Update app.py

app.py

@@ -3,47 +3,41 @@ import requests
 from sklearn.feature_extraction.text import TfidfVectorizer
 from sklearn.metrics.pairwise import cosine_similarity
 from transformers import MarianMTModel, MarianTokenizer
+import sentencepiece
 
 # Set up the Streamlit page
 st.title("AI Opportunity Finder for Youth")
 st.write("Find Scholarships, Internships, Online Courses, and more!")
 
-# Language Translation Function
-def translate_text(text, target_lang='de'):
-    # Use Hugging Face's MarianMT for translation
-    model_name = f'Helsinki-NLP/opus-mt-en-{target_lang}'
-    model = MarianMTModel.from_pretrained(model_name)
-    tokenizer = MarianTokenizer.from_pretrained(model_name)
-
-    translated = model.generate(**tokenizer(text, return_tensors="pt", padding=True, truncation=True))
-    translated_text = tokenizer.decode(translated[0], skip_special_tokens=True)
-    return translated_text
-
-# Mock function to get data from APIs (replace with actual API calls)
-def get_scholarships(country, interests):
-    url = f"https://jsonplaceholder.typicode.com/posts"  # Mock API (replace with real one)
+# Function to get scholarships data from a mock API
+def get_scholarships(location, interests):
+    url = "https://jsonplaceholder.typicode.com/posts"  # Mock API for testing
+    response = requests.get(url)
     
-    # Simulate API response based on country
-    if country == "USA":
-        return [{"title": f"USA Scholarship {i+1}", "description": f"Description for scholarship {i+1} in USA.", "eligibility": "Any student from USA."} for i in range(5)]
-    elif country == "Germany":
-        return [{"title": f"Germany Scholarship {i+1}", "description": f"Description for scholarship {i+1} in Germany.", "eligibility": "Any student from Germany."} for i in range(5)]
+    if response.status_code == 200:
+        # Return a list of mock scholarships
+        return [{"title": f"Scholarship {i+1}", "description": post['body'], "eligibility": "Any student from any background."} for i, post in enumerate(response.json())[:5]]
     else:
-        return [{"title": f"Scholarship {i+1}", "description": f"Description for scholarship {i+1} in {country}.", "eligibility": "Any student from any background."} for i in range(5)]
+        return []
 
-def get_internships(country):
-    url = f"https://jsonplaceholder.typicode.com/posts"  # Mock API for testing
-    # Simulate internships data
-    if country == "USA":
-        return [{"jobtitle": f"Internship {i+1}", "company": "USA Company", "location": "USA", "snippet": "Description of internship in USA."} for i in range(5)]
-    elif country == "Germany":
-        return [{"jobtitle": f"Internship {i+1}", "company": "Germany Company", "location": "Germany", "snippet": "Description of internship in Germany."} for i in range(5)]
+# Function to get internships data from a mock API
+def get_internships():
+    url = "https://jsonplaceholder.typicode.com/posts"  # Mock API for testing
+    response = requests.get(url)
+    
+    if response.status_code == 200:
+        # Return a list of mock internships
+        return [{"jobtitle": f"Internship {i+1}", "company": "Sample Company", "location": "Remote", "snippet": "Description of the internship."} for i in range(5)]
     else:
-        return [{"jobtitle": f"Internship {i+1}", "company": "Sample Company", "location": "Remote", "snippet": "Description of internship."} for i in range(5)]
+        return []
 
+# Function to recommend opportunities based on user input
 def recommend_opportunities(user_interests, user_skills, opportunities):
+    # Combine user profile into a single string
     user_profile = [f"{user_interests} {user_skills}"]
-    opportunities_text = [f"{opportunity.get('description', 'No description available')} {opportunity.get('eligibility', 'No eligibility available')}" for opportunity in opportunities]
+    
+    # Create text data for opportunities based on description & eligibility
+    opportunities_text = [f"{opportunity['description']} {opportunity['eligibility']}" for opportunity in opportunities]
     
     # Vectorize the text using TF-IDF
     vectorizer = TfidfVectorizer(stop_words='english')
@@ -52,70 +46,105 @@ def recommend_opportunities(user_interests, user_skills, opportunities):
     # Compute cosine similarity
     cosine_sim = cosine_similarity(tfidf_matrix[-1], tfidf_matrix[:-1])
     
-    # Get the top 5 recommendations
+    # Get the indices of the top 5 recommended opportunities
     recommendations = cosine_sim[0].argsort()[-5:][::-1]
     
+    # Return recommended opportunities
     return [opportunities[i] for i in recommendations]
 
-# Form to gather user profile and country selection
-with st.form(key='user_form'):
-    st.sidebar.header("User Profile")
-    location = st.selectbox("Select your Country", ["USA", "Germany", "UK", "India", "Australia", "Pakistan"])  # You can add more countries here
-    skills = st.text_input("Skills (e.g., Python, Marketing)")
-    interests = st.text_input("Interests (e.g., Technology, Science)")
-    target_language = st.selectbox("Select target language", ['de', 'fr', 'es', 'it', 'pt'])  # Available language codes for translation
+# Function to load MarianMT translation model
+def load_translation_model(target_language):
+    model_name = f'Helsinki-NLP/opus-mt-en-{target_language}'
+    tokenizer = MarianTokenizer.from_pretrained(model_name)
+    model = MarianMTModel.from_pretrained(model_name)
+    return model, tokenizer
 
