556 lines
34 KiB
Plaintext
556 lines
34 KiB
Plaintext
{
|
|
"nbformat": 4,
|
|
"nbformat_minor": 0,
|
|
"metadata": {
|
|
"colab": {
|
|
"provenance": [],
|
|
"gpuType": "T4"
|
|
},
|
|
"kernelspec": {
|
|
"name": "python3",
|
|
"display_name": "Python 3"
|
|
},
|
|
"language_info": {
|
|
"name": "python"
|
|
},
|
|
"accelerator": "GPU"
|
|
},
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"source": [
|
|
"# **FT; Key Information Extraction**\n",
|
|
"Qwen2VLForConditionalGeneration"
|
|
],
|
|
"metadata": {
|
|
"id": "-b4-SW1aGOcF"
|
|
}
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"source": [
|
|
"!pip install gradio spaces transformers accelerate numpy requests torch torchvision qwen-vl-utils av ipython reportlab fpdf python-docx pillow huggingface_hub"
|
|
],
|
|
"metadata": {
|
|
"colab": {
|
|
"base_uri": "https://localhost:8080/"
|
|
},
|
|
"id": "oDmd1ZObGSel",
|
|
"outputId": "5b01f267-d5af-4409-cf67-6c318388d584"
|
|
},
|
|
"execution_count": 1,
|
|
"outputs": [
|
|
{
|
|
"output_type": "stream",
|
|
"name": "stdout",
|
|
"text": [
|
|
"Collecting gradio\n",
|
|
" Downloading gradio-5.9.1-py3-none-any.whl.metadata (16 kB)\n",
|
|
"Collecting spaces\n",
|
|
" Downloading spaces-0.31.1-py3-none-any.whl.metadata (1.0 kB)\n",
|
|
"Requirement already satisfied: transformers in /usr/local/lib/python3.10/dist-packages (4.47.1)\n",
|
|
"Requirement already satisfied: accelerate in /usr/local/lib/python3.10/dist-packages (1.2.1)\n",
|
|
"Requirement already satisfied: numpy in /usr/local/lib/python3.10/dist-packages (1.26.4)\n",
|
|
"Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (2.32.3)\n",
|
|
"Requirement already satisfied: torch in /usr/local/lib/python3.10/dist-packages (2.5.1+cu121)\n",
|
|
"Requirement already satisfied: torchvision in /usr/local/lib/python3.10/dist-packages (0.20.1+cu121)\n",
|
|
"Collecting qwen-vl-utils\n",
|
|
" Downloading qwen_vl_utils-0.0.8-py3-none-any.whl.metadata (3.6 kB)\n",
|
|
"Collecting av\n",
|
|
" Downloading av-14.0.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (4.5 kB)\n",
|
|
"Requirement already satisfied: ipython in /usr/local/lib/python3.10/dist-packages (7.34.0)\n",
|
|
"Collecting reportlab\n",
|
|
" Downloading reportlab-4.2.5-py3-none-any.whl.metadata (1.5 kB)\n",
|
|
"Collecting fpdf\n",
|
|
" Downloading fpdf-1.7.2.tar.gz (39 kB)\n",
|
|
" Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
|
|
"Collecting python-docx\n",
|
|
" Downloading python_docx-1.1.2-py3-none-any.whl.metadata (2.0 kB)\n",
|
|
"Requirement already satisfied: pillow in /usr/local/lib/python3.10/dist-packages (11.0.0)\n",
|
|
"Requirement already satisfied: huggingface_hub in /usr/local/lib/python3.10/dist-packages (0.27.0)\n",
|
|
"Collecting aiofiles<24.0,>=22.0 (from gradio)\n",
|
|
" Downloading aiofiles-23.2.1-py3-none-any.whl.metadata (9.7 kB)\n",
|
|
"Requirement already satisfied: anyio<5.0,>=3.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (3.7.1)\n",
|
|
"Collecting fastapi<1.0,>=0.115.2 (from gradio)\n",
|
|
" Downloading fastapi-0.115.6-py3-none-any.whl.metadata (27 kB)\n",
|
|
"Collecting ffmpy (from gradio)\n",
|
|
" Downloading ffmpy-0.5.0-py3-none-any.whl.metadata (3.0 kB)\n",
|
|
"Collecting gradio-client==1.5.2 (from gradio)\n",
|
|
" Downloading gradio_client-1.5.2-py3-none-any.whl.metadata (7.1 kB)\n",
|
|
"Requirement already satisfied: httpx>=0.24.1 in /usr/local/lib/python3.10/dist-packages (from gradio) (0.28.1)\n",
|
|
"Requirement already satisfied: jinja2<4.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (3.1.4)\n",
