Jev in production › SQL and data pipelines
datafusion-jev
Rust crate adds a prompt_jev() SQL function to Apache DataFusion 55 so queries can pull typed Jev choices or scores directly from row text.
- Use
- SQL and data pipelines
- Industry
- Data and analytics
- Form
- Open-source tool
- Stage
- Announced
- Plugs into
- Apache DataFusion
- Listed
- 2026-09-25
- Found via
- github
- Repository
- hotdata-dev/datafusion-jev
- Stars
- 7
- Forks
- 0
- Last push
- 2026-09-24
- Language
- Rust
- License
- none stated
The README opens with
Ask questions about your text from SQL. promptjev sends each row to the Jev inference service and returns a typed answer: a probability, a choice from a list you define, or a score on a scale you define.
Works with DataFusion 55. You bring the HTTP client and API key; the crate handles the SQL syntax, batching, retries, and result types.
1. Provide the HTTP client. Implement JevClient with whatever HTTP library you already use. POST the request body as JSON to https://api.typesafe.ai/v1/systemone with your API key in a header, and return the parsed JSON response. Keep the key on the server; it never appears in SQL.
Badge
For the project's own README, linking back here:
Also used for sql and data pipelines
- JevSDSQL $0.389
- grev sub-cent cost per few thousand lines
- Jev IDS 7.7x
- jev-harness (AntonioCoppe) 1.3 seconds
- jev-ultralightspeed 41% less money
- jlink $2.95
- signal-weave 130/144 exact outcome decisions
- jevgrep mean F1 of 0.90