feat: add LLM SQL query assistant and dataset sampler

Browse Source

- ask.py: Python script to query Base dos Dados via natural language using Gemini,
  generates and executes DuckDB SQL from Portuguese questions
- ask/ (Rust): CLI companion for the SQL query assistant with system prompt
- sample_datasets.py: samples parquet files from S3 into a local DuckDB for exploration
- sample_datasets/ (Rust): CLI for dataset sampling
- context/: LLM context bundle (schemas, join keys, file tree) for query generation

...

This commit is contained in:

rafapolo

2026-03-28 11:23:51 +01:00

parent 6801db427e

commit b5d84e3556

13 changed files with 156445 additions and 0 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

147562

context/schemas.json Normal file

File diff suppressed because one or more lines are too long