Artificial Intelligence
Agent Builder
The Agent Builder is an advanced feature that enhances the capabilities of intelligent agents. In this environment, the agent takes control of conversational flows, triggering them according to the u…
Zero Shot Learning
Zero Shot. Zero Shot is a natural language processing technique that enables intelligent agents to recognize features that were not previously trained.
WeniGPT
WeniGPT is a generative AI developed by Weni, with the purpose of providing assertive answers to users, using an exclusive base for the customer. Its key features include advanced intelligence and a…
Weni Platform AI Module
The Weni Platform enables the integration of Artificial Intelligence (AI) layers into your project, enhancing operational efficiency and effectiveness. Its Agent Builder allows for the quick creation of intelligent agents, utilizing native AI models to manage conversational flows and respond to user intents automatically. The platform also supports content integration into the company's knowledge base, enriching interactions. Additionally, Weni offers a repository of pre-trained intelligences for specific tasks and features Zero-Shot integration in the flows module for fast, accurate intent classification without prior training.
Repository - Overview
In this section, you will find information about training, testing, translations, and settings for classification AIs. It allows you to manage phrases, run tests, view interactions, perform translations, integrate with other platforms, and adjust general settings.
What is an Intelligence?
Overview. A Dataset or Intelligence is the main part of your bot. It is where all the training, testing, and translation phrases are located. It is also where you will find the general settings. On the main page, you can…
Intents and Entities
Intent and Entity Classification. The dataset consists of training phrases and test phrases. These phrases contain important elements used to define the context of your AI, including intents and entities.
Hands-on
Define the intentions clearly and keep them specific to enhance accuracy. Create example phrases for each intention to help the AI learn, and use entities if additional information extraction is needed.
Creating an Intelligence
In Weni, you can create as many intelligences as you want. To do so, just follow the step-by-step tutorial below! In the intelligence library, click on the highlighted "new intelligence" card…
Training your Intelligence
Overview: In Weni, we refer to "Training" as the action of generating a new model (AI) from all the existing training phrases. This model will be responsible for receiving user inputs and...
Strength of Intelligence
Strength of Intelligence. The strength of intelligence is a simple way to measure how well the intelligence is designed, providing owners with a point of reference and allowing others to have greater…
Testing your intelligence
Testing your intelligence. After adding several phrases for each intent in your created intelligence, you might want to know if your intelligence is working correctly, right? To check if your trainin…
Interactions
Interactions. The most common needs when using your dataset to predict real data are: Improving the dataset with real data. Weni has a very useful tool to achieve these two points: interactions 💭. It…
Translating your dataset
Translating your dataset. One of the main features of Weni is the ability to translate your dataset into various languages, allowing your intelligence to start predicting and understanding inputs fro…
Versioning
Versioning. A very important feature of Weni is Versioning. This feature allows the user to have multiple versions of the same intelligence, making it possible to switch between datasets to perform t…
Settings
Settings. In the Settings section of your Intelligence, you can manage various information, such as the name, description, main language, categories, whether the intelligence will be public or privat…
API
API. As a platform that allows easy use of NLP in applications, the process of integrating Weni with external services is very simple! In this article, you will learn how to integrate with the predic…
Integrating Intelligence into a Project on the Weni Platform
Integrating Intelligence into a Project on the Weni Platform. Native integration is an exclusive feature of the new Weni Platform.. On the Weni platform, it is possible to add intelligence to your pr…
Introduction to Content Intelligence
The Content Intelligence is an exclusive feature from Weni Platform. Born out of our continuous innovation in Artificial Intelligence studies, a new type of intelligence is available in our module: C…
Integrating a Content Intelligence
Integrating content intelligence is done in just a few steps. In this guide, we'll explain what's needed. Accessing the necessary information. Before making the flow, separate the information that wi…
Interface Updates
A new version of Bothub was released and this post will highlight the main changes.
Glossary
In this article, you will find the meaning of some common terms and expressions used in Weni. Most of these terms are found in NLU platforms, but some are specific to the Weni community, making it ve…
Guidance and Best Practices
To build the best possible intelligence, meaning a dataset that is accurate in its predictions, we must follow certain best practices when creating training phrases. In this article, we will learn ab…