-    submit_button = st.form_submit_button("Find Opportunities")
+# Function to translate text using MarianMT
+def translate_text(text, target_language):
+    try:
+        model, tokenizer = load_translation_model(target_language)
+        
+        # Tokenize and translate text
+        tokens = tokenizer(text, return_tensors="pt", padding=True, truncation=True)
+        translated = model.generate(**tokens)
+        translated_text = tokenizer.decode(translated[0], skip_special_tokens=True)
+        
+        return translated_text
+    except Exception as e:
+        return f"Error during translation: {str(e)}"
 
-# Fetch data based on the user input
-if submit_button:
-    # Fetch scholarships and internships based on the selected country and profile
-    scholarships = get_scholarships(location, interests)
-    internships = get_internships(location)
-    
-    # Display Scholarships
-    if scholarships:
-        st.write("Scholarships found:")
-        for scholarship in scholarships:
-            title = translate_text(scholarship.get('title', 'No title available'), target_language)
-            description = translate_text(scholarship.get('description', 'No description available'), target_language)
-            eligibility = translate_text(scholarship.get('eligibility', 'No eligibility available'), target_language)
-            
-            st.write(f"Title: {title}")
-            st.write(f"Description: {description}")
-            st.write(f"Eligibility: {eligibility}")
-            st.write("---")
-    else:
-        st.write("No scholarships found for the selected country.")
-    
-    # Display Internships
-    if internships:
-        st.write("Internships found:")
-        for internship in internships:
-            title = translate_text(internship.get('jobtitle', 'No title available'), target_language)
-            company = translate_text(internship.get('company', 'No company available'), target_language)
-            location = translate_text(internship.get('location', 'No location available'), target_language)
-            snippet = translate_text(internship.get('snippet', 'No snippet available'), target_language)
-            
-            st.write(f"Title: {title}")
-            st.write(f"Company: {company}")
-            st.write(f"Location: {location}")
-            st.write(f"Snippet: {snippet}")
-            st.write("---")
-    else:
-        st.write("No internships found for the selected country.")
-    
-    # AI Recommendations based on interests and skills
+# User input for profile
+st.sidebar.header("User Profile")
+location = st.sidebar.text_input("Location", "Pakistan")  # Default to 'Pakistan'
+skills = st.sidebar.text_input("Skills (e.g., Python, Marketing)")
+interests = st.sidebar.text_input("Interests (e.g., Technology, Science)")
+
+# Fetch scholarships based on user input
+scholarships = get_scholarships(location, interests)
+
+# Display scholarships if available
+if scholarships:
+    st.write("Scholarships found:")
+    for scholarship in scholarships:
+        st.write(f"Title: {scholarship['title']}")
+        st.write(f"Description: {scholarship['description']}")
+        st.write(f"Eligibility: {scholarship['eligibility']}")
+        st.write("---")
+else:
+    st.write("No scholarships found based on your criteria.")
+
+# Fetch internships based on user input
+internships = get_internships()
+
+# Display internships if available
+if internships:
+    st.write("Internships found:")
+    for internship in internships:
+        st.write(f"Title: {internship['jobtitle']}")
+        st.write(f"Company: {internship['company']}")
+        st.write(f"Location: {internship['location']}")
+        st.write(f"Snippet: {internship['snippet']}")
+        st.write("---")
+else:
+    st.write("No internships found.")
+
+# AI-based recommendations for opportunities
+if st.sidebar.button("Get AI Recommendations"):
+    # Combine scholarships and internships for recommendations
     all_opportunities = scholarships + internships
+    
+    # Get AI recommendations based on user input
     recommended_opportunities = recommend_opportunities(interests, skills, all_opportunities)
     
-    st.write("AI-based Recommended Opportunities based on your profile:")
+    # Display recommended opportunities
+    st.write("Recommended Opportunities based on your profile:")
     for opportunity in recommended_opportunities:
-        title = translate_text(opportunity.get('title', 'No title available'), target_language)
-        description = translate_text(opportunity.get('description', 'No description available'), target_language)
-        eligibility = translate_text(opportunity.get('eligibility', 'Not available'), target_language)
-        
-        st.write(f"Title: {title}")
-        st.write(f"Description: {description}")
-        st.write(f"Eligibility: {eligibility}")
+        st.write(f"Title: {opportunity['title']}")
+        st.write(f"Description: {opportunity['description']}")
+        st.write(f"Eligibility: {opportunity.get('eligibility', 'Not available')}")
         st.write("---")
+
+# Language selection
+languages = {
+    'English': 'english',
+    'German': 'deutch',
+    'French': 'french',
+    'Spanish': 'spanish',
+    'Italian': 'italian',
+    'Portuguese': 'portugese',
+    'Chinese': 'chinese',
+    'Arabic': 'arabic',
+    'Russian': 'russian',
+    'Japanese': 'japanese',
+    'Korean': 'korean',
+    'Urdu': 'urdu'
+}
+
+# Dropdown for language selection
+selected_language = st.selectbox("Select Language", list(languages.keys()))
+
+# Translate the opportunity description based on the selected language
+if selected_language != 'English':
+    # Translate the title of the app or a sample text
+    translated_text = translate_text("Hello, welcome to AI Opportunity Finder!", languages[selected_language])
+    st.write(f"Translated Text ({selected_language}): {translated_text}")