Update app.py

app.py

@@ -40,52 +40,56 @@ def translate_to_english(cv_text):
     else:
         return cv_text, detected_lang 
 
-#if an entered cv is not in English return the job description in the entered cv language 
+#if entered cv is not in english return the job description in the entered cv langauge
 def translate_job_description_if_needed(job_description, target_lang):
-    if target_lang != 'en':
+    if target_lang != 'eng_Latn':
         return translator(job_description, src_lang="eng_Latn", tgt_lang=target_lang)[0]['translation_text']
-    return job_description 
-
-# Function to find top 3 job descriptions matching the CV using semantic similarity
+    return job_description
+    
+# Function to find top 3 job descriptions matching the CV to job descriptions
 def find_top_matches(cv_text):
     if not cv_text:
         return "Error: CV is empty", None
 
-    # Translate CV to English if it contains Arabic text
+    # Translate CV to english if not in english
     cv_text, detected_lang = translate_to_english(cv_text)
-    # Get job descriptions from the DataFrame
+
+    # Get job descriptions from the DataFrame as list
     descriptions = df['Job_Description'].tolist()
 
-    # Encode both the CV and job descriptions
+    # Encode both the CV and job descriptions to calcuate cosine similarities
     descriptions_embeddings = model.encode(descriptions, convert_to_tensor=True)
     cv_embedding = model.encode([cv_text], convert_to_tensor=True)
-    # Calculate cosine similarities between the CV and all job descriptions
     similarities = util.pytorch_cos_sim(cv_embedding, descriptions_embeddings)[0]
 
     # Get the top 3 matches based on similarity scores
-    top_3_indices = similarities.argsort(descending=True)[:3]  # Get the indices of the top 3 matches
+    top_3_indices = similarities.argsort(descending=True)[:3]  # Get the indices of the top 3 matches 
     top_3_matches = df.iloc[top_3_indices]
     top_3_similarities = similarities[top_3_indices].numpy()
 
-    #create vertical bar
+    #create vertical bar of top 3 match jobs to cv
     plt.bar(top_3_matches['Company'], top_3_similarities, color='skyblue')
-
-    # Set the labels and title
     plt.ylabel('Similarity Score')
     plt.xlabel('Company')
     plt.title('Top 3 Job Description Matches')
+
     # Create a detailed summary for the top 3 job descriptions
     job_summaries = ""
     for _, row in top_3_matches.iterrows():
         # Translate job description if the detected language is not English
         job_desc_translated = translate_job_description_if_needed(row['Job_Description'], detected_lang)
 
-        # Show job description only in the detected language if it's not English
-        job_summaries += f"<strong>Company:</strong> {row['Company']}<br>"
-        job_summaries += f"<strong>Job Description :</strong> {job_desc_translated}<br><br>"
+        if detected_lang == 'arb_Arab':
+            # Use dir="rtl" for right-to-left languages
+            job_summaries += f'<div dir="rtl"><strong>الشركة</strong>: {row["Company"]} <br>'
+            job_summaries += f'<strong>وصف الوظيفه :</strong> {job_desc_translated}<br><br></div>'
+        else:
+            # Normal left-to-right display
+            job_summaries += f"<strong>Company:</strong> {row['Company']}<br>"
+            job_summaries += f"<strong>Job Description :</strong> {job_desc_translated}<br><br>"
 
     return job_summaries, plt
-
+ 
 # Define Gradio interface
 demo = gr.Interface(
     fn=find_top_matches,