Spaces:
Sleeping
Sleeping
Created using Colaboratory
Browse files
notebooks/05-Improve_Prompts_+_Add_Source.ipynb
ADDED
@@ -0,0 +1,1901 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"nbformat": 4,
|
3 |
+
"nbformat_minor": 0,
|
4 |
+
"metadata": {
|
5 |
+
"colab": {
|
6 |
+
"provenance": [],
|
7 |
+
"authorship_tag": "ABX9TyP+qPbomvCsKc9OqQJcj+gS",
|
8 |
+
"include_colab_link": true
|
9 |
+
},
|
10 |
+
"kernelspec": {
|
11 |
+
"name": "python3",
|
12 |
+
"display_name": "Python 3"
|
13 |
+
},
|
14 |
+
"language_info": {
|
15 |
+
"name": "python"
|
16 |
+
},
|
17 |
+
"widgets": {
|
18 |
+
"application/vnd.jupyter.widget-state+json": {
|
19 |
+
"88b29c392c7d403488f81903b2395dc1": {
|
20 |
+
"model_module": "@jupyter-widgets/controls",
|
21 |
+
"model_name": "HBoxModel",
|
22 |
+
"model_module_version": "1.5.0",
|
23 |
+
"state": {
|
24 |
+
"_dom_classes": [],
|
25 |
+
"_model_module": "@jupyter-widgets/controls",
|
26 |
+
"_model_module_version": "1.5.0",
|
27 |
+
"_model_name": "HBoxModel",
|
28 |
+
"_view_count": null,
|
29 |
+
"_view_module": "@jupyter-widgets/controls",
|
30 |
+
"_view_module_version": "1.5.0",
|
31 |
+
"_view_name": "HBoxView",
|
32 |
+
"box_style": "",
|
33 |
+
"children": [
|
34 |
+
"IPY_MODEL_81d6771d5cc74dd49cfccc362d5a3c87",
|
35 |
+
"IPY_MODEL_1a021f3baf754210ac8696ecc555d968",
|
36 |
+
"IPY_MODEL_35d8b3afc94b4294ac0d5b090a49003c"
|
37 |
+
],
|
38 |
+
"layout": "IPY_MODEL_2980851a0f0141fcb4b54aba07366ad9"
|
39 |
+
}
|
40 |
+
},
|
41 |
+
"81d6771d5cc74dd49cfccc362d5a3c87": {
|
42 |
+
"model_module": "@jupyter-widgets/controls",
|
43 |
+
"model_name": "HTMLModel",
|
44 |
+
"model_module_version": "1.5.0",
|
45 |
+
"state": {
|
46 |
+
"_dom_classes": [],
|
47 |
+
"_model_module": "@jupyter-widgets/controls",
|
48 |
+
"_model_module_version": "1.5.0",
|
49 |
+
"_model_name": "HTMLModel",
|
50 |
+
"_view_count": null,
|
51 |
+
"_view_module": "@jupyter-widgets/controls",
|
52 |
+
"_view_module_version": "1.5.0",
|
53 |
+
"_view_name": "HTMLView",
|
54 |
+
"description": "",
|
55 |
+
"description_tooltip": null,
|
56 |
+
"layout": "IPY_MODEL_553d09bfb9bc4ceeb0882d5bd6061514",
|
57 |
+
"placeholder": "β",
|
58 |
+
"style": "IPY_MODEL_13d692f33c85490aaf761d9444f6c145",
|
59 |
+
"value": "Parsing nodes: 100%"
|
60 |
+
}
|
61 |
+
},
|
62 |
+
"1a021f3baf754210ac8696ecc555d968": {
|
63 |
+
"model_module": "@jupyter-widgets/controls",
|
64 |
+
"model_name": "FloatProgressModel",
|
65 |
+
"model_module_version": "1.5.0",
|
66 |
+
"state": {
|
67 |
+
"_dom_classes": [],
|
68 |
+
"_model_module": "@jupyter-widgets/controls",
|
69 |
+
"_model_module_version": "1.5.0",
|
70 |
+
"_model_name": "FloatProgressModel",
|
71 |
+
"_view_count": null,
|
72 |
+
"_view_module": "@jupyter-widgets/controls",
|
73 |
+
"_view_module_version": "1.5.0",
|
74 |
+
"_view_name": "ProgressView",
|
75 |
+
"bar_style": "success",
|
76 |
+
"description": "",
|
77 |
+
"description_tooltip": null,
|
78 |
+
"layout": "IPY_MODEL_a3f4c5eb33a64fe895d19a5a52426000",
|
79 |
+
"max": 14,
|
80 |
+
"min": 0,
|
81 |
+
"orientation": "horizontal",
|
82 |
+
"style": "IPY_MODEL_5b0afc9227e6437ca4ca7a4929f47d7a",
|
83 |
+
"value": 14
|
84 |
+
}
|
85 |
+
},
|
86 |
+
"35d8b3afc94b4294ac0d5b090a49003c": {
|
87 |
+
"model_module": "@jupyter-widgets/controls",
|
88 |
+
"model_name": "HTMLModel",
|
89 |
+
"model_module_version": "1.5.0",
|
90 |
+
"state": {
|
91 |
+
"_dom_classes": [],
|
92 |
+
"_model_module": "@jupyter-widgets/controls",
|
93 |
+
"_model_module_version": "1.5.0",
|
94 |
+
"_model_name": "HTMLModel",
|
95 |
+
"_view_count": null,
|
96 |
+
"_view_module": "@jupyter-widgets/controls",
|
97 |
+
"_view_module_version": "1.5.0",
|
98 |
+
"_view_name": "HTMLView",
|
99 |
+
"description": "",
|
100 |
+
"description_tooltip": null,
|
101 |
+
"layout": "IPY_MODEL_39e87e82d7604abfa03879003898259f",
|
102 |
+
"placeholder": "β",
|
103 |
+
"style": "IPY_MODEL_e876a66432c24d39a4630601d0f4ce93",
|
104 |
+
"value": " 14/14 [00:00<00:00, 18.38it/s]"
|
105 |
+
}
|
106 |
+
},
|
107 |
+
"2980851a0f0141fcb4b54aba07366ad9": {
|
108 |
+
"model_module": "@jupyter-widgets/base",
|
109 |
+
"model_name": "LayoutModel",
|
110 |
+
"model_module_version": "1.2.0",
|
111 |
+
"state": {
|
112 |
+
"_model_module": "@jupyter-widgets/base",
|
113 |
+
"_model_module_version": "1.2.0",
|
114 |
+
"_model_name": "LayoutModel",
|
115 |
+
"_view_count": null,
|
116 |
+
"_view_module": "@jupyter-widgets/base",
|
117 |
+
"_view_module_version": "1.2.0",
|
118 |
+
"_view_name": "LayoutView",
|
119 |
+
"align_content": null,
|
120 |
+
"align_items": null,
|
121 |
+
"align_self": null,
|
122 |
+
"border": null,
|
123 |
+
"bottom": null,
|
124 |
+
"display": null,
|
125 |
+
"flex": null,
|
126 |
+
"flex_flow": null,
|
127 |
+
"grid_area": null,
|
128 |
+
"grid_auto_columns": null,
|
129 |
+
"grid_auto_flow": null,
|
130 |
+
"grid_auto_rows": null,
|
131 |
+
"grid_column": null,
|
132 |
+
"grid_gap": null,
|
133 |
+
"grid_row": null,
|
134 |
+
"grid_template_areas": null,
|
135 |
+
"grid_template_columns": null,
|
136 |
+
"grid_template_rows": null,
|
137 |
+
"height": null,
|
138 |
+
"justify_content": null,
|
139 |
+
"justify_items": null,
|
140 |
+
"left": null,
|
141 |
+
"margin": null,
|
142 |
+
"max_height": null,
|
143 |
+
"max_width": null,
|
144 |
+
"min_height": null,
|
145 |
+
"min_width": null,
|
146 |
+
"object_fit": null,
|
147 |
+
"object_position": null,
|
148 |
+
"order": null,
|
149 |
+
"overflow": null,
|
150 |
+
"overflow_x": null,
|
151 |
+
"overflow_y": null,
|
152 |
+
"padding": null,
|
153 |
+
"right": null,
|
154 |
+
"top": null,
|
155 |
+
"visibility": null,
|
156 |
+
"width": null
|
157 |
+
}
|
158 |
+
},
|
159 |
+
"553d09bfb9bc4ceeb0882d5bd6061514": {
|
160 |
+
"model_module": "@jupyter-widgets/base",
|
161 |
+
"model_name": "LayoutModel",
|
162 |
+
"model_module_version": "1.2.0",
|
163 |
+
"state": {
|
164 |
+
"_model_module": "@jupyter-widgets/base",
|
165 |
+
"_model_module_version": "1.2.0",
|
166 |
+
"_model_name": "LayoutModel",
|
167 |
+
"_view_count": null,
|
168 |
+
"_view_module": "@jupyter-widgets/base",
|
169 |
+
"_view_module_version": "1.2.0",
|
170 |
+
"_view_name": "LayoutView",
|
171 |
+
"align_content": null,
|
172 |
+
"align_items": null,
|
173 |
+
"align_self": null,
|
174 |
+
"border": null,
|
175 |
+
"bottom": null,
|
176 |
+
"display": null,
|
177 |
+
"flex": null,
|
178 |
+
"flex_flow": null,
|
179 |
+
"grid_area": null,
|
180 |
+
"grid_auto_columns": null,
|
181 |
+
"grid_auto_flow": null,
|
182 |
+
"grid_auto_rows": null,
|
183 |
+
"grid_column": null,
|
184 |
+
"grid_gap": null,
|
185 |
+
"grid_row": null,
|
186 |
+
"grid_template_areas": null,
|
187 |
+
"grid_template_columns": null,
|
188 |
+
"grid_template_rows": null,
|
189 |
+
"height": null,
|
190 |
+
"justify_content": null,
|
191 |
+
"justify_items": null,
|
192 |
+
"left": null,
|
193 |
+
"margin": null,
|
194 |
+
"max_height": null,
|
195 |
+
"max_width": null,
|
196 |
+
"min_height": null,
|
197 |
+
"min_width": null,
|
198 |
+
"object_fit": null,
|
199 |
+
"object_position": null,
|
200 |
+
"order": null,
|
201 |
+
"overflow": null,
|
202 |
+
"overflow_x": null,
|
203 |
+
"overflow_y": null,
|
204 |
+
"padding": null,
|
205 |
+
"right": null,
|
206 |
+
"top": null,
|
207 |
+
"visibility": null,
|
208 |
+
"width": null
|
209 |
+
}
|
210 |
+
},
|
211 |
+
"13d692f33c85490aaf761d9444f6c145": {
|
212 |
+
"model_module": "@jupyter-widgets/controls",
|
213 |
+
"model_name": "DescriptionStyleModel",
|
214 |
+
"model_module_version": "1.5.0",
|
215 |
+
"state": {
|
216 |
+
"_model_module": "@jupyter-widgets/controls",
|
217 |
+
"_model_module_version": "1.5.0",
|
218 |
+
"_model_name": "DescriptionStyleModel",
|
219 |
+
"_view_count": null,
|
220 |
+