|
|
"Collecting markupsafe~=2.0 (from gradio)\n",
|
|
" Downloading MarkupSafe-2.1.5-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (3.0 kB)\n",
|
|
"Requirement already satisfied: orjson~=3.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (3.10.12)\n",
|
|
"Requirement already satisfied: packaging in /usr/local/lib/python3.10/dist-packages (from gradio) (24.2)\n",
|
|
"Requirement already satisfied: pandas<3.0,>=1.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (2.2.2)\n",
|
|
"Requirement already satisfied: pydantic>=2.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (2.10.3)\n",
|
|
"Collecting pydub (from gradio)\n",
|
|
" Downloading pydub-0.25.1-py2.py3-none-any.whl.metadata (1.4 kB)\n",
|
|
"Collecting python-multipart>=0.0.18 (from gradio)\n",
|
|
" Downloading python_multipart-0.0.20-py3-none-any.whl.metadata (1.8 kB)\n",
|
|
"Requirement already satisfied: pyyaml<7.0,>=5.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (6.0.2)\n",
|
|
"Collecting ruff>=0.2.2 (from gradio)\n",
|
|
" Downloading ruff-0.8.5-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (25 kB)\n",
|
|
"Collecting safehttpx<0.2.0,>=0.1.6 (from gradio)\n",
|
|
" Downloading safehttpx-0.1.6-py3-none-any.whl.metadata (4.2 kB)\n",
|
|
"Collecting semantic-version~=2.0 (from gradio)\n",
|
|
" Downloading semantic_version-2.10.0-py2.py3-none-any.whl.metadata (9.7 kB)\n",
|
|
"Collecting starlette<1.0,>=0.40.0 (from gradio)\n",
|
|
" Downloading starlette-0.45.1-py3-none-any.whl.metadata (6.3 kB)\n",
|
|
"Collecting tomlkit<0.14.0,>=0.12.0 (from gradio)\n",
|
|
" Downloading tomlkit-0.13.2-py3-none-any.whl.metadata (2.7 kB)\n",
|
|
"Requirement already satisfied: typer<1.0,>=0.12 in /usr/local/lib/python3.10/dist-packages (from gradio) (0.15.1)\n",
|
|
"Requirement already satisfied: typing-extensions~=4.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (4.12.2)\n",
|
|
"Collecting uvicorn>=0.14.0 (from gradio)\n",
|
|
" Downloading uvicorn-0.34.0-py3-none-any.whl.metadata (6.5 kB)\n",
|
|
"Requirement already satisfied: fsspec in /usr/local/lib/python3.10/dist-packages (from gradio-client==1.5.2->gradio) (2024.10.0)\n",
|
|
"Requirement already satisfied: websockets<15.0,>=10.0 in /usr/local/lib/python3.10/dist-packages (from gradio-client==1.5.2->gradio) (14.1)\n",
|
|
"Requirement already satisfied: psutil<6,>=2 in /usr/local/lib/python3.10/dist-packages (from spaces) (5.9.5)\n",
|
|
"Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from transformers) (3.16.1)\n",
|
|
"Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.10/dist-packages (from transformers) (2024.11.6)\n",
|
|
"Requirement already satisfied: tokenizers<0.22,>=0.21 in /usr/local/lib/python3.10/dist-packages (from transformers) (0.21.0)\n",
|
|
"Requirement already satisfied: safetensors>=0.4.1 in /usr/local/lib/python3.10/dist-packages (from transformers) (0.4.5)\n",
|
|
"Requirement already satisfied: tqdm>=4.27 in /usr/local/lib/python3.10/dist-packages (from transformers) (4.67.1)\n",
|
|
"Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests) (3.4.0)\n",
|
|
"Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests) (3.10)\n",
|
|
"Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests) (2.2.3)\n",
|
|
"Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests) (2024.12.14)\n",
|
|
"Requirement already satisfied: networkx in /usr/local/lib/python3.10/dist-packages (from torch) (3.4.2)\n",
|
|
"Requirement already satisfied: sympy==1.13.1 in /usr/local/lib/python3.10/dist-packages (from torch) (1.13.1)\n",
|
|
