Merge pull request #447 from guardrails-ai/notebook-fixes

Fix notebook execution

Author: zsimjee

.github/workflows/ci.yml

@@ -139,3 +139,48 @@ jobs:
                     flags: unittests
                     name: codecov-umbrella
                     fail_ci_if_error: true
+    
+    Notebooks:
+        runs-on: ubuntu-latest
+        if: ${{ always() && contains(join(needs.*.result, ','), 'success') }}
+        needs: [Linting, Typing, Pytests]
+        
+        env:
+          COHERE_API_KEY: ${{ secrets.COHERE_API_KEY }}
+          OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+
+
+        steps:
+        - name: Checkout repository
+          uses: actions/checkout@v2
+
+        - name: Set up Python
+          uses: actions/setup-python@v2
+          with:
+            python-version: 3.11.x
+
+        - name: Poetry cache
+          uses: actions/cache@v3
+          with:
+            path: ~/.cache/pypoetry
+            key: poetry-cache-${{ runner.os }}-${{ steps.setup_python.outputs.python-version }}-${{ env.POETRY_VERSION }}
+
+        - name: Install Poetry
+          uses: snok/install-poetry@v1
+          with:
+              virtualenvs-create: true
+              virtualenvs-in-project: true
+              installer-parallel: true
+
+        - name: Install dependencies
+          run: |
+            make full;
+            poetry add openai==0.28.1 jupyter nbconvert cohere;
+            # pip install openai==0.28.1 jupyter nbconvert;
+            # pip install .;
+
+        - name: Check for pypdfium2
+          run: poetry run pip show pypdfium2
+
+        - name: Execute notebooks and check for errors
+          run: ./.github/workflows/scripts/run_notebooks.sh

.github/workflows/examples_check.yml

@@ -31,17 +31,21 @@ jobs:
 
     - name: Install Poetry
       uses: snok/install-poetry@v1
+      with:
+          virtualenvs-create: true
+          virtualenvs-in-project: true
+          installer-parallel: true
 
     - name: Install dependencies
-      run: make full; pip install jupyter nbconvert; pip install .
+      run: |
+        make full;
+        poetry add openai==0.28.1 jupyter nbconvert cohere;
+        # pip install openai==0.28.1 jupyter nbconvert;
+        # pip install .;
+
+    - name: Check for pypdfium2
+      run: poetry run pip show pypdfium2
 
     - name: Execute notebooks and check for errors
-      run: |
-        cd docs/examples
-        for notebook in $(ls *.ipynb); do
-          jupyter nbconvert --to notebook --execute "$notebook"
-          if [ $? -ne 0 ]; then
-            echo "Error found in $notebook"
-            exit 1
-          fi
-        done
+      run: ./.github/workflows/scripts/run_notebooks.sh
+

.github/workflows/scripts/run_notebooks.sh

@@ -0,0 +1,37 @@
+#!/bin/bash
+
+mkdir /tmp/nltk_data;
+poetry run python -m nltk.downloader -d /tmp/nltk_data punkt;
+export NLTK_DATA=/tmp/nltk_data;
+
+cd docs/examples
+
+# Function to process a notebook
+process_notebook() {
+    notebook="$1"
+    if [ "$notebook" != "valid_chess_moves.ipynb" ] && [ "$notebook" != "translation_with_quality_check.ipynb" ]; then
+        echo "Processing $notebook..."
+        poetry run jupyter nbconvert --to notebook --execute "$notebook"
+        if [ $? -ne 0 ]; then
+            echo "Error found in $notebook"
+            echo "Error in $notebook. See logs for details." >> errors.txt
+        fi
+    fi
+}
+
+export -f process_notebook  # Export the function for parallel execution
+
+# Create a file to collect errors
+> errors.txt
+
+# Run in parallel
+ls *.ipynb | parallel process_notebook
+
+# Check if there were any errors
+if [ -s errors.txt ]; then
+    echo "Some notebooks had errors"
+    cat errors.txt
+    exit 1
+else
+    echo "All notebooks ran successfully."
+fi