"_view_module": "@jupyter-widgets/base",
|
221 |
+
"_view_module_version": "1.2.0",
|
222 |
+
"_view_name": "StyleView",
|
223 |
+
"description_width": ""
|
224 |
+
}
|
225 |
+
},
|
226 |
+
"a3f4c5eb33a64fe895d19a5a52426000": {
|
227 |
+
"model_module": "@jupyter-widgets/base",
|
228 |
+
"model_name": "LayoutModel",
|
229 |
+
"model_module_version": "1.2.0",
|
230 |
+
"state": {
|
231 |
+
"_model_module": "@jupyter-widgets/base",
|
232 |
+
"_model_module_version": "1.2.0",
|
233 |
+
"_model_name": "LayoutModel",
|
234 |
+
"_view_count": null,
|
235 |
+
"_view_module": "@jupyter-widgets/base",
|
236 |
+
"_view_module_version": "1.2.0",
|
237 |
+
"_view_name": "LayoutView",
|
238 |
+
"align_content": null,
|
239 |
+
"align_items": null,
|
240 |
+
"align_self": null,
|
241 |
+
"border": null,
|
242 |
+
"bottom": null,
|
243 |
+
"display": null,
|
244 |
+
"flex": null,
|
245 |
+
"flex_flow": null,
|
246 |
+
"grid_area": null,
|
247 |
+
"grid_auto_columns": null,
|
248 |
+
"grid_auto_flow": null,
|
249 |
+
"grid_auto_rows": null,
|
250 |
+
"grid_column": null,
|
251 |
+
"grid_gap": null,
|
252 |
+
"grid_row": null,
|
253 |
+
"grid_template_areas": null,
|
254 |
+
"grid_template_columns": null,
|
255 |
+
"grid_template_rows": null,
|
256 |
+
"height": null,
|
257 |
+
"justify_content": null,
|
258 |
+
"justify_items": null,
|
259 |
+
"left": null,
|
260 |
+
"margin": null,
|
261 |
+
"max_height": null,
|
262 |
+
"max_width": null,
|
263 |
+
"min_height": null,
|
264 |
+
"min_width": null,
|
265 |
+
"object_fit": null,
|
266 |
+
"object_position": null,
|
267 |
+
"order": null,
|
268 |
+
"overflow": null,
|
269 |
+
"overflow_x": null,
|
270 |
+
"overflow_y": null,
|
271 |
+
"padding": null,
|
272 |
+
"right": null,
|
273 |
+
"top": null,
|
274 |
+
"visibility": null,
|
275 |
+
"width": null
|
276 |
+
}
|
277 |
+
},
|
278 |
+
"5b0afc9227e6437ca4ca7a4929f47d7a": {
|
279 |
+
"model_module": "@jupyter-widgets/controls",
|
280 |
+
"model_name": "ProgressStyleModel",
|
281 |
+
"model_module_version": "1.5.0",
|
282 |
+
"state": {
|
283 |
+
"_model_module": "@jupyter-widgets/controls",
|
284 |
+
"_model_module_version": "1.5.0",
|
285 |
+
"_model_name": "ProgressStyleModel",
|
286 |
+
"_view_count": null,
|
287 |
+
"_view_module": "@jupyter-widgets/base",
|
288 |
+
"_view_module_version": "1.2.0",
|
289 |
+
"_view_name": "StyleView",
|
290 |
+
"bar_color": null,
|
291 |
+
"description_width": ""
|
292 |
+
}
|
293 |
+
},
|
294 |
+
"39e87e82d7604abfa03879003898259f": {
|
295 |
+
"model_module": "@jupyter-widgets/base",
|
296 |
+
"model_name": "LayoutModel",
|
297 |
+
"model_module_version": "1.2.0",
|
298 |
+
"state": {
|
299 |
+
"_model_module": "@jupyter-widgets/base",
|
300 |
+
"_model_module_version": "1.2.0",
|
301 |
+
"_model_name": "LayoutModel",
|
302 |
+
"_view_count": null,
|
303 |
+
"_view_module": "@jupyter-widgets/base",
|
304 |
+
"_view_module_version": "1.2.0",
|
305 |
+
"_view_name": "LayoutView",
|
306 |
+
"align_content": null,
|
307 |
+
"align_items": null,
|
308 |
+
"align_self": null,
|
309 |
+
"border": null,
|
310 |
+
"bottom": null,
|
311 |
+
"display": null,
|
312 |
+
"flex": null,
|
313 |
+
"flex_flow": null,
|
314 |
+
"grid_area": null,
|
315 |
+
"grid_auto_columns": null,
|
316 |
+
"grid_auto_flow": null,
|
317 |
+
"grid_auto_rows": null,
|
318 |
+
"grid_column": null,
|
319 |
+
"grid_gap": null,
|
320 |
+
"grid_row": null,
|
321 |
+
"grid_template_areas": null,
|
322 |
+
"grid_template_columns": null,
|
323 |
+
"grid_template_rows": null,
|
324 |
+
"height": null,
|
325 |
+
"justify_content": null,
|
326 |
+
"justify_items": null,
|
327 |
+
"left": null,
|
328 |
+
"margin": null,
|
329 |
+
"max_height": null,
|
330 |
+
"max_width": null,
|
331 |
+
"min_height": null,
|
332 |
+
"min_width": null,
|
333 |
+
"object_fit": null,
|
334 |
+
"object_position": null,
|
335 |
+
"order": null,
|
336 |
+
"overflow": null,
|
337 |
+
"overflow_x": null,
|
338 |
+
"overflow_y": null,
|
339 |
+
"padding": null,
|
340 |
+
"right": null,
|
341 |
+
"top": null,
|
342 |
+
"visibility": null,
|
343 |
+
"width": null
|
344 |
+
}
|
345 |
+
},
|
346 |
+
"e876a66432c24d39a4630601d0f4ce93": {
|
347 |
+
"model_module": "@jupyter-widgets/controls",
|
348 |
+
"model_name": "DescriptionStyleModel",
|
349 |
+
"model_module_version": "1.5.0",
|
350 |
+
"state": {
|
351 |
+
"_model_module": "@jupyter-widgets/controls",
|
352 |
+
"_model_module_version": "1.5.0",
|
353 |
+
"_model_name": "DescriptionStyleModel",
|
354 |
+
"_view_count": null,
|
355 |
+
"_view_module": "@jupyter-widgets/base",
|
356 |
+
"_view_module_version": "1.2.0",
|
357 |
+
"_view_name": "StyleView",
|
358 |
+
"description_width": ""
|
359 |
+
}
|
360 |
+
},
|
361 |
+
"f67382c8ddf248c4b4eeb1b596284917": {
|
362 |
+
"model_module": "@jupyter-widgets/controls",
|
363 |
+
"model_name": "HBoxModel",
|
364 |
+
"model_module_version": "1.5.0",
|
365 |
+
"state": {
|
366 |
+
"_dom_classes": [],
|
367 |
+
"_model_module": "@jupyter-widgets/controls",
|
368 |
+
"_model_module_version": "1.5.0",
|
369 |
+
"_model_name": "HBoxModel",
|
370 |
+
"_view_count": null,
|
371 |
+
"_view_module": "@jupyter-widgets/controls",
|
372 |
+
"_view_module_version": "1.5.0",
|
373 |
+
"_view_name": "HBoxView",
|
374 |
+
"box_style": "",
|
375 |
+
"children": [
|
376 |
+
"IPY_MODEL_61ebc39888444d448f624f1ae848646a",
|
377 |
+
"IPY_MODEL_a692807d09ba4ea89bfdae50821ee518",
|
378 |
+
"IPY_MODEL_7fbeb4bc3ea743168a1816b0021e092b"
|
379 |
+
],
|
380 |
+
"layout": "IPY_MODEL_ac3c4e3c9b0c4703b5a9148a70c23e21"
|
381 |
+
}
|
382 |
+
},
|
383 |
+
"61ebc39888444d448f624f1ae848646a": {
|
384 |
+
"model_module": "@jupyter-widgets/controls",
|
385 |
+
"model_name": "HTMLModel",
|
386 |
+
"model_module_version": "1.5.0",
|
387 |
+
"state": {
|
388 |
+
"_dom_classes": [],
|
389 |
+
"_model_module": "@jupyter-widgets/controls",
|
390 |
+
"_model_module_version": "1.5.0",
|
391 |
+
"_model_name": "HTMLModel",
|
392 |
+
"_view_count": null,
|
393 |
+
"_view_module": "@jupyter-widgets/controls",
|
394 |
+
"_view_module_version": "1.5.0",
|
395 |
+
"_view_name": "HTMLView",
|
396 |
+
"description": "",
|
397 |
+
"description_tooltip": null,
|
398 |
+
"layout": "IPY_MODEL_165ccb061bb843a4b44896df7b4d15b0",
|
399 |
+
"placeholder": "β",
|
400 |
+
"style": "IPY_MODEL_f1a9031e7c3445ee80308888d28f2d66",
|
401 |
+
"value": "Generating embeddings: 100%"
|
402 |
+
}
|
403 |
+
},
|
404 |
+
"a692807d09ba4ea89bfdae50821ee518": {
|
405 |
+
"model_module": "@jupyter-widgets/controls",
|
406 |
+
"model_name": "FloatProgressModel",
|
407 |
+
"model_module_version": "1.5.0",
|
408 |
+
"state": {
|
409 |
+
"_dom_classes": [],
|
410 |
+
"_model_module": "@jupyter-widgets/controls",
|
411 |
+
"_model_module_version": "1.5.0",
|
412 |
+
"_model_name": "FloatProgressModel",
|
413 |
+
"_view_count": null,
|
414 |
+
"_view_module": "@jupyter-widgets/controls",
|
415 |
+
"_view_module_version": "1.5.0",
|
416 |
+
"_view_name": "ProgressView",
|
417 |
+
"bar_style": "success",
|
418 |
+
"description": "",
|
419 |
+
"description_tooltip": null,
|
420 |
+
"layout": "IPY_MODEL_b15acb0416594d44a41df804e42b4cdf",
|
421 |
+
"max": 108,
|
422 |
+
"min": 0,
|
423 |
+
"orientation": "horizontal",
|
424 |
+
"style": "IPY_MODEL_4aeb5362822f490aa6cff491dded8111",
|
425 |
+
"value": 108
|
426 |
+
}
|
427 |
+
},
|
428 |
+
"7fbeb4bc3ea743168a1816b0021e092b": {
|
429 |
+
"model_module": "@jupyter-widgets/controls",
|
430 |
+
"model_name": "HTMLModel",
|
431 |
+
"model_module_version": "1.5.0",
|
432 |
+
"state": {
|
433 |
+
"_dom_classes": [],
|
434 |
+
"_model_module": "@jupyter-widgets/controls",
|
435 |
+
"_model_module_version": "1.5.0",
|
436 |
+
"_model_name": "HTMLModel",
|
437 |
+
"_view_count": null,
|
438 |
+
"_view_module": "@jupyter-widgets/controls",
|
