Retrieval-augmented generation (RAG) is a technique that enables large language models (LLMs) to retrieve and incorporate new information from external data sources. With RAG, LLMs first refer to a specified set of documents, then respond to user queries. These documents supplement information from the LLM's pre-existing training data. This allows LLMs to use domain-specific and/or updated information that is not available in the training data. For example, this enables LLM-based chatbots to access internal company data or generate responses based on authoritative sources. RAG improves LLMs by incorporating information retrieval before generating responses. Unlike LLMs that rely on static training data, RAG pulls relevant text from databases, uploaded documents, or web sources. According to Ars Technica, "RAG is a way of improving LLM performance, in essence by blending the LLM process with a web search or other document look-up process to help LLMs stick to the facts." This method helps reduce AI hallucinations, which have caused chatbots to describe policies that don't exist, or recommend nonexistent legal cases to lawyers that are looking for citations to support their arguments. RAG also reduces the need to retrain LLMs with new data, saving on computational and financial costs. Beyond efficiency gains, RAG also allows LLMs to include sources in their responses, so users can verify the cited sources. This provides greater transparency, as users can cross-check retrieved content to ensure accuracy and relevance. The term retrieval-augmented generation (RAG) was introduced in a 2020 paper that described combining a parametric language model with a non-parametric external memory accessed through retrieval at inference time. == RAG and LLM limitations == LLMs can provide incorrect information. For example, when Google first demonstrated its LLM tool "Google Bard" (later re-branded to Gemini), the LLM provided incorrect information about the James Webb Space Telescope. This error contributed to a $100 billion decline in Google's stock value. RAG is used to prevent these errors, but it does not solve all the problems. For example, LLMs can generate misinformation even when pulling from factually correct sources if they misinterpret the context. MIT Technology Review gives the example of an AI-generated response stating, "The United States has had one Muslim president, Barack Hussein Obama." The model retrieved this from an academic book rhetorically titled Barack Hussein Obama: America's First Muslim President? The LLM did not "know" or "understand" the context of the title, generating a false statement. LLMs with RAG are programmed to prioritize new information. This technique has been called "prompt stuffing." Without prompt stuffing, the LLM's input is generated by a user; with prompt stuffing, additional relevant context is added to this input to guide the model's response. This approach provides the LLM with key information early in the prompt, encouraging it to prioritize the supplied data over pre-existing training knowledge. == Process == Retrieval-augmented generation (RAG) enhances large language models (LLMs) by incorporating an information-retrieval mechanism that allows models to access and utilize additional data beyond their original training set. Ars Technica notes that "when new information becomes available, rather than having to retrain the model, all that's needed is to augment the model's external knowledge base with the updated information" ("augmentation"). IBM states that "in the generative phase, the LLM draws from the augmented prompt and its internal representation of its training data to synthesize" an answer. === RAG key stages === Typically, the data to be referenced is converted into LLM embeddings, numerical representations in the form of a large vector space. RAG can be used on unstructured (usually text), semi-structured, or structured data (for example knowledge graphs). These embeddings are then stored in a vector database to allow for document retrieval. Given a user query, a document retriever is first called to select the most relevant documents that will be used to augment the query. This comparison can be done using a variety of methods, which depend in part on the type of indexing used. The model feeds this relevant retrieved information into the LLM via prompt engineering of the user's original query. Newer implementations (as of 2023) can also incorporate specific augmentation modules with abilities such as expanding queries into multiple domains and using memory and self-improvement to learn from previous retrievals. Finally, the LLM can generate output based on both the query and the retrieved documents. Some models incorporate extra steps to improve output, such as the re-ranking of retrieved information, context selection, and fine-tuning. == Applications == Retrieval-augmented generation is used in applications where generated responses need to be grounded in external or frequently updated information. Commonly cited use cases include search engines, question-answering systems, customer support chatbots, enterprise knowledge assistants, content generation, recommendation systems, retail and e-commerce, and industrial or manufacturing workflows. In healthcare, RAG has been studied as a way to ground large language model outputs in external medical knowledge sources, although reviews have noted continuing challenges around evaluation, ethics, and clinical reliability. == Improvements == Improvements to the basic process above can be applied at different stages in the RAG flow. === Encoder === These methods focus on the encoding of text as either dense or sparse vectors. Sparse vectors, which encode the identity of a word, are