Spaces:
Paused
Paused
Create create_knowledge_base.py
Browse files- create_knowledge_base.py +29 -0
create_knowledge_base.py
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import pandas as pd
|
| 2 |
+
|
| 3 |
+
import numpy as np
|
| 4 |
+
|
| 5 |
+
from sentence_transformers import SentenceTransformer
|
| 6 |
+
|
| 7 |
+
import faiss
|
| 8 |
+
|
| 9 |
+
import pickle
|
| 10 |
+
|
| 11 |
+
from datasets import load_dataset
|
| 12 |
+
|
| 13 |
+
import os
|
| 14 |
+
|
| 15 |
+
|
| 16 |
+
|
| 17 |
+
# Write the code below
|
| 18 |
+
def create_ecommerce_knowledge_base() {
|
| 19 |
+
print("Loading Bitext e-commerce dataset...")
|
| 20 |
+
# Load the dataset
|
| 21 |
+
dataset = load_dataset("bitext/Bitext-customer-support-llm-chatbot-training-dataset")
|
| 22 |
+
print(f"Dataset loaded: {len(dataset['train'])} examples")
|
| 23 |
+
}
|
| 24 |
+
|
| 25 |
+
# Don't remove the following code
|
| 26 |
+
|
| 27 |
+
if __name__ == "__main__":
|
| 28 |
+
|
| 29 |
+
create_ecommerce_knowledge_base()
|