19 terms
Definitions in this topic
- Agentic AIAgentic RAGAgentic RAG explained: how it differs from standard RAG, the retrieve-evaluate-retry loop, and when to use it.
- Agentic AIAgentic SearchAgentic search explained: how an AI agent plans, checks and repeats its own searches, how it differs from one-pass AI search, and our rules for it.
- LLM foundationsContextual RetrievalContextual retrieval explained: how document-aware chunk prefixes improve keyword and vector search in a RAG system.
- LLM foundationsDocument chunkingDocument chunking explained: splitting source material into retrievable passages that preserve enough context for RAG.
- LLM foundationsEmbeddingsEmbeddings explained: how a text-to-vector model captures meaning, and why the choice of model matters for retrieval.
- LLM foundationsGraph RAGGraph RAG explained: using entities, relationships, and graph summaries to ground answers across connected data.
- LLM foundationsHybrid searchHybrid search explained: combining keyword and vector retrieval to improve RAG relevance across exact and semantic queries.
- LLM foundationsKnowledge graphKnowledge graphs explained: representing entities and relationships as structured, queryable context for AI systems.
- LLM foundationsLate ChunkingLate chunking explained: how document-level context improves RAG embeddings for chunks that depend on surrounding text.
- Agentic AILlamaIndexLlamaIndex explained: ingestion, indexing, and query engines over your own data, and how it differs from LangChain.
- LLM foundationsMetadata filteringMetadata filtering explained: pre-filter vs post-filter vector search, why strict filters starve results, and how we filter our own knowledge base.
- LLM foundationsOptical character recognitionOptical character recognition explained: how OCR turns document images into text, where accuracy breaks, and how it supports Document AI.
- LLM foundationsQuery RewritingQuery rewriting explained: how RAG systems reformulate questions to retrieve better evidence without changing the user's intent.
- LLM foundationsRAGRAG explained: the query, retrieve, augment, generate loop, and where it breaks in a real production system.
- LLM foundationsRerankingReranking explained: rescoring top retrieval candidates with a stronger model before they enter an LLM context.
- ProductionSemantic layerSemantic layer explained: shared business definitions between your data and your AI, and why agents need one to answer right.
- LLM foundationsSemantic searchSemantic search explained: retrieving by meaning with embeddings rather than relying only on exact keyword matches.
- LLM foundationsSparse RetrievalWhat sparse retrieval is, how BM25 and SPLADE score documents, and the silent misses we hit when our agents rely on keyword search.
- LLM foundationsVector databaseVector database explained: how similarity search works, and what actually separates one option from another.