You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hi y'all, I thought about writing a notebook that showcases how to create a natural language interface for databases using Hugging Face models, Outlines for structured generation and Lark as a parser for syntax checks.
Outlines is a library that constrain auto-regressive text generation models on outputting text that matches regular expressions, JSON schemas or even grammars, which is pretty amazing.
Including some sort of RAG in order to reduce token size when including db schemas as context for the natural language query would also be beneficial, but I feel like too many recipes in the cookbook already deal with RAG …
Hi y'all, I thought about writing a notebook that showcases how to create a natural language interface for databases using Hugging Face models, Outlines for structured generation and Lark as a parser for syntax checks.
Outlines is a library that constrain auto-regressive text generation models on outputting text that matches regular expressions, JSON schemas or even grammars, which is pretty amazing.
What do you think @MKhalusova ?
The text was updated successfully, but these errors were encountered: