RAG (Retrieval-Augmented Generation)

An intelligent retrieval technique where an LLM decomposes natural language queries into semantic search components and metadata filters. Enables more precise retrieval by automatically extracting structured filters from unstructured queries.

RETA-LLM is a toolkit designed for retrieval-augmented large language models. It is directly relevant to vector databases as it involves retrieval-based methods that typically leverage vector search and vector databases to enhance language model capabilities through external knowledge retrieval.

Advanced retrieval approach combining dense vectors, sparse vectors, and reranking in a multi-stage pipeline, achieving up to 48% better performance than single-method retrieval.

Techniques for managing limited LLM context windows in RAG systems, including chunk selection, summarization, and iterative retrieval. As context windows fill with retrieved documents, strategies ensure the most relevant information reaches the model while respecting token limits.

A two-stage retrieval process where initial candidates from vector search are reordered using more sophisticated models like cross-encoders. Reranking significantly improves result quality by applying computationally expensive models to a small set of candidates, commonly used in RAG systems and search applications.

An advanced RAG chunking strategy that uses LLMs to dynamically determine optimal document splitting based on semantic meaning and content structure. Agentic chunking analyzes document characteristics and adapts the chunking approach per document for superior retrieval accuracy.