"Requirement already satisfied: mpmath<1.4,>=1.1.0 in /usr/local/lib/python3.10/dist-packages (from sympy==1.13.1->torch) (1.3.0)\n",
|
|
"Requirement already satisfied: setuptools>=18.5 in /usr/local/lib/python3.10/dist-packages (from ipython) (75.1.0)\n",
|
|
"Collecting jedi>=0.16 (from ipython)\n",
|
|
" Downloading jedi-0.19.2-py2.py3-none-any.whl.metadata (22 kB)\n",
|
|
"Requirement already satisfied: decorator in /usr/local/lib/python3.10/dist-packages (from ipython) (4.4.2)\n",
|
|
"Requirement already satisfied: pickleshare in /usr/local/lib/python3.10/dist-packages (from ipython) (0.7.5)\n",
|
|
"Requirement already satisfied: traitlets>=4.2 in /usr/local/lib/python3.10/dist-packages (from ipython) (5.7.1)\n",
|
|
"Requirement already satisfied: prompt-toolkit!=3.0.0,!=3.0.1,<3.1.0,>=2.0.0 in /usr/local/lib/python3.10/dist-packages (from ipython) (3.0.48)\n",
|
|
"Requirement already satisfied: pygments in /usr/local/lib/python3.10/dist-packages (from ipython) (2.18.0)\n",
|
|
"Requirement already satisfied: backcall in /usr/local/lib/python3.10/dist-packages (from ipython) (0.2.0)\n",
|
|
"Requirement already satisfied: matplotlib-inline in /usr/local/lib/python3.10/dist-packages (from ipython) (0.1.7)\n",
|
|
"Requirement already satisfied: pexpect>4.3 in /usr/local/lib/python3.10/dist-packages (from ipython) (4.9.0)\n",
|
|
"Requirement already satisfied: chardet in /usr/local/lib/python3.10/dist-packages (from reportlab) (5.2.0)\n",
|
|
"Requirement already satisfied: lxml>=3.1.0 in /usr/local/lib/python3.10/dist-packages (from python-docx) (5.3.0)\n",
|
|
"Requirement already satisfied: sniffio>=1.1 in /usr/local/lib/python3.10/dist-packages (from anyio<5.0,>=3.0->gradio) (1.3.1)\n",
|
|
"Requirement already satisfied: exceptiongroup in /usr/local/lib/python3.10/dist-packages (from anyio<5.0,>=3.0->gradio) (1.2.2)\n",
|
|
"Collecting starlette<1.0,>=0.40.0 (from gradio)\n",
|
|
" Downloading starlette-0.41.3-py3-none-any.whl.metadata (6.0 kB)\n",
|
|
"Requirement already satisfied: httpcore==1.* in /usr/local/lib/python3.10/dist-packages (from httpx>=0.24.1->gradio) (1.0.7)\n",
|
|
"Requirement already satisfied: h11<0.15,>=0.13 in /usr/local/lib/python3.10/dist-packages (from httpcore==1.*->httpx>=0.24.1->gradio) (0.14.0)\n",
|
|
"Requirement already satisfied: parso<0.9.0,>=0.8.4 in /usr/local/lib/python3.10/dist-packages (from jedi>=0.16->ipython) (0.8.4)\n",
|
|
"Requirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.10/dist-packages (from pandas<3.0,>=1.0->gradio) (2.8.2)\n",
|
|
"Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas<3.0,>=1.0->gradio) (2024.2)\n",
|
|
"Requirement already satisfied: tzdata>=2022.7 in /usr/local/lib/python3.10/dist-packages (from pandas<3.0,>=1.0->gradio) (2024.2)\n",
|
|
"Requirement already satisfied: ptyprocess>=0.5 in /usr/local/lib/python3.10/dist-packages (from pexpect>4.3->ipython) (0.7.0)\n",
|
|
"Requirement already satisfied: wcwidth in /usr/local/lib/python3.10/dist-packages (from prompt-toolkit!=3.0.0,!=3.0.1,<3.1.0,>=2.0.0->ipython) (0.2.13)\n",
|
|
"Requirement already satisfied: annotated-types>=0.6.0 in /usr/local/lib/python3.10/dist-packages (from pydantic>=2.0->gradio) (0.7.0)\n",
|
|
"Requirement already satisfied: pydantic-core==2.27.1 in /usr/local/lib/python3.10/dist-packages (from pydantic>=2.0->gradio) (2.27.1)\n",
|
|
"Requirement already satisfied: click>=8.0.0 in /usr/local/lib/python3.10/dist-packages (from typer<1.0,>=0.12->gradio) (8.1.7)\n",
|
|
"Requirement already satisfied: shellingham>=1.3.0 in /usr/local/lib/python3.10/dist-packages (from typer<1.0,>=0.12->gradio) (1.5.4)\n",
