add tracing

bootcamp/tutorials/integration/evaluation_with_phoenix.ipynb

@@ -444,16 +444,65 @@
     "  - **QA Explanation**: Details why an answer is correct or incorrect."
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Phoenix Tracing Overview\n",
+    "\n",
+    "Phoenix provides **OTEL-compatible tracing** for LLM applications, with integrations for frameworks like **Langchain**, **LlamaIndex**, and SDKs such as **OpenAI** and **Mistral**. Tracing captures the entire request flow, offering insights into:\n",
+    "\n",
+    "- **Application Latency**: Identify and optimize slow LLM invocations and component performance.\n",
+    "- **Token Usage**: Break down token consumption for cost optimization.\n",
+    "- **Runtime Exceptions**: Capture critical issues like rate-limiting.\n",
+    "- **Retrieved Documents**: Analyze document retrieval, score, and order.\n",
+    "\n",
+    "By utilizing Phoenix’s tracing, you can **identify bottlenecks**, **optimize resources**, and **ensure system reliability** across various frameworks and languages."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "WARNI [phoenix.session.session] Existing running Phoenix instance detected! Shutting it down and starting a new instance...\n",
+      "WARNI [opentelemetry.instrumentation.instrumentor] Attempting to instrument while already instrumented\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "🌍 To view the Phoenix app in your browser, visit http://localhost:6006/\n",
+      "📖 For more information on how to use Phoenix, check out https://docs.arize.com/phoenix\n"
+     ]
+    }
+   ],
+   "source": [
+    "import phoenix as px\n",
+    "from phoenix.trace.openai import OpenAIInstrumentor\n",
+    "\n",
+    "# To view traces in Phoenix, you will first have to start a Phoenix server. You can do this by running the following:\n",
+    "session = px.launch_app()\n",
+    "\n",
+    "# Initialize OpenAI auto-instrumentation\n",
+    "OpenAIInstrumentor().instrument()"
+   ]
+  },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 11,
    "metadata": {},
    "outputs": [
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "run_evals |██████████| 6/6 (100.0%) | ⏳ 00:04<00:00 |  1.38it/s\n"
+      "run_evals |██████████| 6/6 (100.0%) | ⏳ 00:04<00:00 |  1.46it/s\n"
      ]
     }
    ],