Dbctx

Hi HN, I've been finding increasing need for helping our users chat with the underlying application data in postgresql directly using LLMs, visualize results and so on.A major obstacle to this is -- traditional sql schema doesn't contain enough information for an LLM to easily query things in one shot.For example, traditional schema doesn't say what is the expected/allowed value set in a state field, or what are the paths available embedded in a jsonb field.Also -- given a user query -- only a small fraction of the whole schema is relevant for an LLM to construct SQL queries. So filtering parts of schema relevant to construct a prompt is important.dbctx solves all these by inspecting a postgresql database and turning the results into an sqlite backed ".dtx" file. You can pass your natural language query to dtx, and get relevant tables in a compressed schema format along with field/json intelligence embedded in it. This leads to much better responses from the LLM from the getgo.I have a CLI, library and tiny UI embedded in a single go binary.Do give it a go, and any feedback welcome.