Spaces:

shukdevdatta123
/

openai-o4-mini-multi-modal-chat-app

Running

App Files Files Community

shukdevdatta123 commited on 12 days ago

Commit

037f856

verified ·

1 Parent(s): 2e98654

Add 3 files

Browse files

Files changed (3) hide show

README.md +5 -3
index.html +592 -19
prompts.txt +1 -0

README.md CHANGED Viewed

@@ -1,10 +1,12 @@
 ---
-title: Openai O4 Mini Multi Modal Chat App
-emoji: ⚡
 colorFrom: red
 colorTo: pink
 sdk: static
 pinned: false
 ---
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

 ---
+title: openai-o4-mini-multi-modal-chat-app
+emoji: 🐳
 colorFrom: red
 colorTo: pink
 sdk: static
 pinned: false
+tags:
+  - deepsite
 ---
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

index.html CHANGED Viewed

@@ -1,19 +1,592 @@
-<!doctype html>
-<html>
-	<head>
-		<meta charset="utf-8" />
-		<meta name="viewport" content="width=device-width" />
-		<title>My static Space</title>
-		<link rel="stylesheet" href="style.css" />
-	</head>
-	<body>
-		<div class="card">
-			<h1>Welcome to your static Space!</h1>
-			<p>You can modify this app directly by editing <i>index.html</i> in the Files and versions tab.</p>
-			<p>
-				Also don't forget to check the
-				<a href="https://huggingface.co/docs/hub/spaces" target="_blank">Spaces documentation</a>.
-			</p>
-		</div>
-	</body>
-</html>

