Agentic AI Reference Architecture

Knowledge & Data · Software component

In-Store Vectorizer

Software componentKnowledge & DataKnowledge & Dataarc:InStoreVectorizer

A vector store module that automatically calls an external embedding provider to vectorize raw text on insert and on query when no vector is supplied.

Responsibility. Generates embeddings inside the vector store for objects submitted without vectors.

Also known as: Built-in vectorization module, Vectorizer module

writesis invoked byis configured byinvokesSelf-Managed Vector Index Store: writesSelf-Managed Vector Inde…Vector Batch Ingestor: is invoked byVector Batch IngestorKnowledge Chunk Metadata Schema: is configured byKnowledge Chunk Metadata…Hosted Embedding API Service: invokesHosted Embedding API Ser…
Direct neighbourhood (hover for relationship types)

Relationships

is configured by structural

invokes dependency

is invoked by dependency

writes dependency

Design guidance

Quantitative guidance

As stated by the sources; verify before use.

Classification

Technologies
Weaviate text2vec-openaiWeaviate text2vec-cohereNVIDIA NIM
Quality attributes
Maintainability (ISO/IEC 25010)

Sources

  1. Ch6.2A: T. Nguyen, "Vector Database Selection," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 6.2A. ISBN: 9798244538229.
  2. Ch6.2B: T. Nguyen, "Production Vector Database Deployment," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 6.2B. ISBN: 9798244538229.