Improve user friendly-ness with LLM help?
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 11.5k
- Forks
- 904
- Avg merge
- 4d 17h
- Merged PRs (30d)
- 18
Description
Just tried out datasette for the first time against my claude export history and it's great.
However for now techies, perhaps a cool feature might be to accept text input and to connect datasette to an llm and for the llm to generate the sql that datasette could run against. This can have the benefit of helping a new user get up to speed with sql and to be able to query data in natural language too.
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
The issue names no files, tests, or entry points. Start by reviewing Datasette’s current query experience and SQL execution flow, then clarify the LLM provider, safety boundaries, and generated-query workflow. Done would require an agreed scope and tests covering the proposed natural-language query behavior.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, sql
- Domain
- ai, databases
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100