+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <title>OpenAI O4 Analysis App</title>
+    <script src="https://cdn.tailwindcss.com"></script>
+    <link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/animate.css/4.1.1/animate.min.css"/>
+    <link href="https://fonts.googleapis.com/css2?family=Inter:wght@300;400;500;600;700&display=swap" rel="stylesheet">
+    <script src="https://cdn.jsdelivr.net/npm/axios/dist/axios.min.js"></script>
+    <style>
+        body {
+            font-family: 'Inter', sans-serif;
+            background: linear-gradient(135deg, #f5f7fa 0%, #c3cfe2 100%);
+            min-height: 100vh;
+        }
+        .tab-button {
+            transition: all 0.3s ease;
+        }
+        .tab-button.active {
+            transform: translateY(-2px);
+            box-shadow: 0 4px 6px -1px rgba(0, 0, 0, 0.1), 0 2px 4px -1px rgba(0, 0, 0, 0.06);
+        }
+        .result-box {
+            transition: all 0.3s ease;
+            min-height: 200px;
+        }
+        .loading-dots {
+            display: inline-block;
+        }
+        .loading-dots span {
+            display: inline-block;
+            width: 8px;
+            height: 8px;
+            border-radius: 50%;
+            background-color: #4f46e5;
+            margin: 0 2px;
+            animation: bounce 1.4s infinite ease-in-out both;
+        }
+        .loading-dots span:nth-child(1) {
+            animation-delay: -0.32s;
+        }
+        .loading-dots span:nth-child(2) {
+            animation-delay: -0.16s;
+        }
+        @keyframes bounce {
+            0%, 80%, 100% {
+                transform: scale(0);
+            } 40% {
+                transform: scale(1);
+            }
+        }
+        .file-input-label {
+            transition: all 0.3s ease;
+        }
+        .file-input-label:hover {
+            transform: translateY(-2px);
+            box-shadow: 0 4px 6px -1px rgba(79, 70, 229, 0.3), 0 2px 4px -1px rgba(79, 70, 229, 0.06);
+        }
+        .glow {
+            animation: glow 2s infinite alternate;
+        }
+        @keyframes glow {
+            from {
+                box-shadow: 0 0 5px rgba(79, 70, 229, 0.5);
+            }
+            to {
+                box-shadow: 0 0 20px rgba(79, 70, 229, 0.8);
+            }
+        }
+    </style>
+</head>
+<body class="py-8 px-4 sm:px-6 lg:px-8">
+    <div class="max-w-4xl mx-auto">
+        <!-- Header -->
+        <div class="text-center mb-10 animate__animated animate__fadeIn">
+            <h1 class="text-4xl font-bold text-indigo-600 mb-2">OpenAI O4 Mini Analysis</h1>
+            <p class="text-lg text-gray-600">Analyze PDFs and Images with AI-powered insights</p>
+        </div>
+        <!-- API Key Input -->
+        <div class="bg-white rounded-xl shadow-lg p-6 mb-8 animate__animated animate__fadeInUp">
+            <label for="api-key" class="block text-sm font-medium text-gray-700 mb-1">OpenAI API Key</label>
+            <div class="relative">
+                <input
+                    type="password"
+                    id="api-key"
+                    placeholder="Enter your OpenAI API key here..."
+                    class="w-full px-4 py-3 rounded-lg border border-gray-300 focus:ring-2 focus:ring-indigo-500 focus:border-indigo-500 transition duration-200"
+                >
+                <button
+                    onclick="toggleApiKeyVisibility()"
+                    class="absolute right-3 top-3 text-gray-500 hover:text-indigo-600 focus:outline-none"
+                >
+                    👁️
+                </button>
+            </div>
+            <p class="mt-2 text-sm text-gray-500">Your API key is only used for requests and is not stored.</p>
+        </div>
+        <!-- Tabs -->
+        <div class="flex space-x-2 mb-6 animate__animated animate__fadeIn">
+            <button
+                id="pdf-tab"
+                onclick="switchTab('pdf')"
+                class="tab-button active px-6 py-3 rounded-lg font-medium bg-indigo-600 text-white"
+            >
+                PDF Analysis
+            </button>
+            <button
+                id="image-tab"
+                onclick="switchTab('image')"
+                class="tab-button px-6 py-3 rounded-lg font-medium bg-gray-200 text-gray-700 hover:bg-gray-300"
+            >
+                Image Analysis
+            </button>
+        </div>
+        <!-- PDF Analysis Tab -->
+        <div id="pdf-content" class="animate__animated animate__fadeIn">
+            <div class="bg-white rounded-xl shadow-lg overflow-hidden">
+                <div class="p-6">
+                    <h2 class="text-2xl font-semibold text-gray-800 mb-4">Upload a PDF for Analysis</h2>
+                    <div class="mb-6">
+                        <label class="block text-sm font-medium text-gray-700 mb-2">Upload PDF</label>
+                        <label for="pdf-upload" class="file-input-label cursor-pointer flex flex-col items-center justify-center px-6 py-12 border-2 border-dashed border-gray-300 rounded-lg bg-gray-50 hover:bg-gray-100 transition duration-200">
+                            <svg xmlns="http://www.w3.org/2000/svg" class="h-12 w-12 text-gray-400 mb-2" fill="none" viewBox="0 0 24 24" stroke="currentColor">
+                                <path stroke-linecap="round" stroke-linejoin="round" stroke-width="2" d="M7 21h10a2 2 0 002-2V9.414a1 1 0 00-.293-.707l-5.414-5.414A1 1 0 0012.586 3H7a2 2 0 00-2 2v14a2 2 0 002 2z" />
+                            </svg>
+                            <span class="text-sm font-medium text-gray-600">Click to upload PDF</span>
