Update app.py

app.py

@@ -4,6 +4,9 @@ from langdetect import detect
 from huggingface_hub import InferenceClient
 import pandas as pd
 import os
+import nltk
+nltk.download('punkt')
+from nltk.tokenize import sent_tokenize
 
 HF_TOKEN = os.getenv("HF_TOKEN")
 
@@ -11,16 +14,15 @@ HF_TOKEN = os.getenv("HF_TOKEN")
 def call_zephyr_api(prompt, mode, hf_token=HF_TOKEN):
     client = InferenceClient("HuggingFaceH4/zephyr-7b-beta", token=hf_token)
     try:
-        # Ajuster les paramètres en fonction du mode
         if mode == "Rapide":
-            max_new_tokens = 100  # Réponse courte
-            temperature = 0.5     # Moins de créativité
+            max_new_tokens = 100
+            temperature = 0.5
         elif mode == "Équilibré":
-            max_new_tokens = 200  # Réponse moyenne
-            temperature = 0.7     # Créativité modérée
+            max_new_tokens = 200
+            temperature = 0.7
         else:  # Précis
-            max_new_tokens = 300  # Réponse longue
-            temperature = 0.9     # Plus de créativité
+            max_new_tokens = 300
+            temperature = 0.9
         response = client.text_generation(prompt, max_new_tokens=max_new_tokens, temperature=temperature)
         return response
     except Exception as e:
@@ -33,6 +35,20 @@ classifier = pipeline("sentiment-analysis", model="mrm8488/distilroberta-finetun
 translator_to_en = pipeline("translation", model="Helsinki-NLP/opus-mt-mul-en")
 translator_to_fr = pipeline("translation", model="Helsinki-NLP/opus-mt-en-fr")
 
+# Fonction pour traduire un texte long en le segmentant
+def safe_translate_to_fr(text, max_length=512):
+    # Segmenter le texte en phrases
+    sentences = sent_tokenize(text)
+    translated_sentences = []
+    
+    for sentence in sentences:
+        # Traduire chaque phrase individuellement
+        translated = translator_to_fr(sentence, max_length=max_length)[0]['translation_text']
+        translated_sentences.append(translated)
+    
+    # Recombiner les phrases traduites
+    return " ".join(translated_sentences)
+
 # Fonction pour suggérer le meilleur modèle
 def suggest_model(text):
     word_count = len(text.split())
@@ -57,14 +73,14 @@ def create_sentiment_gauge(sentiment, score):
 
     html = f"""
     <div style='width: 100%; max-width: 300px; margin: 10px 0;'>
-        <div style='background-color: #e0e0e0; border-radius: 5px; height: 20px; position: relative;'>
-            <div style='background-color: {color}; width: {score_percentage}%; height: 100%; border-radius: 5px;'>
+        <div style='background-color: #e0e0e0; border-radius: 5px; height: 20px; position: relative; box-shadow: 0 2px 4px rgba(0,0,0,0.2);'>
+            <div style='background-color: {color}; width: {score_percentage}%; height: 100%; border-radius: 5px; transition: width 0.3s ease-in-out;'>
             </div>
-            <span style='position: absolute; top: 0; left: 50%; transform: translateX(-50%); color: black; font-size: 12px; line-height: 20px;'>
+            <span style='position: absolute; top: 0; left: 50%; transform: translateX(-50%); color: black; font-size: 12px; line-height: 20px; font-weight: 600;'>
                 {score_percentage:.1f}%
             </span>
         </div>
-        <div style='text-align: center; font-size: 14px; margin-top: 5px;'>
+        <div style='text-align: center; font-size: 14px; margin-top: 5px; color: #E0E0E0;'>
             Sentiment: {sentiment}
         </div>
     </div>
@@ -116,7 +132,7 @@ Now, explain why the sentiment is {result['label'].lower()} using a logical, fac
 </s>
 <|assistant|>"""
     explanation_en = call_zephyr_api(explanation_prompt, mode)
-    explanation_fr = translator_to_fr(explanation_en, max_length=512)[0]['translation_text']
+    explanation_fr = safe_translate_to_fr(explanation_en, max_length=512)
 
     count += 1
     history.append({
@@ -138,44 +154,134 @@ def download_history(history):
     df.to_csv(file_path, index=False)
     return file_path
 
