natural-pdf 0.1.3__py3-none-any.whl → 0.1.5__py3-none-any.whl

docs/tutorials/13-semantic-search.ipynb

@@ -0,0 +1,1888 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "f4fa5be5",
+   "metadata": {},
+   "source": [
+    "# Semantic Search Across Multiple Documents\n",
+    "\n",
+    "When working with a collection of PDFs, you might need to find information relevant to a specific query across all documents, not just within a single one. This tutorial demonstrates how to perform semantic search over a `PDFCollection`."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "25274d94",
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2025-04-16T14:59:23.384091Z",
+     "iopub.status.busy": "2025-04-16T14:59:23.383945Z",
+     "iopub.status.idle": "2025-04-16T14:59:23.386424Z",
+     "shell.execute_reply": "2025-04-16T14:59:23.386138Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "#%pip install \"natural-pdf[all]\"\n",
+    "#%pip install \"natural-pdf[search]\"  # Ensure search dependencies are installed"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "78286236",
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2025-04-16T14:59:23.387957Z",
+     "iopub.status.busy": "2025-04-16T14:59:23.387832Z",
+     "iopub.status.idle": "2025-04-16T14:59:33.969693Z",
+     "shell.execute_reply": "2025-04-16T14:59:33.969249Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "natural_pdf.collections.pdf_collection - INFO - Initializing 2 PDF objects...\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\u001b[2m2025-04-16T14:59:29.336679Z\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mInitializing 2 PDF objects... \u001b[0m \u001b[36mlineno\u001b[0m=\u001b[35m145\u001b[0m \u001b[36mmessage\u001b[0m=\u001b[35mInitializing 2 PDF objects...\u001b[0m \u001b[36mmodule\u001b[0m=\u001b[35mnatural_pdf.collections.pdf_collection\u001b[0m\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "[2025-04-16 17:59:29,336] [    INFO] pdf_collection.py:145 - Initializing 2 PDF objects...\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "Loading PDFs:   0%|                                               | 0/2 [00:00<?, ?it/s]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "natural_pdf.core.pdf - INFO - Downloading PDF from URL: https://github.com/jsoma/natural-pdf/raw/refs/heads/main/pdfs/01-practice.pdf\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\u001b[2m2025-04-16T14:59:29.353564Z\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mDownloading PDF from URL: https://github.com/jsoma/natural-pdf/raw/refs/heads/main/pdfs/01-practice.pdf\u001b[0m \u001b[36mlineno\u001b[0m=\u001b[35m80\u001b[0m \u001b[36mmessage\u001b[0m=\u001b[35mDownloading PDF from URL: https://github.com/jsoma/natural-pdf/raw/refs/heads/main/pdfs/01-practice.pdf\u001b[0m \u001b[36mmodule\u001b[0m=\u001b[35mnatural_pdf.core.pdf\u001b[0m\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "[2025-04-16 17:59:29,353] [    INFO] pdf.py:80 - Downloading PDF from URL: https://github.com/jsoma/natural-pdf/raw/refs/heads/main/pdfs/01-practice.pdf\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "natural_pdf.core.pdf - INFO - PDF downloaded to temporary file: /var/folders/25/h3prywj14qb0mlkl2s8bxq5m0000gn/T/tmpwq_3f750.pdf\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\u001b[2m2025-04-16T14:59:29.636697Z\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPDF downloaded to temporary file: /var/folders/25/h3prywj14qb0mlkl2s8bxq5m0000gn/T/tmpwq_3f750.pdf\u001b[0m \u001b[36mlineno\u001b[0m=\u001b[35m93\u001b[0m \u001b[36mmessage\u001b[0m=\u001b[35mPDF downloaded to temporary file: /var/folders/25/h3prywj14qb0mlkl2s8bxq5m0000gn/T/tmpwq_3f750.pdf\u001b[0m \u001b[36mmodule\u001b[0m=\u001b[35mnatural_pdf.core.pdf\u001b[0m\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "[2025-04-16 17:59:29,636] [    INFO] pdf.py:93 - PDF downloaded to temporary file: /var/folders/25/h3prywj14qb0mlkl2s8bxq5m0000gn/T/tmpwq_3f750.pdf\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "natural_pdf.core.pdf - INFO - Initializing PDF from /var/folders/25/h3prywj14qb0mlkl2s8bxq5m0000gn/T/tmpwq_3f750.pdf\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\u001b[2m2025-04-16T14:59:29.637422Z\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mInitializing PDF from /var/folders/25/h3prywj14qb0mlkl2s8bxq5m0000gn/T/tmpwq_3f750.pdf\u001b[0m \u001b[36mlineno\u001b[0m=\u001b[35m106\u001b[0m \u001b[36mmessage\u001b[0m=\u001b[35mInitializing PDF from /var/folders/25/h3prywj14qb0mlkl2s8bxq5m0000gn/T/tmpwq_3f750.pdf\u001b[0m \u001b[36mmodule\u001b[0m=\u001b[35mnatural_pdf.core.pdf\u001b[0m\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "[2025-04-16 17:59:29,637] [    INFO] pdf.py:106 - Initializing PDF from /var/folders/25/h3prywj14qb0mlkl2s8bxq5m0000gn/T/tmpwq_3f750.pdf\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "natural_pdf.ocr.ocr_manager - INFO - OCRManager initialized.\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\u001b[2m2025-04-16T14:59:29.638958Z\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mOCRManager initialized.       \u001b[0m \u001b[36mlineno\u001b[0m=\u001b[35m38\u001b[0m \u001b[36mmessage\u001b[0m=\u001b[35mOCRManager initialized.\u001b[0m \u001b[36mmodule\u001b[0m=\u001b[35mnatural_pdf.ocr.ocr_manager\u001b[0m\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "[2025-04-16 17:59:29,638] [    INFO] ocr_manager.py:38 - OCRManager initialized.\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "natural_pdf.analyzers.layout.layout_manager - INFO - LayoutManager initialized. Available engines: ['yolo', 'tatr', 'paddle', 'surya', 'docling']\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\u001b[2m2025-04-16T14:59:29.639737Z\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mLayoutManager initialized. Available engines: ['yolo', 'tatr', 'paddle', 'surya', 'docling']\u001b[0m \u001b[36mlineno\u001b[0m=\u001b[35m68\u001b[0m \u001b[36mmessage\u001b[0m=\u001b[35mLayoutManager initialized. Available engines: ['yolo', 'tatr', 'paddle', 'surya', 'docling']\u001b[0m \u001b[36mmodule\u001b[0m=\u001b[35mnatural_pdf.analyzers.layout.layout_manager\u001b[0m\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "[2025-04-16 17:59:29,639] [    INFO] layout_manager.py:68 - LayoutManager initialized. Available engines: ['yolo', 'tatr', 'paddle', 'surya', 'docling']\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "natural_pdf.core.highlighting_service - INFO - HighlightingService initialized with ColorManager.\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\u001b[2m2025-04-16T14:59:29.640333Z\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mHighlightingService initialized with ColorManager.\u001b[0m \u001b[36mlineno\u001b[0m=\u001b[35m286\u001b[0m \u001b[36mmessage\u001b[0m=\u001b[35mHighlightingService initialized with ColorManager.\u001b[0m \u001b[36mmodule\u001b[0m=\u001b[35mnatural_pdf.core.highlighting_service\u001b[0m\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "[2025-04-16 17:59:29,640] [    INFO] highlighting_service.py:286 - HighlightingService initialized with ColorManager.\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "natural_pdf.core.pdf - INFO - Initialized HighlightingService.\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\u001b[2m2025-04-16T14:59:29.642175Z\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mInitialized HighlightingService.\u001b[0m \u001b[36mlineno\u001b[0m=\u001b[35m141\u001b[0m \u001b[36mmessage\u001b[0m=\u001b[35mInitialized HighlightingService.\u001b[0m \u001b[36mmodule\u001b[0m=\u001b[35mnatural_pdf.core.pdf\u001b[0m\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "[2025-04-16 17:59:29,641] [    INFO] pdf.py:141 - Initialized HighlightingService.\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "natural_pdf.core.pdf - INFO - PDF 'https://github.com/jsoma/natural-pdf/raw/refs/heads/main/pdfs/01-practice.pdf' initialized with 1 pages.\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\u001b[2m2025-04-16T14:59:29.643262Z\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPDF 'https://github.com/jsoma/natural-pdf/raw/refs/heads/main/pdfs/01-practice.pdf' initialized with 1 pages.\u001b[0m \u001b[36mlineno\u001b[0m=\u001b[35m142\u001b[0m \u001b[36mmessage\u001b[0m=\u001b[35mPDF 'https://github.com/jsoma/natural-pdf/raw/refs/heads/main/pdfs/01-practice.pdf' initialized with 1 pages.\u001b[0m \u001b[36mmodule\u001b[0m=\u001b[35mnatural_pdf.core.pdf\u001b[0m\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "[2025-04-16 17:59:29,643] [    INFO] pdf.py:142 - PDF 'https://github.com/jsoma/natural-pdf/raw/refs/heads/main/pdfs/01-practice.pdf' initialized with 1 pages.\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "Loading PDFs:  50%|███████████████████▌                   | 1/2 [00:00<00:00,  3.44it/s]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "natural_pdf.core.pdf - INFO - Downloading PDF from URL: https://github.com/jsoma/natural-pdf/raw/refs/heads/main/pdfs/Atlanta_Public_Schools_GA_sample.pdf\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\u001b[2m2025-04-16T14:59:29.644068Z\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mDownloading PDF from URL: https://github.com/jsoma/natural-pdf/raw/refs/heads/main/pdfs/Atlanta_Public_Schools_GA_sample.pdf\u001b[0m \u001b[36mlineno\u001b[0m=\u001b[35m80\u001b[0m \u001b[36mmessage\u001b[0m=\u001b[35mDownloading PDF from URL: https://github.com/jsoma/natural-pdf/raw/refs/heads/main/pdfs/Atlanta_Public_Schools_GA_sample.pdf\u001b[0m \u001b[36mmodule\u001b[0m=\u001b[35mnatural_pdf.core.pdf\u001b[0m\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "[2025-04-16 17:59:29,643] [    INFO] pdf.py:80 - Downloading PDF from URL: https://github.com/jsoma/natural-pdf/raw/refs/heads/main/pdfs/Atlanta_Public_Schools_GA_sample.pdf\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "natural_pdf.core.pdf - INFO - PDF downloaded to temporary file: /var/folders/25/h3prywj14qb0mlkl2s8bxq5m0000gn/T/tmpofyt17qz.pdf\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\u001b[2m2025-04-16T14:59:33.955839Z\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPDF downloaded to temporary file: /var/folders/25/h3prywj14qb0mlkl2s8bxq5m0000gn/T/tmpofyt17qz.pdf\u001b[0m \u001b[36mlineno\u001b[0m=\u001b[35m93\u001b[0m \u001b[36mmessage\u001b[0m=\u001b[35mPDF downloaded to temporary file: /var/folders/25/h3prywj14qb0mlkl2s8bxq5m0000gn/T/tmpofyt17qz.pdf\u001b[0m \u001b[36mmodule\u001b[0m=\u001b[35mnatural_pdf.core.pdf\u001b[0m\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "[2025-04-16 17:59:33,952] [    INFO] pdf.py:93 - PDF downloaded to temporary file: /var/folders/25/h3prywj14qb0mlkl2s8bxq5m0000gn/T/tmpofyt17qz.pdf\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "natural_pdf.core.pdf - INFO - Initializing PDF from /var/folders/25/h3prywj14qb0mlkl2s8bxq5m0000gn/T/tmpofyt17qz.pdf\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\u001b[2m2025-04-16T14:59:33.957471Z\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mInitializing PDF from /var/folders/25/h3prywj14qb0mlkl2s8bxq5m0000gn/T/tmpofyt17qz.pdf\u001b[0m \u001b[36mlineno\u001b[0m=\u001b[35m106\u001b[0m \u001b[36mmessage\u001b[0m=\u001b[35mInitializing PDF from /var/folders/25/h3prywj14qb0mlkl2s8bxq5m0000gn/T/tmpofyt17qz.pdf\u001b[0m \u001b[36mmodule\u001b[0m=\u001b[35mnatural_pdf.core.pdf\u001b[0m\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "[2025-04-16 17:59:33,957] [    INFO] pdf.py:106 - Initializing PDF from /var/folders/25/h3prywj14qb0mlkl2s8bxq5m0000gn/T/tmpofyt17qz.pdf\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "natural_pdf.ocr.ocr_manager - INFO - OCRManager initialized.\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\u001b[2m2025-04-16T14:59:33.959364Z\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mOCRManager initialized.       \u001b[0m \u001b[36mlineno\u001b[0m=\u001b[35m38\u001b[0m \u001b[36mmessage\u001b[0m=\u001b[35mOCRManager initialized.\u001b[0m \u001b[36mmodule\u001b[0m=\u001b[35mnatural_pdf.ocr.ocr_manager\u001b[0m\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "[2025-04-16 17:59:33,958] [    INFO] ocr_manager.py:38 - OCRManager initialized.\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "natural_pdf.analyzers.layout.layout_manager - INFO - LayoutManager initialized. Available engines: ['yolo', 'tatr', 'paddle', 'surya', 'docling']\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\u001b[2m2025-04-16T14:59:33.960339Z\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mLayoutManager initialized. Available engines: ['yolo', 'tatr', 'paddle', 'surya', 'docling']\u001b[0m \u001b[36mlineno\u001b[0m=\u001b[35m68\u001b[0m \u001b[36mmessage\u001b[0m=\u001b[35mLayoutManager initialized. Available engines: ['yolo', 'tatr', 'paddle', 'surya', 'docling']\u001b[0m \u001b[36mmodule\u001b[0m=\u001b[35mnatural_pdf.analyzers.layout.layout_manager\u001b[0m\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "[2025-04-16 17:59:33,960] [    INFO] layout_manager.py:68 - LayoutManager initialized. Available engines: ['yolo', 'tatr', 'paddle', 'surya', 'docling']\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "natural_pdf.core.highlighting_service - INFO - HighlightingService initialized with ColorManager.\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\u001b[2m2025-04-16T14:59:33.961122Z\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mHighlightingService initialized with ColorManager.\u001b[0m \u001b[36mlineno\u001b[0m=\u001b[35m286\u001b[0m \u001b[36mmessage\u001b[0m=\u001b[35mHighlightingService initialized with ColorManager.\u001b[0m \u001b[36mmodule\u001b[0m=\u001b[35mnatural_pdf.core.highlighting_service\u001b[0m\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "[2025-04-16 17:59:33,960] [    INFO] highlighting_service.py:286 - HighlightingService initialized with ColorManager.\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "natural_pdf.core.pdf - INFO - Initialized HighlightingService.\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\u001b[2m2025-04-16T14:59:33.964681Z\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mInitialized HighlightingService.\u001b[0m \u001b[36mlineno\u001b[0m=\u001b[35m141\u001b[0m \u001b[36mmessage\u001b[0m=\u001b[35mInitialized HighlightingService.\u001b[0m \u001b[36mmodule\u001b[0m=\u001b[35mnatural_pdf.core.pdf\u001b[0m\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "[2025-04-16 17:59:33,964] [    INFO] pdf.py:141 - Initialized HighlightingService.\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "natural_pdf.core.pdf - INFO - PDF 'https://github.com/jsoma/natural-pdf/raw/refs/heads/main/pdfs/Atlanta_Public_Schools_GA_sample.pdf' initialized with 5 pages.\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\u001b[2m2025-04-16T14:59:33.965372Z\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPDF 'https://github.com/jsoma/natural-pdf/raw/refs/heads/main/pdfs/Atlanta_Public_Schools_GA_sample.pdf' initialized with 5 pages.\u001b[0m \u001b[36mlineno\u001b[0m=\u001b[35m142\u001b[0m \u001b[36mmessage\u001b[0m=\u001b[35mPDF 'https://github.com/jsoma/natural-pdf/raw/refs/heads/main/pdfs/Atlanta_Public_Schools_GA_sample.pdf' initialized with 5 pages.\u001b[0m \u001b[36mmodule\u001b[0m=\u001b[35mnatural_pdf.core.pdf\u001b[0m\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "[2025-04-16 17:59:33,965] [    INFO] pdf.py:142 - PDF 'https://github.com/jsoma/natural-pdf/raw/refs/heads/main/pdfs/Atlanta_Public_Schools_GA_sample.pdf' initialized with 5 pages.\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "Loading PDFs: 100%|███████████████████████████████████████| 2/2 [00:04<00:00,  2.66s/it]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r",
+      "Loading PDFs: 100%|███████████████████████████████████████| 2/2 [00:04<00:00,  2.31s/it]"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "natural_pdf.collections.pdf_collection - INFO - Successfully initialized 2 PDFs. Failed: 0\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\u001b[2m2025-04-16T14:59:33.966755Z\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mSuccessfully initialized 2 PDFs. Failed: 0\u001b[0m \u001b[36mlineno\u001b[0m=\u001b[35m154\u001b[0m \u001b[36mmessage\u001b[0m=\u001b[35mSuccessfully initialized 2 PDFs. Failed: 0\u001b[0m \u001b[36mmodule\u001b[0m=\u001b[35mnatural_pdf.collections.pdf_collection\u001b[0m\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "[2025-04-16 17:59:33,966] [    INFO] pdf_collection.py:154 - Successfully initialized 2 PDFs. Failed: 0\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Created collection with 2 PDFs.\n"
+     ]
+    }
+   ],
+   "source": [
+    "import logging\n",
+    "import natural_pdf\n",
+    "\n",
