Find a file
2018-08-17 15:49:29 -05:00
.vscode build spacy tagger in pipeline/create ner in crf/ build wrapper:Crfutils 2018-08-01 15:25:50 -05:00
BotSharp.Core Add nlp tagger structure. 2018-08-16 17:27:50 -05:00
BotSharp.MachineLearning add BotSharp.NLP library, finish RegexTokenizer. 2018-08-15 17:37:23 -05:00
BotSharp.NLP create a general ngram tagger. 2018-08-17 15:49:29 -05:00
BotSharp.NLP.UnitTest create a general ngram tagger. 2018-08-17 15:49:29 -05:00
BotSharp.RestApi add BotSharp.NLP library, finish RegexTokenizer. 2018-08-15 17:37:23 -05:00
BotSharp.UI add network error message. 2018-08-06 00:01:00 -05:00
BotSharp.UnitTest add BotSharp.NLP library, finish RegexTokenizer. 2018-08-15 17:37:23 -05:00
BotSharp.WebHost add BotSharp.NLP library, finish RegexTokenizer. 2018-08-15 17:37:23 -05:00
.dockerignore docker pull microsoft/aspnetcore-build 2018-08-13 11:12:10 -05:00
.gitignore Add fasttext dependent libs: cyg*.dll. Run in windows now. 2018-08-15 05:46:53 -05:00
BotSharp.sln add BotSharp.NLP library, finish RegexTokenizer. 2018-08-15 17:37:23 -05:00
Dockerfile update botsharp dockerfile and add spaCy dockerfile. 2018-08-13 17:14:19 -05:00
LICENSE Initial commit 2017-12-17 07:51:23 -06:00
README.md add BotSharp.NLP library, finish RegexTokenizer. 2018-08-15 17:37:23 -05:00

The Open Source AI Bot Platform Builder for Enterprise

Open up as much learning power as possible for your enterprise robots and precisely control every step of the AI processing pipeline.

BotSharp is an open source machine learning framework for AI Bot platform builder. This project involves natural language understanding, computer vision and audio processing technologies, and aims to promote the development and application of intelligent robot assistants in enterprise information systems. Out-of-the-box machine learning algorithms allow ordinary programmers to develop artificial intelligence applications faster and easier.

It's witten in C# running on .Net Core that is full cross-platform framework. C# is a enterprise grade programming language which is widely used to code business logic in information management related system. More friendly to corporate developers. BotSharp adopts machine learning algrithm in C/C++ interfaces directly which skips the python interfaces. That will facilitate the feature of the typed language C#, and be more easier when refactoring code in system scope.

Why we do this? because we all know python is not friendly programming language for enterprise developers, it's not only because it's low performance but also it's a type weak language, it will be a disater if you use python to build your bussiness system.

BotSharp is in accordance with components princple strictly, decouples every part that needed in the platform builder. So you can choose different UI/UX, or pick up a different NLP Tagger, or select a more advanced algrithm to do NER task. They are all modulized based an unfied interfaces.

Some Features

  • Built-in multi-Agents management, easy to build Bot as a Service platform.
  • Context In/ Out with lifespan to make conversion flow be controllable.
  • Use the natural language processing pipeline mechanism and the popular NLP algorithm library to build your own unique robot processing flow.
  • Support export/ import agent from other bot platforms directly.
  • Support different UI providers like Rasa UI and Articulate UI.
  • Support for multiple data request and response formats such as Rasa NLU and Dialogflow.
  • Integrate with popular social platforms like Facebook Messenger, Slack and Telegram.

Documents

https://github.com/Oceania2018/BotSharp/wiki

QUICK START

Install in docker container

Make sure you've got Docker installed:

PS D:\> git clone https://github.com/Oceania2018/BotSharp
PS D:\> cd BotSharp
PS D:\BotSharp\> docker build -t botsharp .
PS D:\BotSharp\> docker run -it -p 3112:3112 botsharp

Install in NuGet

PM> Install-Package BotSharp.Core
PM> Install-Package BotSharp.RestApi

Tip Jar

  • Ethereum

Ethereum

0x2FdE97210cd14F6020C67BAFA61d4c227FdC268d