Upload 6 files

app.py

@@ -0,0 +1,217 @@
+import streamlit as st
+import google.generativeai as genai
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+import os
+import sounddevice as sd
+import numpy as np
+import librosa
+import io
+from PIL import Image
+import json
+import requests
+from datetime import datetime
+from streamlit_lottie import st_lottie
+
+# Configure page
+st.set_page_config(page_title="HerCorners", page_icon="👑", layout="wide")
+
+# Initialize Gemini
+genai.configure(api_key=st.secrets["GEMINI_API_KEY"])
+
+# Initialize Gemma
+@st.cache_resource
+def load_gemma_model():
+    tokenizer = AutoTokenizer.from_pretrained("google/gemma-7b")
+    model = AutoModelForCausalLM.from_pretrained("google/gemma-7b")
+    return tokenizer, model
+
+tokenizer, gemma_model = load_gemma_model()
+
+# Mentor profiles
+MENTORS = {
+    "Oprah Winfrey": {
+        "role": "Media Mogul & Philanthropist",
+        "topics": ["leadership", "personal growth", "media"],
+        "style": "inspiring and wise",
+        "prompt_style": "warm, encouraging, and empowering"
+    },
+    "Sara Blakely": {
+        "role": "Founder of Spanx",
+        "topics": ["entrepreneurship", "innovation", "business"],
+        "style": "practical and motivating",
+        "prompt_style": "direct, practical, with real business examples"
+    }
+}
+
+# Custom CSS
+st.markdown("""
+<style>
+    .mentor-card {
+        padding: 20px;
+        border-radius: 10px;
+        background: linear-gradient(145deg, #ffffff, #f0f0f0);
+        box-shadow: 5px 5px 15px rgba(0,0,0,0.1);
+        margin: 10px 0;
+    }
+    .chat-message {
+        padding: 15px;
+        border-radius: 10px;
+        margin: 10px 0;
+    }
+    .user-message {
+        background-color: #e3f2fd;
+        margin-left: 20%;
+    }
+    .mentor-message {
+        background-color: #f5f5f5;
+        margin-right: 20%;
+    }
+</style>
+""", unsafe_allow_html=True)
+
+class HerCorners:
+    def __init__(self):
+        self.initialize_session_state()
+        
+    def initialize_session_state(self):
+        if 'messages' not in st.session_state:
+            st.session_state.messages = []
+        if 'current_corner' not in st.session_state:
+            st.session_state.current_corner = None
+        if 'current_mentor' not in st.session_state:
+            st.session_state.current_mentor = None
+
+    def generate_mentor_response(self, mentor, message):
+        """Generate response using Gemini"""
+        model = genai.GenerativeModel('gemini-pro')
+        prompt = f"""
+        You are {mentor}, {MENTORS[mentor]['role']}.
+        Your communication style is {MENTORS[mentor]['style']}.
+        Respond to this message: {message}
+        Keep your response personal, authentic, and in your voice.
+        """
+        response = model.generate_content(prompt)
+        return response.text
+
+    def generate_support_response(self, story):
+        """Generate emotional support response using Gemma"""
+        prompt = f"As a supportive friend, respond with empathy to this story: {story}"
+        inputs = tokenizer(prompt, return_tensors="pt")
+        outputs = gemma_model.generate(**inputs, max_length=200)
+        response = tokenizer.decode(outputs[0])
+        return response
+
+    def she_legends_corner(self):
+        st.title("👑 She-Legends")
+        st.subheader("Chat with Inspiring Women Leaders")
+
+        # Mentor selection
+        mentor = st.selectbox("Choose your mentor", list(MENTORS.keys()))
+        if mentor:
+            st.session_state.current_mentor = mentor
+            
+            # Chat interface
+            message = st.text_input("Your message:")
+            if st.button("Send"):
+                response = self.generate_mentor_response(mentor, message)
+                st.session_state.messages.append({"role": "user", "content": message})
+                st.session_state.messages.append({"role": "assistant", "content": response})
+
+            # Display chat history
+            for msg in st.session_state.messages:
+                div_class = "user-message" if msg["role"] == "user" else "mentor-message"
+                st.markdown(f"""
+                <div class="chat-message {div_class}">
+                    {msg["content"]}
+                </div>
+                """, unsafe_allow_html=True)
+
+    def she_melted_mascara_corner(self):
+        st.title("💕 She-Melted Mascara")
+        st.subheader("Safe Space for Sharing")
+
+        # Story sharing options
+        share_method = st.radio("How would you like to share?", 
+                              ["Text", "Voice Note", "Upload Image"])
+
+        if share_method == "Text":
+            story = st.text_area("Share your story...")
+            if st.button("Share Anonymously"):
+                response = self.generate_support_response(story)
+                st.markdown(f"""
+                <div class="chat-message mentor-message">
+                    {response}
+                </div>
+                """, unsafe_allow_html=True)
+
+        elif share_method == "Voice Note":
+            if st.button("Start Recording"):
+                # Implement voice recording
+                st.write("Recording... (feature in development)")
+
+        elif share_method == "Upload Image":
+            uploaded_file = st.file_uploader("Upload your image")
+            if uploaded_file is not None:
+                image = Image.open(uploaded_file)
+                st.image(image, caption="Your shared image")
+
+    def she_glows_corner(self):
+        st.title("✨ She-Glows")
+        st.subheader("Economic Education Hub")
+
+        # Learning modules
+        modules = {
+            "Financial Literacy": ["Budgeting Basics", "Investment 101", "Credit Management"],
+            "Entrepreneurship": ["Business Planning", "Marketing Basics", "Funding Sources"],
+            "Leadership": ["Communication Skills", "Team Management", "Decision Making"]
+        }
+
+        selected_topic = st.selectbox("Choose your learning path", list(modules.keys()))
+        selected_module = st.selectbox("Select module", modules[selected_topic])
+
+        if st.button("Start Learning"):
+            # Generate educational content using Gemini
+            model = genai.GenerativeModel('gemini-pro')
+            prompt = f"Create a beginner-friendly lesson about {selected_module}"
+            response = model.generate_content(prompt)
+            st.write(response.text)
+
+    def she_fuels_corner(self):
+        st.title("⚡ She-Fuels")
+        st.subheader("Community Support & Achievements")
+
+        # Achievement sharing
+        achievement = st.text_area("Share your achievement")
+        if st.button("Share with Community"):
+            st.success("Achievement shared successfully!")
+
+        # Display community achievements
+        st.subheader("Recent Community Achievements")
+        # Placeholder for community achievements
+        achievements = [
+            "Started my first business!",
+            "Completed financial literacy course",
+            "Secured first investment"
+        ]
+        for achievement in achievements:
+            st.markdown(f"🌟 {achievement}")
+
+    def main(self):
+        st.sidebar.title("HerCorners")
+        corner = st.sidebar.radio("Choose your corner",
+                                ["She-Legends", "She-Melted Mascara", 
+                                 "She-Glows", "She-Fuels"])
+
+        if corner == "She-Legends":
+            self.she_legends_corner()
+        elif corner == "She-Melted Mascara":
+            self.she_melted_mascara_corner()
+        elif corner == "She-Glows":
+            self.she_glows_corner()
+        elif corner == "She-Fuels":
+            self.she_fuels_corner()
+
+if __name__ == "__main__":
+    app = HerCorners()
+    app.main()

