Upload folder using huggingface_hub

README.md

@@ -5,7 +5,7 @@ emoji: 🔥
 colorFrom: indigo
 colorTo: indigo
 sdk: gradio
-sdk_version: 5.42.0
+sdk_version: 5.43.0
 app_file: run.py
 pinned: false
 hf_oauth: true

run.ipynb

@@ -1 +1 @@
-{"cells": [{"cell_type": "markdown", "id": "302934307671667531413257853548643485645", "metadata": {}, "source": ["# Gradio Demo: highlight_pdf"]}, {"cell_type": "code", "execution_count": null, "id": "272996653310673477252411125948039410165", "metadata": {}, "outputs": [], "source": ["!pip install -q gradio gradio_pdf>=0.0.22 pymupdf>=1.25.3"]}, {"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/highlight_pdf/Lorem_ipsum.pdf"]}, {"cell_type": "code", "execution_count": null, "id": "44380577570523278879349135829904343037", "metadata": {}, "outputs": [], "source": ["import gradio as gr\n", "from gradio_pdf import PDF\n", "import pymupdf\n", "import os\n", "from pathlib import Path\n", "\n", "current_dir = Path(os.path.abspath(''))\n", "\n", "def highlight_text_in_pdf(pdf_file: Path, highlight_text: str):\n", "    page_number = 0\n", "    doc = pymupdf.open(pdf_file)\n", "    for page in doc:\n", "        text_instances = page.search_for(highlight_text)\n", "        if len(text_instances) > 0:\n", "            page_number = page.number\n", "        for inst in text_instances:\n", "            page.add_highlight_annot(inst)\n", "\n", "    new_pdf_file = str(pdf_file.parents[0]) + \"/new_\" + pdf_file.name\n", "    doc.save(new_pdf_file)\n", "\n", "    if page_number is None:\n", "        page_number = 0\n", "    \n", "    return new_pdf_file, page_number + 1\n", "\n", "def ask(query): \n", "    result = f\"Something about : {query}\"\n", "    sources = \"Document 1\"\n", "    pdf_path = current_dir / \"Lorem_ipsum.pdf\"\n", "    pdf_name = \"Document 1\"\n", "    context_to_highlight = \"Ut velit mauris\"\n", "\n", "    pdf, page_number = highlight_text_in_pdf(pdf_path, context_to_highlight)\n", "    return result, sources + f\" - Page {page_number}\", PDF(pdf, label=pdf_name, starting_page=page_number, interactive=True)  # type: ignore\n", "\n", "\n", "if __name__ == \"__main__\":\n", "    with gr.Blocks() as demo:\n", "        title = gr.HTML(f\"<center><h1>Bot</h1></center>\")\n", "        with gr.Row():\n", "            with gr.Column(scale=2):\n", "                input = gr.Textbox(label=\"Question\", autofocus=True, interactive=True)\n", "                btn = gr.Button(\"Ask\", variant=\"primary\")\n", "                output = gr.Markdown(label=\"Anwser\")\n", "            with gr.Column(scale=2):\n", "                srcs = gr.Textbox(label=\"Sources\", interactive=False)\n", "                pdf = PDF(label=\"Document\")\n", "            \n", "        btn.click(fn=ask, inputs=input, outputs=[output, srcs, pdf])\n", "\n", "    demo.launch()\n"]}], "metadata": {}, "nbformat": 4, "nbformat_minor": 5}
+{"cells": [{"cell_type": "markdown", "id": "302934307671667531413257853548643485645", "metadata": {}, "source": ["# Gradio Demo: highlight_pdf"]}, {"cell_type": "code", "execution_count": null, "id": "272996653310673477252411125948039410165", "metadata": {}, "outputs": [], "source": ["!pip install -q gradio gradio_pdf>=0.0.22 pymupdf>=1.25.3"]}, {"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/highlight_pdf/Lorem_ipsum.pdf"]}, {"cell_type": "code", "execution_count": null, "id": "44380577570523278879349135829904343037", "metadata": {}, "outputs": [], "source": ["import gradio as gr\n", "from gradio_pdf import PDF\n", "import pymupdf  # type: ignore\n", "import os\n", "from pathlib import Path\n", "\n", "current_dir = Path(os.path.abspath(''))\n", "\n", "def highlight_text_in_pdf(pdf_file: Path, highlight_text: str):\n", "    page_number = 0\n", "    doc = pymupdf.open(pdf_file)\n", "    for page in doc:\n", "        text_instances = page.search_for(highlight_text)\n", "        if len(text_instances) > 0:\n", "            page_number = page.number\n", "        for inst in text_instances:\n", "            page.add_highlight_annot(inst)\n", "\n", "    new_pdf_file = str(pdf_file.parents[0]) + \"/new_\" + pdf_file.name\n", "    doc.save(new_pdf_file)\n", "\n", "    if page_number is None:\n", "        page_number = 0\n", "    \n", "    return new_pdf_file, page_number + 1\n", "\n", "def ask(query): \n", "    result = f\"Something about : {query}\"\n", "    sources = \"Document 1\"\n", "    pdf_path = current_dir / \"Lorem_ipsum.pdf\"\n", "    pdf_name = \"Document 1\"\n", "    context_to_highlight = \"Ut velit mauris\"\n", "\n", "    pdf, page_number = highlight_text_in_pdf(pdf_path, context_to_highlight)\n", "    return result, sources + f\" - Page {page_number}\", PDF(pdf, label=pdf_name, starting_page=page_number, interactive=True)  # type: ignore\n", "\n", "\n", "if __name__ == \"__main__\":\n", "    with gr.Blocks() as demo:\n", "        title = gr.HTML(f\"<center><h1>Bot</h1></center>\")\n", "        with gr.Row():\n", "            with gr.Column(scale=2):\n", "                input = gr.Textbox(label=\"Question\", autofocus=True, interactive=True)\n", "                btn = gr.Button(\"Ask\", variant=\"primary\")\n", "                output = gr.Markdown(label=\"Anwser\")\n", "            with gr.Column(scale=2):\n", "                srcs = gr.Textbox(label=\"Sources\", interactive=False)\n", "                pdf = PDF(label=\"Document\")\n", "            \n", "        btn.click(fn=ask, inputs=input, outputs=[output, srcs, pdf])\n", "\n", "    demo.launch()\n"]}], "metadata": {}, "nbformat": 4, "nbformat_minor": 5}

run.py

@@ -1,6 +1,6 @@
 import gradio as gr
 from gradio_pdf import PDF
-import pymupdf
+import pymupdf  # type: ignore
 import os
 from pathlib import Path