RAG Emporix Tool
Configure the RAG Emporix tool to index and retrieve products, orders, and custom entities with the native Emporix Vector Database.
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:
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.
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
mixinKey).Each field has
key(required) and optionalname(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 entity (for example, a product or an order) 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.
LLM providers
The configuration for creating embeddings includes choosing the relevant LLM provider. When indexing entities (such as products or orders) 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-smallmodel with embedding dimensions set to1536. 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 you configure a Product RAG tool with code, name.en, and description.en, 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.
For an Orders RAG tool, the available fields depend on the order schema (for example, order identifiers, status, customer references, legal entity identifiers, and line-item details). If fields such as id, status, and customerId are included, the concatenated content might look as follows:
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, an order, or a specified custom entity, it gets reindexed by the RAG tool and its embedding is recalculated if necessary in the background. To index all items in the database, select the Reindex option.
Reindexing is a computationally expensive and time-consuming operation, especially for large catalogs or high order volumes. 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.
Scoped retrieval for orders
When the entity type is Order, retrieval returns only orders that the agent is allowed to access based on the available scopes of the invoking user or integration. Depending on those scopes, the agent can retrieve:
All orders per tenant
Orders belonging to a specific legal entity (or entities)
Orders belonging to a specific customer
Orders belonging to legal entities available to a specific customer
Access follows the invoking context configured on the agent — for example, a Frontend Agent with the Customer scope typically resolves to customer-level or legal-entity-via-customer access, while agents with Employee or Integration scopes can reach broader tenant or legal-entity sets when their scopes allow it. Anonymous invocations must not expose other customers' orders. Configure agent Required scopes accordingly. For follow-up actions on retrieved orders (updates, returns, invoices), attach the relevant Order domain MCP tools.
Impact on context window
Retrieved RAG results are injected into the agent's prompt context. Indexing and retrieval choices therefore affect token usage:
Each indexed entity embeds at most
16 000characters. Index only the fields needed for semantic search so embeddings stay focused and smaller.Every retrieved hit adds content to the agent context. Prefer lean indexed payloads and keep result counts constrained so order (or product) hits do not crowd out the rest of the conversation.
Embedding operations with Emporix OpenAI count against the registered usage limits for indexing and for query-time embeddings.
Agent Max Tokens controls response length, not how much retrieved context is loaded. See AI Agents for model and token configuration.
Example RAG_EMPORIX AI tool flow
The flowchart represents the process flow of the RAG_EMPORIX tool.
When you apply a Product 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.
With an Orders RAG tool attached, the same pattern applies to order discovery. A customer might ask "Show my open solar orders and delays" or "Has my order been confirmed?" The agent uses Orders RAG to find semantically matching orders within the access allowed by available scopes, then can use Order MCP tools for exact details or follow-up actions.
Last updated
Was this helpful?