haystack/tutorials/Tutorial1_Basic_QA_Pipeline.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "pycharm": {
     "is_executing": false
    }
   },
   "outputs": [],
   "source": [
    "from farm_haystack.reader.adaptive_model 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": [
    "## Task: Question Answering for Game of Thrones\n",
    "\n",
    "<img style=\"float: right;\" src=\"https://upload.wikimedia.org/wikipedia/en/d/d8/Game_of_Thrones_title_card.jpg\">\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": "markdown",
   "metadata": {},
   "source": [
    "## Indexing & cleaning documents"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "pycharm": {
     "is_executing": false
    }
   },
   "outputs": [],
   "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/transformation function that is applied to each doc (e.g. to remove headers)\n",
    "# It must take a str as input, and return a str.\n",
    "# Our 517 documents also get splitted into 2068 smaller paragraphs here. \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": null,
   "metadata": {
    "pycharm": {
     "is_executing": false,
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "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": null,
   "metadata": {
    "pycharm": {
     "is_executing": false
    }
   },
   "outputs": [],
   "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\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "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": null,
   "metadata": {
    "pycharm": {
     "is_executing": false
    }
   },
   "outputs": [],
   "source": [
    "prediction = finder.get_answers(question=\"Who is the father of Arya Stark?\", top_k_reader=10, top_k_retriever=5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "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": null,
   "metadata": {
    "pycharm": {
     "is_executing": false,
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "print_answers(prediction, details=\"minimal\")"
   ]
  }
 ],
 "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
}