{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "view-in-github"
   },
   "source": [
    "<a href=\"https://colab.research.google.com/github/R3gm/ConversaDocs/blob/main/ConversaDocs_Colab.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "EnzlcRZycXnr"
   },
   "source": [
    "# ConversaDocs\n",
    "\n",
    "`Chat with your documents using Llama 2, Falcon or OpenAI`\n",
    "\n",
    "- You can upload multiple documents at once to a single database.\n",
    "- Every time a new database is created, the previous one is deleted.\n",
    "- For maximum privacy, you can click \"Load LLAMA GGUF Model\" to use a Llama 2 model. By default, the model llama-2_7B-Chat is loaded.\n",
    "\n",
    "Program that enables seamless interaction with your documents through an advanced vector database and the power of Large Language Model (LLM) technology.\n",
    "\n",
    "| Description | Link |\n",
    "| ----------- | ---- |\n",
    "| 📙 Colab Notebook | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/R3gm/ConversaDocs/blob/main/ConversaDocs_Colab.ipynb) |\n",
    "| 🎉 Repository | [![GitHub Repository](https://img.shields.io/badge/GitHub-Repository-black?style=flat-square&logo=github)](https://github.com/R3gm/ConversaDocs/) |\n",
    "| 🚀 Online Demo | [![Hugging Face Spaces](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Spaces-blue)](https://huggingface.co/spaces/r3gm/ConversaDocs) |\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "S5awiNy-A50W"
   },
   "outputs": [],
   "source": [
    "!git clone https://github.com/R3gm/ConversaDocs.git\n",
    "%cd ConversaDocs\n",
    "!pip install -r requirements.txt"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "_EShTkcgAOWa"
   },
   "source": [
    "Install llama-cpp-python, whether for use on a GPU or solely on a CPU."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "id": "fyPLgbJW95ah"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "CUDA is not available on this system.\n"
     ]
    }
   ],
   "source": [
    "import torch\n",
    "import os\n",
    "if torch.cuda.is_available():\n",
    "    print(\"CUDA is available on this system.\")\n",
    "    os.system('CMAKE_ARGS=\"-DLLAMA_CUBLAS=on\" FORCE_CMAKE=1 pip install llama-cpp-python==0.1.78 --force-reinstall --upgrade --no-cache-dir --verbose')\n",
    "else:\n",
    "    print(\"CUDA is not available on this system.\")\n",
    "    os.system('pip install llama-cpp-python==0.1.78')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "jLfxiOyMEcGF"
   },
   "source": [
    "`RESTART THE RUNTIME` before executing the next cell."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "id": "2F2VGAJtEbb3"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[WinError 3] The system cannot find the path specified: '/content/ConversaDocs'\n",
      "C:\\Users\\Siong Huat\\Project\\ConversaDocs\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Traceback (most recent call last):\n",
      "  File \"app.py\", line 13, in <module>\n",
      "    import gradio as gr\n",
      "ModuleNotFoundError: No module named 'gradio'\n"
     ]
    }
   ],
   "source": [
    "# RUN APP\n",
    "%cd /content/ConversaDocs\n",
    "!python app.py"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "3aEEcmchZIlf"
   },
   "source": [
    "Open the `public URL` when it appears"
   ]
  }
 ],
 "metadata": {
  "accelerator": "GPU",
  "colab": {
   "gpuType": "T4",
   "include_colab_link": true,
   "provenance": [],
   "toc_visible": true
  },
  "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": "3.8.18"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}