RAG AI Tool

RAG AI Tools allow agents to perform LLM-based semantic search.

Retrieval-Augmented Generation (RAG) framework is capable of combining a large language model (LLM) with an external knowledge base to provide more accurate and up-to-date responses. Its inner mechanism consists in first retrieving relevant information from sources (like documents or databases) and then using that information in the LLM, enhancing its output with the specific context. RAG helps AI to generate answers that are highly-grounded in factual, real-time data, reducing "hallucinations".

In the Emporix Agentic AI, Retrieval-Augmented Generation is a capability facilitated by the RAG AI tools that you can use within an AI agent.

These native tools enable agents to perform LLM-based semantic search across various domain-specific entities stored in vector databases.

The RAG AI tools transform user queries into vector embeddings and match them against pre-computed entity embeddings using similarity metrics (for example, cosine similarity).

Crucially, RAG AI tools operate on semantic meaning. This differs from traditional keyword-based search, as RAG enables more accurate and context-aware retrieval even when there is no explicit keyword overlap.

To enhance search for indexed entities (like products) with RAG, an agent must be used with a previously defined RAG AI tool attached to it. The tool configuration requires a prompt, which informs the agent when the tool must be triggered. The Agentic AI provides two tool types designed for RAG workflows:

RAG_EMPORIX
RAG_CUSTOM

`RAG_EMPORIX` tool type

A tool of type RAG_EMPORIX enables configuration and execution of the indexing and retrieval pipeline for selected Emporix-managed entities. This tool type leverages the native Emporix Vector Database, meaning there is no need to manage external infrastructure.

Configuring RAG Emporix tool

To configure a RAG_EMPORIX tool, follow these steps:

Define general tool details

Open the General tab and set the tool basis:

Tool Type – Select RAG Emporix.
Tool ID – The identifier of the tool.
Tool Name – The name displayed in the UI.
Prompt – Instructions for when the agent should invoke this tool once it is attached.

Configure the embeddings LLM provider

Open the Settings tab and configure the LLM provider used to create embeddings. See LLM providers for provider-specific details.

Provider – OpenAI, Self-Hosted Ollama, or Emporix OpenAI.
Model – The model of the chosen LLM.
Dimensions – Embeddings table size (128–4096).
URL – Required for Self-Hosted Ollama only.
Token – Authentication token for the chosen provider.

Emporix OpenAI is preconfigured — no further details are required.

Select the entity type

Choose the Entity Type to index and retrieve — either Product or a custom entity defined in your tenant.

Note that removing a custom entity from the Emporix system results in automatic deletion of RAG tools that reference that entity.

Configure indexed fields

Specify which fields are included in the embedding. See the Indexed fields.

Add default Emporix fields or custom fields to be indexed for search (via the relevant mixin Key).
Each field has key (required) and optional name (alias used in concatenated content).

Indexed fields can include either a parent field (for example, brand) or one of its child fields (for example, brand.localizedDescription.en), but never both at the same time. When a parent field is selected, all of its child fields are automatically included in the concatenated content.

The maximum number of indexed characters in a single product is 16 000. If the content exceeds the limit, the first 16 000 characters are embedded while the remaining characters are ignored.

Configure filter fields

Specify the Filter Fields that can be used to refine and filter vector search results before retrieval. These fields enable the agent to constrain searches based on structured attributes, reducing irrelevant matches and improving the precision and efficiency of the retrieval process.

Save the tool configuration

Review the settings on the General and Settings tabs, then choose Save to store the tool configuration.

LLM providers

The configuration for creating embeddings includes choosing the relevant LLM provider. When indexing products using a RAG tool, the system generates appropriate embeddings by making an HTTP call to the chosen LLM.

There are three supported LLM providers you can use for creating RAG embeddings:

Emporix OpenAI - This provider doesn't require any further configuration on your side, as default settings are used. It uses the OpenAI text-embedding-3-small model with embedding dimensions set to 1536. The number of tokens used by each operation is registered in the Emporix system, and usage is limited to the set limit. When an AI agent uses the RAG tool, the same LLM configuration is used to create embeddings for user queries to perform search operations.
OpenAI - Use your own OpenAI account within the RAG tool. Provide the specific model type, dimensions, and token.
Self-Hosted Ollama - Use a custom Ollama LLM provider and model. In addition to the model, dimensions, and token, you also need to provide the URL of the hosted model to enable valid HTTP communication.

Indexed fields

The values of the indexed fields are later concatenated and converted into embeddings. Each line in this concatenated text corresponds to a single field and follows the structure: {key}: {content}.

For example, if code, name.en, and description.en are included in the configuration, the resulting concatenated content used for embedding looks as follows:

code: 103155592
name.en: Precision Screwdriver
description.en: A high-quality set of precision screwdrivers designed for industrial and professional applications, ensuring durability and precise performance.

Depending on the entity type you selected for the tool, the form fetches the list of available fields you can choose from. The indexed fields list consists of objects with two properties: key and name. The key property is required, while name is optional and can serve as the alias for the key. If you provide the name, it is used in place of the key in the content that is transformed into embeddings.

If you have custom mixin fields maintained outside of the Emporix system, you can add such fields using the Add Custom Field option. The path of the custom field key starts with the mixin. prefix.

Indexing stage

When the tool configuration is ready, the entities can be indexed. Each time you modify a product or a specified custom entity, it gets reindexed by the RAG tool and its embedding is recalculated if necessary in the background. To trigger indexing of all items in the database, you can trigger the Reindex option.

Reindexing is a computationally expensive and time-consuming operation, especially for large catalogs. It may significantly increase infrastructure costs, processing time, and overall system load. For this reason, perform reindexing only when truly necessary - for example, after major configuration changes, embedding model updates, or structural schema modifications. Avoid triggering it frequently or without clear intent.

Retrieving stage

To search for the indexed entities, you need to attach the previously defined RAG tool to an agent. The agent uses the available tool according to the specified prompt definition.

Example `RAG_EMPORIX` AI tool flow

The flowchart represents the process flow of the RAG_EMPORIX tool.

Example search results

When you apply the RAG tool in an agent available at the storefront, a user might, for example, query about products of interest using natural language. In the background, the agent triggers the RAG tool to enhance the search outcomes with RAG embeddings, match the query, and return all available matches to the user.

`RAG_CUSTOM` tool type

A tool of type RAG_CUSTOM enables integration with an external (custom) vector database, not managed by the Emporix platform. This allows the system to perform semantic search operations using embeddings stored outside of the native infrastructure.

This tool type is intended for advanced use cases where organizations prefer complete control over their vector storage, scalability, performance tuning, or cost management.

Configuring RAG Custom tool

To configure a RAG_CUSTOM tool, provide valid and accessible settings so the tool can execute Retrieval-Augmented Generation (RAG) queries successfully.

Before you begin, ensure a Qdrant collection with indexed products already exists and is accessible from the running environment. The tool connects to this external collection rather than creating or managing it.

Follow these steps: