This guide provides specific instructions to help you host your vectara-answer application on one of the popular hosting providers.
We keep adding new hosting providers regularly - please let us know if you need instructions for a hosting provider that is not yet included.
To run a hosted version of vectara-answer you would need to have two files: .env and queries.json.
To prepare the .env file, which combines the information from config.yaml and secrets.toml, run the following command:
python3 prepare_config.py /path/to/<YOUR-CONFIG.yaml> <profile>
At the end of this process you should have two files ready to go:
.envgenerated by the above python3 commandqueries.jsonthat specifies the queries for your application.
To deploy on Render, please follow these steps:
- Sign Up/Log In: If you don't have a Render account, you'll need to create one. If you already have one, just log in.
- Create New Service: Once you're logged in, click on the "New" button usually found on the dashboard and select "Web Service".
- Choose "Deploy an existing image from a registry" and click "Next"
- Specify Docker Image: In the "Image URL" fill in "vectara/vectara-answer" and click "Next"
- Choose a name for your deployment (e.g. "vectara-answer"), and if you need to pick a region or leave the default. Then pick you instance type.
- Click "Create Web Service"
- Click "Environment", then "Add Secret File": name the file
.env, and copy the contents of your local.envfile - Now click "Add Secret File" again and this time name the file
queries.json, and copy the contents of your localqueries.jsonfile - Click "Settings" and go to "Docker Command" and click "Edit", the put in the following command:
/bin/bash -c cp /etc/secrets/queries.json ./build/ && cp /etc/secrets/.env ./ && node server/index.js
Then click "Save Changes", and your application should now be deployed.
To be added soon
To be added soon
To be added soon