Vector Store
A vector store holds embeddings and finds the ones closest to a query. It is the retrieval half of RAG, and Db2 for i has no vector store as of 2026.
What a vector store does
A vector store holds embeddings. An embedding is a list of numbers a model makes for a passage of text, an image or other content. The store answers nearest-neighbor queries, so a system can find the few passages most related to a question.
That lookup is the first half of retrieval-augmented generation. The language model only does the second half.
Why IBM i shops should care
This term matters on IBM i because of what is missing.
Native vector support in Db2
| Database | Native vector type |
|---|---|
| Db2 for Linux, UNIX and Windows 12.1.2 (June 2025) | Yes. A VECTOR data type searched with SQL distance functions |
| Db2 for i, as of September 2026 | No, and no date published |
The July 2026 Technology Refreshes for IBM i 7.6 and 7.5 added no AI items.
Where the index lives instead
IBM points to OpenSearch running on Power. Db2 for i stays the system of record. OpenSearch holds the searchable copy that an AI agent queries. That has two costs.
- A second systemThe vector store is one more system to run, secure and back up.
- A readable copyIt holds a copy of everything you indexed, and it does not inherit your Db2 for i object authority on its own.
Related Terms
Retrieval-Augmented Generation (RAG)
Retrieval-Augmented Generation hands a language model passages pulled from your own data, so it answers from your content. On IBM i, retrieval is the hard half.
OpenSearch
OpenSearch is the open-source hybrid search engine IBM has positioned as the vector, text and structured search layer for RAG on Power, since Db2 for i has none.
Db2 for i
The relational database management system built into every IBM i operating system, tightly integrated with IBM i rather than a separately installed database product.
IBM i MCP Server
An open-source, IBM-published server implementing the Model Context Protocol (MCP), letting AI agents and LLMs query Db2 for i data and take defined actions on IBM i using natural language. In beta since October 2025.
Large Language Model (LLM)
A machine learning model trained on large volumes of text, used as the underlying technology behind generative AI tools including IBM Bob and general-purpose assistants like ChatGPT and Claude.
Foundation Model
A large, general-purpose AI model trained on broad data and then adapted, through prompting, tuning, or fine-tuning, to specific tasks such as RPG code generation.