acadmic texts

Dockerfile

@@ -36,6 +36,7 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
     pandoc texlive-xetex \
     texlive-latex-recommended \
     texlive-fonts-recommended \
+    unpaper \
     calibre \
     ffmpeg \
     libvips-tools \

run.sh

@@ -9,11 +9,11 @@ SECRET_KEY=
 UPLOADS_DIR=./uploads
 PROCESSED_DIR=./processed
 # Start Gunicorn in the background
-gunicorn -w 4 --threads 2 -k uvicorn.workers.UvicornWorker --forwarded-allow-ips='*' --error-logfile - --access-logfile - main:app -b 0.0.0.0:8000 &
+gunicorn -w 4 --threads 2 -k uvicorn.workers.UvicornWorker --forwarded-allow-ips='*' --error-logfile - --access-logfile - main:app -b 0.0.0.0:8008 &
 echo "Started Gunicorn..."
 # Store the Gunicorn process ID
 GUNICORN_PID=$!
 echo "Gunicorn PID: $GUNICORN_PID"
 # Start the Huey consumer in the foreground
 exec huey_consumer.py main.huey -w 4
-echo "Started Huey consumer..."
+echo "Started Huey consumer..."

settings.default.yml

@@ -6,11 +6,11 @@ auth_settings:
   oidc_end_session_endpoint: https://accounts.example.com/oidc/session/end
   admin_users:
   - user@example.com
-web_hook_settings:
+webhook_settings:
   enabled: False
-  allow_chunked_api_uploads": False
+  allow_chunked_api_uploads: False
-  allowed_callback_urls:
+  allowed_callback_urls: []
-  callback_bearer_token":
+  callback_bearer_token:
 tts_settings: 
   piper: 
     model_dir: "./models/tts"
@@ -99,6 +99,13 @@ ocr_settings:
     clean: true
     optimize: 1
     force_ocr: true
+academic_settings:
+  pandoc:
+    csl_files:
+      apa: https://www.zotero.org/styles/apa
+      mla: https://www.zotero.org/styles/modern-language-association
+      chicago: https://www.zotero.org/styles/chicago-author-date
+      chicago-fullnote: https://www.zotero.org/styles/chicago-fullnote-bibliography
 transcription_settings:
   whisper:
     compute_type: int8
@@ -371,3 +378,12 @@ conversion_tools:
       jpg_q85: JPEG (High Quality)
       jpg_q75: JPEG (Web Quality)
       jpg_q60: JPEG (Aggressive Compression)
+  pandoc_academic:
+    name: Pandoc (Academic Document)
+    command_template: "pandoc {main_document} -o {output} --bibliography {bib_file} --citeproc --csl {csl_style}"
+    timeout: 300
+    formats:
+      pdf_apa: "PDF with Bibliography (APA Style)"
+      pdf_mla: "PDF with Bibliography (MLA Style)"
+      pdf_chicago: "PDF with Bibliography (Chicago Style)"
+      pdf_chicago_fullnote: "PDF with Bibliography (Chicago Full Note)"

static/css/settings.css

@@ -9,13 +9,8 @@
     border-bottom: 1px solid var(--divider-color);
 }
 
-.settings-header h1 {e
+.settings-header h1 {
-    margin: 0 0 0.25rem 0;
-}
-
-.settings-header p {
     margin: 0;
-    color: var(--muted-text);
 }
 
 .back-button {
@@ -32,11 +27,18 @@
     background-color: var(--primary-hover);
 }
 
+/* Main layout grid for settings */
+.settings-main-grid {
+    display: grid;
+    grid-template-columns: repeat(auto-fit, minmax(400px, 1fr));
+    gap: 2rem;
+}
+
 .settings-group {
     border: 1px solid var(--border-color);
     border-radius: 8px;
     padding: 1.5rem;
-    margin-bottom: 2rem;
+    margin-bottom: 2rem; /* Kept for spacing when grid stacks */
 }
 
