Upload 2 files

utils/audio_processor.py

@@ -0,0 +1,17 @@
+import speech_recognition as sr
+
+def convert_audio_to_text() -> str:
+    """Convert audio from microphone to text."""
+    recognizer = sr.Recognizer()
+    
+    with sr.Microphone() as source:
+        print("Listening...")
+        audio = recognizer.listen(source)
+        
+    try:
+        text = recognizer.recognize_google(audio)
+        return text
+    except sr.UnknownValueError:
+        return "Could not understand audio"
+    except sr.RequestError:
+        return "Could not request results"

utils/text_analysis.py

@@ -0,0 +1,79 @@
+import google.generativeai as genai
+from typing import List, Dict
+import os
+from dotenv import load_dotenv
+
+load_dotenv()
+
+# Configure Gemini API
+genai.configure(api_key=os.getenv('GOOGLE_API_KEY'))
+model = genai.GenerativeModel('gemini-pro')
+
+def extract_keywords(text: str) -> List[str]:
+    """Extract important keywords from text using Gemini API."""
+    prompt = f"Extract important technical skills, technologies, and key requirements as keywords from this text. Return only the keywords separated by commas: {text}"
+    response = model.generate_content(prompt)
+    keywords = [k.strip() for k in response.text.split(',')]
+    return keywords
+
+def generate_summary(text: str) -> str:
+    """Generate a concise summary of the text using Gemini API."""
+    prompt = f"Provide a concise summary of the following text, focusing on the main points: {text}"
+    response = model.generate_content(prompt)
+    return response.text
+
+def generate_mcqs(resume: str, job_description: str) -> List[Dict]:
+    """Generate MCQs based on resume and job description."""
+    prompt = f"""Based on this resume: {resume}
+    And this job description: {job_description}
+    Generate 30 relevant multiple choice questions. For each question, provide:
+    1. The question
+    2. Four options (A, B, C, D)
+    3. The correct answer
+    Format each question as a dictionary with keys: 'question', 'options', 'correct_answer'
+    Return as a Python list of dictionaries."""
+    
+    response = model.generate_content(prompt)
+    # Process and format the response into a list of dictionaries
+    # This is a simplified version - you'll need to parse the actual response
+    return eval(response.text)
+
+def generate_coding_questions(resume: str, job_description: str) -> List[Dict]:
+    """Generate coding questions based on resume and job description."""
+    prompt = f"""Based on this resume: {resume}
+    And this job description: {job_description}
+    Generate 2 coding questions with:
+    1. Problem statement
+    2. Input/Output examples
+    3. Constraints
+    4. Expected solution approach
+    Format as a list of dictionaries."""
+    
+    response = model.generate_content(prompt)
+    return eval(response.text)
+
+def analyze_interview_response(audio_text: str, job_description: str) -> Dict:
+    """Analyze the interview response and provide feedback."""
+    prompt = f"""Analyze this interview response: {audio_text}
+    For this job description: {job_description}
+    Provide:
+    1. Overall performance score (0-100)
+    2. Strengths
+    3. Areas for improvement
+    4. Specific concepts to study
+    Return as a dictionary."""
+    
+    response = model.generate_content(prompt)
+    return eval(response.text)
+
+def get_learning_resources(concepts: List[str]) -> Dict[str, List[str]]:
+    """Get learning resources for concepts that need improvement."""
+    prompt = f"""For these concepts: {concepts}
+    Provide high-quality learning resources including:
+    1. Online courses
+    2. Documentation
+    3. Practice platforms
+    Format as a dictionary with concept keys and resource list values."""
+    
+    response = model.generate_content(prompt)
+    return eval(response.text)