diff --git a/docs/howtos/customisations/gcp-vertexai.ipynb b/docs/howtos/customisations/gcp-vertexai.ipynb
new file mode 100644
index 000000000..7ddf68f15
--- /dev/null
+++ b/docs/howtos/customisations/gcp-vertexai.ipynb
@@ -0,0 +1,416 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "a6199b61-8084-4a2f-8488-2ddc4c260776",
+   "metadata": {},
+   "source": [
+    "# Using Vertext AI\n",
+    "\n",
+    "Vertex AI offers everything you need to build and use generative AI—from AI solutions, to Search and Conversation, to 100+ foundation models, to a unified AI platform. You get access to models like PaLM 2 which can be used to score your RAG responses and pipelines with Ragas instead of the default OpenAI.\n",
+    "\n",
+    "This tutorial will show you can you can use PaLM 2 with Ragas for evaluation."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "79986e4d-17e4-4e88-ad2e-ca2b34a63de9",
+   "metadata": {},
+   "source": [
+    ":::{Note}\n",
+    "this guide is for folks who are using the Amazon Bedrock endpoints. Check the [evaluation guide](../../getstarted/evaluation.md) if your using OpenAI endpoints.\n",
+    ":::"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "8bd757ae-51ee-4527-b2fb-0d0b88285939",
+   "metadata": {},
+   "source": [
+    "## Load Sample Dataset"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "0d3e6c99-c19c-44a1-8f05-4bde2de30866",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Found cached dataset fiqa (/home/jjmachan/.cache/huggingface/datasets/explodinggradients___fiqa/ragas_eval/1.0.0/3dc7b639f5b4b16509a3299a2ceb78bf5fe98ee6b5fee25e7d5e4d290c88efb8)\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "b0c4c79a44334e1198e1b7283e4532b5",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "  0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/plain": [
+       "DatasetDict({\n",
+       "    baseline: Dataset({\n",
+       "        features: ['question', 'ground_truths', 'answer', 'contexts'],\n",
+       "        num_rows: 30\n",
+       "    })\n",
+       "})"
+      ]
+     },
+     "execution_count": 1,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# data\n",
+    "from datasets import load_dataset\n",
+    "\n",
+    "fiqa_eval = load_dataset(\"explodinggradients/fiqa\", \"ragas_eval\")\n",
+    "fiqa_eval"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "4e67daaa-60e3-4584-8ec6-944c3c5a1a0c",
+   "metadata": {},
+   "source": [
+    "Now lets import the metrics we are going to use"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "42081210-3c0d-4e27-974a-ef152364a4ab",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from ragas.metrics import (\n",
+    "    context_precision,\n",
+    "    answer_relevancy, # AnswerRelevancy\n",
+    "    faithfulness,\n",
+    "    context_recall,\n",
+    ")\n",
+    "from ragas.metrics.critique import harmfulness\n",
+    "\n",
+    "# list of metrics we're going to use\n",
+    "metrics = [\n",
+    "    faithfulness,\n",
+    "    answer_relevancy,\n",
+    "    context_recall,\n",
+    "    context_precision,\n",
+    "    harmfulness\n",
+    "]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "90fa19c3-1356-412f-a39d-f9907c69a80e",
+   "metadata": {},
+   "source": [
+    "By default Ragas uses `ChatOpenAI` for evaluations, lets swap that out with `ChatVertextAI`. We also need to change the embeddings used for evaluations for `OpenAIEmbeddings` to `VertextAIEmbeddings` for metrices that need it, which in our case is `answer_relevancy`.\n",
+    "\n",
+    "Now in order to use the new `ChatVertextAI` llm instance with Ragas metrics, you have to create a new instance of `RagasLLM` using the `ragas.llms.LangchainLLM` wrapper. Its a simple wrapper around langchain that make Langchain LLM/Chat instances compatible with how Ragas metrics will use them."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "09ef783b-12dd-40e8-bdbf-4744e41038dd",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import google.auth\n",
+    "from langchain.chat_models import ChatVertexAI\n",
+    "from ragas.llms import LangchainLLM\n",
+    "from langchain.embeddings import VertexAIEmbeddings\n",
+    "\n",
+    "\n",
+    "\n",
+    "config = {\n",
+    "    \"project_id\": \"tmp-project-404003\",\n",
+    "}\n",
+    "\n",
+    "# authenticate to GCP\n",
+    "creds, _ = google.auth.default(quota_project_id=\"tmp-project-404003\")\n",
+    "# create Langchain LLM and Embeddings\n",
+    "chat = ChatVertexAI(credentials=creds)\n",
+    "vertextai_embeddings = VertexAIEmbeddings(credentials=creds)\n",
+    "\n",
+    "# create a wrapper around it\n",
+    "ragas_vertexai_llm = LangchainLLM(chat)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "90e739a1-dbb4-42ce-adc2-b8cf88ae7a58",
+   "metadata": {},
+   "source": [
+    "Now lets swap out the defaults with the VertexAI LLM and Embeddings we created."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "280464c1-dbef-4200-85ec-dc2a4bffee14",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "for m in metrics:\n",
+    "    # change LLM for metric\n",
+    "    m.__setattr__(\"llm\", ragas_vertexai_llm)\n",
+    "    \n",
+    "    # check if this metric needs embeddings\n",
+    "    if hasattr(m, \"embeddings\"):\n",
+    "        # if so change with VertexAI Embeddings\n",
+    "        m.__setattr__(\"embeddings\", vertextai_embeddings)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "27a34b9d-796e-4025-ba8e-a799f6ab3c6b",