|
|
"Requirement already satisfied: rich>=10.11.0 in /usr/local/lib/python3.10/dist-packages (from typer<1.0,>=0.12->gradio) (13.9.4)\n",
|
|
"Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/dist-packages (from python-dateutil>=2.8.2->pandas<3.0,>=1.0->gradio) (1.17.0)\n",
|
|
"Requirement already satisfied: markdown-it-py>=2.2.0 in /usr/local/lib/python3.10/dist-packages (from rich>=10.11.0->typer<1.0,>=0.12->gradio) (3.0.0)\n",
|
|
"Requirement already satisfied: mdurl~=0.1 in /usr/local/lib/python3.10/dist-packages (from markdown-it-py>=2.2.0->rich>=10.11.0->typer<1.0,>=0.12->gradio) (0.1.2)\n",
|
|
"Downloading gradio-5.9.1-py3-none-any.whl (57.2 MB)\n",
|
|
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m57.2/57.2 MB\u001b[0m \u001b[31m14.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
|
"\u001b[?25hDownloading gradio_client-1.5.2-py3-none-any.whl (320 kB)\n",
|
|
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m320.4/320.4 kB\u001b[0m \u001b[31m29.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
|
"\u001b[?25hDownloading spaces-0.31.1-py3-none-any.whl (28 kB)\n",
|
|
"Downloading qwen_vl_utils-0.0.8-py3-none-any.whl (5.9 kB)\n",
|
|
"Downloading av-14.0.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (33.0 MB)\n",
|
|
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m33.0/33.0 MB\u001b[0m \u001b[31m62.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
|
"\u001b[?25hDownloading reportlab-4.2.5-py3-none-any.whl (1.9 MB)\n",
|
|
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.9/1.9 MB\u001b[0m \u001b[31m84.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
|
"\u001b[?25hDownloading python_docx-1.1.2-py3-none-any.whl (244 kB)\n",
|
|
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m244.3/244.3 kB\u001b[0m \u001b[31m22.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
|
"\u001b[?25hDownloading aiofiles-23.2.1-py3-none-any.whl (15 kB)\n",
|
|
"Downloading fastapi-0.115.6-py3-none-any.whl (94 kB)\n",
|
|
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m94.8/94.8 kB\u001b[0m \u001b[31m9.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
|
"\u001b[?25hDownloading jedi-0.19.2-py2.py3-none-any.whl (1.6 MB)\n",
|
|
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.6/1.6 MB\u001b[0m \u001b[31m75.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
|
"\u001b[?25hDownloading MarkupSafe-2.1.5-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (25 kB)\n",
|
|
"Downloading python_multipart-0.0.20-py3-none-any.whl (24 kB)\n",
|
|
"Downloading ruff-0.8.5-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (11.3 MB)\n",
|
|
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m11.3/11.3 MB\u001b[0m \u001b[31m114.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
|
"\u001b[?25hDownloading safehttpx-0.1.6-py3-none-any.whl (8.7 kB)\n",
|
|
"Downloading semantic_version-2.10.0-py2.py3-none-any.whl (15 kB)\n",
|
|
"Downloading starlette-0.41.3-py3-none-any.whl (73 kB)\n",
|
|
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m73.2/73.2 kB\u001b[0m \u001b[31m6.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
|
"\u001b[?25hDownloading tomlkit-0.13.2-py3-none-any.whl (37 kB)\n",
|
|
"Downloading uvicorn-0.34.0-py3-none-any.whl (62 kB)\n",
|
|
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m62.3/62.3 kB\u001b[0m \u001b[31m6.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
|
"\u001b[?25hDownloading ffmpy-0.5.0-py3-none-any.whl (6.0 kB)\n",
|
|
