Create app.py

app.py

@@ -0,0 +1,63 @@
+import streamlit as st
+from groq import Groq
+from sentence_transformers import SentenceTransformer
+import faiss
+import numpy as np
+import os
+from dotenv import load_dotenv
+
+load_dotenv()
+
+# Load API key from .env or Hugging Face secret
+GROQ_API_KEY = os.getenv("GROQ_API_KEY")
+
+# Initialize Groq client
+groq_client = Groq(api_key=GROQ_API_KEY)
+
+# Sample knowledge base
+docs = [
+    "Generative Engine Optimization improves AI answers for SEO.",
+    "RAG combines retrieval with generation for accurate responses.",
+    "Groq provides ultra-fast inference for LLMs.",
+    "Streamlit is great for building quick ML apps.",
+    "Hugging Face offers powerful transformer models and APIs."
+]
+
+# Load embedding model
+embed_model = SentenceTransformer("all-MiniLM-L6-v2")
+doc_embeddings = embed_model.encode(docs)
+
+# Create FAISS index
+index = faiss.IndexFlatL2(doc_embeddings.shape[1])
+index.add(np.array(doc_embeddings))
+
+# Streamlit UI
+st.set_page_config(page_title="GEO Optimizer MVP", layout="centered")
+st.title("🔍 GEO Optimization Assistant")
+
+query = st.text_input("Ask a question or enter a topic:")
+if st.button("Generate Answer") and query:
+    query_embedding = embed_model.encode([query])
+    _, I = index.search(np.array(query_embedding), k=2)
+
+    context = "\n".join([docs[i] for i in I[0]])
+
+    prompt = f"""You are a helpful assistant. Use the following context to answer the question.
+    
+    Context:
+    {context}
+    
+    Question: {query}
+    
+    Answer:"""
+
+    try:
+        response = groq_client.chat.completions.create(
+            model="llama3-8b-8192",  # or whatever is available
+            messages=[{"role": "user", "content": prompt}]
+        )
+        answer = response.choices[0].message.content
+        st.markdown("### ✅ Answer")
+        st.success(answer)
+    except Exception as e:
+        st.error(f"Error: {str(e)}")