{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "# NBC News Headlines: Exploring Hybrod FTS5 + Vector Search\n", "\n", "This notebooks explore a few different ways one could combine FTS5 and vector search results, when querying \n", "[FTS5](https://www.sqlite.org/fts5.html) and\n", "[`sqlite-vec`](https://github.com/asg017/sqlite-vec) virtual table.\n", "\n", "This dataset is a small list of headines scraped from NBC News, found in the [`./1_scrape.ipynb`](./1_scrape.ipynb) notebook.\n", "To see how the `fts_articles` and `vec_articles` tables were created, see the [`./3_search.ipynb`](./3_search.ipynb) notebook." ] }, { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
| \n", "vec_version()\n", " | \n", "\n", "lembed_version()\n", " | \n", "
|---|---|
| \n", "v0.1.3-alpha.2\n", " | \n", "\n", "v0.0.1-alpha.8\n", " | \n", "
| \n", "rowid\n", " | \n", "\n", "headline\n", " | \n", "\n", "rank\n", " | \n", "
|---|---|---|
| \n", "4666\n", " | \n", "\n", "Kamala Harris visits Planned Parenthood clinic\n", " | \n", "\n", "-18.9139950477264\n", " | \n", "
| \n", "6521\n", " | \n", "\n", "Former Marine sentenced to 9 years in prison for firebombing Planned Parenthood clinic\n", " | \n", "\n", "-14.807022703838651\n", " | \n", "
| \n", "article_id\n", " | \n", "\n", "headline\n", " | \n", "\n", "distance\n", " | \n", "
|---|---|---|
| \n", "4666\n", " | \n", "\n", "Kamala Harris visits Planned Parenthood clinic\n", " | \n", "\n", "0.492593914270401\n", " | \n", "
| \n", "13928\n", " | \n", "\n", "After Dobbs decision, more women are managing their own abortions\n", " | \n", "\n", "0.5789032578468323\n", " | \n", "
| \n", "12636\n", " | \n", "\n", "Transforming Healthcare\n", " | \n", "\n", "0.5822411179542542\n", " | \n", "
| \n", "6979\n", " | \n", "\n", "A timeline of Trump's many, many positions on abortion\n", " | \n", "\n", "0.6101462841033936\n", " | \n", "
| \n", "7038\n", " | \n", "\n", "How a network of abortion pill providers works together in the wake of new threats\n", " | \n", "\n", "0.6196886897087097\n", " | \n", "
| \n", "6914\n", " | \n", "\n", "'Major hurdles': The reality check behind Biden's big abortion promise\n", " | \n", "\n", "0.6198344826698303\n", " | \n", "
| \n", "6794\n", " | \n", "\n", "Trump's conflicting abortion stances are coming back to haunt him — and his party\n", " | \n", "\n", "0.6198986768722534\n", " | \n", "
| \n", "7381\n", " | \n", "\n", "Where abortion rights could be on the ballot this fall: From the Politics Desk\n", " | \n", "\n", "0.6201764345169067\n", " | \n", "
| \n", "6871\n", " | \n", "\n", "How the Biden campaign quickly mobilized on Trump's abortion stance\n", " | \n", "\n", "0.633980393409729\n", " | \n", "
| \n", "5496\n", " | \n", "\n", "Battle over abortion heats up in Arizona — and could be on the 2024 ballot\n", " | \n", "\n", "0.6341449022293091\n", " | \n", "
| \n", "id\n", " | \n", "\n", "headline\n", " | \n", "\n", "match_type\n", " | \n", "\n", "article_id\n", " | \n", "\n", "rank_number\n", " | \n", "\n", "score\n", " | \n", "
|---|---|---|---|---|---|
| \n", "10098\n", " | \n", "\n", "Kamala Harris says abortion bans are creating 'a health care crisis'\n", " | \n", "\n", "fts\n", " | \n", "\n", "10098\n", " | \n", "\n", "1\n", " | \n", "\n", "-10.678829270936067\n", " | \n", "
| \n", "9776\n", " | \n", "\n", "States with abortion bans saw birth control prescriptions fall post-Dobbs, study finds\n", " | \n", "\n", "fts\n", " | \n", "\n", "9776\n", " | \n", "\n", "2\n", " | \n", "\n", "-10.016316725971112\n", " | \n", "
| \n", "2292\n", " | \n", "\n", "Ohio GOP Senate candidates pitch federal abortion bans even after voters protected reproductive rights\n", " | \n", "\n", "fts\n", " | \n", "\n", "2292\n", " | \n", "\n", "3\n", " | \n", "\n", "-9.7149595994016\n", " | \n", "
| \n", "452\n", " | \n", "\n", "64K women and girls became pregnant due to rape in states with abortion bans, study estimates\n", " | \n", "\n", "fts\n", " | \n", "\n", "452\n", " | \n", "\n", "4\n", " | \n", "\n", "-9.163558569425538\n", " | \n", "
| \n", "9187\n", " | \n", "\n", "Abortion bans drive away up to half of young talent, CNBC/Generation Lab youth survey finds\n", " | \n", "\n", "fts\n", " | \n", "\n", "9187\n", " | \n", "\n", "5\n", " | \n", "\n", "-9.163558569425538\n", " | \n", "
| \n", "6989\n", " | \n", "\n", "Trump says abortion restrictions should be left to states, dodging a national ban\n", " | \n", "\n", "vec\n", " | \n", "\n", "6989\n", " | \n", "\n", "1\n", " | \n", "\n", "0.4930749833583832\n", " | \n", "
| \n", "13928\n", " | \n", "\n", "After Dobbs decision, more women are managing their own abortions\n", " | \n", "\n", "vec\n", " | \n", "\n", "13928\n", " | \n", "\n", "2\n", " | \n", "\n", "0.5120846629142761\n", " | \n", "
| \n", "11822\n", " | \n", "\n", "Iowa now bans most abortions after about 6 weeks\n", " | \n", "\n", "vec\n", " | \n", "\n", "11822\n", " | \n", "\n", "3\n", " | \n", "\n", "0.512569785118103\n", " | \n", "
| \n", "7381\n", " | \n", "\n", "Where abortion rights could be on the ballot this fall: From the Politics Desk\n", " | \n", "\n", "vec\n", " | \n", "\n", "7381\n", " | \n", "\n", "4\n", " | \n", "\n", "0.5168291926383972\n", " | \n", "
| \n", "14009\n", " | \n", "\n", "Trump signals openness to banning abortion pill\n", " | \n", "\n", "vec\n", " | \n", "\n", "14009\n", " | \n", "\n", "5\n", " | \n", "\n", "0.5288293957710266\n", " | \n", "
| \n", "4426\n", " | \n", "\n", "Medication abortions rose in year after Dobbs decision, report finds\n", " | \n", "\n", "vec\n", " | \n", "\n", "4426\n", " | \n", "\n", "6\n", " | \n", "\n", "0.5305097699165344\n", " | \n", "
| \n", "4328\n", " | \n", "\n", "Trump signals support for a national 15-week abortion ban\n", " | \n", "\n", "vec\n", " | \n", "\n", "4328\n", " | \n", "\n", "7\n", " | \n", "\n", "0.532848060131073\n", " | \n", "
| \n", "6979\n", " | \n", "\n", "A timeline of Trump's many, many positions on abortion\n", " | \n", "\n", "vec\n", " | \n", "\n", "6979\n", " | \n", "\n", "8\n", " | \n", "\n", "0.533357560634613\n", " | \n", "
| \n", "2092\n", " | \n", "\n", "For the first time in years, Sen. Graham hasn't introduced a national abortion ban\n", " | \n", "\n", "vec\n", " | \n", "\n", "2092\n", " | \n", "\n", "9\n", " | \n", "\n", "0.5336830615997314\n", " | \n", "
| \n", "6794\n", " | \n", "\n", "Trump's conflicting abortion stances are coming back to haunt him — and his party\n", " | \n", "\n", "vec\n", " | \n", "\n", "6794\n", " | \n", "\n", "10\n", " | \n", "\n", "0.5347095131874084\n", " | \n", "
| \n", "id\n", " | \n", "\n", "headline\n", " | \n", "\n", "vec_rank\n", " | \n", "\n", "fts_rank\n", " | \n", "\n", "combined_rank\n", " | \n", "\n", "vec_distance\n", " | \n", "\n", "fts_score\n", " | \n", "
|---|---|---|---|---|---|---|
