この記事は、情報検索・検索技術 Advent Calendar 2023の12月4日の記事である。 昨今のLLMの台頭により、外部情報を In-Context Learning として利用しLLMの生成結果の性能を高めることが可能な RAG(Retrieval Augmented Generation) の重要性の高まりを感じる。ただ、RAG を使ったシステムを構築してみようにも、データが少ないと面白みが少なかったりする。その為、Wikipedia 日本語の約550万文から簡単に検索可能でRAGの入力データとして使えるような embeddings と、素早い速度でベクトル検索できるような faiss 用の index を作成した。 例えば、Wikipedia から該当の文を検索する用途はこのように使える。 from datasets.download import DownloadMana
Wikipediaは任意のページから6回リンクを巡ると、 どんな記事ページにもいけるんだって！ みんなも一緒に実感してみよう！ ※2024/03/01時点のデータを利用しています
Google Knowledge Graph Search API Stay organized with collections Save and categorize content based on your preferences. The Knowledge Graph Search API lets you find entities in the Google Knowledge Graph. The API uses standard schema.org types and is compliant with the JSON-LD specification. Typical use cases Some examples of how you can use the Knowledge Graph Search API include: Getting a ranke
Alexandria Ocasio-Cortez (/oʊˌkɑːsioʊ kɔːrˈtɛz/ ⓘ oh-KAH-see-oh kor-TEZ, Spanish: [aleɣˈsandɾja oˈkasjo koɾˈtes]; born October 13, 1989), also known by her initials AOC, is an American politician and activist serving since 2019 as the U.S. representative for New York's 14th congressional district. She is a member of the Democratic Party. Ocasio-Cortez was born in the New York City borough of the B
"Social media bubble" redirects here. For the technology boom and bust phenomenon, see Social media stock bubble. Social media inadvertently isolates users into their own ideological filter bubbles, according to internet activist Eli Pariser A filter bubble or ideological frame is a state of intellectual isolation[1] that can result from personalized searches, recommendation systems, and algorithm
Jordan Bernt Peterson (born 12 June 1962) is a Canadian psychologist, author, and media commentator. He began to receive widespread attention in the late 2010s for his views on cultural and political issues. Often characterized as conservative, Peterson has described himself as a classic British liberal and a traditionalist. Born and raised in Alberta, he obtained two bachelor's degrees in politic
This article may be too technical for most readers to understand. Please help improve it to make it understandable to non-experts, without removing the technical details. (July 2023) (Learn how and when to remove this message) In the mathematical theory of artificial neural networks, universal approximation theorems are theorems[1][2] of the following form: Given a family of neural networks, for e
A cartoon character producing an object from nowhere - from "hammerspace" Hammerspace (also known as malletspace) is an imaginary extradimensional, instantly accessible storage area in fiction, which is used to explain how characters from animation, comics, and video games can produce objects out of thin air. Typically, when multiple items are available, the desired item is available on the first
Sono Osato (大里 ソノ, Osato Sono, August 29, 1919 – December 26, 2018) was an American dancer and actress.[1] Osato was born in Omaha, Nebraska.[1] She was the oldest of three children of a Japanese father (Shoji Osato, 1885–1955) and a Canadian mother of French-Irish origin (Frances Fitzpatrick, 1897–1954).[2] Her family moved to Chicago in 1925 in order to be closer to Frances' family, and Shoji op
South Korean band BTS has posted 18 of the 30 most retweeted tweets on X (Twitter). This list contains the top 30 posts with the most reposts/retweets (an account's post that is sent again by additional accounts without any change) on the social networking platform X, formerly known as Twitter. X does not provide an official list but news and mainstream media make lists.[1][2] As of October 2024,
Umoja Uaso ("unity" in Swahili, the Uaso Nyiro is a nearby river)[1][2] is a village in Kenya. The village, founded in 1990,[3] is an all-female matriarch village located near the town of Archers Post in Samburu County, 380 km (240 mi) from the capital, Nairobi. It was founded by Rebecca Lolosoli, a Samburu woman, as a sanctuary for homeless survivors of violence against women, and young girls run
This article includes a list of references, related reading, or external links, but its sources remain unclear because it lacks inline citations. Please help improve this article by introducing more precise citations. (February 2022) (Learn how and when to remove this message) In computer graphics, marching squares is an algorithm that generates contours for a two-dimensional scalar field (rectang
In mathematics, a low-discrepancy sequence is a sequence with the property that for all values of , its subsequence has a low discrepancy. Roughly speaking, the discrepancy of a sequence is low if the proportion of points in the sequence falling into an arbitrary set B is close to proportional to the measure of B, as would happen on average (but not for particular samples) in the case of an equidi
The plan, launched in 2018, was structured around ten principles.[3] The key principle states that by 2021, research funded by public or private grants must be published in open-access journals or platforms, or made immediately available in open access repositories without an embargo. The ten principles are: authors should retain copyright on their publications, which must be published under an op
Sprite of a television set (center) resized using simple nearest-neighbor scaling (left) and the 2xSaI interpolation algorithm (right) Comparison of common pixel art scaling algorithms. View in full resolution to see the differences. Pixel art scaling algorithms are graphical filters that attempt to enhance the appearance of hand-drawn 2D pixel art graphics. These algorithms are a form of automati
Abcde (pronounced /ˈæbsədiː/) is a feminine given name in the United States. As many as 328 children, all girls, were named Abcde in the United States between 1990 and 2014.[1] As of 2017, 373 females were named Abcde.[2] The name is derived from the first five letters of the English alphabet in order, and has no other origin or meaning. In November 2018, a five-year-old girl named Abcde was alleg
In the context of software or information modeling, a happy path (sometimes called happy flow) is a default scenario featuring no exceptional or error conditions.[1][2] For example, the happy path for a function validating credit card numbers would be where none of the validation rules raise an error, thus letting execution continue successfully to the end, generating a positive response. Process
Mario Arnold Segale (April 30, 1934 – October 27, 2018) was an American businessman and real estate developer.[1] He was involved in various development projects in the Seattle area from the 1950s onwards.[2] Nintendo's mascot, Mario, was named after Segale while he was renting a warehouse to Nintendo.[3][4] Segale was born in Seattle in April 1934 to two Italian immigrants, Louis and Rina Segale,
"Personification of Tolerance", a statue displayed in Lužánky. The paradox of tolerance is a philosophical concept suggesting that if a society extends tolerance to those who are intolerant, it risks enabling the eventual dominance of intolerance, thereby undermining the very principle of tolerance. This paradox was articulated by philosopher Karl Popper in The Open Society and Its Enemies (1945),
リリース、障害情報などのサービスのお知らせ
最新の人気エントリーの配信
j次のブックマーク
k前のブックマーク
lあとで読む
eコメント一覧を開く
oページを開く