OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Data & Analytics

Chatie

Chatie, the ChatIE project, is a Python-based information-extraction application that uses ChatGPT in a two-stage, multi-turn question-answering framework to extract structured information from plain text without task-specific annotated data. It supports named-entity recognition, entity–relation triple extraction and event extraction for English and Chinese.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Chatie — OpenViST project profile in AI Data & Analytics.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Chatie when you want to explore ChatGPT-based extraction from plain text and can provide or work with the project's default type definitions.

Who it is for

  • Researchers exploring zero-shot information extraction.
  • Developers prototyping extraction workflows for English or Chinese text.
  • Teams testing entity, relation or event schemas on unannotated text.

Documented uses

  • Identify entities in a sentence using specified entity types.
  • Extract subject–relation–object triples from text.
  • Represent events with specified event types and argument roles.
Before you choose

Requirements & limits

The repository says the hosted demo is temporarily unavailable and recommends cloning and running the project locally. ChatGPT-backed use depends on OpenAI API access and a valid key.

  • The three supported tasks use different schema inputs: entity types for NER, relation types for triple extraction, and event types with argument roles for event extraction.
  • The README documents a React front end, Flask back end, and Node.js and npm versions for setup.
  • The project says API response speed can vary with OpenAI service load and notes that a proxy may be needed.
  • The README states that interaction data is collected to help improve the project.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up ChatIE locally

Start the documented React and Flask application locally.

Before you start

  • Clone the ChatIE repository.
  • Node.js 14.17.4 and npm 9.6.0.
  • Python for the back-end command.
  • OpenAI API access and a valid key for ChatGPT-backed use; the project notes a proxy may be needed.

Steps

  1. In the front-end directory, run npm install.

  2. Run npm run start from the front-end directory.

  3. In the back-end directory, run python run.py.

Expected outcome

The README says the front end should open in a browser tab, with the Flask back end started separately.

Guide limitations

  • The hosted demo is described as unavailable because of key costs.
  • The project says API key validity and OpenAI service load can affect use and response speed.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
6 November 2026
Original website title
cocacola-lab/ChatIE · Official homepage title · retained in its source language
How we review sourcesSuggest a correction