Embedchain has a nice and simple abstraction on top of the Modal.com tools to let developers deploy RAG application to modal.com platform seamlessly.

Follow the instructions given below to deploy your first application quickly:

Step-1 Create RAG application:

We provide a command line utility called ec in embedchain that inherits the template for modal.com platform and help you deploy the app. Follow the instructions to create a modal.com app using the template provided:

Create application
pip install embedchain[modal]
mkdir my-rag-app
ec create --template=modal.com

This create command will open a browser window and ask you to login to your modal.com account and will generate a directory structure like this:

โ”œโ”€โ”€ app.py
โ”œโ”€โ”€ .env
โ”œโ”€โ”€ .env.example
โ”œโ”€โ”€ embedchain.json
โ””โ”€โ”€ requirements.txt

Feel free to edit the files as required.

  • app.py: Contains API app code
  • .env: Contains environment variables for production
  • .env.example: Contains dummy environment variables (can ignore this file)
  • embedchain.json: Contains embedchain specific configuration for deployment (you donโ€™t need to configure this)
  • requirements.txt: Contains python dependencies for your FastAPI application

Step-2: Test app locally

You can run the app locally by simply doing:

Run locally
pip install -r requirements.txt
ec dev

Step-3: Deploy to modal.com

You can deploy to modal.com using the following command:

Deploy app
ec deploy

Once this step finished, it will provide you with the deployment endpoint where you can access the app live. It will look something like this (Swagger docs):

Seeking help?

If you run into issues with deployment, please feel free to reach out to us via any of the following methods: