Update app/models.py

app/models.py

@@ -1,40 +1,40 @@
-from transformers import pipeline
-
-# وظيفة تلخيص النصوص
-def summarize_text(document: str):
-    summarizer = pipeline("summarization", model="facebook/bart-large-cnn")
-    summary = summarizer(document, max_length=130, min_length=30, do_sample=False)
-    return summary[0]['summary_text']
-
-# وظيفة تفسير الصور
-def analyze_image(image):
-    image_analyzer = pipeline("image-to-text", model="nlpconnect/vit-gpt2-image-captioning")
-    result = image_analyzer(image)
-    return result[0]['generated_text']
-
-# وظيفة الإجابة على الأسئلة
-def answer_question(question: str, document: str):
-    qa_pipeline = pipeline("question-answering", model="deepset/roberta-base-squad2")
-    result = qa_pipeline(question=question, context=document)
-    return result['answer']
-
-# وظيفة إنشاء تصورات بيانات
-def generate_visualization(data, request):
-    import pandas as pd
-    import matplotlib.pyplot as plt
-    import seaborn as sns
-
-    df = pd.read_excel(data)
-    # تنفيذ الطلب (مثال: رسم مخطط)
-    if "bar" in request:
-        plt.bar(df['column_name'], df['values'])
-    elif "line" in request:
-        plt.plot(df['column_name'], df['values'])
-    plt.savefig("visualization.png")
-    return "visualization.png"
-
-# وظيفة ترجمة المستندات
-def translate_document(document, target_language):
-    translator = pipeline("translation", model=f"Helsinki-NLP/opus-mt-{target_language}")
-    translation = translator(document)
+from transformers import pipeline
+
+# وظيفة تلخيص النصوص
+def summarize_text(document: str):
+    summarizer = pipeline("summarization", model="facebook/bart-large-cnn")
+    summary = summarizer(document, max_length=130, min_length=30, do_sample=False)
+    return summary[0]['summary_text']
+
+# وظيفة تفسير الصور
+def analyze_image(image):
+    image_analyzer = pipeline("image-to-text", model="nlpconnect/vit-gpt2-image-captioning")
+    result = image_analyzer(image)
+    return result[0]['generated_text']
+
+# وظيفة الإجابة على الأسئلة
+def answer_question(question: str, document: str):
+    qa_pipeline = pipeline("question-answering", model="deepset/roberta-base-squad2")
+    result = qa_pipeline(question=question, context=document)
+    return result['answer']
+
+# وظيفة إنشاء تصورات بيانات
+def generate_visualization(data, request):
+    import pandas as pd
+    import matplotlib.pyplot as plt
+    import seaborn as sns
+
+    df = pd.read_excel(data)
+    # تنفيذ الطلب (مثال: رسم مخطط)
+    if "bar" in request:
+        plt.bar(df['column_name'], df['values'])
+    elif "line" in request:
+        plt.plot(df['column_name'], df['values'])
+    plt.savefig("visualization.png")
+    return "visualization.png"
+
+# وظيفة ترجمة المستندات
+def translate_document(document, target_language):
+    translator = pipeline("translation", model=f"Helsinki-NLP/opus-mt-{target_language}")
+    translation = translator(document)
     return translation[0]['translation_text']