Search Results for "web-browser"

MiniSearch is a minimalist web search application with a built-in AI assistant that runs largely inside the browser for privacy-focused information retrieval. The project combines metasearch capabilities with local or remote language model inference to provide conversational answers alongside traditional search results. It is designed to be lightweight, easy to deploy with Docker, and configurable for both personal and hosted use cases.

rag-search is a lightweight Retrieval-Augmented Generation API service designed to provide structured semantic search and answer generation through a simple FastAPI backend. The project integrates web search, vector embeddings, and reranking logic to retrieve relevant context before passing it to a language model for response generation. It is built to be easily deployable, requiring only environment configuration and dependency installation to run a functional RAG service. The system supports configurable filtering, scoring thresholds, and reranking options, allowing developers to fine-tune retrieval quality. ...

...The project emphasizes clarity and accountability, enabling users to monitor applications, follow-ups, and outcomes in a centralized environment. It is typically built with modern web technologies, allowing for easy customization and self-hosting by developers who want full control over their data. Career Ops focuses on reducing the chaos and fragmentation that often comes with job searching by introducing a repeatable workflow that can be iterated and improved over time. It also supports the idea of data-driven job searching.

...The indexer uses efficient n-gram dictionaries and posting lists to keep query latency low, while storing metadata (branch, language, repo) for precise filtering. A built-in web UI and JSON API enable both interactive exploration and integration into editors and other tools. It supports ranking heuristics such as path weighting and symbol awareness to surface likely matches first, even in monorepos. Incremental and parallel indexing let it keep up with active codebases, making it suitable for both local deployments and multi-tenant service setups.

OpenSearchServer is a powerful, enterprise-class, search engine program. Using the web user interface, the crawlers (web, file, database, etc.) and the client libraries (REST/API , Ruby, Rails, Node.js, PHP, Perl) you will be able to integrate quickly and easily advanced full-text search capabilities in your application: Full-text with basic semantic, join queries, boolean queries, facet and filter, document (PDF, Office, etc.) indexation, web scrapping,etc. ...

Aperture is a Java framework for extracting and querying full-text content and metadata from various information systems (file systems, web sites, mail boxes, ...) and the file formats (documents, images, ...) occurring in these systems.

Description pending...

Infofuze is a Java library and server application that can be used to transform and combine data from various sources into a specific XML or other text output format that can be stored or indexed.

a Solr Based Semantic Mediawiki Store

RegExpresso is a "regular expressions" tester, designed to integrate well into modern web browsers. Though it has few features compared to commercial products, it should be usefull to any programmer who uses regular expressions.

OpenEphyra is an open framework for question answering (QA). It retrieves answers to natural language questions from the Web and other sources. Visit http://www.ephyra.info/ for more details and information on joining this open research initiative.

Document summarization system. By adding document content to system, user queries will generate a summary document containing the available information to the system.

The SSAF ("Secure Search And Forwards") is a dirt-simple standalone web app for inexpensive and secure information sharing. Any uploaded record may be forwarded to an intended destination, and may also be stashed in a searchable repository.

iMeMex is a dataspace management system. iMeMex is a research prototype. The package also provides several useful components for research such as external sorting, B+-trees, inverted indexes, content converters, query operators, and graph indexes.

Kato is an approach to bring the work done on software agents out of academia and into the public arena. Developers can create agents as easily as they can Drupal modules.

A framework for transferring implicit or tacit knowledge between members of a community. It works by observing the behavior of community members, and providing them with suggestions from other community members based on their past behavior.

Sabuesonix is a desktop search engine. It can explore your PDF, TXT and HTML files (and more in the future) and create an index for quick documents search.

Mustru is a desktop Q&A search engine based on Lucene. You can search local filesystems using natural language questions or boolean queries. A list of answers or hits will be returned. A web based interface is included.

Didaskon will deliver a framework for assembling a curriculum from existing learning objects provided by e-Learning services. The selection of learning objects will be based on the semantically annotated specification of the user's current skills.

PALOMA Suite allows the referencing of learning resources using metadata according to the international IEEE LOM standard, and SCORM, CANCORE and Normetic application profiles. PALOMA Suite contains: PALOMA (Standard), PALOMAWeb and PALOMARepository.

LaptopBase is meant to serve as a database of laptops running linux. The database will embrace a structure that will bond together make, model, problem and solution! - Using/Choosing laptops in linux should be easier!

A graphical tool to find and display source code symbols generated by Exuberant ctags.

Set of various network observing and searching services (FTP indexer, SMB indexer, gameserver pinger and history logger, web interface for search and management) mainly for LAN-Parties. Technologies: C#, ASP.NET, IIS, MSSQL, Access, TCPIP

A configurable knowledge management framework. It works out of the box, but it's meant mainly as a framework to build complex information retrieval and analysis systems. The 3 major components: Crawler, Analyzer and Indexer can also be used separately.

Xapian is a Search Engine Library, written in C++ with bindings for Perl, Python, PHP, Java, Tcl, C# and Ruby. Xapian allows you to easily add advanced indexing and search facilities to your applications. See www.xapian.org for more information.