+    "# Optional: Configure logging to see progress\n",
+    "natural_pdf.configure_logging(level=logging.INFO)\n",
+    "\n",
+    "# Define the paths to your PDF files\n",
+    "pdf_paths = [\n",
+    "    \"https://github.com/jsoma/natural-pdf/raw/refs/heads/main/pdfs/01-practice.pdf\",\n",
+    "    \"https://github.com/jsoma/natural-pdf/raw/refs/heads/main/pdfs/Atlanta_Public_Schools_GA_sample.pdf\"\n",
+    "    # Add more PDF paths as needed\n",
+    "]\n",
+    "\n",
+    "# Create a PDFCollection\n",
+    "collection = natural_pdf.PDFCollection(pdf_paths)\n",
+    "print(f\"Created collection with {len(collection.pdfs)} PDFs.\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "57c16881",
+   "metadata": {},
+   "source": [
+    "## Initializing the Search Index\n",
+    "\n",
+    "Before performing a search, you need to initialize the search capabilities for the collection. This involves processing the documents and building an index."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "53b5decd",
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2025-04-16T14:59:33.973935Z",
+     "iopub.status.busy": "2025-04-16T14:59:33.972405Z",
+     "iopub.status.idle": "2025-04-16T14:59:37.674880Z",
+     "shell.execute_reply": "2025-04-16T14:59:37.674549Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "natural_pdf.search.searchable_mixin - INFO - Using default collection name 'default_collection' for in-memory service.\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\u001b[2m2025-04-16T14:59:33.975593Z\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mUsing default collection name 'default_collection' for in-memory service.\u001b[0m \u001b[36mlineno\u001b[0m=\u001b[35m104\u001b[0m \u001b[36mmessage\u001b[0m=\u001b[35mUsing default collection name 'default_collection' for in-memory service.\u001b[0m \u001b[36mmodule\u001b[0m=\u001b[35mnatural_pdf.search.searchable_mixin\u001b[0m\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "[2025-04-16 17:59:33,974] [    INFO] searchable_mixin.py:104 - Using default collection name 'default_collection' for in-memory service.\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "natural_pdf.search.searchable_mixin - INFO - Creating new SearchService: name='default_collection', persist=False, model=default\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\u001b[2m2025-04-16T14:59:33.976579Z\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCreating new SearchService: name='default_collection', persist=False, model=default\u001b[0m \u001b[36mlineno\u001b[0m=\u001b[35m106\u001b[0m \u001b[36mmessage\u001b[0m=\u001b[35mCreating new SearchService: name='default_collection', persist=False, model=default\u001b[0m \u001b[36mmodule\u001b[0m=\u001b[35mnatural_pdf.search.searchable_mixin\u001b[0m\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "[2025-04-16 17:59:33,976] [    INFO] searchable_mixin.py:106 - Creating new SearchService: name='default_collection', persist=False, model=default\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "natural_pdf.search.haystack_search_service - INFO - HaystackSearchService initialized for collection='default_collection' (persist=False, model='sentence-transformers/all-MiniLM-L6-v2'). Default path: './natural_pdf_index'\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\u001b[2m2025-04-16T14:59:33.977956Z\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mHaystackSearchService initialized for collection='default_collection' (persist=False, model='sentence-transformers/all-MiniLM-L6-v2'). Default path: './natural_pdf_index'\u001b[0m \u001b[36mlineno\u001b[0m=\u001b[35m106\u001b[0m \u001b[36mmessage\u001b[0m=\u001b[35mHaystackSearchService initialized for collection='default_collection' (persist=False, model='sentence-transformers/all-MiniLM-L6-v2'). Default path: './natural_pdf_index'\u001b[0m \u001b[36mmodule\u001b[0m=\u001b[35mnatural_pdf.search.haystack_search_service\u001b[0m\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "[2025-04-16 17:59:33,977] [    INFO] haystack_search_service.py:106 - HaystackSearchService initialized for collection='default_collection' (persist=False, model='sentence-transformers/all-MiniLM-L6-v2'). Default path: './natural_pdf_index'\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "natural_pdf.search - INFO - Created new HaystackSearchService instance for collection 'default_collection'.\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\u001b[2m2025-04-16T14:59:33.978879Z\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCreated new HaystackSearchService instance for collection 'default_collection'.\u001b[0m \u001b[36mlineno\u001b[0m=\u001b[35m80\u001b[0m \u001b[36mmessage\u001b[0m=\u001b[35mCreated new HaystackSearchService instance for collection 'default_collection'.\u001b[0m \u001b[36mmodule\u001b[0m=\u001b[35mnatural_pdf.search\u001b[0m\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "[2025-04-16 17:59:33,978] [    INFO] __init__.py:80 - Created new HaystackSearchService instance for collection 'default_collection'.\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "natural_pdf.search.searchable_mixin - INFO - index=True: Proceeding to index collection immediately after search initialization.\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\u001b[2m2025-04-16T14:59:33.979919Z\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mindex=True: Proceeding to index collection immediately after search initialization.\u001b[0m \u001b[36mlineno\u001b[0m=\u001b[35m141\u001b[0m \u001b[36mmessage\u001b[0m=\u001b[35mindex=True: Proceeding to index collection immediately after search initialization.\u001b[0m \u001b[36mmodule\u001b[0m=\u001b[35mnatural_pdf.search.searchable_mixin\u001b[0m\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "[2025-04-16 17:59:33,979] [    INFO] searchable_mixin.py:141 - index=True: Proceeding to index collection immediately after search initialization.\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "natural_pdf.search.searchable_mixin - INFO - Starting internal indexing process into SearchService collection 'default_collection'...\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\u001b[2m2025-04-16T14:59:33.980745Z\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mStarting internal indexing process into SearchService collection 'default_collection'...\u001b[0m \u001b[36mlineno\u001b[0m=\u001b[35m152\u001b[0m \u001b[36mmessage\u001b[0m=\u001b[35mStarting internal indexing process into SearchService collection 'default_collection'...\u001b[0m \u001b[36mmodule\u001b[0m=\u001b[35mnatural_pdf.search.searchable_mixin\u001b[0m\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "[2025-04-16 17:59:33,980] [    INFO] searchable_mixin.py:152 - Starting internal indexing process into SearchService collection 'default_collection'...\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "natural_pdf.search.searchable_mixin - INFO - Prepared 6 indexable items for indexing.\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\u001b[2m2025-04-16T14:59:33.981554Z\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPrepared 6 indexable items for indexing.\u001b[0m \u001b[36mlineno\u001b[0m=\u001b[35m165\u001b[0m \u001b[36mmessage\u001b[0m=\u001b[35mPrepared 6 indexable items for indexing.\u001b[0m \u001b[36mmodule\u001b[0m=\u001b[35mnatural_pdf.search.searchable_mixin\u001b[0m\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "[2025-04-16 17:59:33,981] [    INFO] searchable_mixin.py:165 - Prepared 6 indexable items for indexing.