| \n", "4328\n", " | \n", "\n", "Trump signals support for a national 15-week abortion ban\n", " | \n", "\n", "2\n", " | \n", "\n", "3\n", " | \n", "\n", "0.03200204813108039\n", " | \n", "\n", "0.5334203839302063\n", " | \n", "\n", "-9.841645168493953\n", " | \n", "
| \n", "5769\n", " | \n", "\n", "Mitch McConnell shies away from supporting national abortion ban\n", " | \n", "\n", "8\n", " | \n", "\n", "2\n", " | \n", "\n", "0.030834914611005692\n", " | \n", "\n", "0.5501425266265869\n", " | \n", "\n", "-10.19017787567105\n", " | \n", "
| \n", "9507\n", " | \n", "\n", "Arizona Senate passes repeal of 1864 abortion ban\n", " | \n", "\n", "\n", " | \n", "\n", "1\n", " | \n", "\n", "0.01639344262295082\n", " | \n", "\n", "\n", " | \n", "\n", "-10.564302831642667\n", " | \n", "
| \n", "6989\n", " | \n", "\n", "Trump says abortion restrictions should be left to states, dodging a national ban\n", " | \n", "\n", "1\n", " | \n", "\n", "\n", " | \n", "\n", "0.01639344262295082\n", " | \n", "\n", "0.5142395496368408\n", " | \n", "\n", "\n", " | \n", "
| \n", "10717\n", " | \n", "\n", "Supreme Court rejects bid to restrict access to abortion pill\n", " | \n", "\n", "3\n", " | \n", "\n", "\n", " | \n", "\n", "0.015873015873015872\n", " | \n", "\n", "0.5351248383522034\n", " | \n", "\n", "\n", " | \n", "
| \n", "5981\n", " | \n", "\n", "Arizona state House passes bill to repeal 1864 abortion ban\n", " | \n", "\n", "\n", " | \n", "\n", "4\n", " | \n", "\n", "0.015625\n", " | \n", "\n", "\n", " | \n", "\n", "-9.841645168493953\n", " | \n", "
| \n", "14009\n", " | \n", "\n", "Trump signals openness to banning abortion pill\n", " | \n", "\n", "4\n", " | \n", "\n", "\n", " | \n", "\n", "0.015625\n", " | \n", "\n", "0.5364335179328918\n", " | \n", "\n", "\n", " | \n", "
| \n", "6375\n", " | \n", "\n", "Arizona Republicans again quash effort to repeal 1864 abortion ban\n", " | \n", "\n", "\n", " | \n", "\n", "5\n", " | \n", "\n", "0.015384615384615385\n", " | \n", "\n", "\n", " | \n", "\n", "-9.841645168493953\n", " | \n", "
| \n", "7381\n", " | \n", "\n", "Where abortion rights could be on the ballot this fall: From the Politics Desk\n", " | \n", "\n", "5\n", " | \n", "\n", "\n", " | \n", "\n", "0.015384615384615385\n", " | \n", "\n", "0.5462378859519958\n", " | \n", "\n", "\n", " | \n", "
| \n", "9443\n", " | \n", "\n", "Arizona Gov. Katie Hobbs signs repeal of 1864 abortion ban\n", " | \n", "\n", "\n", " | \n", "\n", "6\n", " | \n", "\n", "0.015151515151515152\n", " | \n", "\n", "\n", " | \n", "\n", "-9.841645168493953\n", " | \n", "
| \n", "13928\n", " | \n", "\n", "After Dobbs decision, more women are managing their own abortions\n", " | \n", "\n", "6\n", " | \n", "\n", "\n", " | \n", "\n", "0.015151515151515152\n", " | \n", "\n", "0.5467031002044678\n", " | \n", "\n", "\n", " | \n", "
| \n", "1821\n", " | \n", "\n", "Dominican women fight child marriage, teen pregancy amid total abortion ban\n", " | \n", "\n", "\n", " | \n", "\n", "7\n", " | \n", "\n", "0.014925373134328358\n", " | \n", "\n", "\n", " | \n", "\n", "-9.51616557526609\n", " | \n", "
| \n", "2092\n", " | \n", "\n", "For the first time in years, Sen. Graham hasn't introduced a national abortion ban\n", " | \n", "\n", "7\n", " | \n", "\n", "\n", " | \n", "\n", "0.014925373134328358\n", " | \n", "\n", "0.5477523803710938\n", " | \n", "\n", "\n", " | \n", "
