Spaces:
Running
Running
| <html lang="en"> | |
| <head> | |
| <meta charset="UTF-8"> | |
| <meta name="viewport" content="width=device-width, initial-scale=1.0"> | |
| <title>Train Model from PDFs</title> | |
| <script src="https://cdn.jsdelivr.net/npm/@tensorflow/tfjs"></script> | |
| <script src="https://cdn.jsdelivr.net/npm/pdfjs-dist/build/pdf.min.js"></script> | |
| </head> | |
| <body> | |
| <h1>Train a Model from PDF Files</h1> | |
| <a href="entrenament-pdf.html" style="margin:5px;padding: 5px; border:1px solid green">Entrenament PDF</a> | |
| <a href="preguntar-pdf.html" style="margin:5px;padding: 5px; border:1px solid green">Preguntar PDF</a> | |
| <br> | |
| <input type="file" id="pdfFiles" multiple accept="application/pdf"> | |
| <button id="trainModel">Train Model</button> | |
| <pre id="output"></pre> | |
| <script> | |
| const outputElement = document.getElementById('output'); | |
| async function extractTextFromPDF(file) { | |
| const pdf = await pdfjsLib.getDocument(await file.arrayBuffer()).promise; | |
| let textContent = ''; | |
| for (let i = 1; i <= pdf.numPages; i++) { | |
| const page = await pdf.getPage(i); | |
| const text = await page.getTextContent(); | |
| textContent += text.items.map(item => item.str).join(' '); | |
| } | |
| return textContent; | |
| } | |
| async function trainModelFromPDFs(files) { | |
| const texts = []; | |
| for (const file of files) { | |
| const text = await extractTextFromPDF(file); | |
| texts.push(text); | |
| } | |
| // Tokenize text data and prepare features/labels | |
| const tokenizer = new Set(texts.join(' ').split(/\s+/)); | |
| const tokenToIndex = {}; | |
| let index = 0; | |
| for (const token of tokenizer) { | |
| tokenToIndex[token] = index++; | |
| } | |
| const data = texts.map(text => { | |
| const tokens = text.split(/\s+/); | |
| return tokens.map(token => tokenToIndex[token] || 0); | |
| }); | |
| // Define and train a simple TensorFlow model | |
| const model = tf.sequential(); | |
| model.add(tf.layers.dense({units: 128, activation: 'relu', inputShape: [data[0].length]})); | |
| model.add(tf.layers.dense({units: 1, activation: 'sigmoid'})); | |
| model.compile({optimizer: 'adam', loss: 'binaryCrossentropy'}); | |
| const inputs = tf.tensor2d(data); | |
| const labels = tf.tensor1d(new Array(data.length).fill(1)); // Dummy labels for training | |
| await model.fit(inputs, labels, { | |
| epochs: 10, | |
| callbacks: { | |
| onEpochEnd: (epoch, logs) => { | |
| outputElement.textContent += `Epoch ${epoch + 1}: loss = ${logs.loss}\n`; | |
| } | |
| } | |
| }); | |
| outputElement.textContent += 'Training complete!'; | |
| return model; | |
| } | |
| document.getElementById('trainModel').addEventListener('click', async () => { | |
| const files = document.getElementById('pdfFiles').files; | |
| if (files.length === 0) { | |
| alert('Please select PDF files to train the model.'); | |
| return; | |
| } | |
| outputElement.textContent = 'Training model...\n'; | |
| const model = await trainModelFromPDFs(files); | |
| // Save the model for later use | |
| await model.save('localstorage://pdf-trained-model'); | |
| outputElement.textContent += '\nModel saved locally!'; | |
| }); | |
| </script> | |
| </body> | |
| </html> | |