Chart2CSV

AI-Powered Chart Data Extraction

Extract data from chart images using Mistral Pixtral Vision. 90%+ accuracy.

Live Demo · API Docs · Wiki

---

Quick Start

# API request
curl -X POST "https://chart2csv.kikuai.dev/extract" \
  -F "file=@chart.png"

---

Project Structure

Chart2CSV/
├── api/                    # FastAPI REST API
│   └── main.py             # API endpoints
├── chart2csv/              # Core Python package
│   ├── core/               # Extraction logic
│   │   ├── llm_extraction.py   # Mistral Pixtral LLM
│   │   ├── pipeline.py         # CV pipeline (fallback)
│   │   └── ocr.py              # OCR for axis labels
│   └── cli/                # Command-line interface
├── deploy/                 # Deployment scripts
│   ├── deploy.sh           # Server deployment
│   └── nginx.conf          # Nginx config
├── scripts/                # Development utilities
├── Dockerfile              # Container build
├── docker-compose.yml      # Container orchestration
├── requirements.txt        # Python dependencies
└── setup.py                # Package installation

---

Features

Feature	Description
🧠 Mistral Pixtral	90%+ accuracy with vision LLM
⚡ Zero-Click	Automatic chart understanding
📊 Multi-Chart	Line, scatter, bar charts
🔧 Manual Mode	Calibration endpoint for edge cases
🌐 REST API	Production-ready FastAPI

Powered by Mistral AI

---

API Endpoints

Endpoint	Description
POST /extract	LLM extraction (default)
POST /extract/calibrated	Manual calibration
GET /docs	Swagger UI
GET /health	Health check

---

Installation

pip install -e .

---

Environment Variables

Variable	Description
MISTRAL_API_KEY	Mistral AI API key (required)

---

License

AGPL-3.0. Copyright (c) 2025 KikuAI OÜ