| \n", "7150\n", " | \n", "\n", "Tennessee court weighs challenge to abortion ban’s narrow medical exception\n", " | \n", "\n", "\n", " | \n", "\n", "8\n", " | \n", "\n", "0.014705882352941176\n", " | \n", "\n", "\n", " | \n", "\n", "-9.51616557526609\n", " | \n", "
| \n", "8690\n", " | \n", "\n", "Arizona Supreme Court pushes back enforcement date for 1864 abortion ban\n", " | \n", "\n", "\n", " | \n", "\n", "9\n", " | \n", "\n", "0.014492753623188406\n", " | \n", "\n", "\n", " | \n", "\n", "-9.51616557526609\n", " | \n", "
| \n", "11822\n", " | \n", "\n", "Iowa now bans most abortions after about 6 weeks\n", " | \n", "\n", "9\n", " | \n", "\n", "\n", " | \n", "\n", "0.014492753623188406\n", " | \n", "\n", "0.5557170510292053\n", " | \n", "\n", "\n", " | \n", "
| \n", "2646\n", " | \n", "\n", "Trump campaign scrambles over abortion ban report as Democrats seize the moment\n", " | \n", "\n", "\n", " | \n", "\n", "10\n", " | \n", "\n", "0.014285714285714285\n", " | \n", "\n", "\n", " | \n", "\n", "-9.211525101866211\n", " | \n", "
| \n", "5538\n", " | \n", "\n", "Map: Where medication abortion is and isn’t legal\n", " | \n", "\n", "10\n", " | \n", "\n", "\n", " | \n", "\n", "0.014285714285714285\n", " | \n", "\n", "0.5588464140892029\n", " | \n", "\n", "\n", " | \n", "
| \n", "id\n", " | \n", "\n", "headline\n", " | \n", "\n", "rowid\n", " | \n", "\n", "fts_rank_number\n", " | \n", "\n", "score\n", " | \n", "
|---|---|---|---|---|
| \n", "4328\n", " | \n", "\n", "Trump signals support for a national 15-week abortion ban\n", " | \n", "\n", "4328\n", " | \n", "\n", "3\n", " | \n", "\n", "-9.841645168493953\n", " | \n", "
| \n", "5769\n", " | \n", "\n", "Mitch McConnell shies away from supporting national abortion ban\n", " | \n", "\n", "5769\n", " | \n", "\n", "2\n", " | \n", "\n", "-10.19017787567105\n", " | \n", "
| \n", "2646\n", " | \n", "\n", "Trump campaign scrambles over abortion ban report as Democrats seize the moment\n", " | \n", "\n", "2646\n", " | \n", "\n", "10\n", " | \n", "\n", "-9.211525101866211\n", " | \n", "
| \n", "7150\n", " | \n", "\n", "Tennessee court weighs challenge to abortion ban’s narrow medical exception\n", " | \n", "\n", "7150\n", " | \n", "\n", "8\n", " | \n", "\n", "-9.51616557526609\n", " | \n", "
| \n", "1821\n", " | \n", "\n", "Dominican women fight child marriage, teen pregancy amid total abortion ban\n", " | \n", "\n", "1821\n", " | \n", "\n", "7\n", " | \n", "\n", "-9.51616557526609\n", " | \n", "
| \n", "6375\n", " | \n", "\n", "Arizona Republicans again quash effort to repeal 1864 abortion ban\n", " | \n", "\n", "6375\n", " | \n", "\n", "5\n", " | \n", "\n", "-9.841645168493953\n", " | \n", "
| \n", "9507\n", " | \n", "\n", "Arizona Senate passes repeal of 1864 abortion ban\n", " | \n", "\n", "9507\n", " | \n", "\n", "1\n", " | \n", "\n", "-10.564302831642667\n", " | \n", "
| \n", "8690\n", " | \n", "\n", "Arizona Supreme Court pushes back enforcement date for 1864 abortion ban\n", " | \n", "\n", "8690\n", " | \n", "\n", "9\n", " | \n", "\n", "-9.51616557526609\n", " | \n", "
| \n", "5981\n", " | \n", "\n", "Arizona state House passes bill to repeal 1864 abortion ban\n", " | \n", "\n", "5981\n", " | \n", "\n", "4\n", " | \n", "\n", "-9.841645168493953\n", " | \n", "
| \n", "9443\n", " | \n", "\n", "Arizona Gov. Katie Hobbs signs repeal of 1864 abortion ban\n", " | \n", "\n", "9443\n", " | \n", "\n", "6\n", " | \n", "\n", "-9.841645168493953\n", " | \n", "