File size: 5,569 Bytes
4d35814 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 |
import { convertPDFToImage, convertPDFToText } from './pdf-processing';
import { isSvgMimeType, svgBase64UrlToPngDataURL } from './svg-to-png';
import { isWebpMimeType, webpBase64UrlToPngDataURL } from './webp-to-png';
import { FileTypeCategory } from '$lib/enums/files';
import { config, settingsStore } from '$lib/stores/settings.svelte';
import { supportsVision } from '$lib/stores/server.svelte';
import { getFileTypeCategory } from '$lib/utils/file-type';
import { readFileAsText, isLikelyTextFile } from './text-files';
import { toast } from 'svelte-sonner';
function readFileAsBase64(file: File): Promise<string> {
return new Promise((resolve, reject) => {
const reader = new FileReader();
reader.onload = () => {
// Extract base64 data without the data URL prefix
const dataUrl = reader.result as string;
const base64 = dataUrl.split(',')[1];
resolve(base64);
};
reader.onerror = () => reject(reader.error);
reader.readAsDataURL(file);
});
}
export interface FileProcessingResult {
extras: DatabaseMessageExtra[];
emptyFiles: string[];
}
export async function parseFilesToMessageExtras(
files: ChatUploadedFile[]
): Promise<FileProcessingResult> {
const extras: DatabaseMessageExtra[] = [];
const emptyFiles: string[] = [];
for (const file of files) {
if (getFileTypeCategory(file.type) === FileTypeCategory.IMAGE) {
if (file.preview) {
let base64Url = file.preview;
if (isSvgMimeType(file.type)) {
try {
base64Url = await svgBase64UrlToPngDataURL(base64Url);
} catch (error) {
console.error('Failed to convert SVG to PNG for database storage:', error);
}
} else if (isWebpMimeType(file.type)) {
try {
base64Url = await webpBase64UrlToPngDataURL(base64Url);
} catch (error) {
console.error('Failed to convert WebP to PNG for database storage:', error);
}
}
extras.push({
type: 'imageFile',
name: file.name,
base64Url
});
}
} else if (getFileTypeCategory(file.type) === FileTypeCategory.AUDIO) {
// Process audio files (MP3 and WAV)
try {
const base64Data = await readFileAsBase64(file.file);
extras.push({
type: 'audioFile',
name: file.name,
base64Data: base64Data,
mimeType: file.type
});
} catch (error) {
console.error(`Failed to process audio file ${file.name}:`, error);
}
} else if (getFileTypeCategory(file.type) === FileTypeCategory.PDF) {
try {
// Always get base64 data for preview functionality
const base64Data = await readFileAsBase64(file.file);
const currentConfig = config();
const hasVisionSupport = supportsVision();
// Force PDF-to-text for non-vision models
let shouldProcessAsImages = Boolean(currentConfig.pdfAsImage) && hasVisionSupport;
// If user had pdfAsImage enabled but model doesn't support vision, update setting and notify
if (currentConfig.pdfAsImage && !hasVisionSupport) {
console.log('Non-vision model detected: forcing PDF-to-text mode and updating settings');
// Update the setting in localStorage
settingsStore.updateConfig('pdfAsImage', false);
// Show toast notification to user
toast.warning(
'PDF setting changed: Non-vision model detected, PDFs will be processed as text instead of images.',
{
duration: 5000
}
);
shouldProcessAsImages = false;
}
if (shouldProcessAsImages) {
// Process PDF as images (only for vision models)
try {
const images = await convertPDFToImage(file.file);
// Show success toast for PDF image processing
toast.success(
`PDF "${file.name}" processed as ${images.length} images for vision model.`,
{
duration: 3000
}
);
extras.push({
type: 'pdfFile',
name: file.name,
content: `PDF file with ${images.length} pages`,
images: images,
processedAsImages: true,
base64Data: base64Data
});
} catch (imageError) {
console.warn(
`Failed to process PDF ${file.name} as images, falling back to text:`,
imageError
);
// Fallback to text processing
const content = await convertPDFToText(file.file);
extras.push({
type: 'pdfFile',
name: file.name,
content: content,
processedAsImages: false,
base64Data: base64Data
});
}
} else {
// Process PDF as text (default or forced for non-vision models)
const content = await convertPDFToText(file.file);
// Show success toast for PDF text processing
toast.success(`PDF "${file.name}" processed as text content.`, {
duration: 3000
});
extras.push({
type: 'pdfFile',
name: file.name,
content: content,
processedAsImages: false,
base64Data: base64Data
});
}
} catch (error) {
console.error(`Failed to process PDF file ${file.name}:`, error);
}
} else {
try {
const content = await readFileAsText(file.file);
// Check if file is empty
if (content.trim() === '') {
console.warn(`File ${file.name} is empty and will be skipped`);
emptyFiles.push(file.name);
} else if (isLikelyTextFile(content)) {
extras.push({
type: 'textFile',
name: file.name,
content: content
});
} else {
console.warn(`File ${file.name} appears to be binary and will be skipped`);
}
} catch (error) {
console.error(`Failed to read file ${file.name}:`, error);
}
}
}
return { extras, emptyFiles };
}
|