typically dictionary-length and contain mostly zeros. Dense vectors, which encode meaning, are more compact and contain fewer zeros. Various enhancements can improve the way similarities are calculated in the vector stores (databases). Performance improves by optimizing how vector similarities are calculated. Dot products enhance similarity scoring, while approximate nearest neighbor (ANN) searches improve retrieval efficiency over K-nearest neighbors (KNN) searches. Accuracy may be improved with Late Interactions, which allow the system to compare words more precisely after retrieval. This helps refine document ranking and improve search relevance. Hybrid vector approaches may be used to combine dense vector representations with sparse one-hot vectors, taking advantage of the computational efficiency of sparse dot products over dense vector operations. Other retrieval techniques focus on improving accuracy by refining how documents are selected. Some retrieval methods combine sparse representations, such as SPLADE, with query expansion strategies to improve search accuracy and recall. === Retriever-centric methods === These methods aim to enhance the quality of document retrieval in vector databases: Pre-training the retriever using the Inverse Cloze Task (ICT), a technique that helps the model learn retrieval patterns by predicting masked text within documents. Supervised retriever optimization aligns retrieval probabilities with the generator model's likelihood distribution. This involves retrieving the top-k vectors for a given prompt, scoring the generated response's perplexity, and minimizing KL divergence between the retriever's selections and the model's likelihoods to refine retrieval. Reranking techniques can refine retriever performance by prioritizing the most relevant retrieved documents during training. === Language model === By redesigning the language model with the retriever in mind, a 25-time smaller network can get comparable perplexity as its much larger counterparts. Because it is trained from scratch, this method (Retro) incurs the high cost of training runs that the original RAG scheme avoided. The hypothesis is that by giving domain knowledge during training, Retro needs less focus on the domain and can devote its smaller weight resources only to language semantics. The redesigned language model is shown here. It has been reported that Retro is not reproducible, so modifications were made to make it so. The more reproducible version is called Retro++ and includes in-context RAG. === Chunking === Chunking involves various strategies for breaking up the data into vectors so the retriever can find details in it. Three types of chunking strategies are: Fixed length with overlap. This is fast and easy. Overlapping consecutive chunks helps to maintain semantic context across chunks. Syntax-based chunks can break the document up into sentences. Libraries such as spaCy or NLTK can also help. File format-based chunking. Certain file types have natural chunks built in, and it's best to respect them. For example, code files are best chunked and vectorized as whole functions or classes. HTML files should leave
Feng Office Community Edition (formerly OpenGoo) is an open-source collaboration platform developed and supported by Feng Office and the OpenGoo community. It is a fully featured online office suite with a similar set of features as other online office suites, like Google Workspace, Microsoft 365, Zimbra, LibreOffice Online and Zoho Office Suite. The application can be downloaded and installed on a server. Feng Office could also be categorized as collaborative software and as personal information manager software. == Features == Feng Office Community Edition main features include project management, document management, contact management, e-mail and time management. Text documents and presentations can be created and edited online. Files can be uploaded, organized and shared, independent of file formats. Organization of the information in Feng Office Community Edition is done using workspaces and tags. The application presents the information stored using different interfaces such as lists, dashboards and calendar views. == Licensing == Feng Office Community Edition is distributed under the GNU Affero General Public License, version 3 only. == Technology used == Feng Office uses PHP, JavaScript, AJAX (ExtJS) and MySQL technology. Several open source projects served as a basis for development. ActiveCollab's last open sourced release was used as the initial code base. It includes CKEditor for online document editing. == System requirements == The server could run on any operating system. The system needs the following packages: Apache HTTP Server 2.0+ PHP 5.0+ MySQL 4.1+ (InnoDB support recommended) On the client side, the user is only required to use a modern Web browser. == History == OpenGoo started as a degree project at the faculty of Engineering of the University of the Republic, Uruguay. The project was presented and championed by Software Engineer Conrado Viña. Software Engineers Marcos Saiz and Ignacio de Soto developed the first prototype as their thesis. Professors Eduardo Fernández and Tomas Laurenzo served as tutors. Conrado, Ignacio and Marcos founded the OpenGoo community and remain active members and core developers. The thesis was approved with the highest score. In 2008, Viña joined the Uruguayan software development company Moove It. Currently there is a second project for OpenGoo at the same university being developed by students Fernando Rodríguez, Ignacio Vázquez and Juan Pedro del Campo. Their project aims to build an open source Web-based spreadsheet. In December 2009 the OpenGoo name was changed to Feng Office Community Edition.