\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "natural_pdf.search.haystack_search_service - INFO - Index request for collection='default_collection', docs=6, model='sentence-transformers/all-MiniLM-L6-v2', force=False, persist=False\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\u001b[2m2025-04-16T14:59:33.982471Z\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mIndex request for collection='default_collection', docs=6, model='sentence-transformers/all-MiniLM-L6-v2', force=False, persist=False\u001b[0m \u001b[36mlineno\u001b[0m=\u001b[35m210\u001b[0m \u001b[36mmessage\u001b[0m=\u001b[35mIndex request for collection='default_collection', docs=6, model='sentence-transformers/all-MiniLM-L6-v2', force=False, persist=False\u001b[0m \u001b[36mmodule\u001b[0m=\u001b[35mnatural_pdf.search.haystack_search_service\u001b[0m\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "[2025-04-16 17:59:33,982] [    INFO] haystack_search_service.py:210 - Index request for collection='default_collection', docs=6, model='sentence-transformers/all-MiniLM-L6-v2', force=False, persist=False\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "natural_pdf.search.haystack_search_service - INFO - Created SentenceTransformersDocumentEmbedder. Model: sentence-transformers/all-MiniLM-L6-v2, Device: ComponentDevice(_single_device=Device(type=<DeviceType.MPS: 'mps'>, id=None), _multiple_devices=None)\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\u001b[2m2025-04-16T14:59:36.828108Z\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCreated SentenceTransformersDocumentEmbedder. Model: sentence-transformers/all-MiniLM-L6-v2, Device: ComponentDevice(_single_device=Device(type=<DeviceType.MPS: 'mps'>, id=None), _multiple_devices=None)\u001b[0m \u001b[36mlineno\u001b[0m=\u001b[35m146\u001b[0m \u001b[36mmessage\u001b[0m=\u001b[35mCreated SentenceTransformersDocumentEmbedder. Model: sentence-transformers/all-MiniLM-L6-v2, Device: ComponentDevice(_single_device=Device(type=<DeviceType.MPS: 'mps'>, id=None), _multiple_devices=None)\u001b[0m \u001b[36mmodule\u001b[0m=\u001b[35mnatural_pdf.search.haystack_search_service\u001b[0m\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "[2025-04-16 17:59:36,827] [    INFO] haystack_search_service.py:146 - Created SentenceTransformersDocumentEmbedder. Model: sentence-transformers/all-MiniLM-L6-v2, Device: ComponentDevice(_single_device=Device(type=<DeviceType.MPS: 'mps'>, id=None), _multiple_devices=None)\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "natural_pdf.search.haystack_search_service - INFO - Preparing Haystack Documents from 6 indexable items...\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\u001b[2m2025-04-16T14:59:36.828818Z\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPreparing Haystack Documents from 6 indexable items...\u001b[0m \u001b[36mlineno\u001b[0m=\u001b[35m241\u001b[0m \u001b[36mmessage\u001b[0m=\u001b[35mPreparing Haystack Documents from 6 indexable items...\u001b[0m \u001b[36mmodule\u001b[0m=\u001b[35mnatural_pdf.search.haystack_search_service\u001b[0m\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "[2025-04-16 17:59:36,828] [    INFO] haystack_search_service.py:241 - Preparing Haystack Documents from 6 indexable items...\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "natural_pdf.search.haystack_search_service - INFO - Embedding 6 documents using 'sentence-transformers/all-MiniLM-L6-v2'...\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\u001b[2m2025-04-16T14:59:37.420176Z\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mEmbedding 6 documents using 'sentence-transformers/all-MiniLM-L6-v2'...\u001b[0m \u001b[36mlineno\u001b[0m=\u001b[35m281\u001b[0m \u001b[36mmessage\u001b[0m=\u001b[35mEmbedding 6 documents using 'sentence-transformers/all-MiniLM-L6-v2'...\u001b[0m \u001b[36mmodule\u001b[0m=\u001b[35mnatural_pdf.search.haystack_search_service\u001b[0m\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "[2025-04-16 17:59:37,419] [    INFO] haystack_search_service.py:281 - Embedding 6 documents using 'sentence-transformers/all-MiniLM-L6-v2'...\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "c680fa26e0ff4501b6ef8eacd599090e",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Batches:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "natural_pdf.search.haystack_search_service - INFO - Successfully embedded 6 documents.\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\u001b[2m2025-04-16T14:59:37.669019Z\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mSuccessfully embedded 6 documents.\u001b[0m \u001b[36mlineno\u001b[0m=\u001b[35m286\u001b[0m \u001b[36mmessage\u001b[0m=\u001b[35mSuccessfully embedded 6 documents.\u001b[0m \u001b[36mmodule\u001b[0m=\u001b[35mnatural_pdf.search.haystack_search_service\u001b[0m\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "[2025-04-16 17:59:37,668] [    INFO] haystack_search_service.py:286 - Successfully embedded 6 documents.\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "natural_pdf.search.haystack_search_service - INFO - Writing 6 embedded documents to store 'default_collection'...\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\u001b[2m2025-04-16T14:59:37.669875Z\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mWriting 6 embedded documents to store 'default_collection'...\u001b[0m \u001b[36mlineno\u001b[0m=\u001b[35m302\u001b[0m \u001b[36mmessage\u001b[0m=\u001b[35mWriting 6 embedded documents to store 'default_collection'...\u001b[0m \u001b[36mmodule\u001b[0m=\u001b[35mnatural_pdf.search.haystack_search_service\u001b[0m\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "[2025-04-16 17:59:37,669] [    INFO] haystack_search_service.py:302 - Writing 6 embedded documents to store 'default_collection'...\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "natural_pdf.search.haystack_search_service - INFO - Successfully wrote 6 documents to store 'default_collection'.\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\u001b[2m2025-04-16T14:59:37.671847Z\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mSuccessfully wrote 6 documents to store 'default_collection'.\u001b[0m \u001b[36mlineno\u001b[0m=\u001b[35m308\u001b[0m \u001b[36mmessage\u001b[0m=\u001b[35mSuccessfully wrote 6 documents to store 'default_collection'.\u001b[0m \u001b[36mmodule\u001b[0m=\u001b[35mnatural_pdf.search.haystack_search_service\u001b[0m\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "[2025-04-16 17:59:37,671] [    INFO] haystack_search_service.py:308 - Successfully wrote 6 documents to store 'default_collection'.\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "natural_pdf.search.haystack_search_service - INFO - Store 'default_collection' document count after write: 6\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\u001b[2m2025-04-16T14:59:37.672454Z\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mStore 'default_collection' document count after write: 6\u001b[0m \u001b[36mlineno\u001b[0m=\u001b[35m310\u001b[0m \u001b[36mmessage\u001b[0m=\u001b[35mStore 'default_collection' document count after write: 6\u001b[0m \u001b[36mmodule\u001b[0m=\u001b[35mnatural_pdf.search.haystack_search_service\u001b[0m\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "[2025-04-16 17:59:37,672] [    INFO] haystack_search_service.py:310 - Store 'default_collection' document count after write: 6\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "natural_pdf.search.searchable_mixin - INFO - Successfully completed indexing into SearchService collection 'default_collection'.\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\u001b[2m2025-04-16T14:59:37.673044Z\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mSuccessfully completed indexing into SearchService collection 'default_collection'.\u001b[0m \u001b[36mlineno\u001b[0m=\u001b[35m173\u001b[0m \u001b[36mmessage\u001b[0m=\u001b[35mSuccessfully completed indexing into SearchService collection 'default_collection'.\u001b[0m \u001b[36mmodule\u001b[0m=\u001b[35mnatural_pdf.search.searchable_mixin\u001b[0m\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "[2025-04-16 17:59:37,672] [    INFO] searchable_mixin.py:173 - Successfully completed indexing into SearchService collection 'default_collection'.\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Search index initialized.\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Initialize search. 'index=True' builds the index immediately.\n",
+    "# This might take some time depending on the number and size of PDFs.\n",
+    "collection.init_search(index=True) \n",
+    "print(\"Search index initialized.\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "86416bd8",
+   "metadata": {},
+   "source": [
+    "## Performing a Semantic Search\n",
+    "\n",
+    "Once the index is ready, you can use the `find_relevant()` method to search for content semantically related to your query."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "c4f6ed33",
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2025-04-16T14:59:37.677294Z",
+     "iopub.status.busy": "2025-04-16T14:59:37.677184Z",
+     "iopub.status.idle": "2025-04-16T14:59:37.865461Z",
