ollama-colab.ipynb

ollama-colab.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": [],
      "gpuType": "T4",
      "authorship_tag": "ABX9TyN36v4/9+7UW65X3MdevarM",
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    },
    "accelerator": "GPU"
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/gist/eramax/8533181ad841e4612041c42d154df003/ollama.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "KWH_unS29M1Q",
        "outputId": "fc3dd376-0899-4029-8147-75ab686763b8"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "  % Total    % Received % Xferd  Average Speed   Time    Time     Time  Current\n",
            "                                 Dload  Upload   Total   Spent    Left  Speed\n",
            "100  7983    0  7983    0     0  26910      0 --:--:-- --:--:-- --:--:-- 26969\n",
            ">>> Downloading ollama...\n",
            "############################################################################################# 100.0%\n",
            ">>> Installing ollama to /usr/local/bin...\n",
            ">>> Creating ollama user...\n",
            ">>> Adding current user to ollama group...\n",
            ">>> Creating ollama systemd service...\n",
            "WARNING: Unable to detect NVIDIA GPU. Install lspci or lshw to automatically detect and install NVIDIA CUDA drivers.\n",
            ">>> The Ollama API is now available at 0.0.0.0:11434.\n",
            ">>> Install complete. Run \"ollama\" from the command line.\n",
            "Requirement already satisfied: aiohttp in /usr/local/lib/python3.10/dist-packages (3.9.1)\n",
            "Collecting pyngrok\n",
            "  Downloading pyngrok-7.0.3-py3-none-any.whl (21 kB)\n",
            "Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp) (23.1.0)\n",
            "Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.10/dist-packages (from aiohttp) (6.0.4)\n",
            "Requirement already satisfied: yarl<2.0,>=1.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp) (1.9.4)\n",
            "Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from aiohttp) (1.4.0)\n",
            "Requirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.10/dist-packages (from aiohttp) (1.3.1)\n",
            "Requirement already satisfied: async-timeout<5.0,>=4.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp) (4.0.3)\n",
            "Requirement already satisfied: PyYAML in /usr/local/lib/python3.10/dist-packages (from pyngrok) (6.0.1)\n",
            "Requirement already satisfied: idna>=2.0 in /usr/local/lib/python3.10/dist-packages (from yarl<2.0,>=1.0->aiohttp) (3.6)\n",
            "Installing collected packages: pyngrok\n",
            "Successfully installed pyngrok-7.0.3\n"
          ]
        }
      ],
      "source": [
        "# Download and install ollama to the system\n",
        "!curl https://ollama.ai/install.sh | sh\n",
        "\n",
        "!pip install aiohttp pyngrok\n",
        "\n",
        "import os\n",
        "import asyncio\n",
        "\n",
        "# Set LD_LIBRARY_PATH so the system NVIDIA library\n",
        "os.environ.update({'LD_LIBRARY_PATH': '/usr/lib64-nvidia'})\n",
        "\n",
        "async def run_process(cmd):\n",
        "  print('>>> starting', *cmd)\n",
        "  p = await asyncio.subprocess.create_subprocess_exec(\n",
        "      *cmd,\n",
        "      stdout=asyncio.subprocess.PIPE,\n",
        "      stderr=asyncio.subprocess.PIPE,\n",
        "  )\n",
        "\n",
        "  async def pipe(lines):\n",
        "    async for line in lines:\n",
        "      print(line.strip().decode('utf-8'))\n",
        "\n",
        "  await asyncio.gather(\n",
        "      pipe(p.stdout),\n",
        "      pipe(p.stderr),\n",
        "  )"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "await asyncio.gather(\n",
        "    run_process(['ollama', 'serve']),\n",
        "    run_process(['ngrok', 'http', '--log', 'stderr', '11434']),\n",
        ")\n",
        "\n",
        "#in local machine : export OLLAMA_HOST=https://03c1-35-240-226-254.ngrok.io/"
      ],
      "metadata": {
        "id": "AW_QGAbkRbdF"
      },
      "execution_count": null,
      "outputs": []
    }
  ]
}