gistfile1.txt

docker run --rm --gpus all -p 11434:11434 ollama/ollama:latest

#with persistent storage of models
docker run -d --gpus=all -v ollama:/root/.ollama -p 11434:11434 ollama/ollama:latest

#if wanting to use webui
docker run -d -p 8080:8080 --add-host=host.docker.internal:host-gateway   -v open-webui:/app/backend/data   --name open-webui --restart always ghcr.io/open-webui/open-webui:main

#query models
firefox http://localhost:8080

curl -X POST http://localhost:11434/api/pull   -H "Content-Type: application/json"   -d '{"model": "llama2"}'

./llama.sh "tell me why life is important"

#!/bin/bash

# Check if a question was provided
if [ "$#" -lt 1 ]; then
  echo "Usage: $0 \"Your question here\""
  exit 1
fi

# Get the question from the first command-line argument
QUESTION="$1"

# Execute the curl command with the provided question in the JSON payload
time curl -X POST http://localhost:11434/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
        "model": "llama2",
        "messages": [
          {"role": "user", "content": "'"${QUESTION}"'"}
        ],
        "temperature": 0.7,
        "max_tokens": 1000
      }'