+                            <span class="text-xs text-gray-500 mt-1">.pdf files only</span>
+                            <input id="pdf-upload" type="file" accept=".pdf" class="hidden">
+                        </label>
+                        <p id="pdf-filename" class="mt-2 text-sm text-gray-500 hidden">Selected file: <span class="font-medium"></span></p>
+                    </div>
+                    <div class="mb-6">
+                        <label for="pdf-prompt" class="block text-sm font-medium text-gray-700 mb-2">Prompt</label>
+                        <textarea
+                            id="pdf-prompt"
+                            rows="3"
+                            class="w-full px-4 py-3 rounded-lg border border-gray-300 focus:ring-2 focus:ring-indigo-500 focus:border-indigo-500 transition duration-200"
+                            placeholder="Enter your question about the PDF..."
+                        >What is this PDF about?</textarea>
+                    </div>
+                    <div class="mb-6">
+                        <label class="block text-sm font-medium text-gray-700 mb-2">Reasoning Effort</label>
+                        <div class="flex space-x-4">
+                            <label class="inline-flex items-center">
+                                <input type="radio" name="pdf-effort" value="low" class="h-4 w-4 text-indigo-600 focus:ring-indigo-500">
+                                <span class="ml-2 text-gray-700">Low</span>
+                            </label>
+                            <label class="inline-flex items-center">
+                                <input type="radio" name="pdf-effort" value="medium" checked class="h-4 w-4 text-indigo-600 focus:ring-indigo-500">
+                                <span class="ml-2 text-gray-700">Medium</span>
+                            </label>
+                            <label class="inline-flex items-center">
+                                <input type="radio" name="pdf-effort" value="high" class="h-4 w-4 text-indigo-600 focus:ring-indigo-500">
+                                <span class="ml-2 text-gray-700">High</span>
+                            </label>
+                        </div>
+                    </div>
+                    <button
+                        id="analyze-pdf-btn"
+                        onclick="analyzePDF()"
+                        class="w-full py-3 px-6 bg-indigo-600 hover:bg-indigo-700 text-white font-medium rounded-lg transition duration-200 transform hover:scale-105 focus:outline-none focus:ring-2 focus:ring-indigo-500 focus:ring-offset-2"
+                    >
+                        Analyze PDF
+                    </button>
+                </div>
+                <div id="pdf-result" class="result-box border-t border-gray-200 p-6 bg-gray-50 hidden">
+                    <h3 class="text-lg font-medium text-gray-800 mb-3">Analysis Result</h3>
+                    <div id="pdf-result-content" class="min-h-40 p-4 bg-white rounded-lg border border-gray-200"></div>
+                </div>
+            </div>
+        </div>
+        <!-- Image Analysis Tab -->
+        <div id="image-content" class="hidden animate__animated animate__fadeIn">
+            <div class="bg-white rounded-xl shadow-lg overflow-hidden">
+                <div class="p-6">
+                    <h2 class="text-2xl font-semibold text-gray-800 mb-4">Upload an Image for Analysis</h2>
+                    <div class="grid grid-cols-1 md:grid-cols-2 gap-6 mb-6">
+                        <div>
+                            <label class="block text-sm font-medium text-gray-700 mb-2">Upload Image</label>
+                            <label for="image-upload" class="file-input-label cursor-pointer flex flex-col items-center justify-center px-6 py-12 border-2 border-dashed border-gray-300 rounded-lg bg-gray-50 hover:bg-gray-100 transition duration-200">
+                                <svg xmlns="http://www.w3.org/2000/svg" class="h-12 w-12 text-gray-400 mb-2" fill="none" viewBox="0 0 24 24" stroke="currentColor">
+                                    <path stroke-linecap="round" stroke-linejoin="round" stroke-width="2" d="M4 16l4.586-4.586a2 2 0 012.828 0L16 16m-2-2l1.586-1.586a2 2 0 012.828 0L20 14m-6-6h.01M6 20h12a2 2 0 002-2V6a2 2 0 00-2-2H6a2 2 0 00-2 2v12a2 2 0 002 2z" />
+                                </svg>
+                                <span class="text-sm font-medium text-gray-600">Click to upload image</span>
+                                <span class="text-xs text-gray-500 mt-1">.jpg, .png, etc.</span>
+                                <input id="image-upload" type="file" accept="image/*" class="hidden">
+                            </label>
+                            <p id="image-filename" class="mt-2 text-sm text-gray-500 hidden">Selected file: <span class="font-medium"></span></p>
+                            <div class="mt-4">
+                                <label for="image-url" class="block text-sm font-medium text-gray-700 mb-2">Or enter image URL</label>
+                                <input
+                                    type="text"
+                                    id="image-url"
+                                    placeholder="https://example.com/image.jpg"
+                                    class="w-full px-4 py-3 rounded-lg border border-gray-300 focus:ring-2 focus:ring-indigo-500 focus:border-indigo-500 transition duration-200"
+                                >
+                            </div>
+                        </div>
+                        <div>
+                            <div class="mb-6">
