natural-pdf 0.1.8__py3-none-any.whl → 0.1.9__py3-none-any.whl

docs/tutorials/13-semantic-search.ipynb

@@ -1,1718 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "0b803780",
-   "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": "664b4cd6",
-   "metadata": {
-    "execution": {
-     "iopub.execute_input": "2025-04-27T16:34:55.126546Z",
-     "iopub.status.busy": "2025-04-27T16:34:55.125930Z",
-     "iopub.status.idle": "2025-04-27T16:34:55.132105Z",
-     "shell.execute_reply": "2025-04-27T16:34:55.131378Z"
-    }
-   },
-   "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": "30a0ced5",
-   "metadata": {
-    "execution": {
-     "iopub.execute_input": "2025-04-27T16:34:55.135528Z",
-     "iopub.status.busy": "2025-04-27T16:34:55.135238Z",
-     "iopub.status.idle": "2025-04-27T16:35:03.763400Z",
-     "shell.execute_reply": "2025-04-27T16:35:03.762907Z"
-    }
-   },
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "natural_pdf.collections.pdf_collection - INFO - Initializing 2 PDF objects...\n"
-     ]
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "d7fd32b9ea9f487099b048e5b410f76f",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Loading PDFs:   0%|          | 0/2 [00:00<?, ?it/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "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": [
-      "natural_pdf.core.pdf - INFO - PDF downloaded to temporary file: /var/folders/25/h3prywj14qb0mlkl2s8bxq5m0000gn/T/tmpc7n5dufd.pdf\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "natural_pdf.core.pdf - INFO - Initializing PDF from /var/folders/25/h3prywj14qb0mlkl2s8bxq5m0000gn/T/tmpc7n5dufd.pdf\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "natural_pdf.ocr.ocr_manager - INFO - 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', 'gemini']\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "natural_pdf.core.highlighting_service - INFO - HighlightingService initialized with ColorManager.\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "natural_pdf.classification.manager - INFO - ClassificationManager initialized on device: None\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": [
-      "natural_pdf.classification.manager - INFO - ClassificationManager initialized on device: None\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "natural_pdf.extraction.manager - INFO - Initialized StructuredDataManager.\n"
-     ]
-    },
-    {
-     "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": [
-      "natural_pdf.core.pdf - INFO - PDF downloaded to temporary file: /var/folders/25/h3prywj14qb0mlkl2s8bxq5m0000gn/T/tmp5mocjexv.pdf\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "natural_pdf.core.pdf - INFO - Initializing PDF from /var/folders/25/h3prywj14qb0mlkl2s8bxq5m0000gn/T/tmp5mocjexv.pdf\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "natural_pdf.ocr.ocr_manager - INFO - 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', 'gemini']\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "natural_pdf.core.highlighting_service - INFO - HighlightingService initialized with ColorManager.\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "natural_pdf.classification.manager - INFO - ClassificationManager initialized on device: None\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": [
-      "natural_pdf.classification.manager - INFO - ClassificationManager initialized on device: None\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "natural_pdf.extraction.manager - INFO - Initialized StructuredDataManager.\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "natural_pdf.collections.pdf_collection - INFO - 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": "32cf5680",
-   "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": "a4f73496",
-   "metadata": {
-    "execution": {
-     "iopub.execute_input": "2025-04-27T16:35:03.765700Z",
-     "iopub.status.busy": "2025-04-27T16:35:03.764847Z",
-     "iopub.status.idle": "2025-04-27T16:35:06.500731Z",
-     "shell.execute_reply": "2025-04-27T16:35:06.500375Z"
-    }
-   },