"Downloading pydub-0.25.1-py2.py3-none-any.whl (32 kB)\n",
|
|
"Building wheels for collected packages: fpdf\n",
|
|
" Building wheel for fpdf (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
|
|
" Created wheel for fpdf: filename=fpdf-1.7.2-py2.py3-none-any.whl size=40704 sha256=442a41ba3b572ac9bae1220ac5f13b34f02252630b892bab6e55af0e878115c0\n",
|
|
" Stored in directory: /root/.cache/pip/wheels/f9/95/ba/f418094659025eb9611f17cbcaf2334236bf39a0c3453ea455\n",
|
|
"Successfully built fpdf\n",
|
|
"Installing collected packages: pydub, fpdf, uvicorn, tomlkit, semantic-version, ruff, reportlab, python-multipart, python-docx, markupsafe, jedi, ffmpy, av, aiofiles, starlette, qwen-vl-utils, safehttpx, gradio-client, fastapi, gradio, spaces\n",
|
|
" Attempting uninstall: markupsafe\n",
|
|
" Found existing installation: MarkupSafe 3.0.2\n",
|
|
" Uninstalling MarkupSafe-3.0.2:\n",
|
|
" Successfully uninstalled MarkupSafe-3.0.2\n",
|
|
"Successfully installed aiofiles-23.2.1 av-14.0.1 fastapi-0.115.6 ffmpy-0.5.0 fpdf-1.7.2 gradio-5.9.1 gradio-client-1.5.2 jedi-0.19.2 markupsafe-2.1.5 pydub-0.25.1 python-docx-1.1.2 python-multipart-0.0.20 qwen-vl-utils-0.0.8 reportlab-4.2.5 ruff-0.8.5 safehttpx-0.1.6 semantic-version-2.10.0 spaces-0.31.1 starlette-0.41.3 tomlkit-0.13.2 uvicorn-0.34.0\n"
|
|
]
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"source": [
|
|
"# Authenticate with Hugging Face\n",
|
|
"from huggingface_hub import login\n",
|
|
"\n",
|
|
"# Log in to Hugging Face using the provided token\n",
|
|
"hf_token = '----xxx----'\n",
|
|
"login(hf_token)\n",
|
|
"\n",
|
|
"#Demo\n",
|
|
"import gradio as gr\n",
|
|
"import spaces\n",
|
|
"from transformers import Qwen2VLForConditionalGeneration, AutoProcessor, TextIteratorStreamer\n",
|
|
"from qwen_vl_utils import process_vision_info\n",
|
|
"import torch\n",
|
|
"from PIL import Image\n",
|
|
"import os\n",
|
|
"import uuid\n",
|
|
"import io\n",
|
|
"from threading import Thread\n",
|
|
"from reportlab.lib.pagesizes import A4\n",
|
|
"from reportlab.lib.styles import getSampleStyleSheet\n",
|
|
"from reportlab.lib import colors\n",
|
|
"from reportlab.platypus import SimpleDocTemplate, Image as RLImage, Paragraph, Spacer\n",
|
|
"from reportlab.lib.units import inch\n",
|
|
"from reportlab.pdfbase import pdfmetrics\n",
|
|
"from reportlab.pdfbase.ttfonts import TTFont\n",
|
|
"import docx\n",
|
|
"from docx.enum.text import WD_ALIGN_PARAGRAPH\n",
|
|
"\n",
|
|
"# Define model options\n",
|
|
"MODEL_OPTIONS = {\n",
|
|
" \"OCR-KIE\": \"prithivMLmods/Qwen2-VL-OCR-2B-Instruct\",\n",
|
|
"}\n",
|
|
"\n",
|
|
"# Preload models and processors into CUDA\n",
|
|
"models = {}\n",
|
|
"processors = {}\n",
|
|
"for name, model_id in MODEL_OPTIONS.items():\n",
|
|
" print(f\"Loading {name}...\")\n",
|
|
" models[name] = Qwen2VLForConditionalGeneration.from_pretrained(\n",
|
|
" model_id,\n",
|
|
" trust_remote_code=True,\n",
|
|
" torch_dtype=torch.float16\n",
|
|
" ).to(\"cuda\").eval()\n",
|
|
" processors[name] = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)\n",
|
|
"\n",
|
|
"image_extensions = Image.registered_extensions()\n",
|
|
"\n",
|
|
"def identify_and_save_blob(blob_path):\n",
|
|
" \"\"\"Identifies if the blob is an image and saves it.\"\"\"\n",
|
|
" try:\n",
|
|
" with open(blob_path, 'rb') as file:\n",
|
|
" blob_content = file.read()\n",
|
|
" try:\n",
|
|
" Image.open(io.BytesIO(blob_content)).verify() # Check if it's a valid image\n",
|
|
" extension = \".png\" # Default to PNG for saving\n",
|
|
" media_type = \"image\"\n",
|
|
" except (IOError, SyntaxError):\n",
