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.
OpenSearch is an open-source search and analytics engine, originally forked from Elasticsearch, that combines full-text search, structured filtering and vector similarity search in a single engine. That combination is why IBM picked it. A pure vector database answers semantic questions well, while a hybrid engine can answer a semantic question, a keyword question and a structured filter in one query, which is much closer to the shape of a real business question.
For IBM i, OpenSearch is IBM's answer to a gap rather than a product IBM sells you. Db2 for i has no vector store, so IBM has been pointing IBM i shops at OpenSearch running on Power as the search and vector layer for AI applications built on IBM i data, with Db2 for i staying the system of record and OpenSearch holding the embedded, indexed copy an agent actually searches against.
Two things to be precise about. IBM said Power, not IBM i. In practice that means a Linux on Power partition rather than a PASE build on your production partition, and IBM has published no supported IBM i package for it. And this direction comes from a strategy session and trade press coverage in May 2026, not from a product announcement with a reference architecture behind it. Treat it as the current answer, not as 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.