Text data refinement

This page allows you to configure text processing parameters that determine how documents are processed and stored for optimal retrieval and knowledge base creation.

Select the RAG definition

In this step, configure the data retrieval model that determines how your knowledge base will store, index, and retrieve content to generate accurate, context-aware responses to user queries.

ZBrain supports two RAG storage models:

• Vector store – default, chunk-and-embedding index for semantic similarity search

• Knowledge graph – entity–relationship graph stored in ZBrain’s graph database

Select the one that best matches your data and query needs.

Option	How it works	When to choose it
Vector store	Splits each document into chunks, converts the chunks into high-dimensional embeddings, and saves them in a vector database. At query time, ZBrain performs a semantic-similarity search and supplies the matched chunks to the LLM.	Unstructured text Rapid prototyping
Knowledge graph	Extracts entities and relationships from every chunk, stores them as nodes and edges, and also embeds the chunk text so you can fall back on vector similarity. The query engine can traverse the graph, run vector search, or perform both operations.	Information with critical inter-entity relationships, such as product-component hierarchies, chronological timelines, or complex organizational structures.

Next steps

To finish configuring your knowledge base, choose the retrieval model that best suits your data and follow the step-by-step guide to configure the knowledge base:

Retrieval model	Documentation reference
Vector Store	How to create a knowledge base using vector store?
Knowledge Graph	How to create a knowledge base using knowledge graph?

Follow the appropriate guide, complete the remaining configuration steps, and publish your knowledge base to make it available for querying in ZBrain.