Data & AI

Basic RAG Retrieval Pipeline

Data & AI Pipelines diagram · made in Skemio

RAG pipeline diagram showing user query converted to embedding vector, querying a vector database for chunks, which inject into a prompt template for LLM answer generation.
RAG pipeline diagram showing user query converted to embedding vector, querying a vector database for chunks, which inject into a prompt template for LLM answer generation.
Open it in SkemioMake your own

What it shows

  • User query is converted into a vector embedding using the same model.
  • Vector database runs similarity search (e.g., Cosine/HNSW) for top-k.
  • Retrieved chunks are injected into a prompt template passed to the LLM.

The takeaway

RAG grounds generative models by retrieving external domain knowledge at runtime.

More data & ai pipelines diagrams