Retrieval

• Sparse Retrieval

  Retrieval using inverted-index term matching and scoring functions like BM25 or TF-IDF; contrasts with dense nearest-neighbour methods.

• Recall

  Fraction of relevant documents that are retrieved; measures completeness of retrieval; high recall indicates few false negatives.

• Precision

  Fraction of retrieved documents that are relevant; measures quality of retrieved set; high precision indicates few false positives.

• Hybrid Search

  Combining dense vector similarity and sparse term-matching scores to balance semantic understanding with keyword precision.

• FAISS

  Facebook AI Similarity Search; open-source library implementing multiple approximate nearest-neighbour indexes for efficient similarity search at scale.

• Dense Retrieval

  Retrieval method using nearest-neighbour search over dense embedding vectors; contrasts with inverted-index sparse retrieval like BM25.

• Chunking Strategy

  How documents are split into passages for indexing and retrieval in RAG systems; balance between granularity and context preservation.