Create app.py

app.py

@@ -0,0 +1,78 @@
+import gradio as gr
+import pandas as pd
+from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
+from sentence_transformers import SentenceTransformer
+import faiss
+import torch
+
+# -------------------------------
+# Load dataset
+# -------------------------------
+file_path = "marketing-campaigns.csv"
+df = pd.read_csv(file_path)
+
+# Combine text for embeddings
+df = df.dropna(subset=["campaign_name", "description"])
+df["text"] = df["campaign_name"] + ": " + df["description"]
+
+# -------------------------------
+# Embeddings + FAISS index
+# -------------------------------
+embed_model = SentenceTransformer("all-MiniLM-L6-v2")
+
+embeddings = embed_model.encode(df["text"].tolist(), convert_to_tensor=True, show_progress_bar=True)
+embeddings_np = embeddings.detach().cpu().numpy()
+
+# Build FAISS index
+d = embeddings_np.shape[1]
+index = faiss.IndexFlatL2(d)
+index.add(embeddings_np)
+
+# -------------------------------
+# Load LLM (Phi-4-mini)
+# -------------------------------
+model_name = "microsoft/phi-4-mini"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float32, device_map="auto")
+
+# -------------------------------
+# RAG functions
+# -------------------------------
+def retrieve_context(query, k=3):
+    query_vec = embed_model.encode([query], convert_to_tensor=True).cpu().numpy()
+    D, I = index.search(query_vec, k)
+    results = [df.iloc[i]["text"] for i in I[0]]
+    return results
+
+def generate_with_rag(prompt):
+    # Step 1: Retrieve top campaigns
+    context = retrieve_context(prompt, k=3)
+    context_str = "\n".join(context)
+
+    # Step 2: Build final prompt
+    rag_prompt = f"""
+    You are an AI marketing assistant. 
+    Here are some past campaigns for reference:\n{context_str}\n
+    Based on these, generate a new campaign idea for: {prompt}
+    """
+
+    # Step 3: Generate with Phi-4
+    inputs = tokenizer(rag_prompt, return_tensors="pt").to(model.device)
+    outputs = model.generate(**inputs, max_length=200, temperature=0.7, top_p=0.9)
+    return tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+# -------------------------------
+# Gradio UI
+# -------------------------------
+with gr.Blocks() as demo:
+    gr.Markdown("## 🤖 RAG-powered AI Marketing Campaign Generator")
+
+    with gr.Row():
+        query = gr.Textbox(label="Enter campaign idea or analysis query")
+        output = gr.Textbox(label="Generated Campaign")
+        btn = gr.Button("Generate with RAG")
+
+    btn.click(generate_with_rag, inputs=query, outputs=output)
+
+if __name__ == "__main__":
+    demo.launch()