NBLM2PPTX

Extracts text directly from PDF files using PDF.js library (getDocument(), getPage(), getTextContent() APIs) without invoking Gemini API, providing instant extraction at zero API cost. Falls back to Gemini OCR only when native text extraction fails or returns insufficient content. This hybrid strategy optimizes quota usage by leveraging browser-native PDF capabilities before consuming paid API calls.

Provides two Gemini OCR modes (Lite and Standard) that users can select before processing, trading off API quota consumption and processing speed against text style detection accuracy. Lite mode uses faster, cheaper Gemini models for basic text extraction; Standard mode uses higher-fidelity models that detect font styles, colors, and formatting. Selection is made via UI toggle before batch processing begins, affecting all subsequent API calls in that session.

Maps extracted text to exact positions in PPTX by using bounding box coordinates returned by Gemini OCR. For each text element, calculates PPTX coordinates (left, top, width, height) from OCR bounding boxes, then creates text boxes at those positions. Handles coordinate system conversion from image pixels to PPTX units (EMUs or inches). Text boxes are fully editable in PowerPoint while maintaining original layout positions.

Entire application runs in the browser with no server component; all processing (PDF parsing, image rendering, file I/O) occurs client-side. Only API calls to Google Gemini are sent over the network; all intermediate data (extracted text, images, state) remains in browser memory. Users' files and API keys never leave their machine except for Gemini API calls. No user data is logged, stored, or transmitted to third parties. This architecture eliminates backend infrastructure requirements and privacy concerns.

Processes multiple PDF pages or images concurrently by maintaining a pendingItems queue and executing up to N parallel Gemini API requests simultaneously (where N is configurable, typically 2-4 to respect rate limits). Uses Promise.all() or similar async patterns to coordinate multiple fetchWithRetry() calls, with built-in rate-limit handling that backs off and retries failed requests. Progress tracking updates UI in real-time as items complete.

Generates PowerPoint presentations with a dual-layer architecture: bottom layer contains the original background image with text removed (via Gemini inpainting/image editing), top layer contains extracted text in editable text boxes positioned at original text locations. Uses python-pptx or similar library to construct PPTX structure, embedding images and text boxes with precise coordinate mapping derived from Gemini OCR bounding boxes. Result is fully editable in PowerPoint while preserving original visual design.

Renders PDF pages and images at two different resolutions using Canvas API: 0.5x resolution for UI thumbnails (fast, low memory) and 2.0x resolution for Gemini AI processing (high quality, better OCR accuracy). Maintains separate canvas contexts and buffers for each resolution, allowing users to preview at low resolution while sending high-resolution data to API. This dual-resolution strategy balances UI responsiveness with AI processing quality.

Wraps all Gemini API calls (text extraction, image editing, OCR) with a fetchWithRetry() utility that implements exponential backoff retry strategy: initial 1-second delay, doubling on each retry (1s, 2s, 4s, 8s, etc.) up to configurable maximum (typically 5-10 retries). Handles rate-limit errors (429), server errors (5xx), and network timeouts gracefully, automatically retrying without user intervention. Tracks retry attempts and surfaces errors only after all retries exhausted.

Provides complete application UI in 6 languages (English, Spanish, French, Japanese, Simplified Chinese, Traditional Chinese) via separate standalone HTML files (index-en.html, index-es.html, etc.), each containing full application code with localized strings embedded. No runtime language switching; users select language by opening the appropriate HTML file. Each implementation is independently deployable and contains all necessary JavaScript, CSS, and localization strings.

Manages application state using two primary JavaScript arrays: pendingItems[] for files awaiting processing, and processedResults[] for completed conversions. Each item stores metadata (file name, type, thumbnail, full-resolution image, extracted text, bounding boxes). State updates trigger UI re-renders via direct DOM manipulation or framework bindings. No persistent storage; state is lost on page reload. This simple array-based approach avoids complex state management libraries.

Accepts file uploads via standard HTML file input element and drag-drop interface, supporting 5 formats: PDF, JPG, PNG, WebP, BMP. Uses handleFileSelect() event handler to validate file type and size, then routes to appropriate processing pipeline (PDF.js for PDFs, Canvas rendering for images). Provides visual feedback during drag-over state. No file size limits enforced client-side; browser memory is the practical constraint.

Uses Gemini's image editing capabilities to remove detected text from PDF/image backgrounds via API calls, producing clean background images suitable for PPTX bottom layer. Sends original image and text bounding boxes to Gemini, which inpaints the text regions with contextually appropriate background content. Result is a text-free image that preserves visual design elements (colors, patterns, graphics). Inpainting quality depends on background complexity and Gemini model capabilities.