Add CLAUDE.md with repository guidance for Claude Code

CLAUDE.md

@@ -0,0 +1,61 @@
+# CLAUDE.md
+
+This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
+
+## Project Overview
+
+This is a Hugging Face Spaces application that provides text embeddings using the Nomic AI model (nomic-embed-text-v1.5). It runs on CPU and provides both a web interface and API endpoints for generating text embeddings.
+
+## Key Commands
+
+### Local Development
+```bash
+# Install dependencies
+pip install -r requirements.txt
+
+# Run the application locally
+python app.py
+```
+
+### Git Operations
+```bash
+# Push to Hugging Face Spaces (requires authentication)
+git push origin main
+
+# Note: May need to authenticate with:
+huggingface-cli login
+```
+
+## Architecture
+
+The application consists of a single `app.py` file with:
+- **Model Initialization**: SentenceTransformer with `device='cpu'` (line 6)
+- **Embedding Function**: Simple wrapper that calls model.encode() (lines 9-10)
+- **Gradio Interface**: UI components and API endpoint configuration (lines 13-81)
+- **API Endpoint**: Named "predict" for programmatic access (line 27)
+
+## Important Configuration Details
+
+- **No Queue**: The app launches without `.queue()` to allow direct API calls
+- **CPU Mode**: Explicitly set to CPU to avoid GPU requirements
+- **Trust Remote Code**: Model uses `trust_remote_code=True` for custom Nomic model code
+- **API Structure**: Uses `fn_index: 0` for the predict endpoint
+
+## API Usage
+
+The `/api/predict` endpoint expects:
+```json
+{
+  "fn_index": 0,
+  "data": ["text to embed"]
+}
+```
+
+Returns embedding array in response.data field.
+
+## Deployment Notes
+
+- Deployed on Hugging Face Spaces at https://huggingface.co/spaces/ipepe/nomic-embeddings
+- Runs on port 7860
+- Uses Gradio 4.36.1 (newer versions available)
+- PyTorch configured for CPU-only via `--extra-index-url` in requirements.txt