# Add \`zeta distill\` command \(\#44369\) · gitcafe/zed

[View on GitCafe](https://git.cafe/gitcafe/zed/commit/d312d59ace3feda4a0be5c63aa4f61f2d9ecca19)

Repository: [gitcafe/zed](https://git.cafe/gitcafe/zed)

Visibility: public

Requested revision: d312d59ace3feda4a0be5c63aa4f61f2d9ecca19

Requested commit: d312d59ace3feda4a0be5c63aa4f61f2d9ecca19

Commit: d312d59ace3feda4a0be5c63aa4f61f2d9ecca19

Tree: ab0550d1d521b0829b6848c479af983de77fbecf

Author: Oleksiy Syvokon

Committer: GitHub

## Message

```
Add `zeta distill` command (#44369)

This PR partially implements a knowledge distillation data pipeline.

`zeta distill` gets a dataset of chronologically ordered commits and
generates synthetic predictions with a teacher model (one-shot Claude
Sonnet).

`zeta distill --batches cache.db` will enable Message Batches API. Under
the first run, this command will collect all LLM requests and upload a
batch of them to Anthropic. On subsequent runs, it will check the batch
status. If ready, it will download the result and put them into the
local cache.


Release Notes:

- N/A

---------

Co-authored-by: Piotr Osiewicz <24362066+osiewicz@users.noreply.github.com>
Co-authored-by: Ben Kunkle <ben@zed.dev>
```

## Parents

- [b4083ec47b1ef326ca4d033bd732b9989d5003d0](https://git.cafe/gitcafe/zed/commit/b4083ec47b1ef326ca4d033bd732b9989d5003d0?format=markdown)

[Source at this commit](https://git.cafe/gitcafe/zed/tree/d312d59ace3feda4a0be5c63aa4f61f2d9ecca19?format=markdown)