+                                <label for="image-prompt" class="block text-sm font-medium text-gray-700 mb-2">Prompt</label>
+                                <textarea
+                                    id="image-prompt"
+                                    rows="3"
+                                    class="w-full px-4 py-3 rounded-lg border border-gray-300 focus:ring-2 focus:ring-indigo-500 focus:border-indigo-500 transition duration-200"
+                                    placeholder="Enter your question about the image..."
+                                >What is this image about?</textarea>
+                            </div>
+                            <div class="mb-6">
+                                <label class="block text-sm font-medium text-gray-700 mb-2">Reasoning Effort</label>
+                                <div class="flex space-x-4">
+                                    <label class="inline-flex items-center">
+                                        <input type="radio" name="image-effort" value="low" class="h-4 w-4 text-indigo-600 focus:ring-indigo-500">
+                                        <span class="ml-2 text-gray-700">Low</span>
+                                    </label>
+                                    <label class="inline-flex items-center">
+                                        <input type="radio" name="image-effort" value="medium" checked class="h-4 w-4 text-indigo-600 focus:ring-indigo-500">
+                                        <span class="ml-2 text-gray-700">Medium</span>
+                                    </label>
+                                    <label class="inline-flex items-center">
+                                        <input type="radio" name="image-effort" value="high" class="h-4 w-4 text-indigo-600 focus:ring-indigo-500">
+                                        <span class="ml-2 text-gray-700">High</span>
+                                    </label>
+                                </div>
+                            </div>
+                        </div>
+                    </div>
+                    <button
+                        id="analyze-image-btn"
+                        onclick="analyzeImage()"
+                        class="w-full py-3 px-6 bg-indigo-600 hover:bg-indigo-700 text-white font-medium rounded-lg transition duration-200 transform hover:scale-105 focus:outline-none focus:ring-2 focus:ring-indigo-500 focus:ring-offset-2"
+                    >
+                        Analyze Image
+                    </button>
+                </div>
+                <div id="image-result" class="result-box border-t border-gray-200 p-6 bg-gray-50 hidden">
+                    <h3 class="text-lg font-medium text-gray-800 mb-3">Analysis Result</h3>
+                    <div id="image-result-content" class="min-h-40 p-4 bg-white rounded-lg border border-gray-200"></div>
+                </div>
+            </div>
+        </div>
+        <!-- Footer -->
+        <div class="mt-12 text-center text-gray-500 text-sm animate__animated animate__fadeIn">
+            <p>OpenAI O4 Mini Analysis Application</p>
+        </div>
+    </div>
+    <script>
+        // Toggle API key visibility
+        function toggleApiKeyVisibility() {
+            const apiKeyInput = document.getElementById('api-key');
+            if (apiKeyInput.type === 'password') {
+                apiKeyInput.type = 'text';
+            } else {
+                apiKeyInput.type = 'password';
+            }
+        }
+        // Switch between tabs
+        function switchTab(tab) {
+            const pdfTab = document.getElementById('pdf-tab');
+            const imageTab = document.getElementById('image-tab');
+            const pdfContent = document.getElementById('pdf-content');
+            const imageContent = document.getElementById('image-content');
+            if (tab === 'pdf') {
+                pdfTab.classList.remove('bg-gray-200', 'text-gray-700');
+                pdfTab.classList.add('bg-indigo-600', 'text-white');
+                imageTab.classList.remove('bg-indigo-600', 'text-white');
+                imageTab.classList.add('bg-gray-200', 'text-gray-700');
+                pdfContent.classList.remove('hidden');
+                imageContent.classList.add('hidden');
+                // Add animation
+                pdfContent.classList.remove('animate__fadeIn');
+                void pdfContent.offsetWidth; // Trigger reflow
+                pdfContent.classList.add('animate__fadeIn');
+            } else {
+                imageTab.classList.remove('bg-gray-200', 'text-gray-700');
+                imageTab.classList.add('bg-indigo-600', 'text-white');
+                pdfTab.classList.remove('bg-indigo-600', 'text-white');
+                pdfTab.classList.add('bg-gray-200', 'text-gray-700');
+                imageContent.classList.remove('hidden');
+                pdfContent.classList.add('hidden');
+                // Add animation
+                imageContent.classList.remove('animate__fadeIn');
+                void imageContent.offsetWidth; // Trigger reflow
+                imageContent.classList.add('animate__fadeIn');
+            }
+        }
+        // Handle file upload display
+        document.getElementById('pdf-upload').addEventListener('change', function(e) {
+            const filenameDisplay = document.getElementById('pdf-filename');
+            if (this.files.length > 0) {
+                filenameDisplay.classList.remove('hidden');
+                filenameDisplay.querySelector('span').textContent = this.files[0].name;
+            } else {
