Getting Started

Setting Up the DataBridge server

Direct Installation

Prerequisites

Python

Please ensure that you have Python 3.12 installed on your machine. Guides for installing Python can be found on the Python website.

PostgreSQL

DataBridge requires PostgreSQL with the pgvector extension for vector storage and similarity search capabilities. Follow the installation instructions for your operating system:

• macOS
• Ubuntu/Debian
• Windows

On macOS, you can use Homebrew to install PostgreSQL and pgvector:

brew install postgresql@14
brew install pgvector

Start the PostgreSQL service:

brew services start postgresql@14

Create a database and user for DataBridge:

createdb databridge
createuser -s postgres

These commands create a database named “databridge” and a superuser named “postgres” that the application will use to connect.

After installation, verify that Ollama is running correctly by making a simple query:

After installation, verify that PostgreSQL is running correctly:

psql -U postgres -c "SELECT version();"

You should see the following output:

 version                                                            
------------------------------------------------------------------------------------------------------------------------------
<Your postgres version and some compilation details>

Installing Ollama

• macOS
• Linux
• Windows

Install Ollama using Homebrew:

brew install ollama

Start Ollama:

ollama serve

Pull a model to use with DataBridge (in a new terminal):

ollama pull llama3.2

Cloning the Repository

To get started with DataBridge, we need to first setup the server. This involves cloning the repository, installing the dependencies, and the running the server. You are just a few steps away from accurate, agentic RAG over your multi-modal data!

First, let’s clone the repository from GitHub.

git clone https://github.com/databridge-org/databridge-core.git

After cloning the repository, you will notice a databridge-core folder in your current directory.

ls databridge-core

If you see an error like ls: databridge-core: No such file or directory, it means that the repository is not cloned properly. Please try again.

Once you have cloned the repository, navigate into the databridge-core folder.

cd databridge-core

Next, you need to set up a virtual environment called .venv.

Setting Up the Environment

Installing Python Dependencies

While it is not required, we highly recommend using a virtual environment to ensure dependencies from other projects do not conflict with DataBridge. You may use managers like uv or poetry, but for this guide, we will use the built-in venv module.

python3.12 -m venv .venv

Now, you need to activate the virtual environment. The activation command differs based on your operating system.

• Linux/macOS
• Windows (Command Prompt)
• Windows (PowerShell)

source .venv/bin/activate

After activation, your command prompt should be prefixed with (.venv), indicating that the virtual environment is active. Once your virtual environment is activated, you can install the required dependencies.

pip install -r requirements.txt

Setting up the Server Parameters

At this point, you may want to customize the server - such as use a different embedding model, enable or disable certain features, etc. - you can do so by editing the databridge.toml file. You can find more details about configuration here.

DataBridge uses environment variables to manage secrets and api keys. In order to ensure that any pre-set keys are available to the server, copy the .env.example file to .env:

cp .env.example .env

In case you’re using external models, you may have to edit the .env file with the necessary API keys. Finally, you can run the setup script to install dependencies and setup the database and vector store.

python quick_setup.py

Launching the Server

You are now ready to launch the DataBridge server! Just run the following command to start the server.

python start_server.py

You should see the following output:

INFO:     Started server process [15169]
INFO:     Waiting for application startup.
INFO:     Application startup complete.
INFO:     Uvicorn running on http://localhost:8000 (Press CTRL+C to quit)

This means that the server is running on http://localhost:8000. You can now interact with the server using the API or the Python SDK.

Next Steps

Now that you have the server running, you can explore the different ways to interact with the server.

Configure DataBridge

Configure DataBridge using the databridge.toml file.

API

Use the API to interact with the server.

Python SDK

Use the Python SDK to interact with the server.

DataBridge UI and CLI

Use the DataBridge UI or CLI to interact with the server.

Installing via Ollama