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

Topicgpt

TopicGPT is a Python library for LLM-assisted topic modeling of document collections. It clusters document embeddings, extracts top words, generates topic descriptions and supports retrieval-based questions about topics, along with comparing, splitting, combining, adding and deleting topics.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Topicgpt — 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 TopicGPT when a document collection needs exploratory topic analysis and the resulting clusters should be investigated or adjusted through natural-language interaction.

Who it is for

  • Researchers analyzing themes across a text corpus
  • Analysts who need to inspect and refine topic clusters
  • Python developers building LLM-assisted text-mining workflows

Documented uses

  • Cluster documents and extract representative topic words
  • Generate readable descriptions for identified topics
  • Ask questions to retrieve detailed information from documents associated with a topic
  • Compare or restructure topics through splitting, combining, adding or deleting them
Before you choose

Requirements & limits

The library is installable through PyPI and the public repository is MIT-licensed. The documented workflow requires an OpenAI API key for embeddings and prompts; an Azure OpenAI configuration is also shown.

  • TopicGPT requires an LLM API credential for embeddings and prompts.
  • The README says fitting may take from a few minutes to several hours, depending on corpus size and whether embeddings are supplied.
  • The example allows a fixed topic count or HDBSCAN to determine the number of topics automatically.

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 TopicGPT and prepare a document corpus

Set up the Python library and prepare text in the input format shown in the repository example.

Before you start

  • Python environment
  • A corpus represented as a list of strings, with one document per string
  • An OpenAI API key, or Azure OpenAI credentials and endpoint details for the documented Azure configuration

Steps

  1. Install the package with the command below.

    Documented command
    pip install topicgpt

  2. Prepare the corpus as a list of document strings, removing empty documents if needed.

  3. Initialize TopicGPT with the relevant API key and select a topic count, or configure the Azure endpoint as shown in the README.

Expected outcome

The library is installed and the model is configured with a text corpus format and LLM credentials for the next documented stage, fitting the model.

Guide limitations

  • This guide covers installation, corpus preparation and initialization, not model fitting or analysis.
  • The API key is needed to compute embeddings and execute prompts.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
14 October 2026
Original website title
ArikReuter/TopicGPT · Official homepage title · retained in its source language
How we review sourcesSuggest a correction