+     "shell.execute_reply": "2025-04-16T14:59:37.865159Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "natural_pdf.search.searchable_mixin - INFO - Searching collection 'default_collection' via HaystackSearchService...\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\u001b[2m2025-04-16T14:59:37.678388Z\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mSearching collection 'default_collection' via HaystackSearchService...\u001b[0m \u001b[36mlineno\u001b[0m=\u001b[35m244\u001b[0m \u001b[36mmessage\u001b[0m=\u001b[35mSearching collection 'default_collection' via HaystackSearchService...\u001b[0m \u001b[36mmodule\u001b[0m=\u001b[35mnatural_pdf.search.searchable_mixin\u001b[0m\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "[2025-04-16 17:59:37,677] [    INFO] searchable_mixin.py:244 - Searching collection 'default_collection' via HaystackSearchService...\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "natural_pdf.search.haystack_search_service - INFO - Search request for collection='default_collection', query_type=str, options=TextSearchOptions(top_k=10, retriever_top_k=20, filters=None, use_reranker=True, reranker_instance=None, reranker_model=None, reranker_api_key=None)\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\u001b[2m2025-04-16T14:59:37.679015Z\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mSearch request for collection='default_collection', query_type=str, options=TextSearchOptions(top_k=10, retriever_top_k=20, filters=None, use_reranker=True, reranker_instance=None, reranker_model=None, reranker_api_key=None)\u001b[0m \u001b[36mlineno\u001b[0m=\u001b[35m318\u001b[0m \u001b[36mmessage\u001b[0m=\u001b[35mSearch request for collection='default_collection', query_type=str, options=TextSearchOptions(top_k=10, retriever_top_k=20, filters=None, use_reranker=True, reranker_instance=None, reranker_model=None, reranker_api_key=None)\u001b[0m \u001b[36mmodule\u001b[0m=\u001b[35mnatural_pdf.search.haystack_search_service\u001b[0m\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "[2025-04-16 17:59:37,678] [    INFO] haystack_search_service.py:318 - Search request for collection='default_collection', query_type=str, options=TextSearchOptions(top_k=10, retriever_top_k=20, filters=None, use_reranker=True, reranker_instance=None, reranker_model=None, reranker_api_key=None)\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "natural_pdf.search.haystack_search_service - INFO - Created SentenceTransformersTextEmbedder. Model: sentence-transformers/all-MiniLM-L6-v2, Device: ComponentDevice(_single_device=Device(type=<DeviceType.MPS: 'mps'>, id=None), _multiple_devices=None)\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\u001b[2m2025-04-16T14:59:37.679709Z\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCreated SentenceTransformersTextEmbedder. Model: sentence-transformers/all-MiniLM-L6-v2, Device: ComponentDevice(_single_device=Device(type=<DeviceType.MPS: 'mps'>, id=None), _multiple_devices=None)\u001b[0m \u001b[36mlineno\u001b[0m=\u001b[35m164\u001b[0m \u001b[36mmessage\u001b[0m=\u001b[35mCreated SentenceTransformersTextEmbedder. Model: sentence-transformers/all-MiniLM-L6-v2, Device: ComponentDevice(_single_device=Device(type=<DeviceType.MPS: 'mps'>, id=None), _multiple_devices=None)\u001b[0m \u001b[36mmodule\u001b[0m=\u001b[35mnatural_pdf.search.haystack_search_service\u001b[0m\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "[2025-04-16 17:59:37,679] [    INFO] haystack_search_service.py:164 - Created SentenceTransformersTextEmbedder. Model: sentence-transformers/all-MiniLM-L6-v2, Device: ComponentDevice(_single_device=Device(type=<DeviceType.MPS: 'mps'>, id=None), _multiple_devices=None)\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "d256c819166642f68442fa041de1ba67",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Batches:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "natural_pdf.search.haystack_search_service - INFO - Running retrieval pipeline for collection 'default_collection'...\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\u001b[2m2025-04-16T14:59:37.859154Z\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mRunning retrieval pipeline for collection 'default_collection'...\u001b[0m \u001b[36mlineno\u001b[0m=\u001b[35m401\u001b[0m \u001b[36mmessage\u001b[0m=\u001b[35mRunning retrieval pipeline for collection 'default_collection'...\u001b[0m \u001b[36mmodule\u001b[0m=\u001b[35mnatural_pdf.search.haystack_search_service\u001b[0m\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "[2025-04-16 17:59:37,858] [    INFO] haystack_search_service.py:401 - Running retrieval pipeline for collection 'default_collection'...\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "natural_pdf.search.haystack_search_service - INFO - Retrieved 6 documents.\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\u001b[2m2025-04-16T14:59:37.863278Z\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mRetrieved 6 documents.        \u001b[0m \u001b[36mlineno\u001b[0m=\u001b[35m410\u001b[0m \u001b[36mmessage\u001b[0m=\u001b[35mRetrieved 6 documents.\u001b[0m \u001b[36mmodule\u001b[0m=\u001b[35mnatural_pdf.search.haystack_search_service\u001b[0m\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "[2025-04-16 17:59:37,862] [    INFO] haystack_search_service.py:410 - Retrieved 6 documents.\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "natural_pdf.search.searchable_mixin - INFO - SearchService returned 6 results from collection 'default_collection'.\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\u001b[2m2025-04-16T14:59:37.863850Z\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mSearchService returned 6 results from collection 'default_collection'.\u001b[0m \u001b[36mlineno\u001b[0m=\u001b[35m266\u001b[0m \u001b[36mmessage\u001b[0m=\u001b[35mSearchService returned 6 results from collection 'default_collection'.\u001b[0m \u001b[36mmodule\u001b[0m=\u001b[35mnatural_pdf.search.searchable_mixin\u001b[0m\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "[2025-04-16 17:59:37,863] [    INFO] searchable_mixin.py:266 - SearchService returned 6 results from collection 'default_collection'.\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Found 6 results for 'american president':\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Perform a search query\n",
+    "query = \"american president\"\n",
+    "results = collection.find_relevant(query)\n",
+    "\n",
+    "print(f\"Found {len(results)} results for '{query}':\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "899900f2",
+   "metadata": {},
+   "source": [
+    "## Understanding Search Results\n",
+    "\n",
+    "The `find_relevant()` method returns a list of dictionaries, each representing a relevant text chunk found in one of the PDFs. Each result includes:\n",
+    "\n",
+    "*   `pdf_path`: The path to the PDF document where the result was found.\n",
+    "*   `page_number`: The page number within the PDF.\n",
+    "*   `score`: A relevance score (higher means more relevant).\n",
+    "*   `content_snippet`: A snippet of the text chunk that matched the query."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "846312a5",
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2025-04-16T14:59:37.867689Z",
+     "iopub.status.busy": "2025-04-16T14:59:37.867564Z",
+     "iopub.status.idle": "2025-04-16T14:59:37.870008Z",
+     "shell.execute_reply": "2025-04-16T14:59:37.869701Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "  1. PDF: /var/folders/25/h3prywj14qb0mlkl2s8bxq5m0000gn/T/tmpofyt17qz.pdf\n",
+      "     Page: 2 (Score: 0.0708)\n",
+      "     Snippet:                                                                                     \n",
+      "                                                                                    \n",
+      "    Library Weeding Log       ...\n",
+      "  2. PDF: /var/folders/25/h3prywj14qb0mlkl2s8bxq5m0000gn/T/tmpofyt17qz.pdf\n",
+      "     Page: 5 (Score: 0.0669)\n",
+      "     Snippet:                                                                                     \n",
+      "                                                                                    \n",
+      "    Library Weeding Log       ...\n",
+      "  3. PDF: /var/folders/25/h3prywj14qb0mlkl2s8bxq5m0000gn/T/tmpwq_3f750.pdf\n",
+      "     Page: 1 (Score: -0.0040)\n",
