Skip to content

Pixi Tasks Reference

Udit Asopa edited this page Oct 16, 2025 · 1 revision

Pixi Tasks Reference

Complete reference for all available Pixi tasks in Vision Text Extractor. These tasks provide convenient shortcuts for common operations.

πŸš€ Quick Task Overview

# List all available tasks
pixi task list

# Get help for any task
pixi run <task-name> --help

πŸ“‹ Task Categories

πŸ”§ Setup & Installation

πŸ€– OCR Processing

🎯 Demo Commands

βœ… Testing & Validation

πŸ”„ Utility Tasks

  • clean - Clean cache and temporary files

πŸ“– Detailed Task Reference


Setup & Installation Tasks

setup

Purpose: Complete system validation and setup

pixi run setup
  • βœ… Validates all dependencies
  • βœ… Tests all AI providers
  • βœ… Checks environment configuration
  • βœ… Provides setup recommendations

Dependencies: None
Time: 30-60 seconds


setup-ollama

Purpose: Install Ollama and download LLaVA model

pixi run setup-ollama
  • πŸ“₯ Downloads and installs Ollama
  • πŸ“₯ Pulls LLaVA 7B model (~4GB)
  • βœ… Configures Ollama service
  • βœ… Tests model functionality

Dependencies: Internet connection
Time: 5-15 minutes (depending on internet speed)
Disk Space: ~4GB


setup-smolvlm

Purpose: Download Hugging Face SmolVLM model

pixi run setup-smolvlm
  • πŸ“₯ Downloads SmolVLM-Instruct model (~2GB)
  • βœ… Configures Hugging Face cache
  • βœ… Tests model loading
  • βœ… Validates CUDA availability (if applicable)

Dependencies: Internet connection
Time: 3-10 minutes
Disk Space: ~2GB


setup-env

Purpose: Create environment configuration file

pixi run setup-env
  • πŸ“„ Copies .env.example to .env
  • ⚠️ Won't overwrite existing .env
  • πŸ“ You must manually edit API keys

Dependencies: None
Time: < 1 second


install-deps

Purpose: Install or refresh all dependencies

pixi run install-deps
  • πŸ“¦ Equivalent to pixi install
  • πŸ”„ Useful for refreshing dependencies
  • βœ… Validates environment

Dependencies: Internet connection
Time: 1-5 minutes


OCR Processing Tasks

ocr_llm

Purpose: Flexible OCR using SmolVLM (requires image argument)

pixi run ocr_llm "path/to/image.jpg"
pixi run ocr_llm "https://example.com/image.png"
  • πŸ€– Uses Hugging Face SmolVLM by default
  • πŸ“ Accepts local files or URLs
  • βš™οΈ Requires prior setup-smolvlm

Arguments: Image path (required)
Dependencies: setup-smolvlm


ocr_ollama

Purpose: Flexible OCR using Ollama LLaVA (requires image argument)

pixi run ocr_ollama "path/to/image.jpg"
  • πŸ€– Uses Ollama LLaVA model
  • πŸ“ Accepts local files or URLs
  • βš™οΈ Add --provider ollama --model llava:7b for explicit control

Arguments: Image path (required)
Dependencies: Manual Ollama setup or setup-ollama


ocr_smolvlm

Purpose: Explicit SmolVLM OCR (requires image argument)

pixi run ocr_smolvlm "path/to/image.jpg"
  • πŸ€– Explicitly uses SmolVLM provider
  • πŸ“ Accepts local files or URLs
  • βš™οΈ Identical to ocr_llm but more explicit

Arguments: Image path (required)
Dependencies: setup-smolvlm


ocr_url_example

Purpose: Test OCR with a fixed online image

pixi run ocr_url_example
  • 🌐 Uses fixed recipe image URL
  • βœ… Good for testing URL functionality
  • πŸ” No arguments needed

