Learn AI
Build your understanding from AI fundamentals to production AI systems.
Prefer a guided sequence? Explore Learning PathsAI Data & Retrieval
The real-world implementation of embeddings, vector search, and RAG in production.
7 conceptsEmbeddings in Production
Running embeddings in production means choosing a model, batching generation, and handling re-embedding when documents change.
Intermediate · 4 minVector Databases in Production
Choosing a vector database in practice depends on scale, existing infrastructure, and whether filtering or hybrid search is required.
Intermediate · 4 minRAG Pipelines in Production
A production RAG pipeline chains ingestion, chunking, embedding, retrieval, reranking, and generation into one maintained system.
Advanced · 5 minMetadata Filtering in Retrieval
Filtering retrieval by metadata — tenant, date, permission level — narrows results before similarity ranking even runs.
Intermediate · 4 minHybrid Search Infrastructure
Running hybrid search in production means combining a vector index and a keyword index, then merging their results into one ranking.
Advanced · 4 minSemantic Search Applications
Semantic search products — support search, internal knowledge search, e-commerce search — apply vector retrieval to a specific domain.
Intermediate · 4 minDocument Ingestion for RAG
Ingestion keeps a RAG system in sync with its source documents — detecting new, updated, and deleted content over time.
Intermediate · 4 min