+                filenameDisplay.classList.add('hidden');
+            }
+        });
+        document.getElementById('image-upload').addEventListener('change', function(e) {
+            const filenameDisplay = document.getElementById('image-filename');
+            if (this.files.length > 0) {
+                filenameDisplay.classList.remove('hidden');
+                filenameDisplay.querySelector('span').textContent = this.files[0].name;
+            } else {
+                filenameDisplay.classList.add('hidden');
+            }
+        });
+        // Show loading state
+        function showLoading(element) {
+            element.innerHTML = '<div class="loading-dots"><span></span><span></span><span></span></div>';
+        }
+        // Analyze PDF function
+        async function analyzePDF() {
+            const apiKey = document.getElementById('api-key').value;
+            const pdfFile = document.getElementById('pdf-upload').files[0];
+            const prompt = document.getElementById('pdf-prompt').value;
+            const effortLevel = document.querySelector('input[name="pdf-effort"]:checked').value;
+            const resultContent = document.getElementById('pdf-result-content');
+            const resultBox = document.getElementById('pdf-result');
+            if (!apiKey) {
+                alert('Please provide an OpenAI API key.');
+                return;
+            }
+            if (!pdfFile) {
+                alert('Please upload a PDF file.');
+                return;
+            }
+            // Show loading state
+            resultBox.classList.remove('hidden');
+            showLoading(resultContent);
+            try {
+                // Read the PDF file and convert to base64
+                const pdfBase64 = await new Promise((resolve, reject) => {
+                    const reader = new FileReader();
+                    reader.onload = () => {
+                        const arrayBuffer = reader.result;
+                        const bytes = new Uint8Array(arrayBuffer);
+                        let binary = '';
+                        for (let i = 0; i < bytes.byteLength; i++) {
+                            binary += String.fromCharCode(bytes[i]);
+                        }
+                        const base64 = btoa(binary);
+                        resolve(base64);
+                    };
+                    reader.onerror = reject;
+                    reader.readAsArrayBuffer(pdfFile);
+                });
+                // Create the request payload
+                const payload = {
+                    model: "o4-mini",
+                    input: [
+                        {
+                            role: "user",
+                            content: [
+                                {
+                                    type: "input_text",
+                                    text: prompt
+                                },
+                                {
+                                    type: "input_file",
+                                    filename: pdfFile.name,
+                                    file_data: `data:application/pdf;base64,${pdfBase64}`
+                                }
+                            ]
+                        }
+                    ],
+                    text: {
+                        format: {
+                            type: "text"
+                        }
+                    },
+                    reasoning: {
+                        effort: effortLevel
+                    },
+                    tools: [],
+                    store: true
+                };
+                // Make the API request
+                const response = await axios.post('https://api.openai.com/v1/responses', payload, {
+                    headers: {
+                        'Authorization': `Bearer ${apiKey}`,
+                        'Content-Type': 'application/json'
+                    }
+                });
+                // Process the response
+                const result = extractTextFromResponse(response.data);
+                resultContent.innerHTML = `<div class="text-gray-700 whitespace-pre-wrap">${result}</div>`;
+            } catch (error) {
+                console.error('Error:', error);
+                let errorMessage = 'An error occurred while analyzing the PDF.';
+                if (error.response) {
+                    errorMessage = `Error: ${error.response.data.error?.message || error.response.statusText}`;
+                } else if (error.message) {
+                    errorMessage = `Error: ${error.message}`;
+                }
+                resultContent.innerHTML = `<div class="text-red-600">${errorMessage}</div>`;
+            }
+        }
+        // Analyze Image function
+        async function analyzeImage() {
+            const apiKey = document.getElementById('api-key').value;
+            const imageFile = document.getElementById('image-upload').files[0];
+            const imageUrl = document.getElementById('image-url').value;
+            const prompt = document.getElementById('image-prompt').value;
+            const effortLevel = document.querySelector('input[name="image-effort"]:checked').value;
+            const resultContent = document.getElementById('image-result-content');
+            const resultBox = document.getElementById('image-result');
+            if (!apiKey) {
+                alert('Please provide an OpenAI API key.');
+                return;
+            }
+            if (!imageFile && !imageUrl) {
+                alert('Please upload an image or provide an image URL.');
+                return;
