{"cells": [{"cell_type": "markdown", "id": "302934307671667531413257853548643485645", "metadata": {}, "source": ["# Gradio Demo: mcp_tools"]}, {"cell_type": "code", "execution_count": null, "id": "272996653310673477252411125948039410165", "metadata": {}, "outputs": [], "source": ["!pip install -q gradio "]}, {"cell_type": "code", "execution_count": null, "id": "288918539441861185822528903084949547379", "metadata": {}, "outputs": [], "source": ["# Downloading files from the demo repo\n", "import os\n", "!wget -q https://github.com/gradio-app/gradio/raw/main/demo/mcp_tools/cheetah.jpg"]}, {"cell_type": "code", "execution_count": null, "id": "44380577570523278879349135829904343037", "metadata": {}, "outputs": [], "source": ["import numpy as np\n", "import gradio as gr\n", "from pathlib import Path\n", "import os\n", "from PIL import Image\n", "\n", "def prime_factors(n: str):\n", " \"\"\"\n", " Compute the prime factorization of a positive integer.\n", "\n", " Args:\n", " n (str): The integer to factorize. Must be greater than 1.\n", " \"\"\"\n", " n_int = int(n)\n", " if n_int <= 1:\n", " raise ValueError(\"Input must be an integer greater than 1.\")\n", "\n", " factors = []\n", " while n_int % 2 == 0:\n", " factors.append(2)\n", " n_int //= 2\n", "\n", " divisor = 3\n", " while divisor * divisor <= n_int:\n", " while n_int % divisor == 0:\n", " factors.append(divisor)\n", " n_int //= divisor\n", " divisor += 2\n", "\n", " if n_int > 1:\n", " factors.append(n_int)\n", "\n", " return factors\n", "\n", "\n", "def generate_cheetah_image():\n", " \"\"\"\n", " Generate a cheetah image.\n", "\n", " Returns:\n", " The generated cheetah image.\n", " \"\"\"\n", " return Path(os.path.abspath('')) / \"cheetah.jpg\"\n", "\n", "\n", "def image_orientation(image: Image.Image) -> str:\n", " \"\"\"\n", " Returns whether image is portrait or landscape.\n", "\n", " Args:\n", " image (Image.Image): The image to check.\n", "\n", " Returns:\n", " str: \"Portrait\" if image is portrait, \"Landscape\" if image is landscape.\n", " \"\"\"\n", " return \"Portrait\" if image.height > image.width else \"Landscape\"\n", "\n", "\n", "def sepia(input_img):\n", " \"\"\"\n", " Apply a sepia filter to the input image.\n", "\n", " Args:\n", " input_img (np.array): The input image to apply the sepia filter to.\n", "\n", " Returns:\n", " The sepia filtered image.\n", " \"\"\"\n", " sepia_filter = np.array([\n", " [0.393, 0.769, 0.189],\n", " [0.349, 0.686, 0.168],\n", " [0.272, 0.534, 0.131]\n", " ])\n", " sepia_img = input_img.dot(sepia_filter.T)\n", " sepia_img /= sepia_img.max()\n", " return sepia_img\n", "\n", "\n", "\n", "demo = gr.TabbedInterface(\n", " [\n", " gr.Interface(prime_factors, gr.Textbox(), gr.Textbox(), api_name=\"prime_factors\"),\n", " gr.Interface(generate_cheetah_image, None, gr.Image(), api_name=\"generate_cheetah_image\"),\n", " gr.Interface(image_orientation, gr.Image(type=\"pil\"), gr.Textbox(), api_name=\"image_orientation\"),\n", " gr.Interface(sepia, gr.Image(), gr.Image(), api_name=\"sepia\"),\n", " ],\n", " [\n", " \"Prime Factors\",\n", " \"Cheetah Image\",\n", " \"Image Orientation Checker\",\n", " \"Sepia Filter\",\n", " ]\n", ")\n", "\n", "if __name__ == \"__main__\":\n", " demo.launch(mcp_server=True)\n"]}], "metadata": {}, "nbformat": 4, "nbformat_minor": 5}