# 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](/agentic-commerce-intelligence/agentic-intelligence/configuration/tools/rag.md)

API Reference:

* [RAG AI Tutorial](/api-references/api-guides/artificial-intelligence/ai-rag-indexer/ai-rag-indexer-tutorial.md)
* [RAG AI API Reference](/api-references/api-guides/artificial-intelligence/ai-rag-indexer/api-reference.md)


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://developer.emporix.io/release-notes/archive/2025/2025-12-03-aci-rag.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.