+            }
+            if (!prompt) {
+                alert('Please provide a prompt for the image analysis.');
+                return;
+            }
+            // Show loading state
+            resultBox.classList.remove('hidden');
+            showLoading(resultContent);
+            try {
+                const content = [
+                    {
+                        type: "input_text",
+                        text: prompt
+                    }
+                ];
+                if (imageFile) {
+                    // Read the image file and convert to base64
+                    const imageBase64 = await new Promise((resolve, reject) => {
+                        const reader = new FileReader();
+                        reader.onload = () => {
+                            const base64 = reader.result.split(',')[1];
+                            resolve(base64);
+                        };
+                        reader.onerror = reject;
+                        reader.readAsDataURL(imageFile);
+                    });
+                    content.unshift({
+                        type: "input_image",
+                        image_url: `data:image/png;base64,${imageBase64}`
+                    });
+                } else if (imageUrl) {
+                    content.unshift({
+                        type: "input_image",
+                        image_url: imageUrl
+                    });
+                }
+                // Create the request payload
+                const payload = {
+                    model: "o4-mini",
+                    input: [
+                        {
+                            role: "user",
+                            content: content
+                        }
+                    ],
+                    text: {
+                        format: {
+                            type: "text"
+                        }
+                    },
+                    reasoning: {
+                        effort: effortLevel
+                    },
+                    tools: [],
+                    store: true
+                };
+                // Make the API request
+                const response = await axios.post('https://api.openai.com/v1/responses', payload, {
+                    headers: {
+                        'Authorization': `Bearer ${apiKey}`,
+                        'Content-Type': 'application/json'
+                    }
+                });
+                // Process the response
+                const result = extractTextFromResponse(response.data);
+                resultContent.innerHTML = `<div class="text-gray-700 whitespace-pre-wrap">${result}</div>`;
+            } catch (error) {
+                console.error('Error:', error);
+                let errorMessage = 'An error occurred while analyzing the image.';
+                if (error.response) {
+                    errorMessage = `Error: ${error.response.data.error?.message || error.response.statusText}`;
+                } else if (error.message) {
+                    errorMessage = `Error: ${error.message}`;
+                }
+                resultContent.innerHTML = `<div class="text-red-600">${errorMessage}</div>`;
+            }
+        }
+        // Extract text from response
+        function extractTextFromResponse(response) {
+            try {
+                // First check if response has an output attribute
+                if (response.output) {
+                    const output = response.output;
+                    // Look for message items in the output list
+                    for (const item of output) {
+                        if (item.role === 'assistant') {
+                            for (const contentItem of item.content) {
+                                if (contentItem.type === 'output_text') {
+                                    return contentItem.text;
+                                }
+                            }
+                        }
+                    }
+                    // If we couldn't find it in the expected structure, return an error
+                    return `Couldn't extract text from response: ${JSON.stringify(response)}`;
+                }
+                return `Unexpected response structure: ${JSON.stringify(response)}`;
+            } catch (error) {
+                return `Error processing response: ${error.message}`;
+            }
+        }
+        // Add glow effect to buttons on hover
+        document.querySelectorAll('button').forEach(button => {
+            if (button.id !== 'api-key-toggle') {
+                button.addEventListener('mouseenter', () => {
+                    button.classList.add('glow');
+                });
+                button.addEventListener('mouseleave', () => {
+                    button.classList.remove('glow');
+                });
+            }
+        });
+    </script>
+<p style="border-radius: 8px; text-align: center; font-size: 12px; color: #fff; margin-top: 16px;position: fixed; left: 8px; bottom: 8px; z-index: 10; background: rgba(0, 0, 0, 0.8); padding: 4px 8px;">Made with <img src="https://enzostvs-deepsite.hf.space/logo.svg" alt="DeepSite Logo" style="width: 16px; height: 16px; vertical-align: middle;display:inline-block;margin-right:3px;filter:brightness(0) invert(1);"><a href="https://enzostvs-deepsite.hf.space" style="color: #fff;text-decoration: underline;" target="_blank" >DeepSite</a> - 🧬 <a href="https://enzostvs-deepsite.hf.space?remix=shukdevdatta123/openai-o4-mini-multi-modal-chat-app" style="color: #fff;text-decoration: underline;" target="_blank" >Remix</a></p></body>
+</html>