439 |
+
"_view_module_version": "1.5.0",
|
440 |
+
"_view_name": "HTMLView",
|
441 |
+
"description": "",
|
442 |
+
"description_tooltip": null,
|
443 |
+
"layout": "IPY_MODEL_faa803d16fc74ddcbb003485a506569c",
|
444 |
+
"placeholder": "β",
|
445 |
+
"style": "IPY_MODEL_4f09405744b04ba79ecb18398b49a389",
|
446 |
+
"value": " 108/108 [00:06<00:00, 23.93it/s]"
|
447 |
+
}
|
448 |
+
},
|
449 |
+
"ac3c4e3c9b0c4703b5a9148a70c23e21": {
|
450 |
+
"model_module": "@jupyter-widgets/base",
|
451 |
+
"model_name": "LayoutModel",
|
452 |
+
"model_module_version": "1.2.0",
|
453 |
+
"state": {
|
454 |
+
"_model_module": "@jupyter-widgets/base",
|
455 |
+
"_model_module_version": "1.2.0",
|
456 |
+
"_model_name": "LayoutModel",
|
457 |
+
"_view_count": null,
|
458 |
+
"_view_module": "@jupyter-widgets/base",
|
459 |
+
"_view_module_version": "1.2.0",
|
460 |
+
"_view_name": "LayoutView",
|
461 |
+
"align_content": null,
|
462 |
+
"align_items": null,
|
463 |
+
"align_self": null,
|
464 |
+
"border": null,
|
465 |
+
"bottom": null,
|
466 |
+
"display": null,
|
467 |
+
"flex": null,
|
468 |
+
"flex_flow": null,
|
469 |
+
"grid_area": null,
|
470 |
+
"grid_auto_columns": null,
|
471 |
+
"grid_auto_flow": null,
|
472 |
+
"grid_auto_rows": null,
|
473 |
+
"grid_column": null,
|
474 |
+
"grid_gap": null,
|
475 |
+
"grid_row": null,
|
476 |
+
"grid_template_areas": null,
|
477 |
+
"grid_template_columns": null,
|
478 |
+
"grid_template_rows": null,
|
479 |
+
"height": null,
|
480 |
+
"justify_content": null,
|
481 |
+
"justify_items": null,
|
482 |
+
"left": null,
|
483 |
+
"margin": null,
|
484 |
+
"max_height": null,
|
485 |
+
"max_width": null,
|
486 |
+
"min_height": null,
|
487 |
+
"min_width": null,
|
488 |
+
"object_fit": null,
|
489 |
+
"object_position": null,
|
490 |
+
"order": null,
|
491 |
+
"overflow": null,
|
492 |
+
"overflow_x": null,
|
493 |
+
"overflow_y": null,
|
494 |
+
"padding": null,
|
495 |
+
"right": null,
|
496 |
+
"top": null,
|
497 |
+
"visibility": null,
|
498 |
+
"width": null
|
499 |
+
}
|
500 |
+
},
|
501 |
+
"165ccb061bb843a4b44896df7b4d15b0": {
|
502 |
+
"model_module": "@jupyter-widgets/base",
|
503 |
+
"model_name": "LayoutModel",
|
504 |
+
"model_module_version": "1.2.0",
|
505 |
+
"state": {
|
506 |
+
"_model_module": "@jupyter-widgets/base",
|
507 |
+
"_model_module_version": "1.2.0",
|
508 |
+
"_model_name": "LayoutModel",
|
509 |
+
"_view_count": null,
|
510 |
+
"_view_module": "@jupyter-widgets/base",
|
511 |
+
"_view_module_version": "1.2.0",
|
512 |
+
"_view_name": "LayoutView",
|
513 |
+
"align_content": null,
|
514 |
+
"align_items": null,
|
515 |
+
"align_self": null,
|
516 |
+
"border": null,
|
517 |
+
"bottom": null,
|
518 |
+
"display": null,
|
519 |
+
"flex": null,
|
520 |
+
"flex_flow": null,
|
521 |
+
"grid_area": null,
|
522 |
+
"grid_auto_columns": null,
|
523 |
+
"grid_auto_flow": null,
|
524 |
+
"grid_auto_rows": null,
|
525 |
+
"grid_column": null,
|
526 |
+
"grid_gap": null,
|
527 |
+
"grid_row": null,
|
528 |
+
"grid_template_areas": null,
|
529 |
+
"grid_template_columns": null,
|
530 |
+
"grid_template_rows": null,
|
531 |
+
"height": null,
|
532 |
+
"justify_content": null,
|
533 |
+
"justify_items": null,
|
534 |
+
"left": null,
|
535 |
+
"margin": null,
|
536 |
+
"max_height": null,
|
537 |
+
"max_width": null,
|
538 |
+
"min_height": null,
|
539 |
+
"min_width": null,
|
540 |
+
"object_fit": null,
|
541 |
+
"object_position": null,
|
542 |
+
"order": null,
|
543 |
+
"overflow": null,
|
544 |
+
"overflow_x": null,
|
545 |
+
"overflow_y": null,
|
546 |
+
"padding": null,
|
547 |
+
"right": null,
|
548 |
+
"top": null,
|
549 |
+
"visibility": null,
|
550 |
+
"width": null
|
551 |
+
}
|
552 |
+
},
|
553 |
+
"f1a9031e7c3445ee80308888d28f2d66": {
|
554 |
+
"model_module": "@jupyter-widgets/controls",
|
555 |
+
"model_name": "DescriptionStyleModel",
|
556 |
+
"model_module_version": "1.5.0",
|
557 |
+
"state": {
|
558 |
+
"_model_module": "@jupyter-widgets/controls",
|
559 |
+
"_model_module_version": "1.5.0",
|
560 |
+
"_model_name": "DescriptionStyleModel",
|
561 |
+
"_view_count": null,
|
562 |
+
"_view_module": "@jupyter-widgets/base",
|
563 |
+
"_view_module_version": "1.2.0",
|
564 |
+
"_view_name": "StyleView",
|
565 |
+
"description_width": ""
|
566 |
+
}
|
567 |
+
},
|
568 |
+
"b15acb0416594d44a41df804e42b4cdf": {
|
569 |
+
"model_module": "@jupyter-widgets/base",
|
570 |
+
"model_name": "LayoutModel",
|
571 |
+
"model_module_version": "1.2.0",
|
572 |
+
"state": {
|
573 |
+
"_model_module": "@jupyter-widgets/base",
|
574 |
+
"_model_module_version": "1.2.0",
|
575 |
+
"_model_name": "LayoutModel",
|
576 |
+
"_view_count": null,
|
577 |
+
"_view_module": "@jupyter-widgets/base",
|
578 |
+
"_view_module_version": "1.2.0",
|
579 |
+
"_view_name": "LayoutView",
|
580 |
+
"align_content": null,
|
581 |
+
"align_items": null,
|
582 |
+
"align_self": null,
|
583 |
+
"border": null,
|
584 |
+
"bottom": null,
|
585 |
+
"display": null,
|
586 |
+
"flex": null,
|
587 |
+
"flex_flow": null,
|
588 |
+
"grid_area": null,
|
589 |
+
"grid_auto_columns": null,
|
590 |
+
"grid_auto_flow": null,
|
591 |
+
"grid_auto_rows": null,
|
592 |
+
"grid_column": null,
|
593 |
+
"grid_gap": null,
|
594 |
+
"grid_row": null,
|
595 |
+
"grid_template_areas": null,
|
596 |
+
"grid_template_columns": null,
|
597 |
+
"grid_template_rows": null,
|
598 |
+
"height": null,
|
599 |
+
"justify_content": null,
|
600 |
+
"justify_items": null,
|
601 |
+
"left": null,
|
602 |
+
"margin": null,
|
603 |
+
"max_height": null,
|
604 |
+
"max_width": null,
|
605 |
+
"min_height": null,
|
606 |
+
"min_width": null,
|
607 |
+
"object_fit": null,
|
608 |
+
"object_position": null,
|
609 |
+
"order": null,
|
610 |
+
"overflow": null,
|
611 |
+
"overflow_x": null,
|
612 |
+
"overflow_y": null,
|
613 |
+
"padding": null,
|
614 |
+
"right": null,
|
615 |
+
"top": null,
|
616 |
+
"visibility": null,
|
617 |
+
"width": null
|
618 |
+
}
|
619 |
+
},
|
620 |
+
"4aeb5362822f490aa6cff491dded8111": {
|
621 |
+
"model_module": "@jupyter-widgets/controls",
|
622 |
+
"model_name": "ProgressStyleModel",
|
623 |
+
"model_module_version": "1.5.0",
|
624 |
+
"state": {
|
625 |
+
"_model_module": "@jupyter-widgets/controls",
|
626 |
+
"_model_module_version": "1.5.0",
|
627 |
+
"_model_name": "ProgressStyleModel",
|
628 |
+
"_view_count": null,
|
629 |
+
"_view_module": "@jupyter-widgets/base",
|
630 |
+
"_view_module_version": "1.2.0",
|
631 |
+
"_view_name": "StyleView",
|
632 |
+
"bar_color": null,
|
633 |
+
"description_width": ""
|
634 |
+
}
|
635 |
+
},
|
636 |
+
"faa803d16fc74ddcbb003485a506569c": {
|
637 |
+
"model_module": "@jupyter-widgets/base",
|
638 |
+
"model_name": "LayoutModel",
|
639 |
+
"model_module_version": "1.2.0",
|
640 |
+
"state": {
|
641 |
+
"_model_module": "@jupyter-widgets/base",
|
642 |
+
"_model_module_version": "1.2.0",
|
643 |
+
"_model_name": "LayoutModel",
|
644 |
+
"_view_count": null,
|
645 |
+
"_view_module": "@jupyter-widgets/base",
|
646 |
+
"_view_module_version": "1.2.0",
|
647 |
+
"_view_name": "LayoutView",
|
648 |
+
"align_content": null,
|
649 |
+
"align_items": null,
|
650 |
+
"align_self": null,
|
651 |
+
"border": null,
|
652 |
+
"bottom": null,
|
653 |
+
"display": null,
|
654 |
+
"flex": null,
|
655 |
+
"flex_flow": null,
|
656 |
+
"grid_area": null,
|
657 |
+
"grid_auto_columns": null,
|
658 |
+
"grid_auto_flow": null,
|
659 |
+
"grid_auto_rows": null,
|
660 |
+
"grid_column": null,
|
661 |
+
"grid_gap": null,
|
662 |
+
"grid_row": null,
|
663 |
+
"grid_template_areas": null,
|
664 |
+
"grid_template_columns": null,
|
665 |
+
"grid_template_rows": null,
|
666 |
+
"height": null,
|
667 |
+
"justify_content": null,
|
668 |
+
"justify_items": null,
|
669 |
+
"left": null,
|
670 |
+
