Update ci workflows (#1804)

docs/embedding_model.ipynb

@@ -0,0 +1,160 @@
+{
+ "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": [
+    "import subprocess\n",
+    "import time\n",
+    "import requests\n",
+    "\n",
+    "# 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",
+    "embedding_process = subprocess.Popen(\n",
+    "    [\n",
+    "        \"python\",\n",
+    "        \"-m\",\n",
+    "        \"sglang.launch_server\",\n",
+    "        \"--model-path\",\n",
+    "        \"Alibaba-NLP/gte-Qwen2-7B-instruct\",\n",
+    "        \"--port\",\n",
+    "        \"30010\",\n",
+    "        \"--host\",\n",
+    "        \"0.0.0.0\",\n",
+    "        \"--is-embedding\",\n",
+    "        \"--log-level\",\n",
+    "        \"error\",\n",
+    "    ],\n",
+    "    text=True,\n",
+    "    stdout=subprocess.DEVNULL,\n",
+    "    stderr=subprocess.DEVNULL,\n",
+    ")\n",
+    "\n",
+    "while True:\n",
+    "    try:\n",
+    "        response = requests.get(\n",
+    "            \"http://localhost:30010/v1/models\",\n",
+    "            headers={\"Authorization\": \"Bearer None\"},\n",
+    "        )\n",
+    "        if response.status_code == 200:\n",
+    "            break\n",
+    "    except requests.exceptions.RequestException:\n",
+    "        time.sleep(1)\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)"
+   ]
+  }
+ ],
+ "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
+}