chore: add Vertex AI example

Author: gustavocidornelas

examples/tracing/langchain/langchain_callback.ipynb

@@ -81,7 +81,7 @@
    "id": "76a350b4",
    "metadata": {},
    "source": [
-    "Now, you can pass the `openlayer_handler` as a callback to LLM's or chain invokations."
+    "Now, you can pass the `openlayer_handler` as a callback to LLM's or chain invocations."
    ]
   },
   {
@@ -119,7 +119,7 @@
    "id": "9a702ad1-da68-4757-95a6-4661ddaef251",
    "metadata": {},
    "source": [
-    "That's it! Now your data is being streamed to Openlayer after every invokation."
+    "That's it! Now your data is being streamed to Openlayer after every invocation."
    ]
   },
   {
@@ -147,7 +147,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.6"
+   "version": "3.9.18"
   }
  },
  "nbformat": 4,

examples/tracing/ollama/ollama_tracing.ipynb

@@ -74,7 +74,7 @@
    "source": [
     "## 3. Use an Ollama model with LangChain\n",
     "\n",
-    "Now, you can pass the `openlayer_handler` as a callback to LLM's or chain invokations."
+    "Now, you can pass the `openlayer_handler` as a callback to LLM's or chain invocations."
    ]
   },
   {
@@ -115,7 +115,7 @@
    "id": "9a702ad1-da68-4757-95a6-4661ddaef251",
    "metadata": {},
    "source": [
-    "That's it! Now your data is being streamed to Openlayer after every invokation."
+    "That's it! Now your data is being streamed to Openlayer after every invocation."
    ]
   },
   {
@@ -143,7 +143,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.19"
+   "version": "3.9.18"
   }
  },
  "nbformat": 4,

examples/tracing/vertex-ai/vertex_ai_tracing.ipynb

@@ -0,0 +1,154 @@
+{
+ "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/vertex-ai/vertex_ai_tracing.ipynb)\n",
+    "\n",
+    "\n",
+    "# <a id=\"top\">Vertex AI tracing</a>\n",
+    "\n",
+    "This notebook illustrates how use Openlayer's callback handler to trace calls to Vertex AI Gemini models. \n",
+    "\n",
+    "To use the integration you must:\n",
+    "\n",
+    "- Have your Vertex AI credentials configured for your environment (gcloud, workload identity, etc.)\n",
+    "- Store the path to a service account JSON file as the `GOOGLE_APPLICATION_CREDENTIALS` environment variable."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "020c8f6a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!pip install openlayer langchain-google-vertexai"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "75c2a473",
+   "metadata": {},
+   "source": [
+    "## 1. Set the environment variables"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f3f4fa13",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "\n",
+    "# Openlayer env variables\n",
+    "os.environ[\"OPENLAYER_API_KEY\"] = \"YOUR_OPENLAYER_API_KEY_HERE\"\n",
+    "os.environ[\"OPENLAYER_INFERENCE_PIPELINE_ID\"] = \"YOUR_OPENLAYER_INFERENCE_PIPELINE_ID_HERE\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "9758533f",
+   "metadata": {},
+   "source": [
+    "## 2. Instantiate the `OpenlayerHandler`"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e60584fa",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from openlayer.lib.integrations import langchain_callback\n",
+    "\n",
+    "openlayer_handler = langchain_callback.OpenlayerHandler()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "76a350b4",
+   "metadata": {},
+   "source": [
+    "## 3. Use a Vertex AI model with LangChain\n",
+    "\n",
+    "Now, you can pass the `openlayer_handler` as a callback to LLM's or chain invocations."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e00c1c79",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_google_vertexai import ChatVertexAI"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "abaf6987-c257-4f0d-96e7-3739b24c7206",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "chat = ChatVertexAI(\n",
+    "    model=\"gemini-1.5-flash-001\",\n",
+    "    callbacks=[openlayer_handler]\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "4123669f-aa28-47b7-8d46-ee898aba99e8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "chat.invoke(\"What's the meaning of life?\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "9a702ad1-da68-4757-95a6-4661ddaef251",
+   "metadata": {},
+   "source": [
+    "That's it! Now your data is being streamed to Openlayer after every invocation."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a3092828-3fbd-4f12-bae7-8de7f7319ff0",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "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": "3.9.18"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}