Update app.py

app.py

@@ -1,28 +1,48 @@
-import gradio as gr
-import nltk
+import requests
+import json
 from nltk.tokenize import sent_tokenize, word_tokenize
 from nltk.corpus import stopwords
-from sklearn.feature_extraction.text import TfidfVectorizer
-import openai
-import datetime
+import nltk
+from flask import Flask, request, jsonify
+
+# Download NLTK data
+nltk.download("punkt")
+nltk.download("stopwords")
+
+# Initialize stop words
+stop_words = set(stopwords.words("english"))
 
-# Ensure necessary NLTK resources are downloaded
-try:
-    nltk.data.find('tokenizers/punkt')
-    nltk.data.find('corpora/stopwords')
-except LookupError:
-    nltk.download('punkt')
-    nltk.download('stopwords')
+# Initialize Flask app
+app = Flask(__name__)
+
+# Groq API credentials and endpoints
+GROQ_API_KEY = "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"
+TRANSCRIBE_ENDPOINT = "https://api.groq.com/transcribe"  # Replace with actual endpoint
+KEYWORD_EXTRACTION_ENDPOINT = "https://api.groq.com/keywords"  # Replace with actual endpoint
 
-# Transcription function (mocked for this example)
 def transcribe_audio(file_path):
-    # Assume some transcription service is being used, and return text as output
-    transcript = "This is a sample transcription of an audio file. It contains information that can be converted into important points for study notes."
-    return transcript
+    """Send audio file to Groq's transcription API."""
+    with open(file_path, "rb") as audio_file:
+        response = requests.post(
+            TRANSCRIBE_ENDPOINT,
+            headers={"Authorization": f"Bearer {GROQ_API_KEY}"},
+            files={"file": audio_file}
+        )
+    response.raise_for_status()
+    return response.json()["transcript"]
+
+def extract_keywords(text):
+    """Send text to Groq's keyword extraction API."""
+    response = requests.post(
+        KEYWORD_EXTRACTION_ENDPOINT,
+        headers={"Authorization": f"Bearer {GROQ_API_KEY}", "Content-Type": "application/json"},
+        json={"text": text}
+    )
+    response.raise_for_status()
+    return response.json()["keywords"]
 
-# Function to extract key sentences
 def extract_key_sentences(transcript):
-    stop_words = set(stopwords.words("english"))
+    """Extract sentences containing keywords from the transcript."""
     sentences = sent_tokenize(transcript)
     important_sentences = [
         sentence for sentence in sentences
@@ -30,43 +50,39 @@ def extract_key_sentences(transcript):
     ]
     return important_sentences
 
-# Function to generate study notes from the transcription
+@app.route("/transcribe", methods=["POST"])
+def transcribe():
+    """API endpoint to transcribe audio and generate notes."""
+    if "file" not in request.files:
+        return jsonify({"error": "No file uploaded"}), 400
+    file = request.files["file"]
+    file_path = "/tmp/audio_file.wav"
+    file.save(file_path)
+    
+    # Transcribe the audio
+    transcript = transcribe_audio(file_path)
+    
+    # Generate notes
+    notes = generate_notes(transcript)
+    
+    return jsonify(notes)
+
 def generate_notes(transcript):
+    """Generate summarized notes based on keywords and important sentences."""
+    # Extract key sentences
     key_sentences = extract_key_sentences(transcript)
     
-    # Using TfidfVectorizer for scoring and ranking sentences
-    vectorizer = TfidfVectorizer(stop_words='english')
-    tfidf_matrix = vectorizer.fit_transform(key_sentences)
-    scores = tfidf_matrix.sum(axis=1).A1
-    scored_sentences = sorted(zip(scores, key_sentences), reverse=True)
-
-    # Generating notes as a mix of important sentences
-    long_questions = scored_sentences[:3]  # Take top 3 for long questions
-    short_questions = scored_sentences[3:6]  # Next 3 for short questions
-    mcqs = scored_sentences[6:9]  # Following 3 for MCQs
+    # Extract keywords
+    keywords = extract_keywords(transcript)
     
+    # Prepare notes
     notes = {
-        "Long Questions": [sentence for _, sentence in long_questions],
-        "Short Questions": [sentence for _, sentence in short_questions],
-        "MCQs": [sentence for _, sentence in mcqs],
+        "short_questions": keywords[:5],  # Select top 5 keywords as short questions
+        "long_questions": key_sentences[:3],  # Select first 3 key sentences for long questions
+        "mcq": [{"question": f"What is {kw}?", "answer": "Yes/No"} for kw in keywords[:3]]
     }
     
     return notes
 
-# Main function for Gradio app
-def transcribe(file):
-    transcript = transcribe_audio(file.name)
-    notes = generate_notes(transcript)
-    return notes
-
-# Gradio UI setup
-iface = gr.Interface(
-    fn=transcribe,
-    inputs="file",
-    outputs="json",
-    title="Audio to Study Notes",
-    description="Transcribe audio to extract key sentences for study notes, including Long Questions, Short Questions, and MCQs."
-)
-
-# Run the app
-iface.launch()
+if __name__ == "__main__":
+    app.run(debug=True)