allora-worker

Install requirements

sudo apt update && sudo apt upgrade -y
sudo apt install jq -y

# install docker
curl -fsSL https://download.docker.com/linux/ubuntu/gpg | sudo gpg --dearmor -o /usr/share/keyrings/docker-archive-keyring.gpg

echo "deb [arch=$(dpkg --print-architecture) signed-by=/usr/share/keyrings/docker-archive-keyring.gpg] https://download.docker.com/linux/ubuntu $(lsb_release -cs) stable" | sudo tee /etc/apt/sources.list.d/docker.list > /dev/null

sudo apt-get update
sudo apt-get install docker-ce docker-ce-cli containerd.io
docker version

# install docker-compose
VER=$(curl -s https://api.github.com/repos/docker/compose/releases/latest | grep tag_name | cut -d '"' -f 4)

curl -L "https://github.com/docker/compose/releases/download/"$VER"/docker-compose-$(uname -s)-$(uname -m)" -o /usr/local/bin/docker-compose

chmod +x /usr/local/bin/docker-compose
docker-compose --version

request some faucet from the Allora Testnet Faucet

Stop the old version

If you've previously run the old version and want to stop it before proceeding, follow these commands

cd ~
rm -r ~/allora-worker/
docker stop custom-inference custom-worker custom-worker-0 custom-worker-1
docker container prune -f
docker rmi custom-inference

Run the custom model

Create an account and obtain an Upshot ApiKey here
Clone the git repository

git clone https://github.com/sarox0987/allora-worker.git
cd allora-worker

Run the bash script

bash run.sh

Index: Set your worker index.(the index gives you the ability to run multiple workers on one server)
Mnemonic Phrase: Import you menmonic phrase
Upshot ApiKey: Import your upshot apikey

make sure both custom-worker-0 & custom-inference containers are running with docker ps

check the worker container with docker logs -f custom-worker-0 command

make sure custom-inference returns correct response

curl http://localhost:8001/inference/ETH
curl http://localhost:8001/inference/MEME
curl http://localhost:8001/inference/ELECTION

[DEPRECATED] Run with hugging model and pass your mnemonic phrase to it

curl -LOs https://raw.githubusercontent.com/sarox0987/allora-worker/main/hugging-allora.sh && bash ./hugging-allora.sh

make sure both hugging-worker & hugging-inference containers are running with docker ps

check the worker container with docker logs -f hugging-worker command

make sure hugging-inference is responsive

curl http://localhost:8002/inference/ETH