Text Embedding
A text embedding is a numerical vector representation of a sentence or passage that captures semantic meaning, produced by an embedding model and used to power similarity search in retrieval-augmented generation.
How embeddings find similar text
An embedding turns a sentence or passage into a list of numbers. Passages that mean similar things end up close together. That lets a system find related content even when the exact words do not match.
Getting embeddings from watsonx.ai
- A REST endpoint at /ml/v1/text/embeddings
- A Python Embeddings class
- Up to 1,000 lines of text per request
Embedding models on watsonx.ai
| Model | Details |
|---|---|
| granite-embedding-278m-multilingual | IBM. 768 dimensions, 512 max input tokens |
| slate-125m-english-rtrvr-v2 | IBM. Scheduled for withdrawal August 8, 2026 |
| slate-30m-english-rtrvr-v2 | IBM. Scheduled for withdrawal August 8, 2026 |
| multilingual-e5-large | Microsoft. Supported |
Where IBM i shops keep them
watsonx.ai makes the vectors. As of September 2026 Db2 for i has no vector store to hold them, so they usually land in OpenSearch running on Power.
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.
watsonx.ai
The studio component of watsonx for building, tuning, and deploying foundation models and generative AI applications, including retrieval-augmented generation (RAG) against enterprise data.
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.
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.