ragflow_preprocess/check_prerequisites.ps1

# Prerequisites check script for Ragflow PDF Preprocessing
Write-Host "======================================================" -ForegroundColor Cyan
Write-Host "   Ragflow PDF Preprocessing Prerequisites Check" -ForegroundColor Cyan
Write-Host "======================================================" -ForegroundColor Cyan
Write-Host ""

$allOk = $true

# Check Python and version
try {
    $pythonVersionOutput = (python --version) 2>&1
    $pythonVersion = $pythonVersionOutput -replace "Python "
    
    if ([version]$pythonVersion -ge [version]"3.8") {
        Write-Host "✅ Python $pythonVersion is installed (>= 3.8 required)" -ForegroundColor Green
    } else {
        Write-Host "❌ Python $pythonVersion is installed, but version 3.8 or higher is required" -ForegroundColor Red
        $allOk = $false
    }
} catch {
    Write-Host "❌ Python is not installed or not in PATH" -ForegroundColor Red
    Write-Host "   Required installation: https://www.python.org/downloads/" -ForegroundColor Yellow
    Write-Host "   Make sure to check 'Add Python to PATH' during installation" -ForegroundColor Yellow
    $allOk = $false
}

# Check Tesseract OCR
$tesseractPaths = @(
    "C:\Program Files\Tesseract-OCR\tesseract.exe",
    "C:\Program Files (x86)\Tesseract-OCR\tesseract.exe",
    "C:\Tesseract-OCR\tesseract.exe"
)

$tesseractInstalled = $false
$tesseractPath = ""

foreach ($path in $tesseractPaths) {
    if (Test-Path $path) {
        $tesseractInstalled = $true
        $tesseractPath = $path
        break
    }
}

if ($tesseractInstalled) {
    Write-Host "✅ Tesseract OCR is installed at: $tesseractPath" -ForegroundColor Green
    
    # Check language packs
    $tesseractDir = Split-Path -Parent $tesseractPath
    $langPath = Join-Path $tesseractDir "tessdata"
    $fraLangPath = Join-Path $langPath "fra.traineddata"
    $engLangPath = Join-Path $langPath "eng.traineddata"
    
    if (Test-Path $fraLangPath) {
        Write-Host "  ✅ French language pack (fra) installed" -ForegroundColor Green
    } else {
        Write-Host "  ❌ French language pack (fra) missing" -ForegroundColor Yellow
        Write-Host "     Reinstall Tesseract selecting the language packs" -ForegroundColor Yellow
        $allOk = $false
    }
    
    if (Test-Path $engLangPath) {
        Write-Host "  ✅ English language pack (eng) installed" -ForegroundColor Green
    } else {
        Write-Host "  ❌ English language pack (eng) missing" -ForegroundColor Yellow
        Write-Host "     Reinstall Tesseract selecting the language packs" -ForegroundColor Yellow
        $allOk = $false
    }
} else {
    Write-Host "❌ Tesseract OCR is not installed" -ForegroundColor Red
    Write-Host "   Required installation: https://github.com/UB-Mannheim/tesseract/wiki" -ForegroundColor Yellow
    Write-Host "   Make sure to select French and English language packs" -ForegroundColor Yellow
    $allOk = $false
}

# Check Ollama server
try {
    $response = Invoke-WebRequest -Uri "http://217.182.105.173:11434/api/version" -UseBasicParsing -ErrorAction SilentlyContinue
    if ($response.StatusCode -eq 200) {
        Write-Host "✅ Ollama server is accessible at 217.182.105.173:11434" -ForegroundColor Green
        
        # Check available models
        $modelsResponse = Invoke-WebRequest -Uri "http://217.182.105.173:11434/api/tags" -UseBasicParsing -ErrorAction SilentlyContinue
        $models = ($modelsResponse.Content | ConvertFrom-Json).models
        $modelNames = $models | ForEach-Object { $_.name }
        
        # Required models based on the server's available models
        $requiredModels = @(
            "mistral:latest",
            "llava:34b-v1.6-fp16", 
            "llama3.2-vision:90b-instruct-q8_0"
        )
        
        foreach ($model in $requiredModels) {
            if ($modelNames -contains $model) {
                Write-Host "  ✅ Model $model is available" -ForegroundColor Green
            } else {
                Write-Host "  ❌ Model $model not found on server" -ForegroundColor Yellow
                Write-Host "     This model is required for some features" -ForegroundColor Yellow
                $allOk = $false
            }
        }
    }
} catch {
    Write-Host "❌ Cannot connect to Ollama server at 217.182.105.173:11434" -ForegroundColor Red
    Write-Host "   Make sure you have network connectivity to the Ollama server" -ForegroundColor Yellow
    Write-Host "   This is required for the LLM features of the application" -ForegroundColor Yellow
    $allOk = $false
}

# Check Python libraries
Write-Host ""
Write-Host "Checking required Python libraries:" -ForegroundColor Cyan

$requiredLibraries = @(
    "PyQt6",
    "PyMuPDF",
    "numpy",
    "pytesseract",
    "Pillow",
    "opencv-python",
    "requests"
)

foreach ($lib in $requiredLibraries) {
    try {
        $output = python -c "import $($lib.ToLower().Replace('-', '_')); print('OK')" 2>&1
        if ($output -eq "OK") {
            Write-Host "  ✅ $lib is installed" -ForegroundColor Green
        } else {
            Write-Host "  ❌ $lib is not installed correctly" -ForegroundColor Red
            Write-Host "     Recommended installation: pip install $lib" -ForegroundColor Yellow
            $allOk = $false
        }
    } catch {
        Write-Host "  ❌ $lib is not installed" -ForegroundColor Red
        Write-Host "     Recommended installation: pip install $lib" -ForegroundColor Yellow
        $allOk = $false
    }
}

# Summary
Write-Host ""
Write-Host "======================================================" -ForegroundColor Cyan
if ($allOk) {
    Write-Host "✅ All prerequisites are satisfied!" -ForegroundColor Green
    Write-Host "   You can proceed with the installation and use of Ragflow." -ForegroundColor Green
} else {
    Write-Host "⚠️ Some prerequisites are not satisfied." -ForegroundColor Yellow
    Write-Host "   Please install the missing components before using Ragflow." -ForegroundColor Yellow
}
Write-Host "======================================================" -ForegroundColor Cyan

Read-Host "Press ENTER to exit"