Crawl websites, sync to vector databases, and power RAG applications. Pre-built integrations for LLM pipelines and AI assistants.
Build data pipelines that feed your AI models and agents without managing infrastructure. Crawl any website, transform content, and push directly to your preferred vector store. Use 10,000+ tools for RAG applications, AI assistants, and real-time knowledge bases. Monitor site changes, trigger workflows on new data, and keep your AIs fed with fresh, structured information. Cloud-native, API-first, and free to start until you need to scale.
Try for free
The AI workplace management platform
Plan smart spaces, connect teams, manage assets, and get insights with the leading AI-powered operating system for the built world.
By combining AI workflows, predictive intelligence, and automated insights, OfficeSpace gives leaders a complete view of how their spaces are used and how people work. Facilities, IT, HR, and Real Estate teams use OfficeSpace to optimize space utilization, enhance employee experience, and reduce portfolio costs with precision.
LABB-CAT is a browser-based linguistics research tool that stores recordings and regular-expression searchable text transcripts of interviews. The search results, entire transcripts, and media, can be viewed or exported in a variety of format
Web service providing access to the Autshumato Machine Translation (MT) and other Moses Statistical MT systems. Functionality includes:
- Automatic sentence, document, web page translation.
- Improvements for translations.
- Reviewer requests and interface to review improvements
- Connection to the latest version of the Autshumato ITE, Post Edits done on inserted automatic translations are automatically submitted to the MTWS.
- Administration interface to add users, reviewers and MT...
TIES (Text Information Extraction System) is a clinical text search engine that uses Natural Language Processing techniques to extract medical concepts from free text clinical reports. It provides secure de-identified access to this information and has in built collaboration tools and honest broker functionality. It is licensed for academic use under the BSD license. For commercial use please contact Nexi at http://nexihub.com
*** NOTICE: this software and forum are no longer...
Java API for the Romanian WordNet.
Please note that the actual WordNet for Romanian (the XML file containing the network) is not included, it can be obtained (due to its license restrictions) from: http://ws.racai.ro:9191/repository/browse/romanian-wordnet-30/4611a43efb6811e2a8ad00237df3e3580b6b50d1111c4a6292694bded91d5c14/
****
If you would like a direct download of the API containing the RoWordNet xml file, please download them both from : http://www.racai.ro/tools/text/rowordnet/
****
Please cite:
Dumitrescu, Ștefan Daniel. ...
Award-Winning Medical Office Software Designed for Your Specialty
Succeed and scale your practice with cloud-based, data-backed, AI-powered healthcare software.
RXNT is an ambulatory healthcare technology pioneer that empowers medical practices and healthcare organizations to succeed and scale through innovative, data-backed, AI-powered software.
A very simple tool to automate benchmarking tests on MySQL DBs.
It fills MySQL tables columns;
perform customized tests; and
outputs the results on CSV format.
It uses Xeger, a java package for generating random text from regular expressions (http://code.google.com/p/xeger/).
Xeger uses dk.brics.automaton java package developed by Anders Møller (http://cs.au.dk/~amoeller/automaton/index.html).
This is a Java-based project for complex event extraction from text and co-reference resolution. Currently the code can read BioNLP shared task format (http://2011.bionlp-st.org/) and i2b2 Natural Language Processing for Clinical Data shared task format (https://www.i2b2.org/NLP/DataSets/Main.php). Event extraction includes finding events and the parameters for an event in a text.
The method is based on SVM but other ML algorithms can be adopted. The method details are explained in the...
Connecting Historical Authorities with Links, Contexts and Entities. CHALICE is a historic placename gazetteer for the UK, published as Linked Data and linked to other widely-used sources of placename reference information on the semantic web.
It's a utility application for updating and integrating translation memories, created by the Autshumato ITE, over a network. Licensed under the TMate Open Source License and free to download and be used by anyone.
OrangeHRM provides a world-class HRIS experience and offers everything you and your team need to be that HR hero you know that you are.
Give your HR team the tools they need to streamline administrative tasks, support employees, and make informed decisions with the OrangeHRM free and open source HR software.
A compiler to improve relation management between mobile users. This compiler will handle data islands for data transportation between a client mobile phone and a server node accesing a cellular network.