Update app.py

app.py

@@ -1,6 +1,6 @@
 import gradio as gr
 import pandas as pd
-from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
+from transformers import AutoTokenizer, AutoModelForCausalLM
 from sentence_transformers import SentenceTransformer
 import faiss
 import torch
@@ -11,19 +11,23 @@ import torch
 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"]
+# Flexible column handling
+if "description" in df.columns:
+    df = df.dropna(subset=["campaign_name", "description"])
+    df["text"] = df["campaign_name"].astype(str) + ": " + df["description"].astype(str)
+elif "campaign_name" in df.columns:
+    df = df.dropna(subset=["campaign_name"])
+    df["text"] = df["campaign_name"].astype(str)
+else:
+    raise ValueError("CSV must contain at least a 'campaign_name' column")
 
 # -------------------------------
-# Embeddings + FAISS index
+# Embeddings + FAISS
 # -------------------------------
 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)
@@ -45,18 +49,15 @@ def retrieve_context(query, k=3):
     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. 
+    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}
+    Based on these, generate a new creative 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)
@@ -68,7 +69,7 @@ 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")
+        query = gr.Textbox(label="Enter campaign idea or keyword")
         output = gr.Textbox(label="Generated Campaign")
         btn = gr.Button("Generate with RAG")