"margin": null,
|
671 |
+
"max_height": null,
|
672 |
+
"max_width": null,
|
673 |
+
"min_height": null,
|
674 |
+
"min_width": null,
|
675 |
+
"object_fit": null,
|
676 |
+
"object_position": null,
|
677 |
+
"order": null,
|
678 |
+
"overflow": null,
|
679 |
+
"overflow_x": null,
|
680 |
+
"overflow_y": null,
|
681 |
+
"padding": null,
|
682 |
+
"right": null,
|
683 |
+
"top": null,
|
684 |
+
"visibility": null,
|
685 |
+
"width": null
|
686 |
+
}
|
687 |
+
},
|
688 |
+
"4f09405744b04ba79ecb18398b49a389": {
|
689 |
+
"model_module": "@jupyter-widgets/controls",
|
690 |
+
"model_name": "DescriptionStyleModel",
|
691 |
+
"model_module_version": "1.5.0",
|
692 |
+
"state": {
|
693 |
+
"_model_module": "@jupyter-widgets/controls",
|
694 |
+
"_model_module_version": "1.5.0",
|
695 |
+
"_model_name": "DescriptionStyleModel",
|
696 |
+
"_view_count": null,
|
697 |
+
"_view_module": "@jupyter-widgets/base",
|
698 |
+
"_view_module_version": "1.2.0",
|
699 |
+
"_view_name": "StyleView",
|
700 |
+
"description_width": ""
|
701 |
+
}
|
702 |
+
},
|
703 |
+
"685e146910634868b154ba03885d8b4c": {
|
704 |
+
"model_module": "@jupyter-widgets/controls",
|
705 |
+
"model_name": "HBoxModel",
|
706 |
+
"model_module_version": "1.5.0",
|
707 |
+
"state": {
|
708 |
+
"_dom_classes": [],
|
709 |
+
"_model_module": "@jupyter-widgets/controls",
|
710 |
+
"_model_module_version": "1.5.0",
|
711 |
+
"_model_name": "HBoxModel",
|
712 |
+
"_view_count": null,
|
713 |
+
"_view_module": "@jupyter-widgets/controls",
|
714 |
+
"_view_module_version": "1.5.0",
|
715 |
+
"_view_name": "HBoxView",
|
716 |
+
"box_style": "",
|
717 |
+
"children": [
|
718 |
+
"IPY_MODEL_fefe61069a1a416cbb512e1f006c82b0",
|
719 |
+
"IPY_MODEL_3cac12c147134eb4b71561f17345712d",
|
720 |
+
"IPY_MODEL_810b0e9e274a433892f87040283b4db9"
|
721 |
+
],
|
722 |
+
"layout": "IPY_MODEL_11629aeef5a146e79869fded9f603d6d"
|
723 |
+
}
|
724 |
+
},
|
725 |
+
"fefe61069a1a416cbb512e1f006c82b0": {
|
726 |
+
"model_module": "@jupyter-widgets/controls",
|
727 |
+
"model_name": "HTMLModel",
|
728 |
+
"model_module_version": "1.5.0",
|
729 |
+
"state": {
|
730 |
+
"_dom_classes": [],
|
731 |
+
"_model_module": "@jupyter-widgets/controls",
|
732 |
+
"_model_module_version": "1.5.0",
|
733 |
+
"_model_name": "HTMLModel",
|
734 |
+
"_view_count": null,
|
735 |
+
"_view_module": "@jupyter-widgets/controls",
|
736 |
+
"_view_module_version": "1.5.0",
|
737 |
+
"_view_name": "HTMLView",
|
738 |
+
"description": "",
|
739 |
+
"description_tooltip": null,
|
740 |
+
"layout": "IPY_MODEL_dfe6494357d040ac8d51d03069822e41",
|
741 |
+
"placeholder": "β",
|
742 |
+
"style": "IPY_MODEL_190de89f93d048658ee4788ee4af4418",
|
743 |
+
"value": "Parsing nodes: 100%"
|
744 |
+
}
|
745 |
+
},
|
746 |
+
"3cac12c147134eb4b71561f17345712d": {
|
747 |
+
"model_module": "@jupyter-widgets/controls",
|
748 |
+
"model_name": "FloatProgressModel",
|
749 |
+
"model_module_version": "1.5.0",
|
750 |
+
"state": {
|
751 |
+
"_dom_classes": [],
|
752 |
+
"_model_module": "@jupyter-widgets/controls",
|
753 |
+
"_model_module_version": "1.5.0",
|
754 |
+
"_model_name": "FloatProgressModel",
|
755 |
+
"_view_count": null,
|
756 |
+
"_view_module": "@jupyter-widgets/controls",
|
757 |
+
"_view_module_version": "1.5.0",
|
758 |
+
"_view_name": "ProgressView",
|
759 |
+
"bar_style": "success",
|
760 |
+
"description": "",
|
761 |
+
"description_tooltip": null,
|
762 |
+
"layout": "IPY_MODEL_835fd209022c4086b509bf42084243b2",
|
763 |
+
"max": 14,
|
764 |
+
"min": 0,
|
765 |
+
"orientation": "horizontal",
|
766 |
+
"style": "IPY_MODEL_4b27da15dad34e839a4a02dab06d3e5a",
|
767 |
+
"value": 14
|
768 |
+
}
|
769 |
+
},
|
770 |
+
"810b0e9e274a433892f87040283b4db9": {
|
771 |
+
"model_module": "@jupyter-widgets/controls",
|
772 |
+
"model_name": "HTMLModel",
|
773 |
+
"model_module_version": "1.5.0",
|
774 |
+
"state": {
|
775 |
+
"_dom_classes": [],
|
776 |
+
"_model_module": "@jupyter-widgets/controls",
|
777 |
+
"_model_module_version": "1.5.0",
|
778 |
+
"_model_name": "HTMLModel",
|
779 |
+
"_view_count": null,
|
780 |
+
"_view_module": "@jupyter-widgets/controls",
|
781 |
+
"_view_module_version": "1.5.0",
|
782 |
+
"_view_name": "HTMLView",
|
783 |
+
"description": "",
|
784 |
+
"description_tooltip": null,
|
785 |
+
"layout": "IPY_MODEL_afa339155f4b4ffaa5fc70457b6b7a69",
|
786 |
+
"placeholder": "β",
|
787 |
+
"style": "IPY_MODEL_e8d0668d65dd4743b25c1bc74e1d8057",
|
788 |
+
"value": " 14/14 [00:00<00:00, 20.68it/s]"
|
789 |
+
}
|
790 |
+
},
|
791 |
+
"11629aeef5a146e79869fded9f603d6d": {
|
792 |
+
"model_module": "@jupyter-widgets/base",
|
793 |
+
"model_name": "LayoutModel",
|
794 |
+
"model_module_version": "1.2.0",
|
795 |
+
"state": {
|
796 |
+
"_model_module": "@jupyter-widgets/base",
|
797 |
+
"_model_module_version": "1.2.0",
|
798 |
+
"_model_name": "LayoutModel",
|
799 |
+
"_view_count": null,
|
800 |
+
"_view_module": "@jupyter-widgets/base",
|
801 |
+
"_view_module_version": "1.2.0",
|
802 |
+
"_view_name": "LayoutView",
|
803 |
+
"align_content": null,
|
804 |
+
"align_items": null,
|
805 |
+
"align_self": null,
|
806 |
+
"border": null,
|
807 |
+
"bottom": null,
|
808 |
+
"display": null,
|
809 |
+
"flex": null,
|
810 |
+
"flex_flow": null,
|
811 |
+
"grid_area": null,
|
812 |
+
"grid_auto_columns": null,
|
813 |
+
"grid_auto_flow": null,
|
814 |
+
"grid_auto_rows": null,
|
815 |
+
"grid_column": null,
|
816 |
+
"grid_gap": null,
|
817 |
+
"grid_row": null,
|
818 |
+
"grid_template_areas": null,
|
819 |
+
"grid_template_columns": null,
|
820 |
+
"grid_template_rows": null,
|
821 |
+
"height": null,
|
822 |
+
"justify_content": null,
|
823 |
+
"justify_items": null,
|
824 |
+
"left": null,
|
825 |
+
"margin": null,
|
826 |
+
"max_height": null,
|
827 |
+
"max_width": null,
|
828 |
+
"min_height": null,
|
829 |
+
"min_width": null,
|
830 |
+
"object_fit": null,
|
831 |
+
"object_position": null,
|
832 |
+
"order": null,
|
833 |
+
"overflow": null,
|
834 |
+
"overflow_x": null,
|
835 |
+
"overflow_y": null,
|
836 |
+
"padding": null,
|
837 |
+
"right": null,
|
838 |
+
"top": null,
|
839 |
+
"visibility": null,
|
840 |
+
"width": null
|
841 |
+
}
|
842 |
+
},
|
843 |
+
"dfe6494357d040ac8d51d03069822e41": {
|
844 |
+
"model_module": "@jupyter-widgets/base",
|
845 |
+
"model_name": "LayoutModel",
|
846 |
+
"model_module_version": "1.2.0",
|
847 |
+
"state": {
|
848 |
+
"_model_module": "@jupyter-widgets/base",
|
849 |
+
"_model_module_version": "1.2.0",
|
850 |
+
"_model_name": "LayoutModel",
|
851 |
+
"_view_count": null,
|
852 |
+
"_view_module": "@jupyter-widgets/base",
|
853 |
+
"_view_module_version": "1.2.0",
|
854 |
+
"_view_name": "LayoutView",
|
855 |
+
"align_content": null,
|
856 |
+
"align_items": null,
|
857 |
+
"align_self": null,
|
858 |
+
"border": null,
|
859 |
+
"bottom": null,
|
860 |
+
"display": null,
|
861 |
+
"flex": null,
|
862 |
+
"flex_flow": null,
|
863 |
+
"grid_area": null,
|
864 |
+
"grid_auto_columns": null,
|
865 |
+
"grid_auto_flow": null,
|
866 |
+
"grid_auto_rows": null,
|
867 |
+
"grid_column": null,
|
868 |
+
"grid_gap": null,
|
869 |
+
"grid_row": null,
|
870 |
+
"grid_template_areas": null,
|
871 |
+
"grid_template_columns": null,
|
872 |
+
"grid_template_rows": null,
|
873 |
+
"height": null,
|
874 |
+
"justify_content": null,
|
875 |
+
"justify_items": null,
|
876 |
+
"left": null,
|
877 |
+
"margin": null,
|
878 |
+
"max_height": null,
|
879 |
+
"max_width": null,
|
880 |
+
"min_height": null,
|
881 |
+
"min_width": null,
|
882 |
+
"object_fit": null,
|
883 |
+
"object_position": null,
|
884 |
+
"order": null,
|
885 |
+
"overflow": null,
|
886 |
+
"overflow_x": null,
|
887 |
+
"overflow_y": null,
|
888 |
+
"padding": null,
|
889 |
+
"right": null,
|
890 |
+
"top": null,
|
891 |
+
"visibility": null,
