Skip to content

Commit

Permalink
Update project information in Cargo.toml and README.md files
Browse files Browse the repository at this point in the history
  • Loading branch information
scald committed Nov 29, 2024
1 parent 56e292d commit cf9aae4
Show file tree
Hide file tree
Showing 2 changed files with 40 additions and 70 deletions.
7 changes: 0 additions & 7 deletions Cargo.toml
Original file line number Diff line number Diff line change
Expand Up @@ -3,13 +3,6 @@ name = "eyeris"
version = "0.1.0"
edition = "2021"
authors = ["Steve Caldwell"]
description = "A high-performance image analysis service with AI provider support"
license = "MIT"
repository = "https://github.com/scald/eyeris"
documentation = "https://docs.rs/eyeris"
readme = "README.md"
keywords = ["ai", "image-analysis", "vision", "openai", "ollama"]
categories = ["computer-vision", "api-bindings", "multimedia::images"]

[dependencies]
tokio = { version = "1.0", features = ["full"] }
Expand Down
103 changes: 40 additions & 63 deletions README.md
Original file line number Diff line number Diff line change
@@ -1,90 +1,67 @@
# eyeris
# Eyeris - AI Image Analysis Web App

[![Build Status](https://github.com/scald/eyeris/workflows/CI/badge.svg)](https://github.com/scald/eyeris/actions)
[![License](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE)
[![Crates.io](https://img.shields.io/crates/v/eyeris.svg)](https://crates.io/crates/eyeris)
[![Documentation](https://docs.rs/eyeris/badge.svg)](https://docs.rs/eyeris)

A high-performance image analysis service that leverages AI models to provide detailed analysis of images. Supports multiple AI providers (currently OpenAI and Ollama).
Eyeris is a web application that provides detailed AI-powered image analysis using OpenAI's GPT-4 with vision capabilities. It features a modern, easy-to-use interface for uploading and analyzing images.

## Features

- 🚀 High-performance image processing with parallel execution
- 🤖 Multiple AI provider support (OpenAI, Ollama)
- 📊 Detailed image analysis with customizable formats
- 🖼️ Automatic image optimization and thumbnail generation
- 📈 Token usage tracking
- 🔒 Rate limiting built-in
- 📝 Comprehensive logging
- 🖼️ Simple drag-and-drop image upload interface
- 🤖 Powered by OpenAI's GPT-4 vision model
- 📊 Detailed JSON-structured analysis output
- 🚀 Built with Rust for high performance
- 🌐 Modern web interface

## Quick Start
## Getting Started

```bash
# Clone the repository
git clone https://github.com/scald/eyeris
### Prerequisites

# Navigate to project directory
cd eyeris
- Rust (latest stable version)
- An OpenAI API key

# Configure OpenAI API key (if using OpenAI)
echo "OPENAI_API_KEY=your_key_here" > .env
### Installation

# Run the service
cargo run
```
1. Clone the repository:

## API Usage
```bash
git clone https://github.com/yourusername/eyeris.git
cd eyeris
```

Send an image for analysis:
2. Set up your OpenAI API key:

```bash
curl -X POST http://localhost:3000/process \
-F "image=@path/to/your/image.jpg" \
-F "provider=ollama" \
-F "model=moondream" \
-F "format=json"
export OPENAI_API_KEY='your-api-key-here'
```

## Output Formats
3. Build and run:

- **JSON**: Structured data format for programmatic use
- **Concise**: Brief summary of key elements
- **Detailed**: Comprehensive analysis with multiple aspects
- **List**: Enumerated format for easy reading
```bash
cargo run
```

## Performance
4. Open your browser and navigate to:

The service is optimized for performance through:
```
http://localhost:3000
```

- Parallel processing with Rayon
- Automatic image optimization
- Efficient memory management
- Rate limiting for stability
## Usage

## Project Structure
1. Open the web interface in your browser
2. Drag and drop an image or click "Choose File" to select one
3. Wait for the analysis to complete
4. View the detailed JSON analysis of your image

```bash
src/
├── processor.rs # Core processing logic
├── providers/ # AI provider implementations
├── prompts.rs # Analysis prompt templates
└── main.rs # Service entry point
```
## Tech Stack

## Contributing
- **Backend**: Rust with Axum web framework
- **Frontend**: HTML, CSS, JavaScript
- **AI**: OpenAI GPT-4 Vision API
- **Image Processing**: Rust image crate

Contributions are welcome! Please:
## Contributing

1. Fork the repository
2. Create a feature branch
3. Add your changes
4. Write/update tests
5. Submit a pull request
Contributions are welcome! Please feel free to submit a Pull Request.

## License

MIT License

---

Built with Rust 🦀
This project is licensed under the MIT License - see the LICENSE file for details.

0 comments on commit cf9aae4

Please sign in to comment.