+      "     Snippet:                                                                                     \n",
+      "                                                                                    \n",
+      "                              ...\n",
+      "  4. PDF: /var/folders/25/h3prywj14qb0mlkl2s8bxq5m0000gn/T/tmpofyt17qz.pdf\n",
+      "     Page: 4 (Score: -0.0245)\n",
+      "     Snippet:                                                                                     \n",
+      "                                                                                    \n",
+      "    Library Weeding Log       ...\n",
+      "  5. PDF: /var/folders/25/h3prywj14qb0mlkl2s8bxq5m0000gn/T/tmpofyt17qz.pdf\n",
+      "     Page: 3 (Score: -0.0445)\n",
+      "     Snippet:                                                                                     \n",
+      "                                                                                    \n",
+      "    Library Weeding Log       ...\n",
+      "  6. PDF: /var/folders/25/h3prywj14qb0mlkl2s8bxq5m0000gn/T/tmpofyt17qz.pdf\n",
+      "     Page: 1 (Score: -0.0473)\n",
+      "     Snippet:                                                                                     \n",
+      "                                                                                    \n",
+      "    Library Weeding Log       ...\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Process and display the results\n",
+    "if results:\n",
+    "    for i, result in enumerate(results):\n",
+    "        print(f\"  {i+1}. PDF: {result['pdf_path']}\")\n",
+    "        print(f\"     Page: {result['page_number']} (Score: {result['score']:.4f})\")\n",
+    "        # Display a snippet of the content\n",
+    "        snippet = result.get('content_snippet', '')\n",
+    "        print(f\"     Snippet: {snippet}...\") \n",
+    "else:\n",
+    "    print(\"  No relevant results found.\")\n",
+    "\n",
+    "# You can access the full content if needed via the result object, \n",
+    "# though 'content_snippet' is usually sufficient for display."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0f9261b5",
+   "metadata": {},
+   "source": [
+    "Semantic search allows you to efficiently query large sets of documents to find the most relevant information without needing exact keyword matches, leveraging the meaning and context of your query. "
+   ]
+  }
+ ],
+ "metadata": {
+  "jupytext": {
+   "cell_metadata_filter": "-all",
+   "main_language": "python",
+   "notebook_metadata_filter": "-all"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.13"
+  },
+  "widgets": {
+   "application/vnd.jupyter.widget-state+json": {
+    "state": {
+     "141f2a3636e04c3f9bfde6ffa25253ea": {
+      "model_module": "@jupyter-widgets/base",
+      "model_module_version": "2.0.0",
+      "model_name": "LayoutModel",
+      "state": {
+       "_model_module": "@jupyter-widgets/base",
+       "_model_module_version": "2.0.0",
+       "_model_name": "LayoutModel",
+       "_view_count": null,
+       "_view_module": "@jupyter-widgets/base",
+       "_view_module_version": "2.0.0",
+       "_view_name": "LayoutView",
+       "align_content": null,
+       "align_items": null,
+       "align_self": null,
+       "border_bottom": null,
+       "border_left": null,
+       "border_right": null,
+       "border_top": null,
+       "bottom": null,
+       "display": null,
+       "flex": null,
+       "flex_flow": null,
+       "grid_area": null,
+       "grid_auto_columns": null,
+       "grid_auto_flow": null,
+       "grid_auto_rows": null,
+       "grid_column": null,
+       "grid_gap": null,
+       "grid_row": null,
+       "grid_template_areas": null,
+       "grid_template_columns": null,
+       "grid_template_rows": null,
+       "height": null,
+       "justify_content": null,
+       "justify_items": null,
+       "left": null,
+       "margin": null,
+       "max_height": null,
+       "max_width": null,
+       "min_height": null,
+       "min_width": null,
+       "object_fit": null,
+       "object_position": null,
+       "order": null,
+       "overflow": null,
+       "padding": null,
+       "right": null,
+       "top": null,
+       "visibility": null,
+       "width": null
+      }
+     },
+     "2a420c66cd7c43229bd55cf377d1e00d": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "ProgressStyleModel",
+      "state": {
+       "_model_module": "@jupyter-widgets/controls",
+       "_model_module_version": "2.0.0",
+       "_model_name": "ProgressStyleModel",
+       "_view_count": null,
+       "_view_module": "@jupyter-widgets/base",
+       "_view_module_version": "2.0.0",
+       "_view_name": "StyleView",
+       "bar_color": null,
+       "description_width": ""
+      }
+     },
+     "33c5442a4c63404899f3bfd8e5ee84c4": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "HTMLModel",
+      "state": {
+       "_dom_classes": [],
+       "_model_module": "@jupyter-widgets/controls",
+       "_model_module_version": "2.0.0",
+       "_model_name": "HTMLModel",
+       "_view_count": null,
+       "_view_module": "@jupyter-widgets/controls",
+       "_view_module_version": "2.0.0",
+       "_view_name": "HTMLView",
+       "description": "",
+       "description_allow_html": false,
+       "layout": "IPY_MODEL_141f2a3636e04c3f9bfde6ffa25253ea",
+       "placeholder": "​",
+       "style": "IPY_MODEL_4046efa4d5604c58a344822710b99068",
+       "tabbable": null,
+       "tooltip": null,
+       "value": " 1/1 [00:00&lt;00:00,  5.67it/s]"
+      }
+     },
+     "4046efa4d5604c58a344822710b99068": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "HTMLStyleModel",
+      "state": {
+       "_model_module": "@jupyter-widgets/controls",
+       "_model_module_version": "2.0.0",
+       "_model_name": "HTMLStyleModel",
+       "_view_count": null,
+       "_view_module": "@jupyter-widgets/base",
+       "_view_module_version": "2.0.0",
+       "_view_name": "StyleView",
+       "background": null,
+       "description_width": "",
+       "font_size": null,
+       "text_color": null
+      }
+     },
+     "41578f932e1e4a549a30f80e2a598676": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "HTMLModel",
+      "state": {
+       "_dom_classes": [],
+       "_model_module": "@jupyter-widgets/controls",
+       "_model_module_version": "2.0.0",
+       "_model_name": "HTMLModel",
+       "_view_count": null,
+       "_view_module": "@jupyter-widgets/controls",
+       "_view_module_version": "2.0.0",
+       "_view_name": "HTMLView",
+       "description": "",
+       "description_allow_html": false,
+       "layout": "IPY_MODEL_f21b692c698847d8b9e4a514be59eb4f",
+       "placeholder": "​",
+       "style": "IPY_MODEL_4dd085e5a6c8425b932640ba38cf3c2c",
+       "tabbable": null,
+       "tooltip": null,
+       "value": "Batches: 100%"
+      }
+     },
+     "4569f5281db341da993745bf202d0a05": {
+      "model_module": "@jupyter-widgets/base",
+      "model_module_version": "2.0.0",
+      "model_name": "LayoutModel",
+      "state": {
+       "_model_module": "@jupyter-widgets/base",
+       "_model_module_version": "2.0.0",
+       "_model_name": "LayoutModel",
+       "_view_count": null,
+       "_view_module": "@jupyter-widgets/base",
+       "_view_module_version": "2.0.0",
+       "_view_name": "LayoutView",
+       "align_content": null,
+       "align_items": null,
+       "align_self": null,
+       "border_bottom": null,
+       "border_left": null,
+       "border_right": null,
+       "border_top": null,
+       "bottom": null,
+       "display": null,
+       "flex": null,
+       "flex_flow": null,
+       "grid_area": null,
+       "grid_auto_columns": null,
+       "grid_auto_flow": null,
+       "grid_auto_rows": null,
+       "grid_column": null,
+       "grid_gap": null,
+       "grid_row": null,
+       "grid_template_areas": null,
+       "grid_template_columns": null,
+       "grid_template_rows": null,
+       "height": null,
+       "justify_content": null,
+       "justify_items": null,
+       "left": null,
+       "margin": null,
+       "max_height": null,
+       "max_width": null,
+       "min_height": null,
+       "min_width": null,
+       "object_fit": null,
+       "object_position": null,
+       "order": null,
+       "overflow": null,
+       "padding": null,
