Spaces:
Running
Running
File size: 5,621 Bytes
5db25ba 46ed764 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 |
{
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "view-in-github",
"colab_type": "text"
},
"source": [
"<a href=\"https://colab.research.google.com/github/almutareb/InnovationPathfinderAI/blob/agent_notebook/mixtral_ollama_public_api.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": {
"id": "hdHmLCO48n-H"
},
"outputs": [],
"source": [
"# https://github.com/jmorganca/ollama/blob/main/examples/jupyter-notebook/ollama.ipynb"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "o5Q6OmcN0mkS",
"outputId": "c7a663c4-b1d8-4354-d1f2-fac8f503f4d3"
},
"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 8423 0 8423 0 0 8293 0 --:--:-- 0:00:01 --:--:-- 8298>>> Downloading ollama...\n",
"100 8423 0 8423 0 0 7756 0 --:--:-- 0:00:01 --:--:-- 7763\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",
"System has not been booted with systemd as init system (PID 1). Can't operate.\n",
"Failed to connect to bus: Host is down\n"
]
}
],
"source": [
"!curl https://ollama.ai/install.sh | sh\n",
"!command -v systemctl >/dev/null && sudo systemctl stop ollama"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "TXtmzrel194r"
},
"outputs": [],
"source": [
"!pip install aiohttp pyngrok -q"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "GLPqSWXT3QBg",
"colab": {
"base_uri": "https://localhost:8080/"
},
"outputId": "a7542b67-3287-4ce5-8459-2e86d8ec7dfd"
},
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": []
}
],
"source": [
"from pyngrok import ngrok\n",
"from google.colab import userdata\n",
"\n",
"# https://dashboard.ngrok.com/get-started/your-authtoken\n",
"NGROK_TOKEN = userdata.get('NGROK_TOKEN')\n",
"ngrok.set_auth_token(\"NGROK_TOKEN\")"
]
},
{
"cell_type": "code",
"source": [
"\n",
"\n",
"import os\n",
"import asyncio\n",
"from aiohttp import ClientSession\n",
"from google.colab import userdata\n",
"\n",
"# Set LD_LIBRARY_PATH so the system NVIDIA library becomes preferred\n",
"# over the built-in library. This is particularly important for\n",
"# Google Colab which installs older drivers\n",
"os.environ.update({'LD_LIBRARY_PATH': '/usr/lib64-nvidia'})\n",
"NGROK_TOKEN = userdata.get('NGROK_TOKEN')\n",
"ngrok.set_auth_token(\"NGROK_TOKEN\")\n",
"\n",
"async def run(cmd):\n",
" '''\n",
" run is a helper function to run subcommands asynchronously.\n",
" '''\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",
" )\n",
"\n",
"\n",
"await asyncio.gather(\n",
" run(['ollama', 'serve']),\n",
" run(['ngrok', 'config', 'add-authtoken', NGROK_TOKEN]),\n",
" run(['ngrok', 'http', '--log', 'stderr', '11434']),\n",
" # run([\"ollama\",\"run\",\"llama2\"]),\n",
" run([\"ollama\",\"run\",\"mistral\"]),\n",
")"
],
"metadata": {
"id": "u1PG3y83Z-u5"
},
"execution_count": null,
"outputs": []
}
],
"metadata": {
"colab": {
"provenance": [],
"machine_shape": "hm",
"gpuType": "T4",
"authorship_tag": "ABX9TyMLapRySjkHA++gSoAkRSHn",
"include_colab_link": true
},
"kernelspec": {
"display_name": "Python 3",
"name": "python3"
},
"language_info": {
"name": "python"
},
"accelerator": "GPU"
},
"nbformat": 4,
"nbformat_minor": 0
}
|