-   "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": [
-      "natural_pdf.search.searchable_mixin - INFO - 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": [
-      "natural_pdf.search - INFO - 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": [
-      "natural_pdf.search.searchable_mixin - INFO - 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": [
-      "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": [
-      "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": [
-      "natural_pdf.search.haystack_search_service - INFO - 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"
-     ]
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "168a989d9d724abf92f2c02538b32c39",
-       "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": [
-      "natural_pdf.search.haystack_search_service - INFO - 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": [
-      "natural_pdf.search.haystack_search_service - INFO - 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": "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": "897988b1",
-   "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": "8de85856",
-   "metadata": {
-    "execution": {
-     "iopub.execute_input": "2025-04-27T16:35:06.502157Z",
-     "iopub.status.busy": "2025-04-27T16:35:06.502017Z",
-     "iopub.status.idle": "2025-04-27T16:35:06.629731Z",
-     "shell.execute_reply": "2025-04-27T16:35:06.629475Z"
-    }
-   },
-   "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": [
-      "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": [
-      "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"
-     ]
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "2a9bdf4a442c40ba81ca10ec0d504df4",
-       "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": [
-      "natural_pdf.search.haystack_search_service - INFO - 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": "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": "af2db0c4",
-   "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": "dca1b9a7",
-   "metadata": {
-    "execution": {
-     "iopub.execute_input": "2025-04-27T16:35:06.630985Z",
-     "iopub.status.busy": "2025-04-27T16:35:06.630862Z",
-     "iopub.status.idle": "2025-04-27T16:35:06.633294Z",
-     "shell.execute_reply": "2025-04-27T16:35:06.633045Z"
-    }
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "  1. PDF: /var/folders/25/h3prywj14qb0mlkl2s8bxq5m0000gn/T/tmp5mocjexv.pdf\n",
-      "     Page: 2 (Score: 0.0708)\n",
-      "     Snippet: Library Weeding Log Atlanta Public Schools\n",
-      "From: 8/1/2017 To: 6/30/2023\n",
-      "6/6/2023 - Copies Removed: 130\n",
-      "The Anasazi (Removed: 1)\n",
-      "Author: Petersen, David. ISBN: 0-516-01121-9 (trade) Published: 1991\n",
-      "Sit...\n",
-      "  2. PDF: /var/folders/25/h3prywj14qb0mlkl2s8bxq5m0000gn/T/tmp5mocjexv.pdf\n",
-      "     Page: 5 (Score: 0.0669)\n",
-      "     Snippet: Library Weeding Log Atlanta Public Schools\n",
-      "From: 8/1/2017 To: 6/30/2023\n",
-      "6/6/2023 - Copies Removed: 130\n",
-      "Centennial Place 33170000562167 $13.10 11/5/1999 33554-43170\n",
-      "Academy (Charter)\n",
-      "Was Available -- W...\n",
-      "  3. PDF: /var/folders/25/h3prywj14qb0mlkl2s8bxq5m0000gn/T/tmpc7n5dufd.pdf\n",
-      "     Page: 1 (Score: -0.0040)\n",
-      "     Snippet: Jungle Health and Safety Inspection Service\n",
-      "INS-UP70N51NCL41R\n",
-      "Site: Durham’s Meatpacking Chicago, Ill.\n",
-      "Date: February 3, 1905\n",
-      "Violation Count: 7\n",
-      "Summary: Worst of any, however, were the fertilizer men...\n",
-      "  4. PDF: /var/folders/25/h3prywj14qb0mlkl2s8bxq5m0000gn/T/tmp5mocjexv.pdf\n",
-      "     Page: 4 (Score: -0.0245)\n",
-      "     Snippet: Library Weeding Log Atlanta Public Schools\n",
-      "From: 8/1/2017 To: 6/30/2023\n",
-      "6/6/2023 - Copies Removed: 130\n",
-      "Children of the Philippines (Removed: 1)\n",
-      "Author: Kinkade, Sheila, 1962- ISBN: 0-87614-993-X Publi...\n",
-      "  5. PDF: /var/folders/25/h3prywj14qb0mlkl2s8bxq5m0000gn/T/tmp5mocjexv.pdf\n",
