|
| 1 | +{ |
| 2 | + "cells": [ |
| 3 | + { |
| 4 | + "cell_type": "markdown", |
| 5 | + "id": "87404224-b84b-409f-8683-c4a243d29722", |
| 6 | + "metadata": {}, |
| 7 | + "source": [ |
| 8 | + "# Kiara LLM endpoint\n", |
| 9 | + "In this notebook we will use yet experimental LLM infrastructure infrastructure. To use it, you must enter two enviroment variables `KIARA_API_KEY` and `KIARA_LLM_SERVER`. Also this method uses the OpenAI API and we just change the `base_url`." |
| 10 | + ] |
| 11 | + }, |
| 12 | + { |
| 13 | + "cell_type": "code", |
| 14 | + "execution_count": 1, |
| 15 | + "id": "752e974d-9aaf-44aa-80fb-01a042cf5774", |
| 16 | + "metadata": { |
| 17 | + "tags": [] |
| 18 | + }, |
| 19 | + "outputs": [ |
| 20 | + { |
| 21 | + "data": { |
| 22 | + "text/plain": [ |
| 23 | + "'1.90.0'" |
| 24 | + ] |
| 25 | + }, |
| 26 | + "execution_count": 1, |
| 27 | + "metadata": {}, |
| 28 | + "output_type": "execute_result" |
| 29 | + } |
| 30 | + ], |
| 31 | + "source": [ |
| 32 | + "import os\n", |
| 33 | + "import openai\n", |
| 34 | + "openai.__version__" |
| 35 | + ] |
| 36 | + }, |
| 37 | + { |
| 38 | + "cell_type": "code", |
| 39 | + "execution_count": 2, |
| 40 | + "id": "ab55e229-93b9-4e9b-974d-037002690bf0", |
| 41 | + "metadata": { |
| 42 | + "tags": [] |
| 43 | + }, |
| 44 | + "outputs": [], |
| 45 | + "source": [ |
| 46 | + "def prompt_kiara(message:str, model=\"ollama-llama3-3-70b\"):\n", |
| 47 | + " \"\"\"A prompt helper function that sends a message to kiara LLM server \n", |
| 48 | + " and returns only the text response.\n", |
| 49 | + " \"\"\"\n", |
| 50 | + " import os\n", |
| 51 | + " \n", |
| 52 | + " # convert message in the right format if necessary\n", |
| 53 | + " if isinstance(message, str):\n", |
| 54 | + " message = [{\"role\": \"user\", \"content\": message}]\n", |
| 55 | + " \n", |
| 56 | + " # setup connection to the LLM\n", |
| 57 | + " client = openai.OpenAI(base_url=os.environ.get('KIARA_LLM_SERVER') + \"api/\",\n", |
| 58 | + " api_key=os.environ.get('KIARA_API_KEY')\n", |
| 59 | + " )\n", |
| 60 | + " \n", |
| 61 | + " response = client.chat.completions.create(\n", |
| 62 | + " model=model,\n", |
| 63 | + " messages=message\n", |
| 64 | + " )\n", |
| 65 | + " \n", |
| 66 | + " # extract answer\n", |
| 67 | + " return response.choices[0].message.content" |
| 68 | + ] |
| 69 | + }, |
| 70 | + { |
| 71 | + "cell_type": "code", |
| 72 | + "execution_count": 3, |
| 73 | + "id": "a7654a20-a307-4b26-8d25-bef20b70224e", |
| 74 | + "metadata": { |
| 75 | + "tags": [] |
| 76 | + }, |
| 77 | + "outputs": [ |
| 78 | + { |
| 79 | + "data": { |
| 80 | + "text/plain": [ |
| 81 | + "\"It's nice to meet you. Is there something I can help you with or would you like to chat?\"" |
| 82 | + ] |
| 83 | + }, |
| 84 | + "execution_count": 3, |
| 85 | + "metadata": {}, |
| 86 | + "output_type": "execute_result" |
| 87 | + } |
| 88 | + ], |
| 89 | + "source": [ |
| 90 | + "prompt_kiara(\"Hi!\")" |
| 91 | + ] |
| 92 | + }, |
| 93 | + { |
| 94 | + "cell_type": "markdown", |
| 95 | + "id": "578e9edd-b58f-4fd0-a56d-1966105221dc", |
| 96 | + "metadata": {}, |
| 97 | + "source": [ |
| 98 | + "## Exercise\n", |
| 99 | + "List the models available in the endpoint and try them out by specifying them when calling `prompt_scadsai_llm()`." |
| 100 | + ] |
| 101 | + }, |
| 102 | + { |
| 103 | + "cell_type": "code", |
| 104 | + "execution_count": 4, |
| 105 | + "id": "05171ba7-a775-41c5-954d-7d4fc2b5b625", |
| 106 | + "metadata": {}, |
| 107 | + "outputs": [ |
| 108 | + { |
| 109 | + "name": "stdout", |
| 110 | + "output_type": "stream", |
| 111 | + "text": [ |
| 112 | + "ollama-llama3-3-70b\n", |
| 113 | + "vllm-baai-bge-m3\n", |
| 114 | + "vllm-deepseek-coder-33b-instruct\n", |
| 115 | + "vllm-deepseek-r1-distill-llama-70b\n", |
| 116 | + "vllm-llama-3-3-nemotron-super-49b-v1\n", |
| 117 | + "vllm-llama-4-scout-17b-16e-instruct\n", |
| 118 | + "vllm-meta-llama-llama-3-3-70b-instruct\n", |
| 119 | + "vllm-mistral-small-24b-instruct-2501\n", |
| 120 | + "vllm-multilingual-e5-large-instruct\n", |
| 121 | + "vllm-nvidia-llama-3-3-70b-instruct-fp8\n" |
| 122 | + ] |
| 123 | + } |
| 124 | + ], |
| 125 | + "source": [ |
| 126 | + "client = openai.OpenAI(base_url=os.environ.get('KIARA_LLM_SERVER') + \"api/\",\n", |
| 127 | + " api_key=os.environ.get('KIARA_API_KEY'))\n", |
| 128 | + "\n", |
| 129 | + "print(\"\\n\".join([model.id for model in client.models.list().data]))" |
| 130 | + ] |
| 131 | + }, |
| 132 | + { |
| 133 | + "cell_type": "code", |
| 134 | + "execution_count": null, |
| 135 | + "id": "7e810ee2-4d22-42f6-add5-532cf95b4b9c", |
| 136 | + "metadata": {}, |
| 137 | + "outputs": [], |
| 138 | + "source": [] |
| 139 | + } |
| 140 | + ], |
| 141 | + "metadata": { |
| 142 | + "kernelspec": { |
| 143 | + "display_name": "Python 3 (ipykernel)", |
| 144 | + "language": "python", |
| 145 | + "name": "python3" |
| 146 | + }, |
| 147 | + "language_info": { |
| 148 | + "codemirror_mode": { |
| 149 | + "name": "ipython", |
| 150 | + "version": 3 |
| 151 | + }, |
| 152 | + "file_extension": ".py", |
| 153 | + "mimetype": "text/x-python", |
| 154 | + "name": "python", |
| 155 | + "nbconvert_exporter": "python", |
| 156 | + "pygments_lexer": "ipython3", |
| 157 | + "version": "3.11.11" |
| 158 | + } |
| 159 | + }, |
| 160 | + "nbformat": 4, |
| 161 | + "nbformat_minor": 5 |
| 162 | +} |
0 commit comments