Everything about retrieval
12 connected nodes across dictionary, workflows, comparisons, prompts, tool stacks and use cases.
RAG (Retrieval-Augmented Generation)
Inject external knowledge into an LLM at query time.
Semantic Search
Finding information by meaning rather than exact keyword match.
Agentic RAG
RAG where an agent decides what to retrieve, when, and from which source — instead of a single static query.
Embedding
A numerical vector representation of text, image or audio that captures meaning for similarity search.
Retrieval
Selecting the most relevant chunks for a query before generation.
Reranker
A second-stage model that reorders retrieved chunks for precision.
Hybrid Search
Combining keyword (BM25) and vector search for better recall.
Chunk Size
The length of text segments stored in a vector index.
BM25
The keyword-ranking algorithm behind classic search engines.
Cosine Similarity
The dot-product-of-unit-vectors metric that ranks embeddings.
Vector Index
A data structure that makes nearest-neighbor search fast.
Embedding Dimensions
The vector length of an embedding model's output.