Digital data or digital information, in information theory and information systems, is data or information represented as a string of discrete symbols, each of which can take on one of only a finite number of values from some alphabet, such as letters or digits. An example is a text document, which consists of a string of alphanumeric characters. The most common form of digital data in modern information systems is binary data, which is represented by a string of binary digits (bits) each of which can have one of two values, either 0 or 1. Digital data can be contrasted with analog data, which is represented by a value from a continuous range of real numbers. Analog data is transmitted by an analog signal, which not only takes on continuous values but can vary continuously with time, a continuous real-valued function of time. An example is the air pressure variation in a sound wave. Data requires interpretation to become information. In modern (post-1960) computer systems, all data is digital. The word digital comes from the same source as the words digit and digitus (the Latin word for finger), as fingers are often used for counting. Mathematician George Stibitz of Bell Telephone Laboratories used the word digital in reference to the fast electric pulses emitted by a device designed to aim and fire anti-aircraft guns in 1942. The term is most commonly used in computing and electronics, especially where real-world information is converted to binary numeric form as in digital audio and digital photography. == Symbol to digital conversion == Since symbols (for example, alphanumeric characters) are not continuous, representing symbols digitally is rather simpler than conversion of continuous or analog information to digital. Instead of sampling and quantization as in analog-to-digital conversion, such techniques as polling and encoding are used. A symbol input device usually consists of a group of switches that are polled at regular intervals to see which switches are switched. Data will be lost if, within a single polling interval, two switches are pressed, or a switch is pressed, released, and pressed again. This polling can be done by a specialized processor in the device to prevent burdening the main CPU. When a new symbol has been entered, the device typically sends an interrupt, in a specialized format, so that the CPU can read it. For devices with only a few switches (such as the buttons on a joystick), the status of each can be encoded as bits (usually 0 for released and 1 for pressed) in a single word. This is useful when combinations of key presses are meaningful, and is sometimes used for passing the status of modifier keys on a keyboard (such as shift and control). But it does not scale to support more keys than the number of bits in a single byte or word. Devices with many switches (such as a computer keyboard) usually arrange these switches in a scan matrix, with the individual switches on the intersections of x and y lines. When a switch is pressed, it connects the corresponding x and y lines together. Polling (often called scanning in this case) is done by activating each x line in sequence and detecting which y lines then have a signal, thus which keys are pressed. When the keyboard processor detects that a key has changed state, it sends a signal to the CPU indicating the scan code of the key and its new state. The symbol is then encoded or converted into a number based on the status of modifier keys and the desired character encoding. A custom encoding can be used for a specific application with no loss of data. However, using a standard encoding such as ASCII is problematic if a symbol such as 'ß' needs to be converted but is not in the standard. It is estimated that in the year 1986, less than 1% of the world's technological capacity to store information was digital and in 2007 it was already 94%. The year 2002 is assumed to be the year when humankind was able to store more information in digital than in analog format (the "beginning of the digital age"). == States == Digital data come in these three states: data at rest, data in transit, and data in use. The confidentiality, integrity, and availability have to be managed during the entire lifecycle from 'birth' to the destruction of the data. === Data at rest === Data at rest in information technology means data that is housed physically on computer data storage in any digital form (e.g. cloud storage, file hosting services, databases, data warehouses, spreadsheets, archives, tapes, off-site or cloud backups, mobile devices etc.). Data at rest includes both structured and unstructured data. This type of data is subject to threats from hackers and other malicious threats to gain access to the data digitally or physical theft of the data storage media. To prevent this data from being accessed, modified or stolen, organizations will often employ security protection measures such as password protection, data encryption, or a combination of both. The security options