config.txt

@@ -0,0 +1,6 @@
+[theme]
+primaryColor="#ff4b4b"
+backgroundColor="#ffffff"
+secondaryBackgroundColor="#f0f2f6"
+textColor="#262730"
+font="sans serif"

dockerfile.txt

@@ -0,0 +1,12 @@
+FROM python:3.9-slim
+
+WORKDIR /app
+
+COPY requirements.txt .
+RUN pip install -r requirements.txt
+
+COPY . .
+
+EXPOSE 8501
+
+ENTRYPOINT ["streamlit", "run", "app.py", "--server.port=8501", "--server.address=0.0.0.0"]

gemma_handler.py

@@ -0,0 +1,26 @@
+from huggingface_hub import InferenceClient
+
+class GemmaHandler:
+    def __init__(self, api_token):
+        self.client = InferenceClient(token=api_token)
+        self.model = "google/gemma-7b"
+
+    def generate_response(self, prompt):
+        response = self.client.text_generation(
+            prompt,
+            model=self.model,
+            max_new_tokens=100,
+            temperature=0.7,
+            top_p=0.95,
+            repetition_penalty=1.1
+        )
+        return response
+
+    def generate_emotional_support(self, emotion, story):
+        prompt = f"""
+        As a supportive AI friend, respond to someone who is feeling {emotion}.
+        Their story: {story}
+        
+        Provide empathetic support and encouragement while maintaining authenticity.
+        """
+        return self.generate_response(prompt)

requirements.txt

@@ -0,0 +1,19 @@
+streamlit
+google-generativeai
+transformers
+torch
+python-dotenv
+sounddevice
+librosa
+soundfile
+numpy
+pandas
+plotly
+Pillow
+streamlit-lottie
+streamlit-webrtc
+python-multipart
+requests
+scipy
+nltk
+emoji

voice_handler.py

@@ -0,0 +1,43 @@
+import sounddevice as sd
+import numpy as np
+import librosa
+import torch
+from transformers import pipeline
+
+class VoiceHandler:
+    def __init__(self):
+        self.sample_rate = 16000
+        self.emotion_classifier = pipeline("audio-classification", 
+                                        model="ehcalabres/wav2vec2-lg-xlsr-en-speech-emotion-recognition")
+
+    def record_audio(self, duration=5):
+        """Record audio for specified duration"""
+        recording = sd.rec(int(duration * self.sample_rate),
+                         samplerate=self.sample_rate,
+                         channels=1)
+        sd.wait()
+        return recording
+
+    def process_audio(self, audio_data):
+        """Process audio and detect emotion"""
+        # Convert to mono if needed
+        if len(audio_data.shape) > 1:
+            audio_data = np.mean(audio_data, axis=1)
+        
+        # Normalize audio
+        audio_data = librosa.util.normalize(audio_data)
+        
+        # Get emotion
+        emotion = self.emotion_classifier(audio_data)
+        
+        return audio_data, emotion[0]['label']
+
+    def enhance_audio(self, audio_data):
+        """Enhance audio quality"""
+        # Noise reduction
+        y = librosa.effects.preemphasis(audio_data)
+        
+        # Normalize
+        y = librosa.util.normalize(y)
+        
+        return y