Spaces:
Running
Running
File size: 2,836 Bytes
9bdbf71 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 |
import os
import torch
import pandas as pd
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
# Load model
model_name = "google/flan-t5-small"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
# Load all product CSVs from nested directories
def load_all_product_data(base_path="data"):
all_data = []
for root, dirs, files in os.walk(base_path):
for file in files:
if file.endswith(".csv"):
full_path = os.path.join(root, file)
df = pd.read_csv(full_path)
df["Brand"] = os.path.splitext(file)[0]
df["Store"] = root.split(os.sep)[-4] # e.g., "Store C"
df["Category"] = root.split(os.sep)[-2]
all_data.append(df)
return pd.concat(all_data, ignore_index=True)
df = load_all_product_data("data")
# Generate smart suggestion
def generate_product_description(prompt):
prompt = prompt.lower()
# Basic price filter
price_limit = 99999
if "under" in prompt:
try:
price_limit = int(prompt.split("under")[-1].split()[0])
except:
pass
filtered_df = df[df["Price"] <= price_limit]
filtered_df = filtered_df[df["In Stock"].str.lower() == "yes"]
if "dry hair" in prompt:
filtered_df = filtered_df[filtered_df["Hair Type"].str.lower().str.contains("dry", na=False)]
elif "oily hair" in prompt:
filtered_df = filtered_df[filtered_df["Hair Type"].str.lower().str.contains("oily", na=False)]
elif "normal hair" in prompt:
filtered_df = filtered_df[filtered_df["Hair Type"].str.lower().str.contains("normal", na=False)]
if "gift" in prompt:
filtered_df = filtered_df[filtered_df["Tags"].str.contains("gift", case=False, na=False)]
if "budget" in prompt:
filtered_df = filtered_df[filtered_df["Tags"].str.contains("budget", case=False, na=False)]
if filtered_df.empty:
return "🤷 Sorry, no matching suggestions found."
rows = []
for _, row in filtered_df.iterrows():
line = f"{row['Brand']} {row['Quantity']} – ₹{row['Price']} (Floor {row['Floor']}, Aisle {row['Aisle']})"
if pd.notna(row.get("Offer")) and str(row["Offer"]).strip():
line += f"\n🎉 {row['Offer']}"
rows.append(line)
product_text = "\n".join(rows)
model_prompt = f"Suggest top products:\n{product_text}"
input_ids = tokenizer(model_prompt, return_tensors="pt").input_ids
with torch.no_grad():
output_ids = model.generate(input_ids, max_new_tokens=100)
response = tokenizer.decode(output_ids[0], skip_special_tokens=True)
# Combine product suggestions and model response line by line
return "\n\n".join(rows[:5]) + "\n\n🧠 AI Suggestion: " + response
|