update readme

README.md

@@ -9,9 +9,9 @@ pinned: false
 
 # UV Scripts
 
-**Ready-to-run data processing scripts for the ML community**
+**Ready-to-run ML tools powered by UV - zero setup, maximum power**
 
-Run powerful ML workflows with a single command - no setup required.
+Run state-of-the-art ML workflows with a single command. From OCR to classification, all scripts work instantly with `uv run`.
 
 ## What are UV scripts?
 
@@ -22,18 +22,95 @@ Perfect for:
 - 💻 **Local processing** on your machine  
 - 🔄 **Reproducible pipelines** that work anywhere
 
-## Example
+## 🚀 Quick Example
 
 ```bash
-# Convert PDFs to a dataset
-uv run https://huggingface.co/datasets/uv-scripts/dataset-creation/resolve/main/pdf-to-dataset.py \
-  /path/to/pdfs \
-  username/my-dataset
+# Extract text from images with state-of-the-art OCR
+uv run https://huggingface.co/datasets/uv-scripts/ocr/raw/main/nanonets-ocr.py \
+  your-image-dataset \
+  your-extracted-text
+
+# Or run on GPU with HF Jobs (no local GPU needed!)
+hf jobs uv run --flavor l4x1 \
+  https://huggingface.co/datasets/uv-scripts/ocr/raw/main/nanonets-ocr.py \
+  your-images your-text
 ```
 
-## Browse Scripts
+## 📚 Browse Scripts
 
 | Script Collection | Description | GPU Required |
 |-------------------|-------------|--------------|
-| [dataset-creation](https://huggingface.co/datasets/uv-scripts/dataset-creation) | Create datasets from PDFs and other files | ❌ |
-| More coming soon... | | |
+| [ocr](https://huggingface.co/datasets/uv-scripts/ocr) | Extract text from images with VLMs (LaTeX, tables, forms) | ✅ |
+| [classification](https://huggingface.co/datasets/uv-scripts/classification) | Text classification with guaranteed valid outputs | ✅ |
+| [dataset-creation](https://huggingface.co/datasets/uv-scripts/dataset-creation) | Create datasets from PDFs and files | ❌ |
+| [vllm](https://huggingface.co/datasets/uv-scripts/vllm) | High-performance inference with vLLM | ✅ |
+
+## 🎯 Why UV Scripts?
+
+### Zero Setup
+No virtual environments, no dependency conflicts, no installation steps. UV handles everything automatically when you run the script.
+
+### Production Ready
+These aren't demos - they're production-quality tools used by the community for real ML workflows.
+
+### GPU Optimized
+Seamlessly run on local GPUs or scale to cloud with HF Jobs. Same script, different compute.
+
+### Community Driven
+Browse scripts, contribute your own, and learn from the best practices of the ML community.
+
+## 🌟 Featured Scripts
+
+### OCR Any Document Dataset
+Extract text from images with state-of-the-art accuracy:
+```bash
+# Handles LaTeX, tables, forms, handwriting
+uv run https://huggingface.co/datasets/uv-scripts/ocr/raw/main/nanonets-ocr.py \
+  your-images extracted-text
+```
+
+### Classify with Guaranteed Valid Outputs  
+Text classification that always returns valid labels:
+```bash
+# Uses vLLM's structured generation - no invalid outputs!
+uv run https://huggingface.co/datasets/uv-scripts/classification/raw/main/classify-dataset.py \
+  --input-dataset imdb --column text \
+  --labels "positive,negative" --output-dataset imdb-classified
+```
+
+## 🚀 Getting Started
+
+1. **Install UV** (one-time setup):
+   ```bash
+   curl -LsSf https://astral.sh/uv/install.sh | sh
+   ```
+
+2. **Run any script**:
+   ```bash
+   uv run https://huggingface.co/datasets/uv-scripts/[collection]/raw/main/[script].py
+   ```
+
+3. **Or use HF Jobs** (no local GPU needed):
+   ```bash
+   hf jobs uv run --flavor l4x1 [script-url] [args]
+   ```
+
+## 🤝 Contributing
+
+We welcome scripts that:
+- Solve real ML problems
+- Include clear documentation
+- Follow UV best practices
+- Work on both local and cloud
+
+Submit your scripts as PRs to the relevant collection or propose a new collection!
+
+## 📖 Learn More
+
+- [UV Documentation](https://docs.astral.sh/uv/)
+- [HF Jobs Guide](https://huggingface.co/docs/hub/spaces-gpu-jobs)
+- [Script Examples](https://github.com/astral-sh/uv/tree/main/scripts)
+
+---
+
+*UV Scripts is a community project showcasing the power of [UV](https://github.com/astral-sh/uv) for ML workflows.*