used for this type of data are broadly referred to as data-at-rest protection (DARP). Definitions include: "...all data in computer storage while excluding data that is traversing a network or temporarily residing in computer memory to be read or updated." "...all data in storage but excludes any data that frequently traverses the network or that which resides in temporary memory. Data at rest includes but is not limited to archived data, data which is not accessed or changed frequently, files stored on hard drives, USB thumb drives, files stored on backup tape and disks, and also files stored off-site or on a storage area network (SAN)." While it is generally accepted that archive data (i.e. which never changes), regardless of its storage medium, is data at rest and active data subject to constant or frequent change is data in use. “Inactive data” could be taken to mean data which may change, but infrequently. The imprecise nature of terms such as “constant” and “frequent” means that some stored data cannot be comprehensively defined as either data at rest or in use. These definitions could be taken to assume that Data at Rest is a superset of data in use; however, data in use, subject to frequent change, has distinct processing requirements from data at rest, whether completely static or subject to occasional change. ==== Security ==== Because of its nature data at rest is of increasing concern to businesses, government agencies and other institutions. Mobile devices are often subject to specific security protocols to protect data at rest from unauthorized access when lost or stolen and there is an increasing recognition that database management systems and file servers should also be considered as at risk; the longer data is left unused in storage, the more likely it might be retrieved by unauthorized individuals outside the network. Data encryption, which prevents data visibility in the event of its unauthorized access or theft, is commonly used to protect data in motion and increasingly promoted for protecting data at rest. The encryption of data at rest should only include strong encryption methods such as AES or RSA. Encrypted data should remain encrypted when access controls such as usernames and password fail. Increasing encryption on multiple levels is recommended. Cryptography can be implemented on the database housing the data and on the physical storage where the databases are stored. Data encryption keys should be updated on a regular basis. Encryption keys should be stored separately from the data. Encryption also enables crypto-shredding at the end of the data or hardware lifecycle. Periodic auditing of sensitive data should be part of policy and should occur on scheduled occurrences. Finally, only store the minimum possible amount of sensitive data. Tokenization is a non-mathematical approach to protecting data at rest that replaces sensitive data with non-sensitive substitutes, referred to as tokens, which have no extrinsic or exploitable meaning or value. This process does not alter the type or length of data, which means it can be processed by legacy systems such as databases that may be sensitive to data length and type. Tokens require significantly less computational resources to process and less storage space in databases than traditionally encrypted data. This is achieved by keeping specific data fully or partially visible for processing and analytics while sensitive information is kept hidden. Lower processing and storage requirements makes tokenization an ideal method of securing data at rest in systems that manage large volumes of data. A further method of preventing unwanted access to data at rest is the use of data federation especially when data is distributed globally (e.g. in off-shore archives). An example of this would be a European organisation which stores its archived data off-site in the US. Under the terms of the USA PATRIOT Act the American authorities can demand
FutureMedia is a program that analyzes the state and future of digital, social, and mobile media. It functions as a collaborative initiative at Georgia Tech and the Georgia Tech Research Institute. FutureMedia consults approximately 500 faculty members working in those fields. == History == In 2019, Future Media expanded into the Direct-To-Consumer market by acquiring Australian watchmaker Oak & Jackal. == Programs == === FutureMedia Fest === The organization most recently hosted FutureMedia Fest 2010, a four-day conference (Oct 4–7, 2010) with a keynote addresses from Michael Jones, the chief technology advocate at Google. The event featured panels, workshops, and technology demonstrations. === FutureMedia Outlook === Contemporaneous with FutureMedia Fest 2010, the organization released the FutureMedia Outlook, an analysis of the future of media, concentrating on six major trends in those fields, including information overload, personalization, data integrity, an expectation of multimedia, augmented reality, and collaborative software.
