Local Development Environment

Install Python 3.11 or higher.

Create a virtual environment, activate it, and install RAGStack.

python -m venv <venv-name>
source <venv-name>/bin/activate
pip install ragstack-ai

Once you’re satisfied with your local environment, freeze its dependencies to a requirements.txt file. This file can then be used to recreate the environment elsewhere:

pip freeze > requirements.txt

To take your local environment to a production setting, create a new virtual environment and install the dependencies from the requirements.txt file:

pip install -r requirements.txt

To deactivate the virtual environment, type deactivate.

Install Conda or Miniconda.

Create a virtual environment, activate it, and install RAGStack.

conda create --name <venv-name>
conda activate <venv-name>
pip install ragstack-ai

Once you’re satisfied with your local environment, export it to a YAML file. This file can then be used to recreate the environment elsewhere:

conda env export > environment.yml

To take your local environment to a production setting, create a new conda virtual environment from the environment.yml file:

conda create --name prod-ragstack --clone ragstack-venv

To deactivate the virtual environment, type conda deactivate.

Install Poetry.

If you already have a poetry.lock file, use poetry add ragstack-ai to add RAGStack to your project. If not, continue to the next step.

In your application directory, run poetry init to create a pyproject.toml file. Poetry will ask you a few questions about your project and create the .toml file for you.

poetry init

This command will guide you through creating your pyproject.toml config.

Package name [temporary-astra]:
Version [0.1.0]:
Description []:
Author [Mendon Kissling <59585235+mendonk@users.noreply.github.com>, n to skip]:
License []:
Compatible Python versions [^3.11]:

Would you like to define your main dependencies interactively? (yes/no) [yes] yes
Package to add or search for (leave blank to skip): ragstack-ai
Enter package # to add, or the complete package name if it is not listed []:
 [ 0] ragstack-ai
 > 0
Enter the version constraint to require (or leave blank to use the latest version):
Using version ^0.1.2 for ragstack-ai

When asked Would you like to define your main dependencies interactively? (yes/no), type yes.

When prompted Package to add or search for (leave blank to skip):, type ragstack-ai and leave the version constraint blank to use the latest version.

Once the Poetry virtual environment is created, type poetry shell to activate it as a nested shell.

Type poetry install. This command reads the pyproject.toml file, downloads the latest versions of the dependencies, and installs them in the virtual environment. All packages and their exact versions are written to the poetry.lock file, locking the project to those specific versions. You should commit the poetry.lock file to your project repo so that all people working on the project are locked to the same versions of dependencies.

poetry install
Updating dependencies
Resolving dependencies...

Package operations: 65 installs, 0 updates, 0 removals

  • Installing click (8.1.7)

...

Writing lock file

Installing the current project: temporary-astra (0.1.0)

To deactivate the virtual environment, type exit.

If you don’t have a vector database, create one at https://astra.datastax.com/.

Create a .env file in the root of your program with the values from your Astra Connect tab.

ASTRA_DB_APPLICATION_TOKEN="<AstraCS:...>"
ASTRA_DB_API_ENDPOINT="<Astra DB API endpoint>"
OPENAI_API_KEY="sk-..."
ASTRA_DB_COLLECTION="test"

Test your connection to the database. Create a vector store and print the contents of the data collection:

import os
from dotenv import load_dotenv
from langchain_astradb import AstraDBVectorStore
from langchain_openai import OpenAIEmbeddings

load_dotenv()

ASTRA_DB_APPLICATION_TOKEN = os.environ.get("ASTRA_DB_APPLICATION_TOKEN")
ASTRA_DB_API_ENDPOINT = os.environ.get("ASTRA_DB_API_ENDPOINT")
OPEN_AI_API_KEY = os.environ.get("OPENAI_API_KEY")
ASTRA_DB_COLLECTION = os.environ.get("ASTRA_DB_COLLECTION")

embedding = OpenAIEmbeddings()
vstore = AstraDBVectorStore(
    embedding=embedding,
    collection_name="test",
    token=os.environ["ASTRA_DB_APPLICATION_TOKEN"],
    api_endpoint=os.environ["ASTRA_DB_API_ENDPOINT"],
)
print(vstore.astra_db.collection(ASTRA_DB_COLLECTION).find())

You should get the following output, indicating your collection contains no documents:

{'data': {'documents': [], 'nextPageState': None}}

With your local environment connected to your vector database, continue on to the quickstart to load data and start querying.