Home - News ( United States | United Kingdom | Italy | Germany ) - Football scores

Showing content from https://github.com/antvis/T8/blob/main below:

antvis/T8: 🧬 Narrative text visualization for unstructured data.

English | 简体中文

T8 is a text visualization solution for unstructured data within the AntV technology stack, where T stands for Text, and 8 represents a byte of 8 bits, symbolizing that it can deeply uncover insights hidden beneath the text.

T8 is a declarative JSON Schema syntax that can be used to describe the content of data interpretation reports. Technically, based on the assumption that the JSON Schema data is generated by the server, the frontend simply consumes the Schema for rendering. As the demand for diversity and immediacy in data representation grows, along with the increasing application of AI and NLP technologies, maintaining text templates on the frontend will become unsustainable. In this context, using T8 for unified rendering will be the optimal choice.

• Introduction - a brief overview and T8's motivations.
• T8's Schema - the JSON Schema and description for T8.
• API - interactive case-driven guides of T8's core concepts, and how to use them.
• Example - a live agent for using T8 with ai.

• 🛫 Technology stack agnostic - Can be used into React, Vue, and other frontend stack.
• 🤖 LLM friendly - The T8's schema is easy to be generated by AI with prompt.
• 🛠️ Extensible - Register custom EntityPhrase to easily customize the T8's ui elements.
• 🪩 Lightweight - Few dependencies, small footprint, before gzip it was less than 20 Kb.

T8 is usually installed via a package manager such as npm or Yarn.

The Text object then can be imported from T8.

<div id="container"></div>

import { Text } from '@antv/t8';

// A text json schema to be visualized.
const schema = {
  /*  */
};

// Instantiate a new Text.
const text = new Text({
  container: 'container',
});

// Specify schema visualization.
text.schema(schema).theme('light');

// Render visualization.
const unmont = text.render();

// Destroy.
unmont();

If all goes well, you can get the following narrative text visualization!

T8 can be used to output specific text into a schema that meets the requirements, and then render it in a more easily readable text. For the processing of text, LLM is one of the core advantages of large models. To help you better use T8, we provide several pieces of content that can be used in your own Agent to quickly generate and render text information summaries.

1. JSON Schema: Standard JSON Schema format for describing the format and structure of text, which can be obtained from remote or from the current GitHub repository.
2. Prompt Template: A set of templates for prompting LLMs, see prompt.md and prompt.zh-CN.md.
3. Some examples: T8 Schema Example.
4. An example of an agent based on the tbox: [Text Summary].

We welcome all contributors to T8 and all our backers, and thank you for your suggestions and feedback.

This project exists thanks to all the people who contribute. And thank you to all our backers! 🙏

• Issues - report bugs or request features
• Discussions - discuss on GitHub

MIT@AntV.

RetroSearch is an open source project built by @garambo | Open a GitHub Issue

Search and Browse the WWW like it's 1997 | Search results from DuckDuckGo

HTML: 3.2 | Encoding: UTF-8 | Version: 0.7.4