This repo uses Riza to validate snippets for documentation generated by Fern. Snippets are collected from a site's llms-full.txt
file. While this should be adaptable to any Fern docs site, this example runs snippets from the Elevenlabs and Cohere.
First, create or access your Riza organization.
Next you'll need to create a Custom Runtime for typescript or python so that Riza has the correct packages at runtime
package.json
{
"dependencies": {
"cohere-ai": "latest",
"dotenv": "latest",
"elevenlabs": "latest",
"express": "latest",
"express-ws": "latest",
"twilio": "latest",
"ws": "latest"
}
}
requirements.txt
pydub
elevenlabs
ffmpeg
python-dotenv
fastapi
openai
cohere
Once you have the custom runtimes built, grab the revision ID and an API key and add them to a .env
file in the root of this project.
You will also need API specific keys for cohere and elevenlabs.
This project uses Bun, installation instructions can be found here https://bun.sh/
Finally, install dependencies
bun install
And run the examples!
bun run index.ts provider language
- Where
provider
is eithercohere
orelevenlabs
- Where
langauge
is eithertypescript
orpython
If you want to get a fresh copy of the snippets, download the file from Elevenlabs or Cohere and replace the corresponding .txt
files in this repo