OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Agent Frameworks

AI Data Science Team

AI Data Science Team is a Python library of specialized agents and multi-agent workflows for data-science tasks, accompanied by AI Pipeline Studio, a Streamlit app for building visual, reproducible pipelines.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

AI Data Science Team — OpenViST project profile in Agent Frameworks.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use the library to assemble task-specific data-science agents or multi-agent workflows; use AI Pipeline Studio when a visual, pipeline-first workspace for manual and AI-driven analysis steps is useful.

Who it is for

  • Python developers building agents for data loading, cleaning, analysis, modeling, or SQL work.
  • Data-science practitioners who want to organize manual and AI-assisted work in a visual pipeline.
  • Teams exploring multi-agent patterns for Pandas or SQL data analysis.

Documented uses

  • Load, inspect, clean, and wrangle datasets.
  • Perform exploratory data analysis, visualization, and feature engineering.
  • Build modeling and evaluation workflows using H2O and MLflow tools.
  • Interact with SQL databases through a specialized agent.
  • Record analysis steps in a visual pipeline with lineage and reproducible scripts.
Before you choose

Requirements & limits

The project is identified as MIT-licensed open source. The documented quickstart requires Python 3.10 or later and an OpenAI API key, with Ollama documented as an option for local models.

  • The project includes both a reusable agent library and a separate Streamlit application.
  • OpenAI and Ollama are documented model options; the README shows LangChain integrations for both.
  • AI Pipeline Studio supports saving metadata only or saving full data, and describes storage controls and rehydration workflows.
  • The README labels the project beta and warns of possible breaking changes before version 0.1.0.

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

Install and launch AI Pipeline Studio

Set up the repository package and start the included Streamlit application.

Before you start

  • Python 3.10 or later
  • A cloned repository
  • An OpenAI API key, or Ollama for local models

Steps

  1. From the cloned repository, install the project in editable mode with the command below.

    Documented command
    pip install -e .

  2. Launch the app with streamlit run apps/ai-pipeline-studio-app/app.py.

Expected outcome

The AI Pipeline Studio application starts through Streamlit.

Guide limitations

  • The README labels the project beta and notes breaking changes may occur before version 0.1.0.
  • The guide documents launching the app, not a particular analysis workflow.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
10 October 2026
Original website title
business-science/ai-data-science-team · Official homepage title · retained in its source language
How we review sourcesSuggest a correction