{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Embedding Model"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Launch A Server"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Embedding server is ready. Proceeding with the next steps.\n"
     ]
    }
   ],
   "source": [
    "# Equivalent to running this in the shell:\n",
    "# python -m sglang.launch_server --model-path Alibaba-NLP/gte-Qwen2-7B-instruct --port 30010 --host 0.0.0.0 --is-embedding --log-level error\n",
    "from sglang.utils import execute_shell_command, wait_for_server, terminate_process\n",
    "\n",
    "embedding_process = execute_shell_command(\"\"\"\n",
    "python -m sglang.launch_server --model-path Alibaba-NLP/gte-Qwen2-7B-instruct \\\n",
    "    --port 30010 --host 0.0.0.0 --is-embedding --log-level error\n",
    "\"\"\")\n",
    "\n",
    "wait_for_server(\"http://localhost:30010\")\n",
    "\n",
    "print(\"Embedding server is ready. Proceeding with the next steps.\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Use Curl"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[0.0083160400390625, 0.0006804466247558594, -0.00809478759765625, -0.0006995201110839844, 0.0143890380859375, -0.0090179443359375, 0.01238250732421875, 0.00209808349609375, 0.0062103271484375, -0.003047943115234375]\n"
     ]
    }
   ],
   "source": [
    "# Get the first 10 elements of the embedding\n",
    "\n",
    "! curl -s http://localhost:30010/v1/embeddings \\\n",
    "  -H \"Content-Type: application/json\" \\\n",
    "  -H \"Authorization: Bearer None\" \\\n",
    "  -d '{\"model\": \"Alibaba-NLP/gte-Qwen2-7B-instruct\", \"input\": \"Once upon a time\"}' \\\n",
    "  | python3 -c \"import sys, json; print(json.load(sys.stdin)['data'][0]['embedding'][:10])\""
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Using OpenAI Compatible API"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[0.00603485107421875, -0.0190582275390625, -0.01273345947265625, 0.01552581787109375, 0.0066680908203125, -0.0135955810546875, 0.01131439208984375, 0.0013713836669921875, -0.0089874267578125, 0.021759033203125]\n"
     ]
    }
   ],
   "source": [
    "import openai\n",
    "\n",
    "client = openai.Client(\n",
    "    base_url=\"http://127.0.0.1:30010/v1\", api_key=\"None\"\n",
    ")\n",
    "\n",
    "# Text embedding example\n",
    "response = client.embeddings.create(\n",
    "    model=\"Alibaba-NLP/gte-Qwen2-7B-instruct\",\n",
    "    input=\"How are you today\",\n",
    ")\n",
    "\n",
    "embedding = response.data[0].embedding[:10]\n",
    "print(embedding)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "terminate_process(embedding_process)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "AlphaMeemory",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.11.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}