 .settings-group legend {
@@ -70,36 +72,39 @@
 .form-textarea {
     resize: vertical;
     min-height: 60px;
-    font-family: 'Courier New', Courier, monospace;
+    /* Use a more standard monospace font stack */
+    font-family: Consolas, 'Courier New', Courier, monospace;
 }
 
 .field-description {
-    font-size: 0.85rem;
+    font-size: 0.9rem;
     color: var(--muted-text);
-    margin-top: -0.5rem;
+    margin-top: 0.25rem;
-    margin-bottom: 1rem;
+    margin-bottom: 0.75rem;
+    line-height: 1.4;
 }
 .field-description code {
     background-color: rgba(255,255,255,0.1);
     padding: 0.1rem 0.3rem;
     border-radius: 3px;
-    font-size: 0.8rem;
+    font-size: 0.85rem;
 }
 
 .checkbox-group {
     display: flex;
     align-items: center;
     gap: 0.75rem;
-    margin-bottom: 0.5rem;
+    margin-bottom: 0.75rem;
 }
 .checkbox-group input[type="checkbox"] {
-    width: 1rem;
+    width: 1.1rem;
-    height: 1rem;
+    height: 1.1rem;
+    accent-color: var(--primary-color);
 }
 
 .tool-grid {
     display: grid;
-    grid-template-columns: repeat(auto-fit, minmax(350px, 1fr));
+    grid-template-columns: 1fr; /* Simplified to single column within a settings group */
     gap: 1rem;
 }
 
@@ -121,22 +126,23 @@
     gap: 1rem;
     margin-top: 1.5rem;
 }
+
 .button-primary {
     display: inline-block;
     background: var(--primary-color);
-    background-color: transparent;
+    color: var(--bg-color);
-    border-color: var(--border-color);
+    border: 1px solid var(--primary-color);
-    border-width: 1px;
-    color: #ffffff;
     padding: 0.65rem 1.5rem;
     font-size: 1rem;
     font-weight: 600;
     border-radius: 5px;
     cursor: pointer;
-    transition: background-color 0.15s ease;
+    transition: all 0.15s ease;
 }
 .button-primary:hover {
     background: var(--primary-hover);
+    color: var(--text-color);
+    border-color: var(--primary-hover);
 }
 
 .save-status {
@@ -191,4 +197,16 @@
 }
 .button-danger:hover {
     background-color: #ff8f8f;
-}
+}
+
+/* Responsive adjustments */
+@media (max-width: 768px) {
+    .danger-action {
+        flex-direction: column;
+        align-items: flex-start;
+    }
+    .button-danger {
+        width: 100%;
+        text-align: center;
+    }
+}

static/css/style.css

@@ -18,7 +18,7 @@
     --border-color: rgba(255, 255, 255, 0.1);
     --divider-color: rgba(255, 255, 255, 0.06);
 
-    --font-family: 'Inter', -apple-system, BlinkMacSystemFont, "Segoe UI", Roboto, "Helvetica Neue", Arial, sans-serif;
+    --font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", Roboto, "Helvetica Neue", Arial, sans-serif;
 }
 
 /* Page */

static/js/settings.js

@@ -5,47 +5,51 @@ document.addEventListener('DOMContentLoaded', () => {
     const clearHistoryBtn = document.getElementById('clear-history-btn');
     const deleteFilesBtn = document.getElementById('delete-files-btn');
 
-    // --- Save Settings ---
+    // --- Save Settings --- 
     settingsForm.addEventListener('submit', async (event) => {
         event.preventDefault();
         saveStatus.textContent = 'Saving...';
         saveStatus.classList.remove('success', 'error');
 
-        const formData = new FormData(settingsForm);
         const settingsObject = {};
+        const elements = Array.from(settingsForm.elements);
 