|
892 |
+
"width": null
|
893 |
+
}
|
894 |
+
},
|
895 |
+
"190de89f93d048658ee4788ee4af4418": {
|
896 |
+
"model_module": "@jupyter-widgets/controls",
|
897 |
+
"model_name": "DescriptionStyleModel",
|
898 |
+
"model_module_version": "1.5.0",
|
899 |
+
"state": {
|
900 |
+
"_model_module": "@jupyter-widgets/controls",
|
901 |
+
"_model_module_version": "1.5.0",
|
902 |
+
"_model_name": "DescriptionStyleModel",
|
903 |
+
"_view_count": null,
|
904 |
+
"_view_module": "@jupyter-widgets/base",
|
905 |
+
"_view_module_version": "1.2.0",
|
906 |
+
"_view_name": "StyleView",
|
907 |
+
"description_width": ""
|
908 |
+
}
|
909 |
+
},
|
910 |
+
"835fd209022c4086b509bf42084243b2": {
|
911 |
+
"model_module": "@jupyter-widgets/base",
|
912 |
+
"model_name": "LayoutModel",
|
913 |
+
"model_module_version": "1.2.0",
|
914 |
+
"state": {
|
915 |
+
"_model_module": "@jupyter-widgets/base",
|
916 |
+
"_model_module_version": "1.2.0",
|
917 |
+
"_model_name": "LayoutModel",
|
918 |
+
"_view_count": null,
|
919 |
+
"_view_module": "@jupyter-widgets/base",
|
920 |
+
"_view_module_version": "1.2.0",
|
921 |
+
"_view_name": "LayoutView",
|
922 |
+
"align_content": null,
|
923 |
+
"align_items": null,
|
924 |
+
"align_self": null,
|
925 |
+
"border": null,
|
926 |
+
"bottom": null,
|
927 |
+
"display": null,
|
928 |
+
"flex": null,
|
929 |
+
"flex_flow": null,
|
930 |
+
"grid_area": null,
|
931 |
+
"grid_auto_columns": null,
|
932 |
+
"grid_auto_flow": null,
|
933 |
+
"grid_auto_rows": null,
|
934 |
+
"grid_column": null,
|
935 |
+
"grid_gap": null,
|
936 |
+
"grid_row": null,
|
937 |
+
"grid_template_areas": null,
|
938 |
+
"grid_template_columns": null,
|
939 |
+
"grid_template_rows": null,
|
940 |
+
"height": null,
|
941 |
+
"justify_content": null,
|
942 |
+
"justify_items": null,
|
943 |
+
"left": null,
|
944 |
+
"margin": null,
|
945 |
+
"max_height": null,
|
946 |
+
"max_width": null,
|
947 |
+
"min_height": null,
|
948 |
+
"min_width": null,
|
949 |
+
"object_fit": null,
|
950 |
+
"object_position": null,
|
951 |
+
"order": null,
|
952 |
+
"overflow": null,
|
953 |
+
"overflow_x": null,
|
954 |
+
"overflow_y": null,
|
955 |
+
"padding": null,
|
956 |
+
"right": null,
|
957 |
+
"top": null,
|
958 |
+
"visibility": null,
|
959 |
+
"width": null
|
960 |
+
}
|
961 |
+
},
|
962 |
+
"4b27da15dad34e839a4a02dab06d3e5a": {
|
963 |
+
"model_module": "@jupyter-widgets/controls",
|
964 |
+
"model_name": "ProgressStyleModel",
|
965 |
+
"model_module_version": "1.5.0",
|
966 |
+
"state": {
|
967 |
+
"_model_module": "@jupyter-widgets/controls",
|
968 |
+
"_model_module_version": "1.5.0",
|
969 |
+
"_model_name": "ProgressStyleModel",
|
970 |
+
"_view_count": null,
|
971 |
+
"_view_module": "@jupyter-widgets/base",
|
972 |
+
"_view_module_version": "1.2.0",
|
973 |
+
"_view_name": "StyleView",
|
974 |
+
"bar_color": null,
|
975 |
+
"description_width": ""
|
976 |
+
}
|
977 |
+
},
|
978 |
+
"afa339155f4b4ffaa5fc70457b6b7a69": {
|
979 |
+
"model_module": "@jupyter-widgets/base",
|
980 |
+
"model_name": "LayoutModel",
|
981 |
+
"model_module_version": "1.2.0",
|
982 |
+
"state": {
|
983 |
+
"_model_module": "@jupyter-widgets/base",
|
984 |
+
"_model_module_version": "1.2.0",
|
985 |
+
"_model_name": "LayoutModel",
|
986 |
+
"_view_count": null,
|
987 |
+
"_view_module": "@jupyter-widgets/base",
|
988 |
+
"_view_module_version": "1.2.0",
|
989 |
+
"_view_name": "LayoutView",
|
990 |
+
"align_content": null,
|
991 |
+
"align_items": null,
|
992 |
+
"align_self": null,
|
993 |
+
"border": null,
|
994 |
+
"bottom": null,
|
995 |
+
"display": null,
|
996 |
+
"flex": null,
|
997 |
+
"flex_flow": null,
|
998 |
+
"grid_area": null,
|
999 |
+
"grid_auto_columns": null,
|
1000 |
+
"grid_auto_flow": null,
|
1001 |
+
"grid_auto_rows": null,
|
1002 |
+
"grid_column": null,
|
1003 |
+
"grid_gap": null,
|
1004 |
+
"grid_row": null,
|
1005 |
+
"grid_template_areas": null,
|
1006 |
+
"grid_template_columns": null,
|
1007 |
+
"grid_template_rows": null,
|
1008 |
+
"height": null,
|
1009 |
+
"justify_content": null,
|
1010 |
+
"justify_items": null,
|
1011 |
+
"left": null,
|
1012 |
+
"margin": null,
|
1013 |
+
"max_height": null,
|
1014 |
+
"max_width": null,
|
1015 |
+
"min_height": null,
|
1016 |
+
"min_width": null,
|
1017 |
+
"object_fit": null,
|
1018 |
+
"object_position": null,
|
1019 |
+
"order": null,
|
1020 |
+
"overflow": null,
|
1021 |
+
"overflow_x": null,
|
1022 |
+
"overflow_y": null,
|
1023 |
+
"padding": null,
|
1024 |
+
"right": null,
|
1025 |
+
"top": null,
|
1026 |
+
"visibility": null,
|
1027 |
+
"width": null
|
1028 |
+
}
|
1029 |
+
},
|
1030 |
+
"e8d0668d65dd4743b25c1bc74e1d8057": {
|
1031 |
+
"model_module": "@jupyter-widgets/controls",
|
1032 |
+
"model_name": "DescriptionStyleModel",
|
1033 |
+
"model_module_version": "1.5.0",
|
1034 |
+
"state": {
|
1035 |
+
"_model_module": "@jupyter-widgets/controls",
|
1036 |
+
"_model_module_version": "1.5.0",
|
1037 |
+
"_model_name": "DescriptionStyleModel",
|
1038 |
+
"_view_count": null,
|
1039 |
+
"_view_module": "@jupyter-widgets/base",
|
1040 |
+
"_view_module_version": "1.2.0",
|
1041 |
+
"_view_name": "StyleView",
|
1042 |
+
"description_width": ""
|
1043 |
+
}
|
1044 |
+
}
|
1045 |
+
}
|
1046 |
+
}
|
1047 |
+
},
|
1048 |
+
"cells": [
|
1049 |
+
{
|
1050 |
+
"cell_type": "markdown",
|
1051 |
+
"metadata": {
|
1052 |
+
"id": "view-in-github",
|
1053 |
+
"colab_type": "text"
|
1054 |
+
},
|
1055 |
+
"source": [
|
1056 |
+
"<a href=\"https://colab.research.google.com/github/towardsai/ai-tutor-rag-system/blob/main/notebooks/05-Improve_Prompts_%2B_Add_Source.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
|
1057 |
+
]
|
1058 |
+
},
|
1059 |
+
{
|
1060 |
+
"cell_type": "markdown",
|
1061 |
+
"source": [
|
1062 |
+
"# Install Packages and Setup Variables"
|
1063 |
+
],
|
1064 |
+
"metadata": {
|
1065 |
+
"id": "5BGJ3fxhOk2V"
|
1066 |
+
}
|
1067 |
+
},
|
1068 |
+
{
|
1069 |
+
"cell_type": "code",
|
1070 |
+
"execution_count": null,
|
1071 |
+
"metadata": {
|
1072 |
+
"id": "QPJzr-I9XQ7l",
|
1073 |
+
"colab": {
|
1074 |
+
"base_uri": "https://localhost:8080/"
|
1075 |
+
},
|
1076 |
+
"outputId": "c31cde74-f2a8-4c1b-adce-a8cce4268ec2"
|
1077 |
+
},
|
1078 |
+
"outputs": [
|
1079 |
+
{
|
1080 |
+
"output_type": "stream",
|
1081 |
+
"name": "stdout",
|
1082 |
+
"text": [
|
1083 |
+
"\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m15.7/15.7 MB\u001b[0m \u001b[31m52.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
1084 |
+
"\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m225.4/225.4 kB\u001b[0m \u001b[31m22.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
1085 |
+
"\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m51.7/51.7 kB\u001b[0m \u001b[31m3.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
1086 |
+
"\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m2.0/2.0 MB\u001b[0m \u001b[31m47.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
1087 |
+
"\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m508.6/508.6 kB\u001b[0m \u001b[31m23.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
1088 |
+
"\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m79.9/79.9 MB\u001b[0m \u001b[31m7.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
1089 |
+
"\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m45.7/45.7 kB\u001b[0m \u001b[31m4.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
1090 |
+
"\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m147.9/147.9 kB\u001b[0m \u001b[31m15.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
1091 |
+
"\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m75.9/75.9 kB\u001b[0m \u001b[31m7.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
1092 |
+
