Initial Maintenance

.github/workflows/examples_check.yml

@@ -0,0 +1,62 @@
+name: Notebook Execution and Error Check
+
+on:
+  push:
+    branches:
+      - main
+  pull_request:
+    branches:
+      - main
+  workflow_dispatch:  # This enables manual triggering
+
+jobs:
+  execute_notebooks:
+    runs-on: LargeBois
+    strategy:
+      matrix:
+        transformers_version: ["transformers==4.48.0", "transformers==4.56.1", "--upgrade transformers"]
+        notebook: ["example.ipynb","Jsonformer_example.ipynb"]
+    env:
+      HUGGINGFACE_API_KEY: ${{ secrets.HUGGINGFACE_API_KEY }}
+      NLTK_DATA: /tmp/nltk_data
+    steps:
+    - name: Checkout repository
+      uses: actions/checkout@v4
+      with: 
+        ref: ${{ github.head_ref }}
+        fetch-depth: 0 
+    - name: Set up Python
+      uses: actions/setup-python@v5
+      with: 
+        python-version: 3.12.x
+    - name: Install dependencies
+      run: |
+
+        # Setup Virtual Environment
+        python3 -m venv ./.venv
+        source .venv/bin/activate
+
+        # Install the current branch
+        pip install ${{ matrix.transformers_version }}
+        pip install .
+
+        # Install extra stuff for notebook runs
+        pip install "huggingface_hub[cli]" jupyter nbconvert ipykernel torch accelerate bitsandbytes
+    - name: Huggingface Hub Login
+      run: |
+        source .venv/bin/activate
+        huggingface-cli login --token $HUGGINGFACE_API_KEY
+    - name: Execute notebooks and check for errors
+      run: |
+        source .venv/bin/activate
+        echo "Processing ${{ matrix.notebook }}..."
+        # poetry run jupyter nbconvert --to notebook --execute "${{ matrix.notebook }}"
+        jupyter nbconvert --to notebook --execute "${{ matrix.notebook }}"
+        if [ $? -ne 0 ]; then
+          echo "Error found in ${{ matrix.notebook }}"
+          echo "Error in ${{ matrix.notebook }}. See logs for details." >> errors.txt
+          exit 1
+        fi
+
+        exit 0
+

.github/workflows/release.yml

@@ -0,0 +1,34 @@
+name: Release New PyPi Version
+
+on:
+  workflow_dispatch: # This event allows manual triggering
+
+jobs:
+  release:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout Repository
+        uses: actions/checkout@v5
+
+      - name: Setup Python
+        uses: actions/setup-python@v6
+        with:
+          python-version: 3.13.x
+
+      - name: Poetry cache
+        uses: actions/cache@v4
+        with:
+          path: ~/.cache/pypoetry
+          key: poetry-cache
+
+      - name: Install Poetry
+        uses: snok/install-poetry@v1
+
+      - name: Install dependencies
+        run: poetry install --all-extras
+
+      - name: Upload to PyPI
+        env:
+          PYPI_PASSWORD: ${{ secrets.PYPI_PASSWORD }}
+        run: poetry publish --build -u __token__ -p $PYPI_PASSWORD