docs/examples/bug_free_python_code.ipynb

@@ -38,7 +38,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 39,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -75,13 +75,12 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 40,
    "metadata": {},
    "outputs": [],
    "source": [
     "from pydantic import BaseModel, Field\n",
     "from guardrails.validators import BugFreePython\n",
-    "from guardrails.datatypes import PythonCode\n",
     "\n",
     "prompt = \"\"\"\n",
     "Given the following high level leetcode problem description, write a short Python code snippet that solves the problem.\n",
@@ -92,7 +91,7 @@
     "${gr.complete_json_suffix}\"\"\"\n",
     "\n",
     "class BugFreePythonCode(BaseModel):\n",
-    "    python_code: PythonCode = Field(validators=[BugFreePython(on_fail=\"reask\")])\n",
+    "    python_code: str = Field(validators=[BugFreePython(on_fail=\"reask\")])\n",
     "\n",
     "    class Config:\n",
     "        arbitrary_types_allowed = True"
@@ -114,7 +113,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 41,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -132,9 +131,18 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 42,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/zaydsimjee/workspace/guardrails/guardrails/validatorsattr.py:285: UserWarning: Validator bug-free-python is not valid for element pythoncode.\n",
+      "  warnings.warn(\n"
+     ]
+    }
+   ],
    "source": [
     "guard = gd.Guard.from_rail_string(rail_str)"
    ]
@@ -148,7 +156,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 43,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -165,7 +173,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 44,
    "metadata": {},
    "outputs": [
     {
@@ -182,7 +190,7 @@
        "Given below is XML that describes the information to extract from this document and the tags to extract it into.\n",
        "\n",
        "<span style=\"font-weight: bold\">&lt;</span><span style=\"color: #ff00ff; text-decoration-color: #ff00ff; font-weight: bold\">output</span><span style=\"color: #000000; text-decoration-color: #000000\">&gt;</span>\n",
-       "<span style=\"color: #000000; text-decoration-color: #000000\">    &lt;pythoncode </span><span style=\"color: #808000; text-decoration-color: #808000\">name</span><span style=\"color: #000000; text-decoration-color: #000000\">=</span><span style=\"color: #008000; text-decoration-color: #008000\">\"python_code\"</span><span style=\"color: #000000; text-decoration-color: #000000\"> </span><span style=\"color: #808000; text-decoration-color: #808000\">format</span><span style=\"color: #000000; text-decoration-color: #000000\">=</span><span style=\"color: #008000; text-decoration-color: #008000\">\"bug-free-python\"</span><span style=\"color: #800080; text-decoration-color: #800080\">/</span><span style=\"color: #000000; text-decoration-color: #000000\">&gt;</span>\n",
+       "<span style=\"color: #000000; text-decoration-color: #000000\">    &lt;string </span><span style=\"color: #808000; text-decoration-color: #808000\">name</span><span style=\"color: #000000; text-decoration-color: #000000\">=</span><span style=\"color: #008000; text-decoration-color: #008000\">\"python_code\"</span><span style=\"color: #000000; text-decoration-color: #000000\"> </span><span style=\"color: #808000; text-decoration-color: #808000\">format</span><span style=\"color: #000000; text-decoration-color: #000000\">=</span><span style=\"color: #008000; text-decoration-color: #008000\">\"bug-free-python\"</span><span style=\"color: #800080; text-decoration-color: #800080\">/</span><span style=\"color: #000000; text-decoration-color: #000000\">&gt;</span>\n",
        "<span style=\"color: #000000; text-decoration-color: #000000\">&lt;</span><span style=\"color: #800080; text-decoration-color: #800080\">/</span><span style=\"color: #ff00ff; text-decoration-color: #ff00ff\">output</span><span style=\"color: #000000; text-decoration-color: #000000\">&gt;</span>\n",
        "\n",
        "\n",
@@ -211,7 +219,7 @@
        "Given below is XML that describes the information to extract from this document and the tags to extract it into.\n",
        "\n",
        "\u001b[1m<\u001b[0m\u001b[1;95moutput\u001b[0m\u001b[39m>\u001b[0m\n",
-       "\u001b[39m    <pythoncode \u001b[0m\u001b[33mname\u001b[0m\u001b[39m=\u001b[0m\u001b[32m\"python_code\"\u001b[0m\u001b[39m \u001b[0m\u001b[33mformat\u001b[0m\u001b[39m=\u001b[0m\u001b[32m\"bug\u001b[0m\u001b[32m-free-python\"\u001b[0m\u001b[35m/\u001b[0m\u001b[39m>\u001b[0m\n",
+       "\u001b[39m    <string \u001b[0m\u001b[33mname\u001b[0m\u001b[39m=\u001b[0m\u001b[32m\"python_code\"\u001b[0m\u001b[39m \u001b[0m\u001b[33mformat\u001b[0m\u001b[39m=\u001b[0m\u001b[32m\"bug\u001b[0m\u001b[32m-free-python\"\u001b[0m\u001b[35m/\u001b[0m\u001b[39m>\u001b[0m\n",
        "\u001b[39m<\u001b[0m\u001b[35m/\u001b[0m\u001b[95moutput\u001b[0m\u001b[39m>\u001b[0m\n",
        "\n",
        "\n",
@@ -246,17 +254,9 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 45,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "Async event loop found, but guard was invoked synchronously.For validator parallelization, please call `validate_async` instead.\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "import openai\n",
     "\n",
@@ -285,7 +285,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 46,
    "metadata": {},
    "outputs": [
     {
@@ -326,7 +326,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 47,
    "metadata": {},
    "outputs": [
     {
@@ -371,7 +371,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 48,
    "metadata": {},
    "outputs": [
     {
@@ -413,7 +413,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.4"
+   "version": "3.11.5"
   },
   "orig_nbformat": 4,
   "vscode": {

docs/examples/check_for_pii.ipynb

@@ -259,7 +259,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.6"
+   "version": "3.11.5"
   }
  },
  "nbformat": 4,

docs/examples/generate_structured_data_cohere.ipynb

@@ -1,34 +1,5 @@
 {
  "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "91ba93d4",
-   "metadata": {},
-   "source": [
-    "First, install dependencies. In addition to standard dependencies, this notebook uses cohere, so we install the cohere SDK."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "899221f3-0496-439b-b284-d6a6603b08c1",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m A new release of pip is available: \u001b[0m\u001b[31;49m23.2.1\u001b[0m\u001b[39;49m -> \u001b[0m\u001b[32;49m23.3\u001b[0m\n",
-      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m To update, run: \u001b[0m\u001b[32;49mpip install --upgrade pip\u001b[0m\n",
-      "Note: you may need to restart the kernel to use updated packages.\n"
-     ]
-    }
-   ],
-   "source": [
-    "%pip install cohere guardrails-ai pydantic==1.10.9 typing openai rich -q"
-   ]
-  },
   {
    "cell_type": "markdown",
    "id": "5c4d8348",