fmgonzales / example-llamaindex Goto Github PK

Koyeb Serverless Platform

Deploy LlamaIndex on Koyeb
Learn more about Koyeb · Explore the documentation · Discover our tutorials

Koyeb is a developer-friendly serverless platform to deploy apps globally. No-ops, servers, or infrastructure management.

This repository contains is designed to show how LlamaIndex applications can be deployed to Koyeb. The Dockerfile in this repository builds an image that serves a LlamaIndex application with a Streamlit frontend that queries the OpenAI API about the short story "The Gift of the Magi" by O. Henry.

Follow the steps below to deploy the LlamaIndex application to your Koyeb account.

To use this repository, you need:

• A Koyeb account to build the Docker image and run the Dockerized application. If you don't already have an account, you can sign-up for free.
• An OpenAI API key so that our application can send queries to OpenAI.

The fastest way to deploy the LlamaIndex application is to click the Deploy to Koyeb button below.

Clicking on this button brings you to the Koyeb App creation page with most of the settings pre-configured to launch this application. You will need to replace the value for the following variable:

• OPENAI_API_KEY: Set to your OpenAI API key.

To modify this application example, you will need to fork this repository. Checkout the fork and deploy instructions.

If you want to customize and enhance this application, you need to fork this repository.

If you used the Deploy to Koyeb button, you can simply link your service to your forked repository to be able to push changes. Alternatively, you can manually create the application as described below.

On the Koyeb Control Panel, click the Create App button to go to the App creation page.

1. Click Create App in the Koyeb control panel.
2. Select GitHub as the deployment option.
3. Choose the GitHub repository and branch containing your application code.
4. Name your service, for example example-llamaindex.
5. Select Dockerfile as the builder for the project.
6. Expand the Advanced section and click Add Variable to configure a new environment variable. Create a variable called OPENAI_API_KEY. Select the Secret type and choose Create secret in the value. In the form that appears, create a new secret containing your OpenAI API key.
7. Name the App, for example example-llamaindex.
8. Click the Deploy button.

A container image for the LlamaIndex application will be built and a container will be deployed to Koyeb. You can follow the build process as the repository is cloned, built, and deployed. Once the deployment is complete, it will be accessible using the Koyeb subdomain for your service.

If you have any questions, ideas or suggestions regarding this application sample, feel free to open an issue or fork this repository and open a pull request.

Koyeb - @gokoyeb - Slack