RAG Custom Tool

Configure the RAG Custom tool to perform semantic search against an external vector database such as Qdrant.

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:

1

Define general tool details

Open the General tab and set the tool basis:

• Tool Type – Select RAG Custom.
• 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.

RAG custom tool configuration

2

Connect to the external vector database

Open the Settings tab and configure the external database connection:

• Database URL – The URL of the database where data is stored.
• Database Type – Type of the database.
• Collection Name – The name of the collection where products are stored.
• Database Token – The token for authentication to the database.

Currently, the only available database type is Qdrant.

3

Configure retrieval settings

Define how the tool queries and returns results from the external database:

• Max Results – The maximum number of documents returned by an agent that uses this tool.
• Entity Type – The entity type to retrieve from the database.

Currently, the only available entity type is Product.

4

Configure embeddings

Specify the LLM used to compute embeddings for entities in the collection:

• Model – The model used to compute embeddings.
• Embeddings Token – The token required for computing embeddings.

5

Save the tool configuration

When ready, choose Save to store the tool configuration.

RAG custom tool settings

Retrieving stage

To enhance search for the indexed products with custom-defined RAG, attach the RAG_CUSTOM tool to an agent. The agent uses the available tool according to the specified prompt definition.

Example RAG_CUSTOM AI tool flow

The flowchart represents the process flow of the RAG_CUSTOM tool.