|
|
" raise ValueError(\"Unsupported media type. Please upload a valid image.\")\n",
|
|
"\n",
|
|
" filename = f\"temp_{uuid.uuid4()}_media{extension}\"\n",
|
|
" with open(filename, \"wb\") as f:\n",
|
|
" f.write(blob_content)\n",
|
|
"\n",
|
|
" return filename, media_type\n",
|
|
"\n",
|
|
" except FileNotFoundError:\n",
|
|
" raise ValueError(f\"The file {blob_path} was not found.\")\n",
|
|
" except Exception as e:\n",
|
|
" raise ValueError(f\"An error occurred while processing the file: {e}\")\n",
|
|
"\n",
|
|
"@spaces.GPU\n",
|
|
"def qwen_inference(model_name, media_input, text_input=None):\n",
|
|
" \"\"\"Handles inference for the selected model.\"\"\"\n",
|
|
" model = models[model_name]\n",
|
|
" processor = processors[model_name]\n",
|
|
"\n",
|
|
" if isinstance(media_input, str):\n",
|
|
" media_path = media_input\n",
|
|
" if media_path.endswith(tuple([i for i in image_extensions.keys()])):\n",
|
|
" media_type = \"image\"\n",
|
|
" else:\n",
|
|
" try:\n",
|
|
" media_path, media_type = identify_and_save_blob(media_input)\n",
|
|
" except Exception as e:\n",
|
|
" raise ValueError(\"Unsupported media type. Please upload a valid image.\")\n",
|
|
"\n",
|
|
" messages = [\n",
|
|
" {\n",
|
|
" \"role\": \"user\",\n",
|
|
" \"content\": [\n",
|
|
" {\n",
|
|
" \"type\": media_type,\n",
|
|
" media_type: media_path\n",
|
|
" },\n",
|
|
" {\"type\": \"text\", \"text\": text_input},\n",
|
|
" ],\n",
|
|
" }\n",
|
|
" ]\n",
|
|
"\n",
|
|
" text = processor.apply_chat_template(\n",
|
|
" messages, tokenize=False, add_generation_prompt=True\n",
|
|
" )\n",
|
|
" image_inputs, _ = process_vision_info(messages)\n",
|
|
" inputs = processor(\n",
|
|
" text=[text],\n",
|
|
" images=image_inputs,\n",
|
|
" padding=True,\n",
|
|
" return_tensors=\"pt\",\n",
|
|
" ).to(\"cuda\")\n",
|
|
"\n",
|
|
" streamer = TextIteratorStreamer(\n",
|
|
" processor.tokenizer, skip_prompt=True, skip_special_tokens=True\n",
|
|
" )\n",
|
|
" generation_kwargs = dict(inputs, streamer=streamer, max_new_tokens=1024)\n",
|
|
"\n",
|
|
" thread = Thread(target=model.generate, kwargs=generation_kwargs)\n",
|
|
" thread.start()\n",
|
|
"\n",
|
|
" buffer = \"\"\n",
|
|
" for new_text in streamer:\n",
|
|
" buffer += new_text\n",
|
|
" # Remove <|im_end|> or similar tokens from the output\n",
|
|
" buffer = buffer.replace(\"<|im_end|>\", \"\")\n",
|
|
" yield buffer\n",
|
|
"\n",
|
|
"def format_plain_text(output_text):\n",
|
|
" \"\"\"Formats the output text as plain text without LaTeX delimiters.\"\"\"\n",
|
|
" # Remove LaTeX delimiters and convert to plain text\n",
|
|
" plain_text = output_text.replace(\"\\\\(\", \"\").replace(\"\\\\)\", \"\").replace(\"\\\\[\", \"\").replace(\"\\\\]\", \"\")\n",
|
|
" return plain_text\n",
|
|
"\n",
|
|
"def generate_document(media_path, output_text, file_format, font_size, line_spacing, alignment, image_size):\n",
|
|
" \"\"\"Generates a document with the input image and plain text output.\"\"\"\n",
|
|
" plain_text = format_plain_text(output_text)\n",
|
|
" if file_format == \"pdf\":\n",
|
|
" return generate_pdf(media_path, plain_text, font_size, line_spacing, alignment, image_size)\n",
|
|
" elif file_format == \"docx\":\n",
|
|
" return generate_docx(media_path, plain_text, font_size, line_spacing, alignment, image_size)\n",
|
|
"\n",
|
|
"def generate_pdf(media_path, plain_text, font_size, line_spacing, alignment, image_size):\n",
|
|
" \"\"\"Generates a PDF document.\"\"\"\n",
|
|
" filename = f\"output_{uuid.uuid4()}.pdf\"\n",
|
|
" doc = SimpleDocTemplate(\n",
