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.
Why IBM picked a hybrid engine
A pure vector database answers questions about meaning well. A hybrid engine answers a meaning question, a keyword question and a structured filter in one query. Real business questions usually look like that mix.
How it fits beside Db2 for i
| System | Role |
|---|---|
| Db2 for i | The system of record |
| OpenSearch on Power | The embedded, indexed copy an AI agent searches |
IBM does not sell you OpenSearch. It is IBM's answer to a gap, because Db2 for i has no vector store.
Two things to get right
- Power, not IBM iIBM said Power. In practice that means a Linux on Power partition, not a PASE build on your production partition. IBM has published no supported IBM i package.
- A direction, not a productThis came from a May 2026 strategy session and trade press, not a product announcement with a reference architecture. Treat it as the current answer, not a supported stack.
Related Terms
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.
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.
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.