topicGPT
topicGPT copied to clipboard
Code & Prompts for TopicGPT paper
Hi, after using the module, I realized that your code only accepts specific types of models in openAI, which are GPT 3.5 and GPT 4 (not turbo). Since there are...
How to use azure api or other api?
This is a great framework, and I'm learning to use it. However, I haven’t found an output or function that shows the final topic assigned to each document (with "others"...
**Problem Description:** The current process for generating topics using the OpenAI API is experiencing a significant bottleneck due to sequential processing. Each text requires an individual API call, which takes...
1. assignment should use prompt file for assignment not generation_1 2. topic file is input for assignment not output, fix typos
for generation_2, the path of input data by default should be the output of the generation_1
I'm encountering the following error when using generate_topic_lvl1, passing "vertex" as api and "gemini-2.0-flash-001" as model: File "/root/.local/lib/python3.10/site-packages/topicgpt_python/utils.py", line 234, in iterative_prompt response = self.model_obj.generate_content( File "/root/.local/lib/python3.10/site-packages/google/generativeai/generative_models.py", line 305, in...
Both prompts for correction and assignment are the same. So what is the difference between both processes ?
Hi, Can you tell me how to change the number of topics? Why does the lvl2 keep on running for me?