-# Interface Gradio
+# Interface Gradio améliorée
 def launch_app():
-    with gr.Blocks(theme=gr.themes.Base(), css="body {background-color: #0D1117; color: white;} .gr-button {background-color: #161B22; border: 1px solid #30363D;}") as iface:
+    custom_css = """
+    @import url('https://fonts.googleapis.com/css2?family=Inter:wght@300;400;600;700&display=swap');
+
+    body {
+        background: linear-gradient(135deg, #1A1A2E 0%, #16213E 100%);
+        color: #E0E0E0;
+        font-family: 'Inter', sans-serif;
+    }
+
+    .gr-box {
+        background: #2A2A4A !important;
+        border-radius: 12px !important;
+        border: 1px solid #3A3A5A !important;
+        box-shadow: 0 4px 12px rgba(0, 0, 0, 0.3) !important;
+        padding: 20px !important;
+        margin: 10px 0 !important;
+    }
+
+    .gr-textbox, .gr-dropdown {
+        background: #3A3A5A !important;
+        border: 1px solid #4A4A7A !important;
+        border-radius: 8px !important;
+        color: #E0E0E0 !important;
+        font-size: 16px !important;
+        padding: 12px !important;
+        transition: border-color 0.3s ease, box-shadow 0.3s ease !important;
+    }
+
+    .gr-textbox:focus, .gr-dropdown:focus {
+        border-color: #FFD700 !important;
+        box-shadow: 0 0 8px rgba(255, 215, 0, 0.3) !important;
+    }
+
+    .gr-button {
+        background: linear-gradient(90deg, #FFD700 0%, #D4AF37 100%) !important;
+        color: #1A1A2E !important;
+        border: none !important;
+        border-radius: 8px !important;
+        padding: 12px 24px !important;
+        font-weight: 600 !important;
+        font-size: 16px !important;
+        transition: transform 0.1s ease, box-shadow 0.3s ease !important;
+        box-shadow: 0 2px 8px rgba(255, 215, 0, 0.2) !important;
+    }
+
+    .gr-button:hover {
+        transform: translateY(-2px) !important;
+        box-shadow: 0 4px 12px rgba(255, 215, 0, 0.4) !important;
+    }
+
+    h1, h2, h3 {
+        color: #FFD700 !important;
+        font-weight: 700 !important;
+        text-shadow: 0 2px 4px rgba(0, 0, 0, 0.2) !important;
+    }
+
+    .gr-row {
+        margin: 15px 0 !important;
+    }
+
+    .gr-column {
+        padding: 10px !important;
+    }
+
+    label {
+        color: #FFD700 !important;
+        font-weight: 600 !important;
+        font-size: 16px !important;
+        margin-bottom: 8px !important;
+        display: flex !important;
+        align-items: center !important;
+    }
+
+    label::before {
+        content: '📊 ';
+        margin-right: 8px;
+    }
+
+    .gr-html label::before {
+        content: '📈 ';
+    }
+
+    .gr-file label::before {
+        content: '💾 ';
+    }
+    """
+
+    with gr.Blocks(theme=gr.themes.Base(), css=custom_css) as iface:
         gr.Markdown("# 📈 Analyse Financière Premium + Explication IA", elem_id="title")
-        gr.Markdown("Entrez une question sur un événement économique. L'IA prédit l'impact et attribue un sentiment (positif, négatif, neutre).")
+        gr.Markdown("Posez une question sur un événement économique. L'IA prédit l'impact et attribue un sentiment (positif, négatif, neutre).", elem_classes=["subtitle"])
 
         count = gr.State(0)
         history = gr.State([])
 
         with gr.Row():
-            input_text = gr.Textbox(lines=4, placeholder="Entrez une question ici (ex. 'La Réserve fédérale augmentera-t-elle ses taux d'intérêt avant 2025 ?')", label="Question économique")
+            with gr.Column(scale=2):
+                input_text = gr.Textbox(
+                    lines=4,
+                    placeholder="Entrez une question ici (ex. 'La Réserve fédérale augmentera-t-elle ses taux d'intérêt avant 2025 ?')",
+                    label="Question Économique"
+                )
+            with gr.Column(scale=1):
+                mode_selector = gr.Dropdown(
+                    choices=["Rapide", "Équilibré", "Précis"],
+                    value="Équilibré",
+                    label="Mode (longueur et style de réponse)"
+                )
+                detail_mode_selector = gr.Dropdown(
+                    choices=["Normal", "Expert"],
+                    value="Normal",
+                    label="Niveau de détail (simplicité ou technicité)"
+                )
 
         with gr.Row():
-            mode_selector = gr.Dropdown(
-                choices=["Rapide", "Équilibré", "Précis"],
-                value="Équilibré",
-                label="Mode (longueur et style de réponse)"
-            )
-            detail_mode_selector = gr.Dropdown(
-                choices=["Normal", "Expert"],
-                value="Normal",
-                label="Niveau de détail (simplicité ou technicité)"
-            )
-
-        analyze_btn = gr.Button("Analyser")
-        reset_graph_btn = gr.Button("Reset Graphique")
-        download_btn = gr.Button("Télécharger CSV")
-
-        with gr.Row():
-            sentiment_output = gr.Textbox(label="Résultat du Sentiment Prédictif")
-
-        sentiment_gauge = gr.HTML(label="Jauge de Sentiment")
+            analyze_btn = gr.Button("Analyser")
+            reset_graph_btn = gr.Button("Réinitialiser")
+            download_btn = gr.Button("Télécharger CSV")
 
         with gr.Row():
-            with gr.Column():
-                explanation_output_en = gr.Textbox(label="Explication en Anglais")
-            with gr.Column():
-                explanation_output_fr = gr.Textbox(label="Explication en Français")
+            with gr.Column(scale=1):
+                sentiment_output = gr.Textbox(label="Résultat du Sentiment Prédictif")
+                sentiment_gauge = gr.HTML(label="Jauge de Sentiment")
+            with gr.Column(scale=2):
+                with gr.Row():
+                    explanation_output_en = gr.Textbox(label="Explication en Anglais")
+                    explanation_output_fr = gr.Textbox(label="Explication en Français")
 
         download_file = gr.File(label="Fichier CSV")