Prerequisites
- Python 3.10 or later.
- Curator, installed with
pip install bespokelabs-curator. - Ollama, from the Ollama download page.
1
Create an LLM subclass
2
Start Ollama
Pull a model and start the server.
3
Connect Curator to Ollama
Add the Curator sends Ollama requests through the LiteLLM backend.
ollama/ prefix to the model name, and set base_url to your Ollama server.4
Generate the data