prompts.txt ADDED Viewed

	@@ -0,0 +1 @@

+ import gradio as gr import base64 import os from openai import OpenAI import tempfile def extract_text_from_response(response): """Extract text from OpenAI API response based on the actual structure""" try: # First check if response has an output attribute if hasattr(response, 'output'): output = response.output # Look for message items in the output list for item in output: if hasattr(item, 'role') and item.role == 'assistant': for content_item in item.content: if hasattr(content_item, 'type') and content_item.type == 'output_text': return content_item.text # If we couldn't find it in the expected structure, return an error return f"Couldn't extract text from response: {str(response)}" except Exception as e: return f"Error processing response: {str(e)}" def analyze_pdf(api_key, pdf_file, prompt, effort_level): """Analyze a PDF file using OpenAI API""" if not api_key: return "Please provide an OpenAI API key." if pdf_file is None: return "Please upload a PDF file." # Initialize OpenAI client with the provided API key client = OpenAI(api_key=api_key) # Read the PDF file and encode it in base64 with open(pdf_file.name, "rb") as file: pdf_bytes = file.read() pdf_base64 = base64.b64encode(pdf_bytes).decode("utf-8") try: # Create the request response = client.responses.create( model="o4-mini", input=[ { "role": "user", "content": [ { "type": "input_text", "text": prompt }, { "type": "input_file", "filename": os.path.basename(pdf_file.name), "file_data": f"data:application/pdf;base64,{pdf_base64}" } ] } ], text={ "format": { "type": "text" } }, reasoning={ "effort": effort_level }, tools=[], store=True ) return extract_text_from_response(response) except Exception as e: return f"Error: {str(e)}" def analyze_image(api_key, image, image_url, prompt, effort_level): """Analyze an image using OpenAI API""" if not api_key: return "Please provide an OpenAI API key." if image is None and not image_url: return "Please upload an image or provide an image URL." if not prompt: return "Please provide a prompt for the image analysis." # Initialize OpenAI client with the provided API key client = OpenAI(api_key=api_key) content = [] # Add text prompt content.append({ "type": "input_text", "text": prompt }) # Add image - either from uploaded file or URL try: if image is not None: # Convert image to base64 with open(image, "rb") as img_file: img_bytes = img_file.read() img_base64 = base64.b64encode(img_bytes).decode("utf-8") content.insert(0, { "type": "input_image", "image_url": f"data:image/png;base64,{img_base64}" }) elif image_url: content.insert(0, { "type": "input_image", "image_url": image_url }) # Create the request response = client.responses.create( model="o4-mini", input=[ { "role": "user", "content": content } ], text={ "format": { "type": "text" } }, reasoning={ "effort": effort_level }, tools=[], store=True ) return extract_text_from_response(response) except Exception as e: return f"Error: {str(e)}" # Create Gradio interface with gr.Blocks(title="OpenAI O4 Analysis App") as app: gr.Markdown("# OpenAI O4 Mini Analysis Application") # API Key input (used across both tabs) api_key_input = gr.Textbox( label="OpenAI API Key", placeholder="Enter your OpenAI API key here...", type="password" ) with gr.Tab("PDF Analysis"): gr.Markdown("## Upload a PDF file for analysis") with gr.Row(): pdf_input = gr.File(label="Upload PDF", file_types=[".pdf"]) pdf_prompt = gr.Textbox( label="Prompt", placeholder="Enter your question about the PDF...", value="What is this PDF about?" ) pdf_effort = gr.Radio( ["low", "medium", "high"], label="Reasoning Effort", value="medium" ) pdf_button = gr.Button("Analyze PDF") pdf_output = gr.Textbox(label="Analysis Result", lines=10) pdf_button.click( analyze_pdf, inputs=[api_key_input, pdf_input, pdf_prompt, pdf_effort], outputs=pdf_output ) with gr.Tab("Image Analysis"): gr.Markdown("## Upload an image or provide an image URL for analysis") with gr.Row(): with gr.Column(): img_input = gr.Image(label="Upload Image", type="filepath") img_url = gr.Textbox( label="Or enter image URL", placeholder="https://example.com/image.jpg" ) img_prompt = gr.Textbox( label="Prompt", placeholder="Enter your question about the image...", value="What is this image about?" ) img_effort = gr.Radio( ["low", "medium", "high"], label="Reasoning Effort", value="medium" ) img_output = gr.Textbox(label="Analysis Result", lines=10) img_button = gr.Button("Analyze Image") img_button.click( analyze_image, inputs=[api_key_input, img_input, img_url, img_prompt, img_effort], outputs=img_output ) gr.Markdown(""" ### Note: - Your OpenAI API key is required to use this application - The API key is only used for requests and is not stored """) # Launch the app if __name__ == "__main__": app.launch() (please convert this code to a very very awesome looking website with amazing animations... make sure the website works exactly in the same way the above project code works)