Quickstart Setup

Navigate to the app directory and create a new virtual environment:

cd ~/workshop/agentic-ai/base-app
python3 -m venv .venv
source .venv/bin/activate

The app already installs langchain, langchain-openai, langgraph, and flask via its requirements.txt. Galileo’s LangChain callback ships with the galileo package, so let’s add it here.

Open the ~/workshop/agentic-ai/base-app/requirements.txt file for editing and add the following packages:

galileo
python-dotenv

Then add all of the packages to the virtual environment:

pip install -r requirements.txt

Your EC2 instance comes pre-configured with OPENAI_API_KEY and OPENAI_BASE_URL environment variables, which will be used by the application.

To define additional environment variables, create a new file named ~/workshop/agentic-ai/base-app/.env and add your credentials:

GALILEO_API_KEY="your-galileo-api-key"
GALILEO_CONSOLE_URL="https://console.multitenant.galileocloud.io"
# If you comment out the next two uncommented lines, Galileo uses a project and log
# stream both named "default".
GALILEO_PROJECT="Workshop19Galileo"
GALILEO_LOG_STREAM="TravelPlanner-${INSTANCE}"

Initialize Galileo near the top of ~/workshop/agentic-ai/base-app/main.py, right before import logging. Passing the environment variables through means the project and log stream come from your .env when set, and fall back to Galileo’s default/default when not:

import os
from dotenv import load_dotenv
from galileo import galileo_context

load_dotenv()

galileo_context.init(project=os.getenv("GALILEO_PROJECT"),
                     log_stream=os.getenv("GALILEO_LOG_STREAM"))