Google Colab Notebooks for LLMs, Embedders and VectorDBs (#821)

notebooks/pinecone.ipynb

@@ -0,0 +1,181 @@
+{
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "b02n_zJ_hl3d"
+      },
+      "source": [
+        "## Cookbook for using PineconeDB with Embedchain"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "gyJ6ui2vhtMY"
+      },
+      "source": [
+        "### Step-1: Install embedchain package"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "-NbXjAdlh0vJ"
+      },
+      "outputs": [],
+      "source": [
+        "!pip install embedchain"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "nGnpSYAAh2bQ"
+      },
+      "source": [
+        "### Step-2: Set environment variables needed for Pinecone and install the dependencies.\n",
+        "\n",
+        "You can find this env variable on your [OpenAI dashboard](https://platform.openai.com/account/api-keys) and [Pinecone dashboard](https://app.pinecone.io/). Now lets install the dependencies needed for Pinecone."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "-MUFRfxV7Jk7"
+      },
+      "outputs": [],
+      "source": [
+        "!pip install --upgrade 'embedchain[pinecone]'"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "0fBdQ9GAiRvK"
+      },
+      "outputs": [],
+      "source": [
+        "import os\n",
+        "from embedchain import App\n",
+        "\n",
+        "os.environ[\"OPENAI_API_KEY\"] = \"sk-xxx\"\n",
+        "os.environ[\"PINECONE_API_KEY\"] = \"xxx\"\n",
+        "os.environ[\"PINECONE_ENV\"] = \"xxx\""
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "Ns6RhPfbiitr"
+      },
+      "source": [
+        "### Step-3: Define your Vector Database config"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "S9CkxVjriotB"
+      },
+      "outputs": [],
+      "source": [
+        "config = \"\"\"\n",
+        "vectordb:\n",
+        "  provider: pinecone\n",
+        "  config:\n",
+        "    metric: cosine\n",
+        "    vector_dimension: 768\n",
+        "    collection_name: pc-index\n",
+        "\"\"\"\n",
+        "\n",
+        "# Write the multi-line string to a YAML file\n",
+        "with open('pinecone.yaml', 'w') as file:\n",
+        "    file.write(config)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "PGt6uPLIi1CS"
+      },
+      "source": [
+        "### Step-4 Create embedchain app based on the config"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "Amzxk3m-i3tD"
+      },
+      "outputs": [],
+      "source": [
+        "app = App.from_config(yaml_path=\"pinecone.yaml\")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "XNXv4yZwi7ef"
+      },
+      "source": [
+        "### Step-5: Add data sources to your app"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "Sn_0rx9QjIY9"
+      },
+      "outputs": [],
+      "source": [
+        "app.add(\"https://www.forbes.com/profile/elon-musk\")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "_7W6fDeAjMAP"
+      },
+      "source": [
+        "### Step-6: All set. Now start asking questions related to your data"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "cvIK7dWRjN_f"
+      },
+      "outputs": [],
+      "source": [
+        "while(True):\n",
+        "    question = input(\"Enter question: \")\n",
+        "    if question in ['q', 'exit', 'quit']:\n",
+        "        break\n",
+        "    answer = app.query(question)\n",
+        "    print(answer)"
+      ]
+    }
+  ],
+  "metadata": {
+    "colab": {
+      "provenance": []
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}