-        // Convert FormData to a nested object
+        for (const el of elements) {
-        formData.forEach((value, key) => {
+            if (!el.name || el.type === 'submit') continue; // Skip elements without a name and submit buttons
-            // Handle checkboxes that might not be submitted if unchecked
+
-            if (key.includes('ocr_settings')) {
+            let value;
-                 const checkbox = document.querySelector(`[name="${key}"]`);
+            const keys = el.name.split('.');
-                 if (checkbox && checkbox.type === 'checkbox') {
+
-                    value = checkbox.checked;
+            // Determine value based on element type
-                 }
+            if (el.type === 'checkbox') {
+                value = el.checked;
+            } else if (el.tagName === 'TEXTAREA') {
+                // Convert comma-separated text into an array of strings
+                value = el.value.split(',')
+                    .map(item => item.trim())
+                    .filter(item => item); // Remove empty strings from the list
+            } else if (el.type === 'number') {
+                value = parseFloat(el.value);
+                if (isNaN(value)) {
+                    value = null; // Represent empty number fields as null
+                }
+            } else {
+                value = el.value;
             }
 
-            const keys = key.split('.');
+            // Build nested object from dot-notation name
             let current = settingsObject;
             keys.forEach((k, index) => {
                 if (index === keys.length - 1) {
                     current[k] = value;
                 } else {
-                    current[k] = current[k] || {};
+                    if (!current[k]) {
+                        current[k] = {};
+                    }
                     current = current[k];
                 }
             });
-        });
+        }
-        
-        // Ensure unchecked OCR boxes are sent as false
-        const ocrCheckboxes = settingsForm.querySelectorAll('input[type="checkbox"][name^="ocr_settings"]');
-        ocrCheckboxes.forEach(cb => {
-            const keys = cb.name.split('.');
-            if (!formData.has(cb.name)) {
-                 // this is a bit of a hack but gets the job done for this specific form
-                 settingsObject[keys[0]][keys[1]][keys[2]] = false;
-            }
-        });
-
 
         try {
             const response = await fetch('/settings/save', {
@@ -74,7 +78,7 @@ document.addEventListener('DOMContentLoaded', () => {
         }
     });
 
-    // --- Clear History ---
+    // --- Clear History --- 
     clearHistoryBtn.addEventListener('click', async () => {
         if (!confirm('ARE YOU SURE?\n\nThis will permanently delete all job history records from the database.')) {
             return;
@@ -90,7 +94,7 @@ document.addEventListener('DOMContentLoaded', () => {
         }
     });
 
-    // --- Delete Files ---
+    // --- Delete Files --- 
     deleteFilesBtn.addEventListener('click', async () => {
         if (!confirm('ARE YOU SURE?\n\nThis will permanently delete all files in the "processed" folder.')) {
             return;
@@ -105,4 +109,4 @@ document.addEventListener('DOMContentLoaded', () => {
             console.error(error);
         }
     });
-});
+});

templates/settings.html

@@ -6,9 +6,7 @@
     <title>Settings - File Wizard</title>
     <link rel="stylesheet" href="{{ url_for('static', path='/css/style.css') }}">
     <link rel="stylesheet" href="{{ url_for('static', path='/css/settings.css') }}">
-    <link rel="preconnect" href="https://fonts.googleapis.com">
+
-    <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
-    <link href="https://fonts.googleapis.com/css2?family=Inter:wght@400;500;700&display=swap" rel="stylesheet">
 </head>
 <body>
     <div class="container">
@@ -21,14 +19,44 @@
 