+       "right": null,
+       "top": null,
+       "visibility": null,
+       "width": null
+      }
+     },
+     "4dd085e5a6c8425b932640ba38cf3c2c": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "HTMLStyleModel",
+      "state": {
+       "_model_module": "@jupyter-widgets/controls",
+       "_model_module_version": "2.0.0",
+       "_model_name": "HTMLStyleModel",
+       "_view_count": null,
+       "_view_module": "@jupyter-widgets/base",
+       "_view_module_version": "2.0.0",
+       "_view_name": "StyleView",
+       "background": null,
+       "description_width": "",
+       "font_size": null,
+       "text_color": null
+      }
+     },
+     "570e89d1cf884bec858eda7795166c72": {
+      "model_module": "@jupyter-widgets/base",
+      "model_module_version": "2.0.0",
+      "model_name": "LayoutModel",
+      "state": {
+       "_model_module": "@jupyter-widgets/base",
+       "_model_module_version": "2.0.0",
+       "_model_name": "LayoutModel",
+       "_view_count": null,
+       "_view_module": "@jupyter-widgets/base",
+       "_view_module_version": "2.0.0",
+       "_view_name": "LayoutView",
+       "align_content": null,
+       "align_items": null,
+       "align_self": null,
+       "border_bottom": null,
+       "border_left": null,
+       "border_right": null,
+       "border_top": null,
+       "bottom": null,
+       "display": null,
+       "flex": null,
+       "flex_flow": null,
+       "grid_area": null,
+       "grid_auto_columns": null,
+       "grid_auto_flow": null,
+       "grid_auto_rows": null,
+       "grid_column": null,
+       "grid_gap": null,
+       "grid_row": null,
+       "grid_template_areas": null,
+       "grid_template_columns": null,
+       "grid_template_rows": null,
+       "height": null,
+       "justify_content": null,
+       "justify_items": null,
+       "left": null,
+       "margin": null,
+       "max_height": null,
+       "max_width": null,
+       "min_height": null,
+       "min_width": null,
+       "object_fit": null,
+       "object_position": null,
+       "order": null,
+       "overflow": null,
+       "padding": null,
+       "right": null,
+       "top": null,
+       "visibility": null,
+       "width": null
+      }
+     },
+     "58d4efb95b3b4c11a7f27a3e92067ca3": {
+      "model_module": "@jupyter-widgets/base",
+      "model_module_version": "2.0.0",
+      "model_name": "LayoutModel",
+      "state": {
+       "_model_module": "@jupyter-widgets/base",
+       "_model_module_version": "2.0.0",
+       "_model_name": "LayoutModel",
+       "_view_count": null,
+       "_view_module": "@jupyter-widgets/base",
+       "_view_module_version": "2.0.0",
+       "_view_name": "LayoutView",
+       "align_content": null,
+       "align_items": null,
+       "align_self": null,
+       "border_bottom": null,
+       "border_left": null,
+       "border_right": null,
+       "border_top": null,
+       "bottom": null,
+       "display": null,
+       "flex": null,
+       "flex_flow": null,
+       "grid_area": null,
+       "grid_auto_columns": null,
+       "grid_auto_flow": null,
+       "grid_auto_rows": null,
+       "grid_column": null,
+       "grid_gap": null,
+       "grid_row": null,
+       "grid_template_areas": null,
+       "grid_template_columns": null,
+       "grid_template_rows": null,
+       "height": null,
+       "justify_content": null,
+       "justify_items": null,
+       "left": null,
+       "margin": null,
+       "max_height": null,
+       "max_width": null,
+       "min_height": null,
+       "min_width": null,
+       "object_fit": null,
+       "object_position": null,
+       "order": null,
+       "overflow": null,
+       "padding": null,
+       "right": null,
+       "top": null,
+       "visibility": null,
+       "width": null
+      }
+     },
+     "58e6754f29874f6d9afd0f2fcaa6477c": {
+      "model_module": "@jupyter-widgets/base",
+      "model_module_version": "2.0.0",
+      "model_name": "LayoutModel",
+      "state": {
+       "_model_module": "@jupyter-widgets/base",
+       "_model_module_version": "2.0.0",
+       "_model_name": "LayoutModel",
+       "_view_count": null,
+       "_view_module": "@jupyter-widgets/base",
+       "_view_module_version": "2.0.0",
+       "_view_name": "LayoutView",
+       "align_content": null,
+       "align_items": null,
+       "align_self": null,
+       "border_bottom": null,
+       "border_left": null,
+       "border_right": null,
+       "border_top": null,
+       "bottom": null,
+       "display": null,
+       "flex": null,
+       "flex_flow": null,
+       "grid_area": null,
+       "grid_auto_columns": null,
+       "grid_auto_flow": null,
+       "grid_auto_rows": null,
+       "grid_column": null,
+       "grid_gap": null,
+       "grid_row": null,
+       "grid_template_areas": null,
+       "grid_template_columns": null,
+       "grid_template_rows": null,
+       "height": null,
+       "justify_content": null,
+       "justify_items": null,
+       "left": null,
+       "margin": null,
+       "max_height": null,
+       "max_width": null,
+       "min_height": null,
+       "min_width": null,
+       "object_fit": null,
+       "object_position": null,
+       "order": null,
+       "overflow": null,
+       "padding": null,
+       "right": null,
+       "top": null,
+       "visibility": null,
+       "width": null
+      }
+     },
+     "7699c3d8986d4a6e8d8bb4217053059e": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "HTMLStyleModel",
+      "state": {
+       "_model_module": "@jupyter-widgets/controls",
+       "_model_module_version": "2.0.0",
+       "_model_name": "HTMLStyleModel",
+       "_view_count": null,
+       "_view_module": "@jupyter-widgets/base",
+       "_view_module_version": "2.0.0",
+       "_view_name": "StyleView",
+       "background": null,
+       "description_width": "",
+       "font_size": null,
+       "text_color": null
+      }
+     },
+     "7bd2a232a56d480ca596b415ef3ed717": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "HTMLModel",
+      "state": {
+       "_dom_classes": [],
+       "_model_module": "@jupyter-widgets/controls",
+       "_model_module_version": "2.0.0",
+       "_model_name": "HTMLModel",
+       "_view_count": null,
+       "_view_module": "@jupyter-widgets/controls",
+       "_view_module_version": "2.0.0",
+       "_view_name": "HTMLView",
+       "description": "",
+       "description_allow_html": false,
+       "layout": "IPY_MODEL_570e89d1cf884bec858eda7795166c72",
+       "placeholder": "​",
+       "style": "IPY_MODEL_e119ef47c621423185cd7d198c61d218",
+       "tabbable": null,
+       "tooltip": null,
+       "value": " 1/1 [00:00&lt;00:00,  4.09it/s]"
+      }
+     },
+     "7d81b94c96664753b5c7f2eda5405f17": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "FloatProgressModel",
+      "state": {
+       "_dom_classes": [],
+       "_model_module": "@jupyter-widgets/controls",
+       "_model_module_version": "2.0.0",
+       "_model_name": "FloatProgressModel",
+       "_view_count": null,
+       "_view_module": "@jupyter-widgets/controls",
+       "_view_module_version": "2.0.0",
+       "_view_name": "ProgressView",
+       "bar_style": "success",
+       "description": "",
+       "description_allow_html": false,
+       "layout": "IPY_MODEL_bba7faa7f1874023b8b3f44e0980a1dc",
+       "max": 1.0,
+       "min": 0.0,
+       "orientation": "horizontal",
+       "style": "IPY_MODEL_2a420c66cd7c43229bd55cf377d1e00d",
+       "tabbable": null,
+       "tooltip": null,
+       "value": 1.0
+      }
+     },
+     "81bee5ad297641bda75ce7076242489d": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "ProgressStyleModel",
+      "state": {
+       "_model_module": "@jupyter-widgets/controls",
+       "_model_module_version": "2.0.0",
+       "_model_name": "ProgressStyleModel",
+       "_view_count": null,
+       "_view_module": "@jupyter-widgets/base",
+       "_view_module_version": "2.0.0",
+       "_view_name": "StyleView",
+       "bar_color": null,
+       "description_width": ""
+      }
+     },
+     "8a00c11016924cebbb3cbc2c8a06e4e5": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "HTMLModel",
+      "state": {
+       "_dom_classes": [],
+       "_model_module": "@jupyter-widgets/controls",
+       "_model_module_version": "2.0.0",
