark done
3. Sentence TransformersHugging Face · Open models for embeddings, and how to use them.Mark done
4. Contextual retrievalAnthropic · Why retrieval misses, and a way to fix much of it.Mark done
5. Advanced RAGHugging Face · A full pipeline, with the choices that matter.Mark done

• RAG (retrieval-augmented generation)
• Embedding
• Vector database
• Semantic search
• Context window
• Hallucination

1. Learning Popularity-Aware User Representations for Sequential Recommendation via Retrieval-Augmentation
2. Private Retrieval Augmented Generation via Random Projection
3. Encoded but Exposed: Language Embeddings can Reveal More Than They Should in Recommender Systems
4. ConStore: Search-Overlapped Prefetch and Co-Retrieval-Aware Content Storage for Disk-Based ANNS
5. Poisoning the Neighborhood: A Topology-Aware Topic-Level Attack on Large-Scale HNSW-based RAG Systems

More in Search and retrieval →