Martin Fredlund, Magnus Herstedt:
Evaluating Database Types for AI Chatbot Data Retrieval,
summary, report, March 2026.

Abstract:

Customer Relationship Management (CRM) solutions increasingly integrate AI chatbots. The requirements for information retrieval are complex, making the selection of the optimal database type critical. This thesis analyzes how different database types compare in their retrieval capabilities within a CRM context.

This thesis was divided into two phases, first we conducted interviews with stakeholders to gain insight into use cases and system requirements. These insights were utilized in phase 2 that was an experimental phase over four iterations in which each completed iteration was evaluated and new exploratory ideas were carried on.

The results demonstrated that while graph databases generally delivered strong overall performance and high accuracy by utilizing graph traversal, vector databases outperformed them in specific use cases specifically on retrieval from unstructured data and semantic queries. Furthermore, the evaluation demonstrates that minimizing tool calls is the most critical factor for designing an efficient retriever..