|
|
" filename,\n",
|
|
" pagesize=A4,\n",
|
|
" rightMargin=inch,\n",
|
|
" leftMargin=inch,\n",
|
|
" topMargin=inch,\n",
|
|
" bottomMargin=inch\n",
|
|
" )\n",
|
|
" styles = getSampleStyleSheet()\n",
|
|
" styles[\"Normal\"].fontSize = int(font_size)\n",
|
|
" styles[\"Normal\"].leading = int(font_size) * line_spacing\n",
|
|
" styles[\"Normal\"].alignment = {\n",
|
|
" \"Left\": 0,\n",
|
|
" \"Center\": 1,\n",
|
|
" \"Right\": 2,\n",
|
|
" \"Justified\": 4\n",
|
|
" }[alignment]\n",
|
|
"\n",
|
|
" story = []\n",
|
|
"\n",
|
|
" # Add image with size adjustment\n",
|
|
" image_sizes = {\n",
|
|
" \"Small\": (200, 200),\n",
|
|
" \"Medium\": (400, 400),\n",
|
|
" \"Large\": (600, 600)\n",
|
|
" }\n",
|
|
" img = RLImage(media_path, width=image_sizes[image_size][0], height=image_sizes[image_size][1])\n",
|
|
" story.append(img)\n",
|
|
" story.append(Spacer(1, 12))\n",
|
|
"\n",
|
|
" # Add plain text output\n",
|
|
" text = Paragraph(plain_text, styles[\"Normal\"])\n",
|
|
" story.append(text)\n",
|
|
"\n",
|
|
" doc.build(story)\n",
|
|
" return filename\n",
|
|
"\n",
|
|
"def generate_docx(media_path, plain_text, font_size, line_spacing, alignment, image_size):\n",
|
|
" \"\"\"Generates a DOCX document.\"\"\"\n",
|
|
" filename = f\"output_{uuid.uuid4()}.docx\"\n",
|
|
" doc = docx.Document()\n",
|
|
"\n",
|
|
" # Add image with size adjustment\n",
|
|
" image_sizes = {\n",
|
|
" \"Small\": docx.shared.Inches(2),\n",
|
|
" \"Medium\": docx.shared.Inches(4),\n",
|
|
" \"Large\": docx.shared.Inches(6)\n",
|
|
" }\n",
|
|
" doc.add_picture(media_path, width=image_sizes[image_size])\n",
|
|
" doc.add_paragraph()\n",
|
|
"\n",
|
|
" # Add plain text output\n",
|
|
" paragraph = doc.add_paragraph()\n",
|
|
" paragraph.paragraph_format.line_spacing = line_spacing\n",
|
|
" paragraph.paragraph_format.alignment = {\n",
|
|
" \"Left\": WD_ALIGN_PARAGRAPH.LEFT,\n",
|
|
" \"Center\": WD_ALIGN_PARAGRAPH.CENTER,\n",
|
|
" \"Right\": WD_ALIGN_PARAGRAPH.RIGHT,\n",
|
|
" \"Justified\": WD_ALIGN_PARAGRAPH.JUSTIFY\n",
|
|
" }[alignment]\n",
|
|
" run = paragraph.add_run(plain_text)\n",
|
|
" run.font.size = docx.shared.Pt(int(font_size))\n",
|
|
"\n",
|
|
" doc.save(filename)\n",
|
|
" return filename\n",
|
|
"\n",
|
|
"# CSS for output styling\n",
|
|
"css = \"\"\"\n",
|
|
" #output {\n",
|
|
" height: 500px;\n",
|
|
" overflow: auto;\n",
|
|
" border: 1px solid #ccc;\n",
|
|
" }\n",
|
|
".submit-btn {\n",
|
|
" background-color: #cf3434 !important;\n",
|
|
" color: white !important;\n",
|
|
"}\n",
|
|
".submit-btn:hover {\n",
|
|
" background-color: #ff2323 !important;\n",
|
|
"}\n",
|
|
".download-btn {\n",
|
|
" background-color: #35a6d6 !important;\n",
|
|
" color: white !important;\n",
|
|
"}\n",
|
|
".download-btn:hover {\n",
|
|
" background-color: #22bcff !important;\n",
|
|
"}\n",
|
|
"\"\"\"\n",
|
|
"\n",
|
|
"# Gradio app setup\n",
|
|
"with gr.Blocks(css=css) as demo:\n",
|
|
" gr.Markdown(\"# Qwen2VL Models: Vision and Language Processing\")\n",
|
|
"\n",
|
|
" with gr.Tab(label=\"Image Input\"):\n",
|
|
"\n",
|
|
" with gr.Row():\n",
|
|
" with gr.Column():\n",
|
|
" model_choice = gr.Dropdown(\n",
|
|
" label=\"Model Selection\",\n",
|
|
" choices=list(MODEL_OPTIONS.keys()),\n",
|
|
" value=\"OCR-KIE\"\n",
|
|
" )\n",
|
|
" input_media = gr.File(\n",
|
|
" label=\"Upload Image\", type=\"filepath\"\n",
|
|
" )\n",
|
|
" text_input = gr.Textbox(label=\"Question\", placeholder=\"Ask a question about the image...\")\n",
|
|
" submit_btn = gr.Button(value=\"Submit\", elem_classes=\"submit-btn\")\n",
|
