Using with DB-GPT

1. About DB-GPT

DB-GPT is an open-source AI-native data application development framework that provides capabilities including multi-model management, Text2SQL optimization, a RAG framework, and Multi-Agent collaboration.

2. Get Your API Key

Open the Cube AI Console and register an account (or log in if you already have one). After registering, go to API Keys, create a new API key, and copy it for later use.

3. Deploy DB-GPT

3.1 Clone the DB-GPT Repository

git clone https://github.com/eosphoros-ai/DB-GPT.git
cd DB-GPT

3.2 Create a Virtual Environment and Install Dependencies

conda create -n dbgpt_env python=3.10
conda activate dbgpt_env
pip install -e ".[proxy]"

3.3 Configure Environment Variables

cp .env.template .env

Edit the .env file to configure the Cube AI model:

# Use Cube AI as the proxy model
LLM_MODEL=proxy_openai
PROXY_OPENAI_API_BASE=https://ai.cubeuaeai.com/v1
PROXY_OPENAI_API_KEY={your-cube-api-key}
PROXY_OPENAI_BACKEND=gpt-4o

# Embedding model configuration
EMBEDDING_MODEL=proxy_http_openapi
PROXY_HTTP_OPENAPI_PROXY_SERVER_URL=https://ai.cubeuaeai.com/v1/embeddings
PROXY_HTTP_OPENAPI_PROXY_API_KEY={your-cube-api-key}
PROXY_HTTP_OPENAPI_PROXY_BACKEND=text-embedding-3-small

3.4 Start the DB-GPT Service

dbgpt start webserver --port 5670

Open http://127.0.0.1:5670/ in your browser to access the interface.

4. Using Cube AI Models via the DB-GPT Python SDK

4.1 Installation

pip install "dbgpt>=0.6.3rc2" openai

4.2 Using Cube AI LLMs

from openai import OpenAI

client = OpenAI(
    api_key="{your-cube-api-key}",
    base_url="https://ai.cubeuaeai.com/v1"
)

response = client.chat.completions.create(
    model="gpt-4o",
    messages=[
        {"role": "system", "content": "You are a helpful AI assistant."},
        {"role": "user", "content": "Hello"}
    ]
)
print(response.choices[0].message.content)

5. Getting Started Guide

Add a Data Source — Choose a database type (e.g. MySQL, PostgreSQL) and connect.
Select ChatData Conversation Type — Use natural language to interact with your data.
Start Data Conversation — Select a Cube AI model and the corresponding database to begin your data dialogue.

​1. About DB-GPT

​2. Get Your API Key

​3. Deploy DB-GPT

​3.1 Clone the DB-GPT Repository

​3.2 Create a Virtual Environment and Install Dependencies

​3.3 Configure Environment Variables

​3.4 Start the DB-GPT Service

​4. Using Cube AI Models via the DB-GPT Python SDK

​4.1 Installation

​4.2 Using Cube AI LLMs

​5. Getting Started Guide