-      "     Page: 3 (Score: -0.0445)\n",
-      "     Snippet: Library Weeding Log Atlanta Public Schools\n",
-      "From: 8/1/2017 To: 6/30/2023\n",
-      "6/6/2023 - Copies Removed: 130\n",
-      "Centennial Place 33170000507600 $19.45 2/21/2000 33554-43170\n",
-      "Academy (Charter)\n",
-      "Was Available -- W...\n",
-      "  6. PDF: /var/folders/25/h3prywj14qb0mlkl2s8bxq5m0000gn/T/tmp5mocjexv.pdf\n",
-      "     Page: 1 (Score: -0.0473)\n",
-      "     Snippet: Library Weeding Log Atlanta Public Schools\n",
-      "From: 8/1/2017 To: 6/30/2023\n",
-      "6/12/2023 - Copies Removed: 2\n",
-      "Tristan Strong punches a hole in the sky (Removed: 1)\n",
-      "Author: Mbalia, Kwame. ISBN: 978-1-36803993-...\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": "71acde4d",
-   "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"
-  },
-  "kernelspec": {
-   "display_name": "Python (natural-pdf)",
-   "language": "python",
-   "name": "natural-pdf"
-  },
-  "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": {
-     "045481258c7a4764b11034c22edd1940": {
-      "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
-      }
-     },
-     "04f0fb9dfb2645cd8a728bf068b2ed2d": {
-      "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
-      }
-     },
-     "0a8d6584c2c745b19fbbe35ad99312a6": {
-      "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": ""
-      }
-     },
-     "168a989d9d724abf92f2c02538b32c39": {
-      "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_f1c19e7db0684964b147abb8c00c0bbe",
-        "IPY_MODEL_ccb14891737b488ebfc6ae39fb14a6a1",
-        "IPY_MODEL_7690b035d029413bb7a6f6d849c4777e"
-       ],
-       "layout": "IPY_MODEL_563942a751b54656a2c953abf1b908cc",
-       "tabbable": null,
-       "tooltip": null
-      }
-     },
-     "1fe57cefc03543c1af6ea64f44226e50": {
-      "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
-      }
-     },
-     "2a9bdf4a442c40ba81ca10ec0d504df4": {
-      "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_3b31de14259840818658de02f2c8a1c6",
-        "IPY_MODEL_57b2175f96744c5da2054d5290a13f67",
-        "IPY_MODEL_a6e177ae59604ba997934e000199f8ba"
-       ],
-       "layout": "IPY_MODEL_c46851eb620b40588a40695a0041cf9d",
-       "tabbable": null,
-       "tooltip": null
-      }
-     },
-     "2d844fb4766849dab371d9e05be77694": {
-      "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_d20824fb12014cb8addd60a28c0356b7",
-       "placeholder": "​",
-       "style": "IPY_MODEL_1fe57cefc03543c1af6ea64f44226e50",
-       "tabbable": null,
-       "tooltip": null,
-       "value": " 2/2 [00:01&lt;00:00,  1.20it/s]"
-      }
-     },
-     "3b31de14259840818658de02f2c8a1c6": {
-      "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_c018bc738c14432abced177e7f346463",
-       "placeholder": "​",
-       "style": "IPY_MODEL_4632137f9ca8492bb0c1ff2a928ac0f8",
-       "tabbable": null,
-       "tooltip": null,
-       "value": "Batches: 100%"
-      }
-     },
-     "454ce0223f794fc580050bf4e13cc3a7": {
-      "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
-      }
-     },
-     "4632137f9ca8492bb0c1ff2a928ac0f8": {
-      "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
-      }
-     },
-     "52447d1bde014cb2b04eb51c7f7288b7": {
-      "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
-      }
-     },
-     "563942a751b54656a2c953abf1b908cc": {
-      "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
-      }
-     },
-     "57b2175f96744c5da2054d5290a13f67": {
-      "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_04f0fb9dfb2645cd8a728bf068b2ed2d",
-       "max": 1.0,
-       "min": 0.0,
-       "orientation": "horizontal",
-       "style": "IPY_MODEL_c6f89de8432b4587bec4e3e2cca32cbc",
-       "tabbable": null,
-       "tooltip": null,
-       "value": 1.0
-      }
-     },
-     "5d6e9dd429f14ee2b5de4b741602f944": {
-      "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
-      }
-     },
-     "6024f87266144f52a440ee05bcc407c8": {
