davanstrien HF Staff commited on
Commit
87deff1
Β·
verified Β·
1 Parent(s): d0813ca

Sync from GitHub via hub-sync

Browse files
Files changed (1) hide show
  1. README.md +13 -14
README.md CHANGED
@@ -11,21 +11,17 @@ pinned: false
11
 
12
  **Run a data or ML task over a Hugging Face dataset in one command β€” for humans and agents.**
13
 
14
- Each recipe is a single self-contained [UV script](https://docs.astral.sh/uv/guides/scripts/): dependencies are declared inline, so you run it straight from a URL with no clone, no virtualenv, no `pip install`. Run it locally with `uv run` where you have the hardware, or hand it to [Hugging Face Jobs](https://huggingface.co/docs/hub/jobs) for a managed GPU. Most recipes read a Hub dataset and write a new one, so they chain into pipelines.
15
 
16
- ## See every recipe (no GPU, no token)
17
 
18
- The lowest-friction start β€” just [uv](https://docs.astral.sh/uv/getting-started/installation/), runs locally in seconds:
19
 
20
  ```bash
21
  uv run https://huggingface.co/datasets/uv-scripts/jobs-utils/raw/main/list-recipes.py
22
  ```
23
 
24
- It prints a runnable URL for every recipe in the org. Run any of them the same way: `uv run <url>` locally, or `hf jobs uv run <url>` on a GPU.
25
-
26
- ## Run one for real
27
-
28
- The flagship is **[OCR](https://huggingface.co/datasets/uv-scripts/ocr)** β€” turn an image dataset into text & structured data, 30+ models. On a managed GPU (no hardware of your own; pay-per-second):
29
 
30
  ```bash
31
  hf jobs uv run --flavor l4x1 --secrets HF_TOKEN \
@@ -33,11 +29,12 @@ hf jobs uv run --flavor l4x1 --secrets HF_TOKEN \
33
  davanstrien/ufo-ColPali your-username/ufo-ocr --max-samples 10
34
  ```
35
 
36
- One command β†’ a new dataset with a `markdown` column.
37
 
38
- ## For your coding agent
 
39
 
40
- Recipes are built to be agent-driven β€” same `input output` arg order, runnable from a URL, self-describing headers. Two prompts to paste into Claude Code, Cursor, or similar:
41
 
42
  **Try it now** β€” runs a real OCR job and hands back a dataset:
43
 
@@ -60,8 +57,10 @@ Pick the one that fits, read its script header for the arguments, and run it wit
60
  Each recipe reads a Hub dataset and writes a new one, so chain them as needed.
61
  ```
62
 
63
- Prefer a packaged setup? The cookbook ships an **agent skill** for discovering and running recipes β€” see the [GitHub repo](https://github.com/davanstrien/uv-scripts-for-ai). Hugging Face also ships an [`hf` CLI skill for agents](https://huggingface.co/docs/hub/agents-cli). _(We'll refine these prompts over time.)_
 
 
64
 
65
- ## More
66
 
67
- Every other recipe is in the list below β€” detection & segmentation, audio transcription, NER & classification, embeddings & atlas maps, batch LLM/VLM inference, synthetic data, and dataset creation. Or browse on **[GitHub](https://github.com/davanstrien/uv-scripts-for-ai)** Β· run `hf jobs hardware` for GPU flavors & pricing.
 
11
 
12
  **Run a data or ML task over a Hugging Face dataset in one command β€” for humans and agents.**
13
 
14
+ Each recipe is a single self-contained [UV script](https://docs.astral.sh/uv/guides/scripts/): dependencies are declared inline, so you run it straight from a URL β€” no clone, no virtualenv, no `pip install`. Run it locally with `uv run`, or hand it to [Hugging Face Jobs](https://huggingface.co/docs/hub/jobs) for a managed GPU. Most recipes read a Hub dataset and write a new one, so they chain into pipelines.
15
 
16
+ ## Quickstart
17
 
18
+ **See every recipe** β€” locally, no GPU or token:
19
 
20
  ```bash
21
  uv run https://huggingface.co/datasets/uv-scripts/jobs-utils/raw/main/list-recipes.py
22
  ```
23
 
24
+ **Run one on a GPU** β€” the flagship, OCR an image dataset to text:
 
 
 
 
25
 
26
  ```bash
27
  hf jobs uv run --flavor l4x1 --secrets HF_TOKEN \
 
29
  davanstrien/ufo-ColPali your-username/ufo-ocr --max-samples 10
30
  ```
31
 
32
+ One command β†’ a new dataset with a `markdown` column. Pay-per-second, no hardware of your own.
33
 
34
+ <details>
35
+ <summary><b>Drive it with your coding agent β†’</b></summary>
36
 
37
+ Recipes take their arguments in the same `input output` order and run from a URL, so an agent can pick one and run it with no setup. Paste into Claude Code, Cursor, or similar:
38
 
39
  **Try it now** β€” runs a real OCR job and hands back a dataset:
40
 
 
57
  Each recipe reads a Hub dataset and writes a new one, so chain them as needed.
58
  ```
59
 
60
+ The cookbook also ships a ready-made **agent skill** for discovering and running recipes β€” see the [GitHub repo](https://github.com/davanstrien/uv-scripts-for-ai), and Hugging Face's own [`hf` CLI skill for agents](https://huggingface.co/docs/hub/agents-cli). _(We'll refine these prompts over time.)_
61
+
62
+ </details>
63
 
64
+ ## Browse
65
 
66
+ Every recipe is in the list below β€” OCR, detection & segmentation, audio transcription, NER & classification, embeddings & atlas maps, batch LLM/VLM inference, synthetic data, and dataset creation. Or browse on **[GitHub](https://github.com/davanstrien/uv-scripts-for-ai)** Β· run `hf jobs hardware` for GPU flavors & pricing.