tablegpt/tablegpt-agent

A pre-built agent for TableGPT2.

What it solves

It provides a user-friendly interface and agentic framework for interacting with TableGPT2, a series of Large Multimodal Models (LMMs) specifically designed for table-based question answering.

How it works

The agent is built using the Langgraph library, acting as a pre-built wrapper that enables users to query and interact with the TableGPT2 models to extract answers from tabular data.

Who it’s for

Developers and researchers who want to implement table-based question answering systems using the TableGPT2 model series.

Highlights

  • Built on top of Langgraph for agentic capabilities.
  • Integrated with TableGPT2 models for specialized tabular data processing.
  • Includes evaluation scripts and datasets for table-related benchmarks via the realtabbench directory.

Related

  • Project
    langchain-ai/react-agent

    A LangGraph template for implementing a ReAct agent that iteratively reasons and executes tool-based actions to solve complex user queries.

  • Project
    GiovanniPasq/agentic-rag-for-dummies

    A modular Agentic RAG framework using LangGraph that implements hierarchical indexing, multi-agent parallel retrieval, and human-in-the-loop query clarification.

  • Project
    cqzyys/lang-agent

    A visual configuration platform based on LangGraph that allows users to build complex AI agents using a drag-and-drop interface with customizable state variables for precise logic control.

  • Project
    JoshuaC215/agent-service-toolkit

    A full-stack toolkit for building and deploying AI agents using LangGraph, FastAPI, and Streamlit, providing a complete template from agent definition to user interface.

  • Project
    CopilotKit/open-multi-agent-canvas

    An open-source multi-agent chat interface that lets users manage multiple AI agents in one dynamic conversation using Next.js, LangGraph, and CopilotKit.