{
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "b02n_zJ_hl3d"
      },
      "source": [
        "## Cookbook for using Hugging Face Hub with Embedchain"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "gyJ6ui2vhtMY"
      },
      "source": [
        "### Step-1: Install embedchain package"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 1000
        },
        "id": "-NbXjAdlh0vJ",
        "outputId": "35ddc904-8067-44cf-dcc9-3c8b4cd29989"
      },
      "outputs": [],
      "source": [
        "!pip install embedchain"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "nGnpSYAAh2bQ"
      },
      "source": [
        "### Step-2: Set Hugging Face Hub related environment variables and install dependencies\n",
        "\n",
        "You can find your `HUGGINGFACE_ACCESS_TOKEN` key on your [Hugging Face Hub dashboard](https://huggingface.co/settings/tokens) and install the dependencies"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "VfDNZJCqNfqo",
        "outputId": "34894d35-7142-42ee-8564-2e9f718afcbb"
      },
      "outputs": [],
      "source": [
        "!pip install embedchain[huggingface-hub]"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "SCNT8khqcR3G",
        "outputId": "b789ee77-ef50-4330-8ac6-5da645dc36d6"
      },
      "outputs": [],
      "source": [
        "!pip install embedchain[opensource]"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "0fBdQ9GAiRvK"
      },
      "outputs": [],
      "source": [
        "import os\n",
        "from embedchain import App\n",
        "\n",
        "os.environ[\"HUGGINGFACE_ACCESS_TOKEN\"] = \"hf_xxx\""
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "Ns6RhPfbiitr"
      },
      "source": [
        "### Step-3: Define your llm and embedding model config"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "S9CkxVjriotB"
      },
      "outputs": [],
      "source": [
        "config = \"\"\"\n",
        "llm:\n",
        "  provider: huggingface\n",
        "  config:\n",
        "    model: 'google/flan-t5-xxl'\n",
        "    temperature: 0.5\n",
        "    max_tokens: 1000\n",
        "    top_p: 0.8\n",
        "    stream: false\n",
        "\n",
        "embedder:\n",
        "  provider: huggingface\n",
        "  config:\n",
        "    model: 'sentence-transformers/all-mpnet-base-v2'\n",
        "\"\"\"\n",
        "\n",
        "# Write the multi-line string to a YAML file\n",
        "with open('huggingface.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=\"huggingface.yaml\")"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "XNXv4yZwi7ef"
      },
      "source": [
        "### Step-5: Add data sources to your app"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 70
        },
        "id": "Sn_0rx9QjIY9",
        "outputId": "3c2a803a-3a93-4b0d-a6ae-17ae3c96c3c2"
      },
      "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": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "cvIK7dWRjN_f",
        "outputId": "47a89d1c-b322-495c-822a-6c2ecef894d2"
      },
      "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)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "HvZVn6gU5xB_"
      },
      "outputs": [],
      "source": []
    }
  ],
  "metadata": {
    "colab": {
      "provenance": []
    },
    "kernelspec": {
      "display_name": "Python 3",
      "name": "python3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 0
}