DataMass Gdańsk Summit 2023
Gdańsk, Poland —
Enriching datasets with LLMs: JSON output modes, schema definitions with Pydantic, evaluating structured data extraction, Function Calling.
Large Language Models (LLMs) have proven useful for numerous tasks. They can summarise text, generate text, classify text, or translate text. LLMs can also convert unstructured data to structured data.
This can have huge benefits. Useful facts that were previously hidden inside a large piece of text can now be unveiled, allowing you to use properties of a dataset that could before not be directly accessed. LLMs come in useful to build such extraction tools quickly, cutting development time significantly. Though more importantly, with the power behind LLMs, the properties to be extracted can be more complex than what was previously possible with traditional methods.
Excerpt of slides used during the presentation on LLM data extraction.
