Can't TextQL generate SQL directly from a schema and column annotations? (Advanced)
Can't TextQL generate SQL directly from a schema and column annotations? (Advanced)
The below section is rather intricate and technical. Feel free to skip it.
- Verification of raw SQL outputs is extremely difficult for anyone who is not an expert in the data warehouse, and impossible for customers who aren’t highly technical.
- There is no clear path to improving performance; you can write more docs or re-train ($$) with additional examples, but as long as language models are opaque and have wildly varying behavior compared to humans, it’s impossible to know if you’ve really added enough, or if what you’ve added clashes with something already in memory.
- In the case of a schema change, it’s not clear which documentation to change or what examples to prune.
- A language model cannot be deterministically forced to use a certain KPI formula in a SQL query.
- You cannot tell if the LLM hallucinated a piece of information or retrieved it from the context store, without reading all fetched documentation yourself.