{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "## Task: Question Answering for Game of Thrones\n", "\n", "\n", "\n", "Question Answering can be used in a variety of use cases. A very common one: Using it to navigate through complex knowledge bases or long documents (\"search setting\").\n", "\n", "A \"knowledge base\" could for example be your website, an internal wiki or a collection of financial reports. \n", "In this tutorial we will work on a slightly different domain: \"Game of Thrones\". \n", "\n", "Let's see how we can use a bunch of wikipedia articles to answer a variety of questions about the \n", "marvellous seven kingdoms... \n" ] }, { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Current working directory is /home/mp/deepset/dev/haystack\n" ] } ], "source": [ "# Let's start by adjust the working directory so that it is the root of the repository\n", "# This should be run just once.\n", "import os\n", "os.chdir('../')\n", "print(\"Current working directory is {}\".format(os.getcwd()))" ] }, { "cell_type": "code", "execution_count": 2, "metadata": { "pycharm": { "is_executing": false } }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "I1125 16:55:41.544814 139975239116608 file_utils.py:39] PyTorch version 1.3.0 available.\n", "I1125 16:55:41.619155 139975239116608 modeling_xlnet.py:194] Better speed can be achieved with apex installed from https://www.github.com/nvidia/apex .\n" ] } ], "source": [ "from farm_haystack.reader.farm import FARMReader\n", "from farm_haystack.retriever.tfidf import TfidfRetriever\n", "from farm_haystack import Finder\n", "from farm_haystack.indexing.io import write_documents_to_db, fetch_archive_from_http\n", "from farm_haystack.indexing.cleaning import clean_wiki_text\n", "from farm_haystack.utils import print_answers" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Indexing & cleaning documents" ] }, { "cell_type": "code", "execution_count": 3, "metadata": { "pycharm": { "is_executing": false } }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "I1125 16:55:41.863932 139975239116608 io.py:57] Fetching from https://s3.eu-central-1.amazonaws.com/deepset.ai-farm-qa/datasets/documents/wiki_gameofthrones_txt.zip to `data/article_txt_got`\n", "100%|██████████| 1167348/1167348 [00:00<00:00, 9196388.44B/s]\n", "I1125 16:55:47.962270 139975239116608 io.py:30] Wrote 517 docs to DB\n" ] } ], "source": [ "# Init a database (default: sqllite)\n", "from farm_haystack.database import db\n", "db.create_all()\n", "\n", "# Let's first get some documents that we want to query\n", "# Here: 517 Wikipedia articles for Game of Thrones\n", "doc_dir = \"data/article_txt_got\"\n", "s3_url = \"https://s3.eu-central-1.amazonaws.com/deepset.ai-farm-qa/datasets/documents/wiki_gameofthrones_txt.zip\"\n", "fetch_archive_from_http(url=s3_url, output_dir=doc_dir)\n", "\n", "# Now, let's write the docs to our DB. \n", "# You can supply a cleaning function that is applied to each doc (e.g. to remove footers)\n", "# It must take a str as input, and return a str.\n", "write_documents_to_db(document_dir=doc_dir, clean_func=clean_wiki_text)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Initalize Reader, Retriever & Finder" ] }, { "cell_type": "code", "execution_count": 4, "metadata": { "pycharm": { "is_executing": false, "name": "#%%\n" } }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "I1125 16:55:48.018222 139975239116608 tfidf.py:69] Found 2811 candidate paragraphs from 517 docs in DB\n" ] } ], "source": [ "# A retriever identifies the k most promising chunks of text that might contain the answer for our question\n", "# Retrievers use some simple but fast algorithm, here: TF-IDF\n", "retriever = TfidfRetriever()" ] }, { "cell_type": "code", "execution_count": 5, "metadata": { "pycharm": { "is_executing": false } }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "W1125 16:55:53.613250 139975239116608 processor.py:170] Loading tokenizer from deprecated FARM config. If you used `custom_vocab` or `never_split_chars`, this won't work anymore.