-      "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
-      }
-     },
-     "654a2b80c08b40beba55515d525a59af": {
-      "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
-      }
-     },
-     "7690b035d029413bb7a6f6d849c4777e": {
-      "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_a1972af713cf43aaaa9b6b695eaf5193",
-       "placeholder": "​",
-       "style": "IPY_MODEL_d35dfa8c17d64d4996e4ec6beb51d9cb",
-       "tabbable": null,
-       "tooltip": null,
-       "value": " 1/1 [00:00&lt;00:00,  4.47it/s]"
-      }
-     },
-     "a1972af713cf43aaaa9b6b695eaf5193": {
-      "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
-      }
-     },
-     "a6e177ae59604ba997934e000199f8ba": {
-      "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_b240a7aeec0a4e3faaef25c910fcf62e",
-       "placeholder": "​",
-       "style": "IPY_MODEL_6024f87266144f52a440ee05bcc407c8",
-       "tabbable": null,
-       "tooltip": null,
-       "value": " 1/1 [00:00&lt;00:00,  8.45it/s]"
-      }
-     },
-     "a72a536d760a4ccd95f857d2db3cc8be": {
-      "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
-      }
-     },
-     "b240a7aeec0a4e3faaef25c910fcf62e": {
-      "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
-      }
-     },
-     "c018bc738c14432abced177e7f346463": {
-      "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
-      }
-     },
-     "c30057e29da04e6bb16cbbf1038338b9": {
-      "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_52447d1bde014cb2b04eb51c7f7288b7",
-       "placeholder": "​",
-       "style": "IPY_MODEL_f2f35bcfdb8c44cda4afab0f92a73de8",
-       "tabbable": null,
-       "tooltip": null,
-       "value": "Loading PDFs: 100%"
-      }
-     },
-     "c46851eb620b40588a40695a0041cf9d": {
-      "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
-      }
-     },
-     "c585a351229e48ba83f972610c1548bc": {
-      "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_654a2b80c08b40beba55515d525a59af",
-       "max": 2.0,
-       "min": 0.0,
-       "orientation": "horizontal",
-       "style": "IPY_MODEL_f0bd73ebff9942168e0f68823c099dd1",
-       "tabbable": null,
-       "tooltip": null,
-       "value": 2.0
-      }
-     },
-     "c6f89de8432b4587bec4e3e2cca32cbc": {
-      "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": ""
-      }
-     },
-     "ccb14891737b488ebfc6ae39fb14a6a1": {
-      "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_5d6e9dd429f14ee2b5de4b741602f944",
-       "max": 1.0,
-       "min": 0.0,
-       "orientation": "horizontal",
-       "style": "IPY_MODEL_0a8d6584c2c745b19fbbe35ad99312a6",
-       "tabbable": null,
-       "tooltip": null,
-       "value": 1.0
-      }
-     },
-     "d20824fb12014cb8addd60a28c0356b7": {
-      "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
-      }
-     },
-     "d35dfa8c17d64d4996e4ec6beb51d9cb": {
-      "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
-      }
-     },
-     "d7fd32b9ea9f487099b048e5b410f76f": {
-      "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_c30057e29da04e6bb16cbbf1038338b9",
-        "IPY_MODEL_c585a351229e48ba83f972610c1548bc",
-        "IPY_MODEL_2d844fb4766849dab371d9e05be77694"
-       ],
-       "layout": "IPY_MODEL_454ce0223f794fc580050bf4e13cc3a7",
-       "tabbable": null,
-       "tooltip": null
-      }
-     },
-     "f0bd73ebff9942168e0f68823c099dd1": {
-      "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": ""
-      }
-     },
-     "f1c19e7db0684964b147abb8c00c0bbe": {
-      "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_a72a536d760a4ccd95f857d2db3cc8be",
-       "placeholder": "​",
-       "style": "IPY_MODEL_045481258c7a4764b11034c22edd1940",
-       "tabbable": null,
-       "tooltip": null,
-       "value": "Batches: 100%"
-      }
-     },
-     "f2f35bcfdb8c44cda4afab0f92a73de8": {
-      "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
-      }
-     }
-    },
-    "version_major": 2,
-    "version_minor": 0
-   }
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}