+       "_model_name": "HTMLModel",
+       "_view_count": null,
+       "_view_module": "@jupyter-widgets/controls",
+       "_view_module_version": "2.0.0",
+       "_view_name": "HTMLView",
+       "description": "",
+       "description_allow_html": false,
+       "layout": "IPY_MODEL_58e6754f29874f6d9afd0f2fcaa6477c",
+       "placeholder": "​",
+       "style": "IPY_MODEL_7699c3d8986d4a6e8d8bb4217053059e",
+       "tabbable": null,
+       "tooltip": null,
+       "value": "Batches: 100%"
+      }
+     },
+     "bba7faa7f1874023b8b3f44e0980a1dc": {
+      "model_module": "@jupyter-widgets/base",
+      "model_module_version": "2.0.0",
+      "model_name": "LayoutModel",
+      "state": {
+       "_model_module": "@jupyter-widgets/base",
+       "_model_module_version": "2.0.0",
+       "_model_name": "LayoutModel",
+       "_view_count": null,
+       "_view_module": "@jupyter-widgets/base",
+       "_view_module_version": "2.0.0",
+       "_view_name": "LayoutView",
+       "align_content": null,
+       "align_items": null,
+       "align_self": null,
+       "border_bottom": null,
+       "border_left": null,
+       "border_right": null,
+       "border_top": null,
+       "bottom": null,
+       "display": null,
+       "flex": null,
+       "flex_flow": null,
+       "grid_area": null,
+       "grid_auto_columns": null,
+       "grid_auto_flow": null,
+       "grid_auto_rows": null,
+       "grid_column": null,
+       "grid_gap": null,
+       "grid_row": null,
+       "grid_template_areas": null,
+       "grid_template_columns": null,
+       "grid_template_rows": null,
+       "height": null,
+       "justify_content": null,
+       "justify_items": null,
+       "left": null,
+       "margin": null,
+       "max_height": null,
+       "max_width": null,
+       "min_height": null,
+       "min_width": null,
+       "object_fit": null,
+       "object_position": null,
+       "order": null,
+       "overflow": null,
+       "padding": null,
+       "right": null,
+       "top": null,
+       "visibility": null,
+       "width": null
+      }
+     },
+     "c680fa26e0ff4501b6ef8eacd599090e": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "HBoxModel",
+      "state": {
+       "_dom_classes": [],
+       "_model_module": "@jupyter-widgets/controls",
+       "_model_module_version": "2.0.0",
+       "_model_name": "HBoxModel",
+       "_view_count": null,
+       "_view_module": "@jupyter-widgets/controls",
+       "_view_module_version": "2.0.0",
+       "_view_name": "HBoxView",
+       "box_style": "",
+       "children": [
+        "IPY_MODEL_8a00c11016924cebbb3cbc2c8a06e4e5",
+        "IPY_MODEL_7d81b94c96664753b5c7f2eda5405f17",
+        "IPY_MODEL_7bd2a232a56d480ca596b415ef3ed717"
+       ],
+       "layout": "IPY_MODEL_4569f5281db341da993745bf202d0a05",
+       "tabbable": null,
+       "tooltip": null
+      }
+     },
+     "d256c819166642f68442fa041de1ba67": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "HBoxModel",
+      "state": {
+       "_dom_classes": [],
+       "_model_module": "@jupyter-widgets/controls",
+       "_model_module_version": "2.0.0",
+       "_model_name": "HBoxModel",
+       "_view_count": null,
+       "_view_module": "@jupyter-widgets/controls",
+       "_view_module_version": "2.0.0",
+       "_view_name": "HBoxView",
+       "box_style": "",
+       "children": [
+        "IPY_MODEL_41578f932e1e4a549a30f80e2a598676",
+        "IPY_MODEL_dbbfdddf99314100a558b197a6d393a4",
+        "IPY_MODEL_33c5442a4c63404899f3bfd8e5ee84c4"
+       ],
+       "layout": "IPY_MODEL_58d4efb95b3b4c11a7f27a3e92067ca3",
+       "tabbable": null,
+       "tooltip": null
+      }
+     },
+     "dbbfdddf99314100a558b197a6d393a4": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "FloatProgressModel",
+      "state": {
+       "_dom_classes": [],
+       "_model_module": "@jupyter-widgets/controls",
+       "_model_module_version": "2.0.0",
+       "_model_name": "FloatProgressModel",
+       "_view_count": null,
+       "_view_module": "@jupyter-widgets/controls",
+       "_view_module_version": "2.0.0",
+       "_view_name": "ProgressView",
+       "bar_style": "success",
+       "description": "",
+       "description_allow_html": false,
+       "layout": "IPY_MODEL_fc757532ed1d453882911701c1c95190",
+       "max": 1.0,
+       "min": 0.0,
+       "orientation": "horizontal",
+       "style": "IPY_MODEL_81bee5ad297641bda75ce7076242489d",
+       "tabbable": null,
+       "tooltip": null,
+       "value": 1.0
+      }
+     },
+     "e119ef47c621423185cd7d198c61d218": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "HTMLStyleModel",
+      "state": {
+       "_model_module": "@jupyter-widgets/controls",
+       "_model_module_version": "2.0.0",
+       "_model_name": "HTMLStyleModel",
+       "_view_count": null,
+       "_view_module": "@jupyter-widgets/base",
+       "_view_module_version": "2.0.0",
+       "_view_name": "StyleView",
+       "background": null,
+       "description_width": "",
+       "font_size": null,
+       "text_color": null
+      }
+     },
+     "f21b692c698847d8b9e4a514be59eb4f": {
+      "model_module": "@jupyter-widgets/base",
+      "model_module_version": "2.0.0",
+      "model_name": "LayoutModel",
+      "state": {
+       "_model_module": "@jupyter-widgets/base",
+       "_model_module_version": "2.0.0",
+       "_model_name": "LayoutModel",
+       "_view_count": null,
+       "_view_module": "@jupyter-widgets/base",
+       "_view_module_version": "2.0.0",
+       "_view_name": "LayoutView",
+       "align_content": null,
+       "align_items": null,
+       "align_self": null,
+       "border_bottom": null,
+       "border_left": null,
+       "border_right": null,
+       "border_top": null,
+       "bottom": null,
+       "display": null,
+       "flex": null,
+       "flex_flow": null,
+       "grid_area": null,
+       "grid_auto_columns": null,
+       "grid_auto_flow": null,
+       "grid_auto_rows": null,
+       "grid_column": null,
+       "grid_gap": null,
+       "grid_row": null,
+       "grid_template_areas": null,
+       "grid_template_columns": null,
+       "grid_template_rows": null,
+       "height": null,
+       "justify_content": null,
+       "justify_items": null,
+       "left": null,
+       "margin": null,
+       "max_height": null,
+       "max_width": null,
+       "min_height": null,
+       "min_width": null,
+       "object_fit": null,
+       "object_position": null,
+       "order": null,
+       "overflow": null,
+       "padding": null,
+       "right": null,
+       "top": null,
+       "visibility": null,
+       "width": null
+      }
+     },
+     "fc757532ed1d453882911701c1c95190": {
+      "model_module": "@jupyter-widgets/base",
+      "model_module_version": "2.0.0",
+      "model_name": "LayoutModel",
+      "state": {
+       "_model_module": "@jupyter-widgets/base",
+       "_model_module_version": "2.0.0",
+       "_model_name": "LayoutModel",
+       "_view_count": null,
+       "_view_module": "@jupyter-widgets/base",
+       "_view_module_version": "2.0.0",
+       "_view_name": "LayoutView",
+       "align_content": null,
+       "align_items": null,
+       "align_self": null,
+       "border_bottom": null,
+       "border_left": null,
+       "border_right": null,
+       "border_top": null,
+       "bottom": null,
+       "display": null,
+       "flex": null,
+       "flex_flow": null,
+       "grid_area": null,
+       "grid_auto_columns": null,
+       "grid_auto_flow": null,
+       "grid_auto_rows": null,
+       "grid_column": null,
+       "grid_gap": null,
+       "grid_row": null,
+       "grid_template_areas": null,
+       "grid_template_columns": null,
+       "grid_template_rows": null,
+       "height": null,
+       "justify_content": null,
+       "justify_items": null,
+       "left": null,
+       "margin": null,
+       "max_height": null,
+       "max_width": null,
+       "min_height": null,
+       "min_width": null,
+       "object_fit": null,
+       "object_position": null,
+       "order": null,
+       "overflow": null,
+       "padding": null,
+       "right": null,
+       "top": null,
+       "visibility": null,
+       "width": null
+      }
+     }
+    },
+    "version_major": 2,
+    "version_minor": 0
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}