Search Results for "artificial intelligence linux"

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...

Paul Graham GPT is a specialized AI-powered search and chat app built on a corpus of essays from Paul Graham, giving users the ability to query and discuss his writings in a conversational way. The repo stores the full text of his essays (chunked), uses embeddings (e.g. via OpenAI embeddings) to allow semantic search over that corpus, and hosts a chat interface that combines retrieval results with LLM-based answering — enabling RAG (retrieval-augmented generation) over a fixed dataset. The...

CRGREP searches for matching text in databases, various document formats, archives and other difficult to access resources. A command line tool for name and content text matching in database tables, plain files, MS Office documents, PDF, archives, MP3 audio, image meta-data, scanned documents, maven dependencies and web resources. CRGREP will search resources within resources of any arbitrary combination or depth, so text within a document within a zip archive, and so on. Here you...

The goal of DynaQ is to develop an inquiry system to explore the personal information space, supporting you with the searching paradigm 'orienteering'. DynaQ is a (desktop)search engine with enhanced functionality for file, email and blog search. Look at our GitLab homepage for sourcecode and documentation: http://dynaq.opendfki.de

This package contains different tools to add NLP capabilities for Lucene 4.x (it has been tested using Lucene version from 4.6.x to 4.8.1). Although it was originally developed for German, it is, mostly, language independent. It allows the user to lemmatize words to be indexed, to weight termy ba their parts of speech (e.g. weighting nouns mor hevaily than pronouns), and to add synonyms taken from GermaNet or a list you provide to the search index and thereby increase recall of lucene.

The semantic annotation system OPTIMA is the result of Andreas Vlachidis PhD work, (supervised by Prof. Douglas Tudhope, University of Glamorgan, UK). OPTIMA performs the NLP tasks of Named Entity Recognition, Relation Extraction, Negation Detection and Word Sense Disambiguation using hand-crafted rules and SKOS terminological resources (English Heritage Thesauri and Glossaries). The resulted semantic annotations are associated with classes of the (ISO 21127:2006) CIDOC Conceptual...

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.

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.

Meme is a multi-agent system. It aggregates literature information gathered from different sources into a viable format. It provides a visualization search and exports the literature information for users. It also integrates JADE and Nutch.

Single Click Real Time searching of both structured and unstructured data and information. Simultaneous searching of Structured: databases and unstructured: documents from within a web browser, desktop application and application plugins

Music agent is a software agent designed to help people discover new creative commons licensed music according to their personal taste.