"\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m3.1/3.1 MB\u001b[0m \u001b[31m79.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
1093 |
+
"\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m2.4/2.4 MB\u001b[0m \u001b[31m71.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
1094 |
+
"\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m92.0/92.0 kB\u001b[0m \u001b[31m9.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
1095 |
+
"\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m60.7/60.7 kB\u001b[0m \u001b[31m5.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
1096 |
+
"\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m40.8/40.8 kB\u001b[0m \u001b[31m3.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
1097 |
+
"\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m5.4/5.4 MB\u001b[0m \u001b[31m61.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
1098 |
+
"\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m6.8/6.8 MB\u001b[0m \u001b[31m61.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
1099 |
+
"\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m57.9/57.9 kB\u001b[0m \u001b[31m6.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
1100 |
+
"\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m105.6/105.6 kB\u001b[0m \u001b[31m11.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
1101 |
+
"\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m67.3/67.3 kB\u001b[0m \u001b[31m6.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
1102 |
+
"\u001b[?25h Installing build dependencies ... \u001b[?25l\u001b[?25hdone\n",
|
1103 |
+
" Getting requirements to build wheel ... \u001b[?25l\u001b[?25hdone\n",
|
1104 |
+
" Preparing metadata (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n",
|
1105 |
+
"\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m698.9/698.9 kB\u001b[0m \u001b[31m52.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
1106 |
+
"\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m1.6/1.6 MB\u001b[0m \u001b[31m64.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
1107 |
+
"\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m67.6/67.6 kB\u001b[0m \u001b[31m6.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
1108 |
+
"\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m71.1/71.1 kB\u001b[0m \u001b[31m7.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
1109 |
+
"\u001b[2K \u001b[90mβββββββββββββββββββββοΏ½οΏ½ββββββββββββββββββ\u001b[0m \u001b[32m76.9/76.9 kB\u001b[0m \u001b[31m7.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
1110 |
+
"\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m58.3/58.3 kB\u001b[0m \u001b[31m6.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
1111 |
+
"\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m46.0/46.0 kB\u001b[0m \u001b[31m4.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
1112 |
+
"\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m50.8/50.8 kB\u001b[0m \u001b[31m4.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
1113 |
+
"\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m341.4/341.4 kB\u001b[0m \u001b[31m30.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
1114 |
+
"\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m3.4/3.4 MB\u001b[0m \u001b[31m59.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
1115 |
+
"\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m1.3/1.3 MB\u001b[0m \u001b[31m70.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
1116 |
+
"\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m130.2/130.2 kB\u001b[0m \u001b[31m13.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
1117 |
+
"\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m49.4/49.4 kB\u001b[0m \u001b[31m5.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
1118 |
+
"\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m86.8/86.8 kB\u001b[0m \u001b[31m8.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
|
1119 |
+
"\u001b[?25h Building wheel for pypika (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n",
|
1120 |
+
"\u001b[31mERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\n",
|
1121 |
+
"tensorflow-probability 0.22.0 requires typing-extensions<4.6.0, but you have typing-extensions 4.9.0 which is incompatible.\u001b[0m\u001b[31m\n",
|
1122 |
+
"\u001b[0m"
|
1123 |
+
]
|
1124 |
+
}
|
1125 |
+
],
|
1126 |
+
"source": [
|
1127 |
+
"!pip install -q llama-index==0.9.21 openai==1.6.0 cohere==4.39 tiktoken==0.5.2 chromadb==0.4.21 kaleido==0.2.1 python-multipart==0.0.6 html2text==2020.1.16"
|
1128 |
+
]
|
1129 |
+
},
|
1130 |
+
{
|
1131 |
+
"cell_type": "code",
|
1132 |
+
"source": [
|
1133 |
+
"import os\n",
|
1134 |
+
"\n",
|
1135 |
+
"# Set the \"OPENAI_API_KEY\" in the Python environment. Will be used by OpenAI client later.\n",
|
1136 |
+
"os.environ[\"OPENAI_API_KEY\"] = \"<YOUR_OPENAI_KEY>\""
|
1137 |
+
],
|
1138 |
+
"metadata": {
|
1139 |
+
"id": "riuXwpSPcvWC"
|
1140 |
+
},
|
1141 |
+
"execution_count": null,
|
1142 |
+
"outputs": []
|
1143 |
+
},
|
1144 |
+
{
|
1145 |
+
"cell_type": "code",
|
1146 |
+
"source": [
|
1147 |
+
"import nest_asyncio\n",
|
1148 |
+
"\n",
|
1149 |
+
"nest_asyncio.apply()"
|
1150 |
+
],
|
1151 |
+
"metadata": {
|
1152 |
+
"id": "km-KQOrgr3VB"
|
1153 |
+
},
|
1154 |
+
"execution_count": null,
|
1155 |
+
"outputs": []
|
1156 |
+
},
|
1157 |
+
{
|
1158 |
+
"cell_type": "markdown",
|
1159 |
+
"source": [
|
1160 |
+
"# Load a Model"
|
1161 |
+
],
|
1162 |
+
"metadata": {
|
1163 |
+
"id": "Bkgi2OrYzF7q"
|
1164 |
+
}
|
1165 |
+
},
|
1166 |
+
{
|
1167 |
+
"cell_type": "code",
|
1168 |
+
"source": [
|
1169 |
+
"from llama_index.llms import OpenAI\n",
|
1170 |
+
"\n",
|
1171 |
+
"llm = OpenAI(temperature=0.9, model=\"gpt-3.5-turbo\", max_tokens=512)"
|
1172 |
+
],
|
1173 |
+
"metadata": {
|
1174 |
+
"id": "9oGT6crooSSj"
|
1175 |
+
},
|
1176 |
+
"execution_count": null,
|
1177 |
+
"outputs": []
|
1178 |
+
},
|
1179 |
+
{
|
1180 |
+
"cell_type": "markdown",
|
1181 |
+
"source": [
|
1182 |
+
"# Create a VectoreStore"
|
1183 |
+
],
|
1184 |
+
"metadata": {
|
1185 |
+
"id": "0BwVuJXlzHVL"
|
1186 |
+
}
|
1187 |
+
},
|
1188 |
+
{
|
1189 |
+
"cell_type": "code",
|
1190 |
+
"source": [
|
1191 |
+
"import chromadb\n",
|
1192 |
+
"\n",
|
1193 |
+
"# create client and a new collection\n",
|
1194 |
+
"# chromadb.EphemeralClient saves data in-memory.\n",
|
1195 |
+
"chroma_client = chromadb.PersistentClient(path=\"./mini-llama-articles\")\n",
|
1196 |
+
"chroma_collection = chroma_client.create_collection(\"mini-llama-articles\")"
|
1197 |
+
],
|
1198 |
+
"metadata": {
|
1199 |
+
"id": "SQP87lHczHKc"
|
1200 |
+
},
|
1201 |
+
"execution_count": null,
|
1202 |
+
"outputs": []
|
1203 |
+
},
|
1204 |
+
{
|
1205 |
+
"cell_type": "code",
|
1206 |
+
"source": [
|
1207 |
+
"from llama_index.vector_stores import ChromaVectorStore\n",
|
1208 |
+
"\n",
|
1209 |
+
"# Define a storage context object using the created vector database.\n",
|
1210 |
+
"vector_store = ChromaVectorStore(chroma_collection=chroma_collection)"
|
1211 |
+
],
|
1212 |
+
"metadata": {
|
1213 |
+
"id": "zAaGcYMJzHAN"
|
1214 |
+
},
|
1215 |
+
"execution_count": null,
|
1216 |
+
"outputs": []
|
1217 |
+
},
|
1218 |
+
{
|
1219 |
+
"cell_type": "markdown",
|
1220 |
+
"source": [
|
1221 |
+
"# Load the Dataset (CSV)"
|
1222 |
+
],
|
1223 |
+
"metadata": {
|
1224 |
+
"id": "I9JbAzFcjkpn"
|
1225 |
+
}
|
1226 |
+
},
|
1227 |
+
{
|
1228 |
+
"cell_type": "markdown",
|
1229 |
+
"source": [
|
1230 |
+
"## Download"
|
1231 |
+
],
|
1232 |
+
"metadata": {
|
1233 |
+
"id": "_Tif8-JoRH68"
|
1234 |
+
}
|
1235 |
+
},
|
1236 |
+
{
|
1237 |
+
"cell_type": "markdown",
|
1238 |
+
"source": [
|
1239 |
+
"The dataset includes several articles from the TowardsAI blog, which provide an in-depth explanation of the LLaMA2 model."
