Service Architecture Overview

The following figure shows the overall service architecture of FineChatBI.

Service	Description	Help Document
FineChatBI	FineChatBI is based on FineBI with AI components added.	Using FineOps to Deploy AI Services for FineBI
General LLM	General large language models (LLMs) support the following functions: Data asking (semantic understanding and transcription in the intelligent mode) Idea asking One-click synonym configuration	General LLM
Reasoning LLM (optional)	Reasoning LLMs support the following functions: Data interpretation Attribution analysis Note: If resources are limited, a general LLM can be used with, however, compromised effects.	Reasoning LLM

FineBI Server Configuration

Since FineChatBI is based on FineBI, FineBI of V6.1 or later versions needs to be deployed.

Select the required server by referring to Confirming Server Configuration of the FineBI Project.

Calculation rule: Count FineChatBI users as FineBI's daily active users, calculate required server resources, and reserve an additional 10% of server resources for FineChatBI use.

AI Component Server Configuration

Since AI components require a lot of resources, you are advised to prepare a separate server for AI components.

The server requirements are as follows:

• Recommended configuration: 16-core CPU, available 32 GB memory, available 100 GB disk, and AI component-dedicated server

• Minimum configuration: 12-core CPU, available 24 GB memory, available 50 GB disk, and server shared by AI components and projects

For details, see Preparing the AI Component Server.