chtmp223/topicGPT
A prompt-based framework that uses large language models to perform topic modeling on text collections.
Not currently ranked — collecting fresh signals.
star history
TopicGPT leverages LLMs through structured prompting to generate hierarchical topics from documents. It implements a multi-stage pipeline: generating high-level topics with generate_topic_lvl1, creating sub-topics with generate_topic_lvl2, refining topics by merging similar ones, assigning topics to input text with supporting quotes, and correcting assignments for consistency. The framework supports multiple LLM backends including OpenAI API, VertexAI, Azure, Gemini, and vLLM for local GPU inference.
Frequently asked
- What is chtmp223/topicGPT?
- A prompt-based framework that uses large language models to perform topic modeling on text collections.
- Is topicGPT open source?
- Yes — chtmp223/topicGPT is open source, released under the MIT license.
- What language is topicGPT written in?
- chtmp223/topicGPT is primarily written in Python.
- How popular is topicGPT?
- chtmp223/topicGPT has 410 stars on GitHub.
- Where can I find topicGPT?
- chtmp223/topicGPT is on GitHub at https://github.com/chtmp223/topicGPT.