Jsonformer_example.ipynb

@@ -3,8 +3,8 @@
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "view-in-github",
-        "colab_type": "text"
+        "colab_type": "text",
+        "id": "view-in-github"
       },
       "source": [
         "<a href=\"https://colab.research.google.com/github/1rgs/jsonformer/blob/main/Jsonformer_example.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
@@ -22,8 +22,8 @@
       },
       "outputs": [
         {
-          "output_type": "stream",
           "name": "stdout",
+          "output_type": "stream",
           "text": [
             "Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n",
             "Requirement already satisfied: transformers in /usr/local/lib/python3.10/dist-packages (4.28.1)\n",
@@ -64,7 +64,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 2,
+      "execution_count": 1,
       "metadata": {
         "colab": {
           "base_uri": "https://localhost:8080/"
@@ -74,8 +74,17 @@
       },
       "outputs": [
         {
+          "name": "stderr",
           "output_type": "stream",
+          "text": [
+            "/Users/calebcourier/Projects/jsonformer/.venv/lib/python3.12/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
+            "  from .autonotebook import tqdm as notebook_tqdm\n",
+            "W0915 16:52:21.949000 36819 torch/distributed/elastic/multiprocessing/redirects.py:29] NOTE: Redirects are currently not supported in Windows or MacOs.\n"
+          ]
+        },
+        {
           "name": "stdout",
+          "output_type": "stream",
           "text": [
             "Loading model and tokenizer...\n",
             "Loaded model and tokenizer\n"
@@ -94,7 +103,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 6,
+      "execution_count": 2,
       "metadata": {
         "colab": {
           "base_uri": "https://localhost:8080/"
@@ -104,40 +113,47 @@
       },
       "outputs": [
         {
+          "name": "stderr",
           "output_type": "stream",
+          "text": [
+            "The attention mask is not set and cannot be inferred from input because pad token is same as eos token. As a consequence, you may observe unexpected behavior. Please pass your input's `attention_mask` to obtain reliable results.\n"
+          ]
+        },
+        {
           "name": "stdout",
+          "output_type": "stream",
           "text": [
             "Generating...\n",
             "{\n",
             "  car: {\n",
-            "    make: \"audi\",\n",
-            "    model: \"model A8\",\n",
-            "    year: 2016.0,\n",
+            "    make: \u001b[32m\"Chevrolet\"\u001b[0m,\n",
+            "    model: \u001b[32m\"Corvette\"\u001b[0m,\n",
+            "    year: \u001b[32m2016.0\u001b[0m,\n",
             "    colors: [\n",
-            "      \"blue\"\n",
+            "      \u001b[32m\"Red\"\u001b[0m\n",
             "    ],\n",
             "    features: {\n",
             "      audio: {\n",
-            "        brand: \"sony\",\n",
-            "        speakers: 2.0,\n",
-            "        hasBluetooth: True\n",
+            "        brand: \u001b[32m\"Sony\"\u001b[0m,\n",
+            "        speakers: \u001b[32m2.0\u001b[0m,\n",
+            "        hasBluetooth: \u001b[32mTrue\u001b[0m\n",
             "      },\n",
             "      safety: {\n",
-            "        airbags: 2.0,\n",
-            "        parkingSensors: True,\n",
-            "        laneAssist: True\n",
+            "        airbags: \u001b[32m2.0\u001b[0m,\n",
+            "        parkingSensors: \u001b[32mTrue\u001b[0m,\n",
+            "        laneAssist: \u001b[32mTrue\u001b[0m\n",
             "      },\n",
             "      performance: {\n",
-            "        engine: \"4.0\",\n",
-            "        horsepower: 220.0,\n",
-            "        topSpeed: 220.0\n",
+            "        engine: \u001b[32m\"4.0\"\u001b[0m,\n",
+            "        horsepower: \u001b[32m220.0\u001b[0m,\n",
+            "        topSpeed: \u001b[32m220.0\u001b[0m\n",
             "      }\n",
             "    }\n",
             "  },\n",
             "  owner: {\n",
-            "    firstName: \"John\",\n",
-            "    lastName: \"Doe\",\n",
-            "    age: 40.0\n",
+            "    firstName: \u001b[32m\"John\"\u001b[0m,\n",
+            "    lastName: \u001b[32m\"Doe\"\u001b[0m,\n",
+            "    age: \u001b[32m40.0\u001b[0m\n",
             "  }\n",
             "}\n"
           ]
@@ -217,30 +233,40 @@
     },
     {
       "cell_type": "code",
-      "source": [],
+      "execution_count": null,
       "metadata": {
         "id": "0eA8hzFHA1jo"
       },
-      "execution_count": null,
-      "outputs": []
+      "outputs": [],
+      "source": []
     }
   ],
   "metadata": {
     "accelerator": "GPU",
     "colab": {
+      "include_colab_link": true,
       "machine_shape": "hm",
-      "provenance": [],
-      "include_colab_link": true
+      "provenance": []
     },
     "gpuClass": "premium",
     "kernelspec": {
-      "display_name": "Python 3",
+      "display_name": ".venv",
+      "language": "python",
       "name": "python3"
     },
     "language_info": {
-      "name": "python"
+      "codemirror_mode": {
+        "name": "ipython",
+        "version": 3
+      },
+      "file_extension": ".py",
+      "mimetype": "text/x-python",
+      "name": "python",
+      "nbconvert_exporter": "python",
+      "pygments_lexer": "ipython3",
+      "version": "3.12.11"
     }
   },
   "nbformat": 4,
   "nbformat_minor": 0
-}
+}

README.md

@@ -121,3 +121,4 @@ poetry run python -m jsonformer.example
 ## License
 
 Jsonformer is released under the MIT License. You are free to use, modify, and distribute this software for any purpose, commercial or non-commercial, as long as the original copyright and license notice are included.
+