         <main>
             <form id="settings-form">
-                
+                <div class="settings-main-grid">
-                <fieldset class="settings-group">
+                    <fieldset class="settings-group">
-                    <legend><h2>General Settings</h2></legend>
+                        <legend><h2>General Settings</h2></legend>
-                    <div class="form-control">
+                        <div class="form-control">
-                        <label for="app-max-file-size">Max Upload Size (MB)</label>
+                            <label for="app-public-url">App Public URL</label>
-                        <input type="number" id="app-max-file-size" name="app_settings.max_file_size_mb" value="{{ config.app_settings.max_file_size_mb }}" class="form-input">
+                            <p class="field-description">The public-facing base URL of the application (e.g., https://files.example.com). Used for generating absolute URLs in webhooks.</p>
-                    </div>
+                            <input type="text" id="app-public-url" name="app_settings.app_public_url" value="{{ config.app_settings.get('app_public_url', '') }}" class="form-input" placeholder="https://... ">
-                </fieldset>
+                        </div>
+                        <div class="form-control">
+                            <label for="app-max-file-size">Max Upload Size (MB)</label>
+                            <input type="number" id="app-max-file-size" name="app_settings.max_file_size_mb" value="{{ config.app_settings.max_file_size_mb }}" class="form-input">
+                        </div>
+                        <div class="form-control">
+                            <label for="app-allowed-extensions">Allowed File Extensions for Conversion</label>
+                            <p class="field-description">A comma-separated list of file extensions (e.g., .pdf, .docx, .png). If empty, all files are allowed.</p>
+                            <textarea id="app-allowed-extensions" name="app_settings.allowed_all_extensions" class="form-textarea" rows="2">{{ config.app_settings.get('allowed_all_extensions', []) | join(', ') }}</textarea>
+                        </div>
+                    </fieldset>
+
+                    <fieldset class="settings-group">
+                        <legend><h2>Performance Tuning</h2></legend>
+                         <div class="form-control">
+                            <label for="perf-model-concurrency">Model Concurrency Limit</label>
+                            <p class="field-description">Maximum number of AI models (e.g., Piper TTS) that can run in parallel. Helps prevent CPU/GPU overload.</p>
+                            <input type="number" id="perf-model-concurrency" name="app_settings.model_concurrency" value="{{ config.app_settings.get('model_concurrency', 1) }}" class="form-input">
+                        </div>
+                         <div class="form-control">
+                            <label for="perf-model-timeout">Model Inactivity Timeout (seconds)</label>
+                            <p class="field-description">Time in seconds before an unused Whisper model is unloaded from memory.</p>
+                            <input type="number" id="perf-model-timeout" name="app_settings.model_inactivity_timeout" value="{{ config.app_settings.get('model_inactivity_timeout', 1800) }}" class="form-input">
+                        </div>
+                         <div class="form-control">
+                            <label for="perf-cache-interval">Cache Check Interval (seconds)</label>
+                            <p class="field-description">How often to check for inactive models to unload.</p>
+                            <input type="number" id="perf-cache-interval" name="app_settings.cache_check_interval" value="{{ config.app_settings.get('cache_check_interval', 300) }}" class="form-input">
+                        </div>
+                    </fieldset>
+                </div>
                 
                 <fieldset class="settings-group">
                     <legend><h2>OCR (ocrmypdf)</h2></legend>
@@ -48,6 +76,7 @@
 
                 <fieldset class="settings-group">
                     <legend><h2>Transcription (Whisper)</h2></legend>
+                    <p class="field-description">Device settings (CPU/GPU) are configured via environment variables (see documentation).</p>
                     <div class="form-control">
                         <label for="whisper-compute-type">Compute Type</label>
                         <select id="whisper-compute-type" name="transcription_settings.whisper.compute_type" class="form-select">
@@ -58,6 +87,71 @@
                     </div>
                 </fieldset>
 
