OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Chat & Assistants

Eve Bot

Eve Bot is an open-source customer-service chatbot project demonstrated as a Twitter Apple Support bot. Its code and notebooks cover support-text preprocessing, intent exploration and classification, named-entity recognition, and mapping model outputs to responses in a Streamlit application.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Eve Bot — OpenViST project profile in Chat & Assistants.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it as a code reference or starting point when exploring a Twitter-style customer-support chatbot workflow, especially one based on intent classification and entity extraction.

Who it is for

  • Developers studying how to build a support chatbot from social-media text.
  • Practitioners exploring intent classification and named-entity recognition in a conversational workflow.
  • Readers who want a code example connecting predicted intents and extracted entities to response actions.

Documented uses

  • Explore and preprocess customer-support tweets for chatbot training.
  • Group and label support questions by intent.
  • Create Doc2Vec-based training data and classify input intents with a Keras model.
  • Extract entities from a question and use intent and entity outputs to select a response.
  • Launch the described Streamlit app locally.
Before you choose

Requirements & limits

The repository is public and marked MIT-licensed. The README provides a local Streamlit launch instruction.

  • The demonstration is based on Twitter Apple Support questions, so a different support domain would require evaluating its data, intents, entities and response actions.
  • The README identifies Keras intent classification with a bidirectional LSTM, Doc2Vec training data and custom named-entity recognition.
  • The app depends on saved model and object files; the README says some entity-recognition model files are omitted and can take a long time to generate.
  • The repository describes a Streamlit application as well as Jupyter notebooks for analysis and modeling.

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

Launch the Streamlit app locally

Open the repository’s Streamlit application and navigate its available pages.

Before you start

  • A local copy of the repository
  • Python and Streamlit installed
  • The model and object files the application expects

Steps

  1. Change into the repository’s deploy directory.

  2. Run streamlit run app.py.

  3. Navigate to the pages available in the app.

Expected outcome

The Streamlit application opens with its available pages, including the chatbot page described in the repository.

Guide limitations

  • The README does not provide a complete dependency-installation procedure.
  • The app assumes required model and object files are available; some entity-recognition model files are not included and may take a long time to generate.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
17 October 2026
Original website title
mtaruno/eve-bot · Official homepage title · retained in its source language
How we review sourcesSuggest a correction