Digital classics is the application of the tools of digital humanities to the field of classics, or more broadly to the study of the ancient world. == History == Classics was one of the first of the humanities disciplines to adopt computing approaches; the first references to the use of computing in the classical humanities date to the early 1960s, which might be surprising considering the reputation of the discipline as old-fashioned and stuffily traditionalist. Major projects such as the Thesaurus Linguae Graecae, founded in 1972, and the text collections of the Packard Humanities Institute set the trend, and there are still a significantly large number of ancient world projects among Humanities Computing projects today. Also, the success of traditional scholarly publications in digital guises, such as seen in the Bryn Mawr Classical Review, and the early adoption of hypertext in high profile projects like the Perseus Digital Library helped to legitimize computing in the study of classics in ways that has not always been the case in other areas of the humanities. This apparent paradox may be as a result of the many methodologies and different sources of evidence that classicists have always had to embrace, from literary sources and linguistics, to art history and archaeology, history, philosophy, religious theory, ancient documents such as inscriptions and papyri, and so forth. The fragmentary nature of many of the texts and languages of the ancient world, the scattered evidence from the material culture of ancient Greece and Rome, and the necessity to evaluate all these varieties of evidence in context are particularly likely to benefit from digital approaches such as databases, text markup, image manipulation and machine learning. == Digital classics projects == There are currently several major projects that aim to encourage and develop digital approaches to classical scholarship. The Stoa Consortium at the University of Kentucky distributes news of the discipline, and serves as a peer-reviewed electronic publication venue, and encourages open source approaches to digital classics. The Perseus Project is a digital library that also provides a collection of digital texts and analysis tools to the public; principally (but not exclusively) classical. Digital Classicist is another project and community which shares information and advice about the digital humanities applied to the field of classics. Epigraphy.info is an international open community pursuing a collaborative environment for digital epigraphy. The Liverpool Classics Mailing List is a project which can be subscribed to in which one receives email regarding Classics events around the world, as well as call for papers, studentships and public lectures.
RFinder ("repeater finder") is a subscription-based website and mobile app. RFinder's main service is the World Wide Repeater Directory (WWRD), which is a directory of amateur radio repeaters. RFinder is the official repeater directory of several amateur radio associations. RFinder has listings for several amateur radio modes, including FM, D-STAR, DMR, and ATV. == World Wide Repeater Directory == Repeaters are listed in the directory along with its call sign, Maidenhead Locator System and GPS coordinates, transmit/receive offset ("split"), CTCSS and DCS squelch settings, and VoIP settings (IRLP and Echolink nodes). The directory has over 50,000 repeater listings in over 170 countries. === Website === The RFinder website has several search options including for routes. === Forums === RFinder user forums is for help and support for the app and hardware. === Mobile app === RFinder has mobile apps for Android and iOS. When using the mobile app, RFinder can display the distance to repeaters, based on the mobile device's current location. === ARRL Repeater Directory === The ARRL publishes the ARRL Repeater Directory which contains over 31,000 repeater listings for the US and Canada with listings provided by RFinder. == Subscription == RFinder requires a subscription. A one-year subscription is US$12.99. == Radio programming software == Some radio programming software applications can query RFinder and download repeater listing to program radios. Compatible software includes: CHIRP RT Systems == Radio associations == RFinder is the official repeater directory of the following associations: Amateur Radio Society Italy American Radio Relay League Cayman Amateur Radio Society Deutscher Amateur Radio Club Federacion Mexicana de Radio Experimentadores L’association Réseau des Émetteurs Français Lietuvos Radijo Mėgėjų Draugija Liga de Amadores Brasilieros de Radio Emissão Radio Amateurs of Canada Radio Society of Great Britain Rede dos Emissores Portugueses Unión de Radioaficionados Españoles
Asynchronous module definition (AMD) is a specification for the programming language JavaScript. It defines an application programming interface (API) that defines code modules and their dependencies, and loads them asynchronously if desired. Implementations of AMD provide the following benefits: Website performance improvements. AMD implementations load smaller JavaScript files, and then only when they are needed. Fewer page errors. AMD implementations allow developers to define dependencies that must load before a module is executed, so the module does not try to use outside code that is not available yet.... In addition to loading multiple JavaScript files at runtime, AMD implementations allow developers to encapsulate code in smaller, more logically-organized files, in a way similar to other programming languages such as Java. For production and deployment, developers can concatenate and minify JavaScript modules based on an AMD API into one file, the same as traditional JavaScript. AMD provides some CommonJS interoperability. It allows for using a similar exports and require() interface in the code, although its own define() interface is more basal and preferred. The AMD specification is implemented by Dojo Toolkit, RequireJS, and other libraries.