+                <fieldset class="settings-group">
+                    <legend><h2>Authentication (OIDC)</h2></legend>
+                    <p class="field-description">Used for logging in users. Requires `LOCAL_ONLY=False` environment variable.</p>
+                    <div class="form-control">
+                        <label for="auth-client-id">Client ID</label>
+                        <input type="text" id="auth-client-id" name="auth_settings.oidc_client_id" value="{{ config.auth_settings.get('oidc_client_id', '') }}" class="form-input">
+                    </div>
+                    <div class="form-control">
+                        <label for="auth-client-secret">Client Secret</label>
+                        <input type="password" id="auth-client-secret" name="auth_settings.oidc_client_secret" value="{{ config.auth_settings.get('oidc_client_secret', '') }}" class="form-input">
+                    </div>
+                    <div class="form-control">
+                        <label for="auth-metadata-url">Server Metadata URL</label>
+                        <input type="text" id="auth-metadata-url" name="auth_settings.oidc_server_metadata_url" value="{{ config.auth_settings.get('oidc_server_metadata_url', '') }}" class="form-input" placeholder="https://your-auth-server/.well-known/openid-configuration">
+                    </div>
+                    <div class="form-control">
+                        <label for="auth-admin-users">Admin User Emails</label>
+                        <p class="field-description">Comma-separated list of email addresses for users who should have admin rights.</p>
+                        <textarea id="auth-admin-users" name="auth_settings.admin_users" class="form-textarea" rows="2">{{ config.auth_settings.get('admin_users', []) | join(', ') }}</textarea>
+                    </div>
+                </fieldset>
+
+                 <fieldset class="settings-group">
+                    <legend><h2>Webhooks</h2></legend>
+                    <p class="field-description">Allow programmatic access and job status callbacks.</p>
+                    <div class="form-control checkbox-group">
+                        <input type="checkbox" id="webhook-enabled" name="webhook_settings.enabled" {% if config.webhook_settings.get('enabled') %}checked{% endif %}>
+                        <label for="webhook-enabled">Enable Webhook API</label>
+                    </div>
+                     <div class="form-control checkbox-group">
+                        <input type="checkbox" id="webhook-chunked-uploads" name="webhook_settings.allow_chunked_api_uploads" {% if config.webhook_settings.get('allow_chunked_api_uploads') %}checked{% endif %}>
+                        <label for="webhook-chunked-uploads">Allow Chunked Uploads via API</label>
+                    </div>
+                    <div class="form-control">
+                        <label for="webhook-allowed-urls">Allowed Callback URLs</label>
+                        <p class="field-description">Comma-separated list of URLs or domain prefixes that are allowed for callbacks (e.g., https://n8n.example.com).</p>
+                        <textarea id="webhook-allowed-urls" name="webhook_settings.allowed_callback_urls" class="form-textarea" rows="2">{{ config.webhook_settings.get('allowed_callback_urls', []) | join(', ') }}</textarea>
+                    </div>
+                    <div class="form-control">
+                        <label for="webhook-token">Callback Bearer Token</label>
+                        <p class="field-description">If set, this token will be sent in the `Authorization` header for all callback requests.</p>
+                        <input type="password" id="webhook-token" name="webhook_settings.callback_bearer_token" value="{{ config.webhook_settings.get('callback_bearer_token', '') }}" class="form-input">
+                    </div>
+                </fieldset>
+
+                <fieldset class="settings-group">
+                    <legend><h2>TTS (Piper)</h2></legend>
+                    <div class="form-control checkbox-group">
+                        <input type="checkbox" id="tts-piper-cuda" name="tts_settings.piper.use_cuda" {% if config.tts_settings.piper.get('use_cuda') %}checked{% endif %}>
+                        <label for="tts-piper-cuda">Use CUDA (GPU)</label>
+                    </div>
+                    <div class="form-control">
+                        <label for="tts-piper-length">Length Scale</label>
+                        <input type="number" step="0.1" id="tts-piper-length" name="tts_settings.piper.synthesis_config.length_scale" value="{{ config.tts_settings.piper.synthesis_config.get('length_scale', 1.0) }}" class="form-input">
+                    </div>
+                    <div class="form-control">
+                        <label for="tts-piper-noise">Noise Scale</label>
+                        <input type="number" step="0.1" id="tts-piper-noise" name="tts_settings.piper.synthesis_config.noise_scale" value="{{ config.tts_settings.piper.synthesis_config.get('noise_scale', 0.667) }}" class="form-input">
+                    </div>
+                    <div class="form-control">
+                        <label for="tts-piper-noise-w">Noise W</label>
+                        <input type="number" step="0.1" id="tts-piper-noise-w" name="tts_settings.piper.synthesis_config.noise_w" value="{{ config.tts_settings.piper.synthesis_config.get('noise_w', 0.8) }}" class="form-input">
+                    </div>
+                </fieldset>
+
                 <fieldset class="settings-group">
                     <legend><h2>Conversion Tools</h2></legend>
                     <p class="field-description">