Arguments: None
Dependencies: setup-smolvlm, Internet connection


Demo Commands

demo-ocr-huggingface

Purpose: Quick SmolVLM demo with sample image

pixi run demo-ocr-huggingface
  • πŸ–ΌοΈ Uses images/chocolate_cake_recipe.png
  • πŸ€– Hugging Face SmolVLM provider
  • βœ… Perfect for testing after installation

Arguments: None
Dependencies: setup-smolvlm


demo-ocr-ollama

Purpose: Quick Ollama demo with sample image

pixi run demo-ocr-ollama
  • πŸ–ΌοΈ Uses images/chocolate_cake_recipe.png
  • πŸ€– Ollama LLaVA 7B model
  • βœ… Good for comparing with SmolVLM

Arguments: None
Dependencies: setup-ollama


demo-ocr-openai

Purpose: Quick OpenAI demo with sample image

pixi run demo-ocr-openai
  • πŸ–ΌοΈ Uses images/chocolate_cake_recipe.png
  • πŸ€– OpenAI GPT-4o model
  • πŸ”‘ Requires valid API key in .env

Arguments: None
Dependencies: OpenAI API key in .env


Testing & Validation Tasks

test-setup

Purpose: Validate all dependencies are working

pixi run test-setup
  • βœ… Tests Python imports
  • βœ… Validates core libraries
  • βœ… Checks environment setup
  • πŸ“Š Provides detailed status report

Arguments: None
Dependencies: None


test-components

Purpose: Test actual functionality without API calls

pixi run test-components
  • πŸ–ΌοΈ Tests image loading
  • πŸ“ Validates file paths
  • πŸ”§ Tests component integration
  • ⚠️ No actual AI model calls

Arguments: None
Dependencies: None


test-imports

Purpose: Quick import validation

pixi run test-imports
  • ⚑ Fast dependency check
  • πŸ“¦ Tests critical imports only
  • βœ… Good for CI/CD pipelines

Arguments: None
Dependencies: None


check-env

Purpose: Verify environment variables

pixi run check-env
  • πŸ”‘ Checks OpenAI API key status
  • πŸ“„ Validates .env file
  • ⚠️ Shows which keys are set/missing

Arguments: None
Dependencies: None


Utility Tasks

clean

Purpose: Clean cache and temporary files

pixi run clean
  • 🧹 Removes .pixi cache
  • πŸ—‘οΈ Cleans Python __pycache__ directories
  • πŸ’Ύ Frees up disk space
  • ⚠️ Safe to run anytime

Arguments: None
Dependencies: None


πŸ”„ Task Workflows

First-Time Setup

# Complete installation and setup
pixi install
pixi run setup-env          # Create .env file
pixi run setup-smolvlm      # Download SmolVLM (recommended)
pixi run test-setup         # Validate everything
pixi run demo-ocr-huggingface  # Test with sample

Daily Usage

# Process your images
pixi run ocr_llm "my-document.pdf"
pixi run ocr_ollama "receipt.jpg"

# Compare providers
pixi run demo-ocr-huggingface
pixi run demo-ocr-ollama
pixi run demo-ocr-openai

Troubleshooting

# Diagnose issues
pixi run test-imports       # Check dependencies
pixi run test-components    # Test functionality
pixi run check-env          # Verify API keys
pixi run clean             # Clear cache if needed

Development

# Enter development environment
pixi shell -e dev
jupyter lab

# Test changes
pixi run test-setup
pixi run test-components

πŸ’‘ Pro Tips

Task Chaining

# Run multiple tasks in sequence
pixi run setup-smolvlm && pixi run demo-ocr-huggingface

# Conditional execution
pixi run test-setup && pixi run ocr_llm "image.jpg"

Custom Arguments

# Most tasks accept additional arguments
pixi run ocr_llm "image.jpg" --prompt "Extract specific data"
pixi run demo-ocr-huggingface --prompt "Focus on ingredients only"

Environment Variables

# Set custom cache locations
HF_HOME=/custom/path pixi run setup-smolvlm
OLLAMA_MODELS=/custom/path pixi run setup-ollama

This reference covers all available Pixi tasks. Use these shortcuts to streamline your Vision Text Extractor workflow!

Clone this wiki locally