Choosing Your Extractor

Back in the first lesson of the short-term module, you wrote one line into agent.py that this lesson is about: extractor_type=ExtractorType.LLM.

The package's default is actually a pipeline — spaCy first, GLiNER next, and the LLMiGo to glossary for large language model (opens in a new tab)A model trained on text to predict the next token, and so to generate language. only as a fallback. That one line switched the pipeline off and sent every message straight to the LLM instead.