2025-12-03: ACI - AI RAG Tools

Overview

Retrieval-Augmented Generation (RAG) AI Tools facilitate the execution of semantic search operations by AI agents across domain-specific entities stored in vector databases, utilising LLMs. This capability enhances agent responses by grounding them in factual, real-time data, reducing hallucinations and improving accuracy.

RAG transforms user queries into vector embeddings and matches them against pre-computed entity embeddings using similarity metrics, enabling more accurate and context-aware retrieval even when there is no explicit keyword overlap.

New features

Feature	Benefit
RAG_EMPORIX tool	Leverage the native Emporix tool for indexing and retrieval of Emporix-managed entities without managing external infrastructure. Configure semantic search for products with customizable indexed fields including mixins.
Semantic search	Enable agents to perform context-aware searches based on semantic meaning rather than keyword matching. This can automatically break large product content into AI-friendly chunks to boost response quality across AI-powered search and assistants.
Automatic reindexing	Enable controlled full reindex runs, making large catalog changes or data clean-ups safe. Products are automatically reindexed when modified, ensuring embeddings stay up-to-date with the latest product information.
RAG Tool creation	Introduce reusable RAG tools that product, sales, and support applications can plug into, accelerating rollout of new AI use cases.
RAG_CUSTOM tool	Integrate with external vector databases (currently Qdrant) for organizations that prefer complete control tailored RAG experiences over vector storage, scalability, performance tuning, or cost management.
Configurable indexed fields	Select specific product fields to include in embeddings, with support for localized fields and mixin schemas, allowing fine-tuned search relevance.

Fixes and improvements

None as this is a new feature.

Known problems

No known problems at time of release.

Documentation and links

User Guides:

• RAG AI Tools

API Reference:

• RAG AI Tutorial

• RAG AI API Reference