AI, LLM & Machine Learning Engineering

RAG, Embeddings & Vector Search Calculators

Sizing a retrieval-augmented generation system: how a corpus divides into chunks, what embedding it costs, how much a vector index consumes in memory, and how much retrieved context each request carries.

3 calculators in this category

RAG Chunking CalculatorFixed-size sliding-window chunkingThis calculator answers the two questions that decide a retrieval pipeline's shape: how many chunks your corpus becomes at a…
Vector Database Storage CalculatorHNSW graph index (Malkov & Yashunin, 2016)This calculator sizes a vector index the way it actually consumes memory: the raw embedding bytes, plus the neighbour lists an…
Embedding Cost CalculatorThis calculator prices the three separate embedding bills a retrieval system generates: the one-off cost of embedding your…

More ai, llm & machine learning engineering categories

LLM Inference Cost & Serving Model Memory & GPU Sizing Training & Fine-Tuning Compute Model Evaluation & Metrics