nlp.js
wink-nlp
Our great sponsors
nlp.js | wink-nlp | |
---|---|---|
9 | 21 | |
6,076 | 1,143 | |
1.1% | 1.7% | |
3.8 | 8.1 | |
about 1 month ago | 16 days ago | |
JavaScript | JavaScript | |
MIT License | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
nlp.js
-
Natural Language Processing (NLP) in JavaScript (series 2)
We'll use the "natural" NLP library; follow the previous session to understand how to set up your environment.
-
Natural Language Processing (NLP) in JavaScript (series)
Several NLP libraries are available, each offering distinct features and functionalities. One popular choice in the JavaScript ecosystem is the Natural Language Toolkit for JavaScript (NLP.js), which provides a wide range of NLP capabilities.
-
Couple Uncomfortable Facts About AI As It Is Right Now
nlp.js/docs/v4/nlp-intent-logics.md at master · axa-group/nlp.js · GitHub
-
[AskJS] Rate a string on how much sense it makes
For a JS based approach you could try NLP libraries like this one: https://github.com/axa-group/nlp.js
- Ich hab eine Browser-Extension erstellt, die hilft, die WM in Katar auf deutschen News-Websites zu boykottieren.
-
The full tech stack to run a chatbot — behind the scenes of an open source bot platform
To determine which chatbot intent is the best match for the user textual input, we rely on nlp.js (in JS) though we are in the process of moving to our new Python NLP server for better optimization of the needs of eCommerce conversations. A preprocessor language model is also used to improve the chances of a matching.
-
How to build your own chatbot NLP engine
Probably not. In fact, in Xatkit we aim to be a chatbot orchestration platform exactly to avoid reinventing the wheel and the non-invented here syndrome. So, in most cases, other existing platform (like DialogFlow or nlp.js) will work just fine. But we have also realized that there are always some particularly tricky bots for which you really need to be able to customize your engine to the specific chatbot semantics to get the results you want.
-
On premises chatbot
Also, if security is so important, you may want to configure Xatkit to work with nlp.js (see our wiki for instructions( so that even the intent matching part is done locally without sending the input text to the cloud (as it would happen if you decide to use, for instance, a NLP engine such as DialogFlowx)
-
Getting Rid of Dust / 1.0.0-beta.4
Since the previous release, NLP.js pushed a lot of work and has released a major version, moving from a monolithic library to multiple independent packages. So I spent some time to make Leon's NLP compatible to the latest changes.
wink-nlp
-
Show HN: Next-token prediction in JavaScript – build fast LLMs from scratch
This is awesome, thanks. I've been messing with wink's NLP library (https://winkjs.org/wink-nlp/) to transform user queries and format responses so I can make a proper chat bot - will see what I can learn from these!
- Show HN: WinkNLP introduces key sentence extraction
- WinkNLP's recent feature — key sentence extraction delivers a performance of over 450,000 tokens/second or 1500 sentences/second on Apple M1/16GB
-
How to visualize timeline of a Wiki article?
Automatic generation of the timeline — a graphical representation of a time period, on which important events are marked — from a Wikipedia article is a fascinating idea and very useful in quickly grasping the historical perspective. This post outlines the approach to create a well formatted timeline from any Wikipedia article using WinkNLP’s API and Named Entity Recognition (NER) feature:
- WinkNLP delivers 600k tokens/second speed on browsers (MBP M1)
-
Hacker News top posts: Nov 24, 2022
Show HN: WinkNLP delivers 600k tokens/second speed on browsers\ (2 comments)
- Show HN: WinkNLP delivers 600k tokens/second speed on browsers (MBP M1)
What are some alternatives?
natural - general natural language facilities for node
ml-classify-text-js - Machine learning based text classification in JavaScript using n-grams and cosine similarity
franc - Natural language detection
wink-eng-lite-model - English lite language model for wink-nlp.
leven - Measure the difference between two strings with the fastest JS implementation of the Levenshtein distance algorithm
Recognizers-Text - Microsoft.Recognizers.Text provides recognition and resolution of numbers, units, date/time, etc. in multiple languages (ZH, EN, FR, ES, PT, DE, IT, TR, HI, NL. Partial support for JA, KO, AR, SV). Packages available at: https://www.nuget.org/profiles/Recognizers.Text, https://www.npmjs.com/~recognizers.text
retext - natural language processor powered by plugins part of the @unifiedjs collective
DataTurks - ML data annotations made super easy for teams. Just upload data, add your team and build training/evaluation dataset in hours.
dialogflow-web-v2 - Dialogflow Web Integration. Supports rich components
wink-mqtt-rs - MQTT Relay for the Jailbroken Wink Hub v1, with Home Assistant MQTT autodiscovery support
text2token - break down a corpus of text into lines and tokens
echarts4r - 🐳 ECharts 5 for R