\n" ] } ], "source": [ "# A reader scans the text chunks in detail and extracts the k best answers\n", "# Reader use more powerful but slower deep learning models, here: a BERT QA model trained via FARM on Squad 2.0\n", "reader = FARMReader(model_dir=\"../FARM/saved_models/bert-english-qa-large\", use_gpu=False)" ] }, { "cell_type": "code", "execution_count": 6, "metadata": { "pycharm": { "is_executing": false } }, "outputs": [], "source": [ "# The Finder sticks together retriever and retriever in a pipeline to answer our actual questions \n", "finder = Finder(reader, retriever)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Voilá! Ask a question!" ] }, { "cell_type": "code", "execution_count": 7, "metadata": { "pycharm": { "is_executing": false } }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "I1125 16:55:54.057870 139975239116608 __init__.py:92] Identified 10 candidates via retriever:\n", " paragraph_id document_id text\n", " 1257 227 \\n===Arya Stark===\\n'''Arya Stark''' portrayed by Maisie Williams. Arya Star...\n", " 1023 169 \\n====Season 8====\\nArya reunites with Jon, Gendry, and the Hound, who have ...\n", " 1016 169 \\n====Season 1====\\nArya accompanies her father Ned and her sister Sansa to ...\n", " 718 144 \\n===''A Game of Thrones''===\\nSansa Stark begins the novel by being betroth...\n", " 161 33 \\n===In Braavos===\\nLady Crane returns to her chambers to find a wounded Ary...\n", " 1846 304 \\n== Characters ==\\nThe tale is told through the eyes of 9 recurring POV cha...\n", " 1009 169 \\n==== ''A Game of Thrones'' ====\\nArya adopts a direwolf cub, which she nam...\n", " 1022 169 \\n====Season 7====\\nTaking the face of Walder Frey, Arya gathers the men of ...\n", " 847 163 \\n=== Arya Stark ===\\nArya Stark is the third child and younger daughter of ...\n", " 562 117 \\n===On the Kingsroad===\\nCity Watchmen search the caravan for Gendry but ar...\n", "I1125 16:55:54.058521 139975239116608 __init__.py:95] Applying the reader now to look for the answer in detail ...\n", "Inferencing: 100%|██████████| 1/1 [00:24<00:00, 24.35s/it]\n" ] } ], "source": [ "# You can configure how many candidates the reader and retriever shall return\n", "# The higher top_k_retriever, the better (but also the slower) your answers. \n", "prediction = finder.get_answers(question=\"Who is the father of Arya Stark?\", top_k_retriever=10, top_k_reader=5)" ] }, { "cell_type": "code", "execution_count": 8, "metadata": {}, "outputs": [], "source": [ "#prediction = finder.get_answers(question=\"Who created the Dothraki vocabulary?\", top_k_reader=5)\n", "#prediction = finder.get_answers(question=\"Who is the sister of Sansa?\", top_k_reader=5)" ] }, { "cell_type": "code", "execution_count": 9, "metadata": { "pycharm": { "is_executing": false, "name": "#%%\n" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[ { 'answer': 'Eddard',\n", " 'context': 'ry warrior queen. She travels with her father, Eddard, to '\n", " \"King's Landing when he is made Hand of the\"},\n", " { 'answer': 'Ned',\n", " 'context': '\\n'\n", " '====Season 1====\\n'\n", " 'Arya accompanies her father Ned and her sister Sansa to '\n", " \"King's Landing. Before the\"},\n", " { 'answer': 'Lord Eddard',\n", " 'context': ' is the younger daughter and third child of Lord Eddard '\n", " 'and Catelyn Stark of Winterfell. Ever the to'},\n", " { 'answer': 'Lord Eddard Stark',\n", " 'context': ' Tourney of the Hand to honour her father Lord Eddard '\n", " 'Stark, Sansa Stark is enchanted by the knights'},\n", " { 'answer': 'Eddard and Catelyn Stark',\n", " 'context': 'e third child and younger daughter of Eddard and Catelyn '\n", " 'Stark. She serves as a POV character for 33'}]\n" ] } ], "source": [ "print_answers(prediction, details=\"minimal\")" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "Python 3", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.7.3" }, "pycharm": { "stem_cell": { "cell_type": "raw", "metadata": { "collapsed": false }, "source": [] } } }, "nbformat": 4, "nbformat_minor": 2 }