|
1240 |
+
],
|
1241 |
+
"metadata": {
|
1242 |
+
"id": "4fQaa1LN1mXL"
|
1243 |
+
}
|
1244 |
+
},
|
1245 |
+
{
|
1246 |
+
"cell_type": "code",
|
1247 |
+
"source": [
|
1248 |
+
"!wget https://raw.githubusercontent.com/AlaFalaki/tutorial_notebooks/main/data/mini-llama-articles.csv"
|
1249 |
+
],
|
1250 |
+
"metadata": {
|
1251 |
+
"colab": {
|
1252 |
+
"base_uri": "https://localhost:8080/"
|
1253 |
+
},
|
1254 |
+
"id": "fQtpDvUzKNzI",
|
1255 |
+
"outputId": "9a62a730-6fe0-4542-cfd1-cbb1f84d889e"
|
1256 |
+
},
|
1257 |
+
"execution_count": null,
|
1258 |
+
"outputs": [
|
1259 |
+
{
|
1260 |
+
"output_type": "stream",
|
1261 |
+
"name": "stdout",
|
1262 |
+
"text": [
|
1263 |
+
"--2024-02-01 14:53:37-- https://raw.githubusercontent.com/AlaFalaki/tutorial_notebooks/main/data/mini-llama-articles.csv\n",
|
1264 |
+
"Resolving raw.githubusercontent.com (raw.githubusercontent.com)... 185.199.108.133, 185.199.109.133, 185.199.110.133, ...\n",
|
1265 |
+
"Connecting to raw.githubusercontent.com (raw.githubusercontent.com)|185.199.108.133|:443... connected.\n",
|
1266 |
+
"HTTP request sent, awaiting response... 200 OK\n",
|
1267 |
+
"Length: 173646 (170K) [text/plain]\n",
|
1268 |
+
"Saving to: βmini-llama-articles.csvβ\n",
|
1269 |
+
"\n",
|
1270 |
+
"\rmini-llama-articles 0%[ ] 0 --.-KB/s \rmini-llama-articles 100%[===================>] 169.58K --.-KB/s in 0.02s \n",
|
1271 |
+
"\n",
|
1272 |
+
"2024-02-01 14:53:37 (6.64 MB/s) - βmini-llama-articles.csvβ saved [173646/173646]\n",
|
1273 |
+
"\n"
|
1274 |
+
]
|
1275 |
+
}
|
1276 |
+
]
|
1277 |
+
},
|
1278 |
+
{
|
1279 |
+
"cell_type": "markdown",
|
1280 |
+
"source": [
|
1281 |
+
"## Load the Articles"
|
1282 |
+
],
|
1283 |
+
"metadata": {
|
1284 |
+
"id": "zk-4alIxROo8"
|
1285 |
+
}
|
1286 |
+
},
|
1287 |
+
{
|
1288 |
+
"cell_type": "code",
|
1289 |
+
"source": [
|
1290 |
+
"import csv\n",
|
1291 |
+
"\n",
|
1292 |
+
"rows = []\n",
|
1293 |
+
"\n",
|
1294 |
+
"# Load the file as a JSON\n",
|
1295 |
+
"with open(\"./mini-llama-articles.csv\", mode=\"r\", encoding=\"utf-8\") as file:\n",
|
1296 |
+
" csv_reader = csv.reader(file)\n",
|
1297 |
+
"\n",
|
1298 |
+
" for idx, row in enumerate( csv_reader ):\n",
|
1299 |
+
" if idx == 0: continue; # Skip header row\n",
|
1300 |
+
" rows.append( row )\n",
|
1301 |
+
"\n",
|
1302 |
+
"# The number of characters in the dataset.\n",
|
1303 |
+
"len( rows )"
|
1304 |
+
],
|
1305 |
+
"metadata": {
|
1306 |
+
"colab": {
|
1307 |
+
"base_uri": "https://localhost:8080/"
|
1308 |
+
},
|
1309 |
+
"id": "_WER5lt0N7c5",
|
1310 |
+
"outputId": "3abbb956-12ed-4663-ade9-eb45d0784ee1"
|
1311 |
+
},
|
1312 |
+
"execution_count": null,
|
1313 |
+
"outputs": [
|
1314 |
+
{
|
1315 |
+
"output_type": "execute_result",
|
1316 |
+
"data": {
|
1317 |
+
"text/plain": [
|
1318 |
+
"14"
|
1319 |
+
]
|
1320 |
+
},
|
1321 |
+
"metadata": {},
|
1322 |
+
"execution_count": 27
|
1323 |
+
}
|
1324 |
+
]
|
1325 |
+
},
|
1326 |
+
{
|
1327 |
+
"cell_type": "code",
|
1328 |
+
"source": [
|
1329 |
+
"rows[0][3]"
|
1330 |
+
],
|
1331 |
+
"metadata": {
|
1332 |
+
"colab": {
|
1333 |
+
"base_uri": "https://localhost:8080/",
|
1334 |
+
"height": 35
|
1335 |
+
},
|
1336 |
+
"id": "NonYMN-Ihx1O",
|
1337 |
+
"outputId": "f6fc2829-8a5b-493e-ec97-e1b8d6b66c03"
|
1338 |
+
},
|
1339 |
+
"execution_count": null,
|
1340 |
+
"outputs": [
|
1341 |
+
{
|
1342 |
+
"output_type": "execute_result",
|
1343 |
+
"data": {
|
1344 |
+
"text/plain": [
|
1345 |
+
"'towards_ai'"
|
1346 |
+
],
|
1347 |
+
"application/vnd.google.colaboratory.intrinsic+json": {
|
1348 |
+
"type": "string"
|
1349 |
+
}
|
1350 |
+
},
|
1351 |
+
"metadata": {},
|
1352 |
+
"execution_count": 34
|
1353 |
+
}
|
1354 |
+
]
|
1355 |
+
},
|
1356 |
+
{
|
1357 |
+
"cell_type": "markdown",
|
1358 |
+
"source": [
|
1359 |
+
"# Convert to Document obj"
|
1360 |
+
],
|
1361 |
+
"metadata": {
|
1362 |
+
"id": "wxEStggPdxYs"
|
1363 |
+
}
|
1364 |
+
},
|
1365 |
+
{
|
1366 |
+
"cell_type": "code",
|
1367 |
+
"source": [
|
1368 |
+
"from llama_index import Document\n",
|
1369 |
+
"\n",
|
1370 |
+
"# Convert the chunks to Document objects so the LlamaIndex framework can process them.\n",
|
1371 |
+
"documents = [Document(text=row[1], metadata={\"title\": row[0], \"url\": row[2], \"source_name\": row[3]}) for row in rows]"
|
1372 |
+
],
|
1373 |
+
"metadata": {
|
1374 |
+
"id": "lFvW_886dxKX"
|
1375 |
+
},
|
1376 |
+
"execution_count": null,
|
1377 |
+
"outputs": []
|
1378 |
+
},
|
1379 |
+
{
|
1380 |
+
"cell_type": "code",
|
1381 |
+
"source": [
|
1382 |
+
"len( documents )"
|
1383 |
+
],
|
1384 |
+
"metadata": {
|
1385 |
+
"colab": {
|
1386 |
+
"base_uri": "https://localhost:8080/"
|
1387 |
+
},
|
1388 |
+
"id": "Njoc3XEVkKkf",
|
1389 |
+
"outputId": "02f05737-9dbf-4398-fe21-1f385eacbd13"
|
1390 |
+
},
|
1391 |
+
"execution_count": null,
|
1392 |
+
"outputs": [
|
1393 |
+
{
|
1394 |
+
"output_type": "execute_result",
|
1395 |
+
"data": {
|
1396 |
+
"text/plain": [
|
1397 |
+
"14"
|
1398 |
+
]
|
1399 |
+
},
|
1400 |
+
"metadata": {},
|
1401 |
+
"execution_count": 44
|
1402 |
+
}
|
1403 |
+
]
|
1404 |
+
},
|
1405 |
+
{
|
1406 |
+
"cell_type": "markdown",
|
1407 |
+
"source": [
|
1408 |
+
"# Transforming"
|
1409 |
+
],
|
1410 |
+
"metadata": {
|
1411 |
+
"id": "S17g2RYOjmf2"
|
1412 |
+
}
|
1413 |
+
},
|
1414 |
+
{
|
1415 |
+
"cell_type": "code",
|
1416 |
+
"source": [
|
1417 |
+
"from llama_index.text_splitter import TokenTextSplitter\n",
|
1418 |
+
"\n",
|
1419 |
+
"text_splitter = TokenTextSplitter(\n",
|
1420 |
+
" separator=\" \", chunk_size=512, chunk_overlap=128\n",
|
1421 |
+
")"
|
1422 |
+
],
|
1423 |
+
"metadata": {
|
1424 |
+
"id": "STACTMUR1z9N"
|
1425 |
+
},
|
1426 |
+
"execution_count": null,
|
1427 |
+
"outputs": []
|
1428 |
+
},
|
1429 |
+
{
|
1430 |
+
"cell_type": "code",
|
1431 |
+
"source": [
|
1432 |
+
"from llama_index.extractors import (\n",
|
1433 |
+
" SummaryExtractor,\n",
|
1434 |
+
" QuestionsAnsweredExtractor,\n",
|
1435 |
+
" KeywordExtractor,\n",
|
1436 |
+
")\n",
|
1437 |
+
"from llama_index.embeddings import OpenAIEmbedding\n",
|
1438 |
+
"from llama_index.ingestion import IngestionPipeline\n",
|
1439 |
+
"\n",
|
1440 |
+
"pipeline = IngestionPipeline(\n",
|
1441 |
+
" transformations=[\n",
|
1442 |
+
" text_splitter,\n",
|
1443 |
+
" QuestionsAnsweredExtractor(questions=3, llm=llm),\n",
