chore: add Semantic Kernel tracing example

Author: gustavocidornelas

examples/tracing/semantic-kernel/semantic_kernel.ipynb

@@ -0,0 +1,175 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "2722b419",
+   "metadata": {},
+   "source": [
+    "[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/openlayer-ai/openlayer-python/blob/main/examples/tracing/semantic-kernel/semantic_kernel.ipynb)\n",
+    "\n",
+    "\n",
+    "# <a id=\"top\">Semantic Kernel quickstart</a>\n",
+    "\n",
+    "This notebook shows how to export traces captured by [Semantic Kernel](https://learn.microsoft.com/en-us/semantic-kernel/overview/) to Openlayer. The integration is done via the Openlayer's [OpenTelemetry endpoint](https://www.openlayer.com/docs/integrations/opentelemetry)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "020c8f6a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!pip install openlit semantic-kernel"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "75c2a473",
+   "metadata": {},
+   "source": [
+    "## 1. Set the environment variables"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "f3f4fa13",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "\n",
+    "os.environ[\"OPENAI_API_KEY\"] = \"YOUR_OPENAI_API_KEY_HERE\"\n",
+    "\n",
+    "# Env variables pointing to Openlayer's OpenTelemetry endpoint\n",
+    "os.environ[\"OTEL_EXPORTER_OTLP_ENDPOINT\"] = \"https://api.openlayer.com/v1/otel\"\n",
+    "os.environ[\"OTEL_EXPORTER_OTLP_HEADERS\"] = \"Authorization=Bearer YOUR_OPENLAYER_API_KEY_HERE, x-bt-parent=pipeline_id:YOUR_OPENLAYER_PIPELINE_ID_HERE\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "9758533f",
+   "metadata": {},
+   "source": [
+    "## 2. Initialize OpenLIT and Semantic Kernel"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "c35d9860-dc41-4f7c-8d69-cc2ac7e5e485",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import openlit\n",
+    "\n",
+    "openlit.init()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "9c0d5bae",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from semantic_kernel import Kernel\n",
+    "\n",
+    "kernel = Kernel()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "72a6b954",
+   "metadata": {},
+   "source": [
+    "## 3. Use LLMs as usual\n",
+    "\n",
+    "That's it! Now you can continue using LLMs and workflows as usual. The trace data is automatically exported to Openlayer and you can start creating tests around it."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "e00c1c79",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from semantic_kernel.connectors.ai.open_ai import OpenAIChatCompletion\n",
+    "\n",
+    "kernel.add_service(\n",
+    "    OpenAIChatCompletion(ai_model_id=\"gpt-4o-mini\"),\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "abaf6987-c257-4f0d-96e7-3739b24c7206",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from semantic_kernel.prompt_template import InputVariable, PromptTemplateConfig\n",
+    "\n",
+    "prompt = \"\"\"{{$input}}\n",
+    "Please provide a concise response to the question above.\n",
+    "\"\"\"\n",
+    "\n",
+    "prompt_template_config = PromptTemplateConfig(\n",
+    "    template=prompt,\n",
+    "    name=\"question_answerer\",\n",
+    "    template_format=\"semantic-kernel\",\n",
+    "    input_variables=[\n",
+    "        InputVariable(name=\"input\", description=\"The question from the user\", is_required=True),\n",
+    "    ]\n",
+    ")\n",
+    "\n",
+    "summarize = kernel.add_function(\n",
+    "    function_name=\"answerQuestionFunc\",\n",
+    "    plugin_name=\"questionAnswererPlugin\",\n",
+    "    prompt_template_config=prompt_template_config,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "49c606ac",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "await kernel.invoke(summarize, input=\"What's the meaning of life?\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f0377af7",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "semantic-kernel-2",
+   "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": "3.10.16"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}