RASA STACK AND ROCKETCHAT

Slide 1

Slide 1 text

All power of bleeding edge deep learning technologies to build clever bots & Rasa.ai

Slide 2

Slide 2 text

No content

Slide 3

Slide 3 text

Uma plataforma de código aberto que permite a troca de mensagens em tempo real entre colaboradores, clientes e fornecedores relevantes. Rocket.Chat STARS 17.4K FORKS 3.7K CONTRIBUTORS 416 RASA NLU STARS 3K FORKS 1K CONTRIBUTORS 76

Slide 4

Slide 4 text

MUDANÇAS DE PARADIGMA 80s - desktop & clients 90s - browser & websites 00s - smartphones & apps 10s - it’s the turn of messaging & bots

Slide 5

Slide 5 text

On-Premises On Cloud Implementação Instale no seu próprio servidor. Ideal para empresas que lidam com informações sigilosas. Na sua Infraestrutura Rode de forma segura e escalável. Não se preocupe com a parte técnica. Na nuvem da Rocket.Chat

Slide 6

Slide 6 text

Clientes

Slide 7

Slide 7 text

Exemplo de Customização Change Theme Colors https://thedevconf.rocket.chat

Slide 8

Slide 8 text

No content

Slide 9

Slide 9 text

How chatbots work Dialog Engine NLP API Chat usuário Intenção 1 Ação 1 Resposta Intenção 2 Resposta

Slide 10

Slide 10 text

No content

Slide 11

Slide 11 text

No content

Slide 12

Slide 12 text

we wanted more…

Slide 13

Slide 13 text

STACK RASA uses Python libraries for machine learning, deep learning and natural language understanding, making it the most powerful and promising open source framework in the scene. RASA Stack is made of 2 independent solutions: RASA NLU & RASA Core Rasa Stack

Slide 14

Slide 14 text

CORE

Slide 15

Slide 15 text

CORE domain.yml Rasa Stack

Slide 16

Slide 16 text

CORE Arquivo de histórias story.md Rasa Stack

Slide 17

Slide 17 text

CORE … or they can be trained using interactive learning, like this Rasa Stack

Slide 18

Slide 18 text

NLU Configurar seu próprio pipeline de NLU nlu_model_config.json

Slide 19

Slide 19 text

NLU Configurar seu próprio pipeline de NLU nlu_model_config.json

Slide 20

Slide 20 text

NLU RASA Natural Language Understanding Um interpretador próprio que pode funcionar como um server http: "I am looking for Mexican food" returns:

Slide 21

Slide 21 text

CORE INTERESTING RASA Core can track conversation status, by saving information about users interactions with the bot, and execute a action according with a certain custom policy Rasa Stack

Slide 22

Slide 22 text

STACK CARACTERÍSTICAS POSITIVAS - Powerful deep learning engine - Separated NLU server - MS LUIS and WIT.AI compatible - NLU pipeline rendering - Interactive Learning tool - Easy configuration file syntax - Custom Policy and Featurization for model tuning NEGATIVAS - Needs Deep Learning skills for model tuning - Configuration UI is not Free (RASA Platform) - Early project with NO analytics, plugins, and not much examples available

Slide 23

Slide 23 text

/BOTS Mande um e-mail para diego.dorgam@rocket.chat @diego.dorgam Converse com a gente no Rocket.Chat Acesse o servidor do time da Rocket.Chat no link open.rocket.chat . Teste a plataforma e nos encontro nos canais: ● #general General discussion channel ● #support Rocket.Chat support channel