Create app.py

app.py

@@ -0,0 +1,70 @@
+%%writefile app.py
+import streamlit as st
+import os
+import faiss
+import numpy as np
+import PyPDF2
+from sentence_transformers import SentenceTransformer
+from groq import Groq
+
+# Set Groq API key
+GROQ_API_KEY = "your-groq-api-key"
+groq_client = Groq(api_key=GROQ_API_KEY)
+embedder = SentenceTransformer("all-MiniLM-L6-v2")
+
+# Example job descriptions
+job_data = {
+    "Data Scientist": "Python, Machine Learning, Data Analysis, Pandas, Scikit-learn, SQL",
+    "Software Engineer": "C++, Java, Git, Object Oriented Programming, System Design",
+    "Web Developer": "HTML, CSS, JavaScript, React, Responsive Design, Web APIs"
+}
+job_chunks = [f"{k}: {v}" for k, v in job_data.items()]
+job_embeddings = embedder.encode(job_chunks)
+faiss_index = faiss.IndexFlatL2(job_embeddings.shape[1])
+faiss_index.add(np.array(job_embeddings).astype("float32"))
+
+# ----------- Functions -----------
+def extract_text_from_pdf(uploaded_file):
+    reader = PyPDF2.PdfReader(uploaded_file)
+    return " ".join([page.extract_text() for page in reader.pages if page.extract_text()])
+
+def find_best_job_match(resume_text):
+    query_embed = embedder.encode([resume_text])
+    _, indices = faiss_index.search(np.array(query_embed).astype("float32"), 1)
+    return job_chunks[indices[0][0]]
+
+def query_llm(context, question):
+    prompt = f"""You are an expert job coach. Based on the resume below and the job context:
+    
+Context: {context}
+
+Resume: {question}
+
+Give a simple analysis of how well this resume fits and what's missing."""
+    
+    response = groq_client.chat.completions.create(
+        model="llama-3-8b-8192",
+        messages=[{"role": "user", "content": prompt}]
+    )
+    return response.choices[0].message.content
+
+# ----------- Streamlit UI -----------
+st.set_page_config(page_title="🧠 Resume Analyzer + Job Match AI")
+st.title("📄 Resume Analyzer + Job Match AI")
+
+uploaded_file = st.file_uploader("Upload Your Resume (PDF)", type=["pdf"])
+if uploaded_file:
+    resume_text = extract_text_from_pdf(uploaded_file)
+    st.success("Resume Uploaded Successfully!")
+    
+    st.subheader("💼 Analyzing for Job Match...")
+    best_job = find_best_job_match(resume_text)
+    st.write(f"🔍 Best Job Match Found: **{best_job}**")
+    
+    with st.spinner("Analyzing Resume Fit..."):
+        response = query_llm(best_job, resume_text)
+    
+    st.subheader("🧾 AI Feedback:")
+    st.write(response)
+
+st.info("This app is for guidance only. Tailor your resume per job posting!")