docs: azure openai quickstart (#155)

Added documentation for azure-openai as alternative quickstart

shoutout to @Techneaux for helping test this

Author: jjmachan

docs/guides/llms.ipynb

@@ -12,7 +12,9 @@
     "- [Completion LLMs Supported](https://api.python.langchain.com/en/latest/api_reference.html#module-langchain.llms)\n",
     "- [Chat based LLMs Supported](https://api.python.langchain.com/en/latest/api_reference.html#module-langchain.chat_models)\n",
     "\n",
-    "This guide will show you how to use another or LLM API for evaluation."
+    "This guide will show you how to use another or LLM API for evaluation.\n",
+    "\n",
+    "> **Note**: If your looking to use Azure OpenAI for evaluation checkout [this guide](./quickstart-azure-openai.ipynb)"
    ]
   },
   {
@@ -29,7 +31,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": null,
    "id": "a6d96660",
    "metadata": {},
    "outputs": [],
@@ -57,34 +59,34 @@
    "id": "f1fdb48b",
    "metadata": {},
    "source": [
-    "Now initialise `Faithfulness` with `gpt4`"
+    "Now lets replace the `llm` used in faithfulness with `gpt4`"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 2,
    "id": "307321ed",
    "metadata": {},
    "outputs": [],
    "source": [
-    "from ragas.metrics import Faithfulness\n",
+    "from ragas.metrics import faithfulness\n",
     "\n",
-    "faithfulness_gpt4 = Faithfulness(name=\"faithfulness_gpt4\", llm=gpt4, batch_size=3)"
+    "faithfulness.llm = gpt4"
    ]
   },
   {
    "cell_type": "markdown",
    "id": "1930dd49",
    "metadata": {},
    "source": [
-    "That's it!\n",
+    "That's it! faithfulness will now be using GPT-4 under the hood for evaluations.\n",
     "\n",
     "Now lets run the evaluations using the example from [quickstart](../quickstart.ipnb)."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 3,
    "id": "62c0eadb",
    "metadata": {},
    "outputs": [
@@ -98,7 +100,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "c55f09ffe1094e6190c255c09c0eb141",
+       "model_id": "9fb581d4057d4e70a0b70830b2f5f487",
        "version_major": 2,
        "version_minor": 0
       },
@@ -120,7 +122,7 @@
        "})"
       ]
      },
-     "execution_count": 6,
+     "execution_count": 3,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -135,31 +137,31 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 5,
    "id": "c4396f6e",
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "evaluating with [faithfulness_gpt4]\n"
+      "evaluating with [faithfulness]\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████████████████████████████████████████████████████| 10/10 [15:38<00:00, 93.84s/it]\n"
+      "100%|████████████████████████████████████████████████████████████| 2/2 [22:28<00:00, 674.38s/it]\n"
      ]
     },
     {
      "data": {
       "text/plain": [
-       "{'faithfulness_gpt4': 0.6594}"
+       "{'faithfulness': 0.7237}"
       ]
      },
-     "execution_count": 10,
+     "execution_count": 5,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -168,7 +170,7 @@
     "# evaluate\n",
     "from ragas import evaluate\n",
     "\n",
-    "result = evaluate(fiqa_eval[\"baseline\"], metrics=[faithfulness_gpt4])\n",
+    "result = evaluate(fiqa_eval[\"baseline\"], metrics=[faithfulness])\n",
     "\n",
     "result"
    ]