Update app.py

app.py

@@ -1,88 +1,60 @@
 import streamlit as st
-import pdfplumber
-import spacy
-import openai
 import os
 from dotenv import load_dotenv
-import subprocess
+from groq import Groq
 
-# Load environment variables from .env file
+# Load API Key from .env
 load_dotenv()
+api_key = os.getenv("GROQ_API_KEY")
 
-# Set OpenAI API key
-openai.api_key = os.getenv("OPENAI_API_KEY")
+# Initialize Groq Client
+client = Groq(api_key=api_key)
 
-# Load spaCy model with error handling
-try:
-    nlp = spacy.load("en_core_web_sm")
-except OSError:
-    st.warning("Downloading 'en_core_web_sm' model. Please wait...")
-    subprocess.run(["python", "-m", "spacy", "download", "en_core_web_sm"])
-    nlp = spacy.load("en_core_web_sm")
+# Chatbot System Prompt
+system_prompt = """
+You are an AI Resume Analyzer designed to provide feedback on resumes. 
+Your goal is to analyze resumes, identify missing keywords, rate resumes, 
+and suggest better skills to highlight.
 
-def extract_text_from_pdf(pdf_file):
-    """Extracts text from an uploaded PDF resume."""
-    text = ""
-    try:
-        with pdfplumber.open(pdf_file) as pdf:
-            for page in pdf.pages:
-                text += page.extract_text() + "\n"
-    except Exception as e:
-        st.error(f"Error extracting text from PDF: {e}")
-    return text.strip()
-
-def extract_keywords(text):
-    """Extracts important keywords from resume text using spaCy."""
-    doc = nlp(text)
-    keywords = set()
-    for token in doc:
-        if token.pos_ in ["NOUN", "PROPN"]:  # Extract nouns and proper nouns
-            keywords.add(token.text.lower())
-    return list(keywords)
-
-def analyze_resume(text):
-    """Uses OpenAI GPT to analyze resume and suggest improvements."""
-    prompt = f"""
-    You are a professional resume analyzer. Given the following resume text, 
-    provide a rating (out of 10), identify missing keywords based on general job trends, 
-    and suggest improvements.
-
-    Resume Text:
-    {text}
-
-    Your response should be in this structured format:
-    - Resume Rating: (score out of 10)
-    - Missing Keywords: (comma-separated list)
-    - Suggestions for Improvement: (bullet points)
-    """
-
-    response = openai.ChatCompletion.create(
-        model="gpt-4",
-        messages=[{"role": "user", "content": prompt}]
-    )
-    return response["choices"][0]["message"]["content"]
+### Response Format:
+1️⃣ **Resume Rating:** (Score out of 10)
+2️⃣ **Missing Keywords:** (Comma-separated list)
+3️⃣ **Suggested Skills:** (Bullet points)
+4️⃣ **Expert Improvement Tips:** (Clear and actionable advice)
+"""
 
 # Streamlit UI
-st.title("📝 AI-Powered Resume Analyzer")
-st.write("Upload your resume, and AI will provide feedback to improve it!")
+st.title("📄 AI-Powered Resume Analyzer 🤖")
+st.write("Upload your resume, and AI will analyze it for improvements!")
 
-uploaded_file = st.file_uploader("Upload your Resume (PDF format)", type=["pdf"])
+# File Uploader for PDF
+uploaded_file = st.file_uploader("Upload Your Resume (PDF)", type=["pdf"])
 
 if uploaded_file is not None:
-    with st.spinner("Processing your resume..."):
-        resume_text = extract_text_from_pdf(uploaded_file)
-        
-        if resume_text:
-            keywords = extract_keywords(resume_text)
-            analysis_result = analyze_resume(resume_text)
-
-            st.subheader("🔍 Resume Analysis Report")
-            st.write(analysis_result)
-
-            st.subheader("📌 Extracted Keywords")
-            st.write(", ".join(keywords))
-
-            st.success("✅ Resume analyzed successfully!")
-        else:
-            st.error("Could not extract text from the PDF. Please try another file.")
-
+    with st.spinner("Analyzing your resume..."):
+        resume_text = uploaded_file.read().decode("utf-8")  # Decode PDF text
+        user_message = f"Resume Content:\n{resume_text}\n\nAnalyze the resume based on the given criteria."
+
+        # Send request to Groq API
+        completion = client.chat.completions.create(
+            model="deepseek-r1-distill-llama-70b",
+            messages=[
+                {"role": "system", "content": system_prompt},
+                {"role": "user", "content": user_message},
+            ],
+            temperature=0.6,
+            max_tokens=4096,
+            top_p=0.95,
+            stream=True,
+        )
+
+        # Stream response
+        st.subheader("💡 Resume Analysis")
+        full_response = ""
+        for chunk in completion:
+            chunk_text = chunk.choices[0].delta.content or ""
+            full_response += chunk_text
+            st.write(chunk_text)
+
+        # Display final response
+        st.success("✅ Resume analyzed successfully!")