|
"\n",
|
|
" with gr.Column():\n",
|
|
" output_text = gr.Textbox(label=\"Output Text\", lines=10)\n",
|
|
" plain_text_output = gr.Textbox(label=\"Standardized Plain Text\", lines=10)\n",
|
|
"\n",
|
|
" submit_btn.click(\n",
|
|
" qwen_inference, [model_choice, input_media, text_input], [output_text]\n",
|
|
" ).then(\n",
|
|
" lambda output_text: format_plain_text(output_text), [output_text], [plain_text_output]\n",
|
|
" )\n",
|
|
"\n",
|
|
" # Add examples directly usable by clicking\n",
|
|
" with gr.Row():\n",
|
|
" with gr.Column():\n",
|
|
" line_spacing = gr.Dropdown(\n",
|
|
" choices=[0.5, 1.0, 1.15, 1.5, 2.0, 2.5, 3.0],\n",
|
|
" value=1.5,\n",
|
|
" label=\"Line Spacing\"\n",
|
|
" )\n",
|
|
" font_size = gr.Dropdown(\n",
|
|
" choices=[\"8\", \"10\", \"12\", \"14\", \"16\", \"18\", \"20\", \"22\", \"24\"],\n",
|
|
" value=\"18\",\n",
|
|
" label=\"Font Size\"\n",
|
|
" )\n",
|
|
" alignment = gr.Dropdown(\n",
|
|
" choices=[\"Left\", \"Center\", \"Right\", \"Justified\"],\n",
|
|
" value=\"Justified\",\n",
|
|
" label=\"Text Alignment\"\n",
|
|
" )\n",
|
|
" image_size = gr.Dropdown(\n",
|
|
" choices=[\"Small\", \"Medium\", \"Large\"],\n",
|
|
" value=\"Small\",\n",
|
|
" label=\"Image Size\"\n",
|
|
" )\n",
|
|
" file_format = gr.Radio([\"pdf\", \"docx\"], label=\"File Format\", value=\"pdf\")\n",
|
|
" get_document_btn = gr.Button(value=\"Get Document\", elem_classes=\"download-btn\")\n",
|
|
"\n",
|
|
" get_document_btn.click(\n",
|
|
" generate_document, [input_media, output_text, file_format, font_size, line_spacing, alignment, image_size], gr.File(label=\"Download Document\")\n",
|
|
" )\n",
|
|
"\n",
|
|
"demo.launch(debug=True)"
|
|
],
|
|
"metadata": {
|
|
"colab": {
|
|
"base_uri": "https://localhost:8080/",
|
|
"height": 715
|
|
},
|
|
"id": "ovBSsRFhGbs2",
|
|
"outputId": "2a5bc724-4eab-4167-9c52-b378ce3799e3"
|
|
},
|
|
"execution_count": 4,
|
|
"outputs": [
|
|
{
|
|
"output_type": "stream",
|
|
"name": "stderr",
|
|
"text": [
|
|
"The argument `trust_remote_code` is to be used with Auto classes. It has no effect here and is ignored.\n"
|
|
]
|
|
},
|
|
{
|
|
"output_type": "stream",
|
|
"name": "stdout",
|
|
"text": [
|
|
"Loading OCR-KIE...\n",
|
|
"Running Gradio in a Colab notebook requires sharing enabled. Automatically setting `share=True` (you can turn this off by setting `share=False` in `launch()` explicitly).\n",
|
|
"\n",
|
|
"Colab notebook detected. This cell will run indefinitely so that you can see errors and logs. To turn off, set debug=False in launch().\n",
|
|
"* Running on public URL: https://49b22c4dd53a6ec06e.gradio.live\n",
|
|
"\n",
|
|
"This share link expires in 72 hours. For free permanent hosting and GPU upgrades, run `gradio deploy` from the terminal in the working directory to deploy to Hugging Face Spaces (https://huggingface.co/spaces)\n"
|
|
]
|
|
},
|
|
{
|
|
"output_type": "display_data",
|
|
"data": {
|
|
"text/plain": [
|
|
"<IPython.core.display.HTML object>"
|
|
],
|
|
"text/html": [
|
|
"<div><iframe src=\"https://49b22c4dd53a6ec06e.gradio.live\" width=\"100%\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
|
|
]
|
|
},
|
|
"metadata": {}
|
|
},
|
|
{
|
|
"output_type": "stream",
|
|
"name": "stdout",
|
|
"text": [
|
|
"Keyboard interruption in main thread... closing server.\n",
|
|
"Killing tunnel 127.0.0.1:7860 <> https://49b22c4dd53a6ec06e.gradio.live\n"
|
|
]
|
|
},
|
|
{
|
|
"output_type": "execute_result",
|
|
"data": {
|
|
"text/plain": []
|
|
},
|
|
"metadata": {},
|
|
"execution_count": 4
|
|
}
|
|
]
|
|
}
|
|
]
|
|
} |