+   "metadata": {},
+   "source": [
+    "## Evaluation\n",
+    "\n",
+    "Running the evalutation is as simple as calling evaluate on the `Dataset` with the metrics of your choice."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "5e739223-4e34-4dc0-9892-4625fdea7489",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "evaluating with [faithfulness]\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "100%|█████████████████████████████████████████████████████████████| 1/1 [00:04<00:00,  4.53s/it]\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "evaluating with [answer_relevancy]\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "100%|█████████████████████████████████████████████████████████████| 1/1 [00:03<00:00,  3.88s/it]\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "evaluating with [context_recall]\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "100%|█████████████████████████████████████████████████████████████| 1/1 [00:02<00:00,  2.71s/it]\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "evaluating with [context_precision]\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "100%|█████████████████████████████████████████████████████████████| 1/1 [00:00<00:00,  1.05it/s]\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "evaluating with [harmfulness]\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "100%|█████████████████████████████████████████████████████████████| 1/1 [00:00<00:00,  1.02it/s]\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "{'faithfulness': 1.0000, 'answer_relevancy': 0.9113, 'context_recall': 0.0000, 'context_precision': 0.0000, 'harmfulness': 0.0000}"
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from ragas import evaluate\n",
+    "import nest_asyncio # CHECK NOTES\n",
+    "\n",
+    "# NOTES: Only used when running on a jupyter notebook, otherwise comment or remove this function. \n",
+    "nest_asyncio.apply()  \n",
+    "\n",
+    "result = evaluate(\n",
+    "    fiqa_eval[\"baseline\"].select(range(1)), # using 1 as example due to quota constrains\n",
+    "    metrics=metrics,\n",
+    ")\n",
+    "\n",
+    "result"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "960f88fc-c90b-4ac6-8e97-252edd2f1661",
+   "metadata": {},
+   "source": [
+    "and there you have the it, all the scores you need. `ragas_score` gives you a single metric that you can use while the other onces measure the different parts of your pipeline.\n",
+    "\n",
+    "now if we want to dig into the results and figure out examples where your pipeline performed worse or really good you can easily convert it into a pandas array and use your standard analytics tools too!"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "bc72c682-b0c0-4314-9da5-9b22aae722a4",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>question</th>\n",
+       "      <th>contexts</th>\n",
+       "      <th>answer</th>\n",
+       "      <th>ground_truths</th>\n",
+       "      <th>faithfulness</th>\n",
+       "      <th>answer_relevancy</th>\n",
+       "      <th>context_recall</th>\n",
+       "      <th>context_precision</th>\n",
+       "      <th>harmfulness</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>How to deposit a cheque issued to an associate...</td>\n",
+       "      <td>[Just have the associate sign the back and the...</td>\n",
+       "      <td>\\nThe best way to deposit a cheque issued to a...</td>\n",
+       "      <td>[Have the check reissued to the proper payee.J...</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0.911332</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                                            question  \\\n",
+       "0  How to deposit a cheque issued to an associate...   \n",
+       "\n",
+       "                                            contexts  \\\n",
+       "0  [Just have the associate sign the back and the...   \n",
+       "\n",
+       "                                              answer  \\\n",
+       "0  \\nThe best way to deposit a cheque issued to a...   \n",
+       "\n",
+       "                                       ground_truths  faithfulness  \\\n",
+       "0  [Have the check reissued to the proper payee.J...           1.0   \n",
+       "\n",
+       "   answer_relevancy  context_recall  context_precision  harmfulness  \n",
+       "0          0.911332             0.0                0.0            0  "
+      ]
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df = result.to_pandas()\n",
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "c08f613d-880c-4e13-9716-05ce23fa4576",
+   "metadata": {},
+   "source": [
+    "And thats it!\n",
+    "\n",
+    "if you have any suggestion/feedbacks/things your not happy about, please do share it in the [issue section](https://github.com/explodinggradients/ragas/issues). We love hearing from you 😁"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "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": "3.10.12"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
diff --git a/docs/howtos/customisations/index.md b/docs/howtos/customisations/index.md
index f56c4ee1d..0c8e35357 100644
--- a/docs/howtos/customisations/index.md
+++ b/docs/howtos/customisations/index.md
@@ -6,4 +6,5 @@ How to customize Ragas for your needs
 llms.ipynb
 azure-openai.ipynb
 aws-bedrock.ipynb
+gcp-vertexai.ipynb
 :::