Update app.py

app.py

@@ -7,16 +7,41 @@ import torch
 import faiss
 import numpy as np
 from gtts import gTTS
-import io
-from PIL import Image
-from flask import Flask, request, jsonify
-from werkzeug.utils import secure_filename
 
-# Initialize Streamlit components
-st.title("Parenting Guide App")
+# Function to convert audio file to text
+def audio_to_text(audio_file):
+    recognizer = sr.Recognizer()
+    with sr.AudioFile(audio_file) as source:
+        audio = recognizer.record(source)
+    try:
+        text = recognizer.recognize_google(audio)
+        return text
+    except sr.UnknownValueError:
+        return "Sorry, I did not understand the audio"
+    except sr.RequestError:
+        return "Sorry, there was a problem with the request"
+
+# Function to extract text from a PDF file
+def extract_text_from_pdf(pdf_file):
+    text = ""
+    pdf_document = fitz.open(pdf_file)
+    for page_num in range(len(pdf_document)):
+        page = pdf_document.load_page(page_num)
+        text += page.get_text()
+    return text
 
-# HTML component for the recording interface
-st.components.v1.html(open("audio_recorder.html").read(), height=600)
+# Function to embed text using a transformer model
+def embed_text(texts, model, tokenizer):
+    inputs = tokenizer(texts, return_tensors='pt', truncation=True, padding=True)
+    with torch.no_grad():
+        embeddings = model(**inputs).last_hidden_state.mean(dim=1).numpy()
+    return embeddings
+
+# Function to convert text to speech
+def text_to_speech(text, output_file):
+    tts = gTTS(text=text, lang='en')
+    tts.save(output_file)
+    return output_file
 
 # Initialize model and tokenizer
 tokenizer = AutoTokenizer.from_pretrained("bert-base-uncased")
@@ -41,28 +66,31 @@ for path in pdf_paths:
 embeddings = embed_text(texts, model, tokenizer)
 index.add(embeddings)
 
-# Define Flask app to handle audio uploads
-app = Flask(__name__)
+# Streamlit application
+st.title("Parenting Guide App")
 
-@app.route('/upload-audio', methods=['POST'])
-def upload_audio():
-    audio_file = request.files['audio']
-    if audio_file:
-        audio_file.save('temp_audio.wav')
-        text = audio_to_text('temp_audio.wav')
+# Upload an audio file
+audio_file = st.file_uploader("Record and upload your audio file (WAV/MP3)", type=["wav", "mp3"])
 
-        # Find relevant advice
-        query_embedding = embed_text([text], model, tokenizer)
-        D, I = index.search(query_embedding, k=1)  # Search for the most similar advice
-        closest_text = texts[I[0][0]]
+if audio_file:
+    st.write("Processing...")
 
-        # Convert advice to speech
-        output_file = "advice.mp3"
-        output_path = text_to_speech(closest_text, output_file)
+    # Save the uploaded audio file
+    with open("temp_audio.wav", "wb") as f:
+        f.write(audio_file.getbuffer())
 
-        return jsonify({'status': 'success', 'audio': output_file})
+    # Convert audio to text
+    text = audio_to_text("temp_audio.wav")
+    st.write("Voice command:", text)
 
-    return jsonify({'status': 'error', 'message': 'No audio file received'})
+    # Find relevant advice
+    query_embedding = embed_text([text], model, tokenizer)
+    D, I = index.search(query_embedding, k=1)  # Search for the most similar advice
+    closest_text = texts[I[0][0]]
+    
+    st.write("Advice:", closest_text)
 
-if __name__ == '__main__':
-    app.run(debug=True)
+    # Convert advice to speech
+    output_file = "advice.mp3"
+    output_path = text_to_speech(closest_text, output_file)
+    st.audio(output_path)