This is part 2 of a two-part series on Structured Extraction with LLM on Databricks. Read here for part 1!
Introduction
In part 1 of this series, I demonstrated how to use a large language model (LLM) with structured output and AI_QUERY to perform ...
This is part 1 of a two-part series on Structured Extraction with LLM on Databricks. Read here for part 2!
What is structured extraction?
Structured extraction, sometimes referred to as “key information extraction,” “entity extraction,” or simpl...
@Mantsama4 sorry for the late reply! Synthetic data generation and whether they are as good as the real data is an open research question. I recommend fine-tuning on synthetic data iteratively, in small batches, and make sure you have a robust evalua...
You can achieve that by using metadata filtering when querying the VS index. Check this section in our VS Index documentation: https://docs.databricks.com/en/generative-ai/create-query-vector-search.html#query-a-vector-search-endpoint