|
1444 |
+
" SummaryExtractor(summaries=[\"prev\", \"self\"], llm=llm),\n",
|
1445 |
+
" KeywordExtractor(keywords=10, llm=llm),\n",
|
1446 |
+
" OpenAIEmbedding(),\n",
|
1447 |
+
" ],\n",
|
1448 |
+
" vector_store=vector_store\n",
|
1449 |
+
")\n",
|
1450 |
+
"\n",
|
1451 |
+
"pipeline.run(documents=documents, show_progress=True)"
|
1452 |
+
],
|
1453 |
+
"metadata": {
|
1454 |
+
"id": "CtdsIUQ81_hT",
|
1455 |
+
"colab": {
|
1456 |
+
"base_uri": "https://localhost:8080/",
|
1457 |
+
"height": 385,
|
1458 |
+
"referenced_widgets": [
|
1459 |
+
"88b29c392c7d403488f81903b2395dc1",
|
1460 |
+
"81d6771d5cc74dd49cfccc362d5a3c87",
|
1461 |
+
"1a021f3baf754210ac8696ecc555d968",
|
1462 |
+
"35d8b3afc94b4294ac0d5b090a49003c",
|
1463 |
+
"2980851a0f0141fcb4b54aba07366ad9",
|
1464 |
+
"553d09bfb9bc4ceeb0882d5bd6061514",
|
1465 |
+
"13d692f33c85490aaf761d9444f6c145",
|
1466 |
+
"a3f4c5eb33a64fe895d19a5a52426000",
|
1467 |
+
"5b0afc9227e6437ca4ca7a4929f47d7a",
|
1468 |
+
"39e87e82d7604abfa03879003898259f",
|
1469 |
+
"e876a66432c24d39a4630601d0f4ce93",
|
1470 |
+
"f67382c8ddf248c4b4eeb1b596284917",
|
1471 |
+
"61ebc39888444d448f624f1ae848646a",
|
1472 |
+
"a692807d09ba4ea89bfdae50821ee518",
|
1473 |
+
"7fbeb4bc3ea743168a1816b0021e092b",
|
1474 |
+
"ac3c4e3c9b0c4703b5a9148a70c23e21",
|
1475 |
+
"165ccb061bb843a4b44896df7b4d15b0",
|
1476 |
+
"f1a9031e7c3445ee80308888d28f2d66",
|
1477 |
+
"b15acb0416594d44a41df804e42b4cdf",
|
1478 |
+
"4aeb5362822f490aa6cff491dded8111",
|
1479 |
+
"faa803d16fc74ddcbb003485a506569c",
|
1480 |
+
"4f09405744b04ba79ecb18398b49a389"
|
1481 |
+
]
|
1482 |
+
},
|
1483 |
+
"outputId": "b29154c5-8209-4d0e-b546-2e546e6ceeeb"
|
1484 |
+
},
|
1485 |
+
"execution_count": null,
|
1486 |
+
"outputs": [
|
1487 |
+
{
|
1488 |
+
"output_type": "display_data",
|
1489 |
+
"data": {
|
1490 |
+
"text/plain": [
|
1491 |
+
"Parsing nodes: 0%| | 0/14 [00:00<?, ?it/s]"
|
1492 |
+
],
|
1493 |
+
"application/vnd.jupyter.widget-view+json": {
|
1494 |
+
"version_major": 2,
|
1495 |
+
"version_minor": 0,
|
1496 |
+
"model_id": "88b29c392c7d403488f81903b2395dc1"
|
1497 |
+
}
|
1498 |
+
},
|
1499 |
+
"metadata": {}
|
1500 |
+
},
|
1501 |
+
{
|
1502 |
+
"output_type": "stream",
|
1503 |
+
"name": "stdout",
|
1504 |
+
"text": [
|
1505 |
+
"464\n",
|
1506 |
+
"452\n",
|
1507 |
+
"457\n",
|
1508 |
+
"465\n",
|
1509 |
+
"448\n",
|
1510 |
+
"468\n",
|
1511 |
+
"434\n",
|
1512 |
+
"447\n",
|
1513 |
+
"455\n",
|
1514 |
+
"445\n",
|
1515 |
+
"449\n",
|
1516 |
+
"455\n",
|
1517 |
+
"431\n",
|
1518 |
+
"453\n"
|
1519 |
+
]
|
1520 |
+
},
|
1521 |
+
{
|
1522 |
+
"output_type": "stream",
|
1523 |
+
"name": "stderr",
|
1524 |
+
"text": [
|
1525 |
+
"100%|ββββββββββ| 108/108 [00:48<00:00, 2.22it/s]\n",
|
1526 |
+
"100%|ββββββββββ| 108/108 [01:05<00:00, 1.65it/s]\n",
|
1527 |
+
"100%|ββββββββββ| 108/108 [00:48<00:00, 2.22it/s]\n"
|
1528 |
+
]
|
1529 |
+
},
|
1530 |
+
{
|
1531 |
+
"output_type": "display_data",
|
1532 |
+
"data": {
|
1533 |
+
"text/plain": [
|
1534 |
+
"Generating embeddings: 0%| | 0/108 [00:00<?, ?it/s]"
|
1535 |
+
],
|
1536 |
+
"application/vnd.jupyter.widget-view+json": {
|
1537 |
+
"version_major": 2,
|
1538 |
+
"version_minor": 0,
|
1539 |
+
"model_id": "f67382c8ddf248c4b4eeb1b596284917"
|
1540 |
+
}
|
1541 |
+
},
|
1542 |
+
"metadata": {}
|
1543 |
+
}
|
1544 |
+
]
|
1545 |
+
},
|
1546 |
+
{
|
1547 |
+
"cell_type": "markdown",
|
1548 |
+
"source": [
|
1549 |
+
"# Load Indexes"
|
1550 |
+
],
|
1551 |
+
"metadata": {
|
1552 |
+
"id": "EV0ll57p46Dc"
|
1553 |
+
}
|
1554 |
+
},
|
1555 |
+
{
|
1556 |
+
"cell_type": "code",
|
1557 |
+
"source": [
|
1558 |
+
"# Create your index\n",
|
1559 |
+
"db = chromadb.PersistentClient(path=\"./mini-llama-articles\")\n",
|
1560 |
+
"chroma_collection = db.get_or_create_collection(\"mini-llama-articles\")\n",
|
1561 |
+
"vector_store = ChromaVectorStore(chroma_collection=chroma_collection)"
|
1562 |
+
],
|
1563 |
+
"metadata": {
|
1564 |
+
"id": "PS215gCGkGD-"
|
1565 |
+
},
|
1566 |
+
"execution_count": null,
|
1567 |
+
"outputs": []
|
1568 |
+
},
|
1569 |
+
{
|
1570 |
+
"cell_type": "code",
|
1571 |
+
"source": [
|
1572 |
+
"# Create your index\n",
|
1573 |
+
"from llama_index import VectorStoreIndex\n",
|
1574 |
+
"\n",
|
1575 |
+
"index = VectorStoreIndex.from_vector_store(vector_store)"
|
1576 |
+
],
|
1577 |
+
"metadata": {
|
1578 |
+
"id": "HbT3-kRO4Qpt"
|
1579 |
+
},
|
1580 |
+
"execution_count": null,
|
1581 |
+
"outputs": []
|
1582 |
+
},
|
1583 |
+
{
|
1584 |
+
"cell_type": "code",
|
1585 |
+
"source": [
|
1586 |
+
"query_engine = index.as_query_engine()"
|
1587 |
+
],
|
1588 |
+
"metadata": {
|
1589 |
+
"id": "sb61DWU84bHP"
|
1590 |
+
},
|
1591 |
+
"execution_count": null,
|
1592 |
+
"outputs": []
|
1593 |
+
},
|
1594 |
+
{
|
1595 |
+
"cell_type": "code",
|
1596 |
+
"source": [
|
1597 |
+
"res = query_engine.query(\"How many parameters LLaMA2 model has?\")"
|
1598 |
+
],
|
1599 |
+
"metadata": {
|
1600 |
+
"id": "G32W2LMMCmnv"
|
1601 |
+
},
|
1602 |
+
"execution_count": null,
|
1603 |
+
"outputs": []
|
1604 |
+
},
|
1605 |
+
{
|
1606 |
+
"cell_type": "code",
|
1607 |
+
"source": [
|
1608 |
+
"res.response"
|
1609 |
+
],
|
1610 |
+
"metadata": {
|
1611 |
+
"colab": {
|
1612 |
+
"base_uri": "https://localhost:8080/",
|
1613 |
+
"height": 35
|
1614 |
+
},
|
1615 |
+
"id": "obc20cU5Cxf2",
|
1616 |
+
"outputId": "fafff42a-b10d-47e9-8b7f-b0b8d256e31c"
|
1617 |
+
},
|
1618 |
+
"execution_count": null,
|
1619 |
+
"outputs": [
|
1620 |
+
{
|
1621 |
+
"output_type": "execute_result",
|
1622 |
+
"data": {
|
1623 |
+
"text/plain": [
|
1624 |
+
"'The LLaMA2 model has four different parameter sizes: 7 billion, 13 billion, 34 billion, and 70 billion.'"
|
1625 |
+
],
|
1626 |
+
"application/vnd.google.colaboratory.intrinsic+json": {
|
1627 |
+
"type": "string"
|
1628 |
+
}
|
1629 |
+
},
|
1630 |
+
"metadata": {},
|
1631 |
+
"execution_count": 131
|
1632 |
+
}
|
1633 |
+
]
|
1634 |
+
},
|
1635 |
+
{
|
1636 |
+
"cell_type": "code",
|
1637 |
+
"source": [
|
1638 |
+
"for src in res.source_nodes:\n",
|
1639 |
+
" print(\"Node ID\\t\", src.node_id)\n",
|
1640 |
+
" print(\"Title\\t\", src.metadata['title'])\n",
|
1641 |
+
" print(\"Text\\t\", src.text)\n",
|
1642 |
+
" print(\"Score\\t\", src.score)\n",
|
1643 |
+
" print(\"-_\"*20)"
|
1644 |
+
],
|
1645 |
+
"metadata": {
|
1646 |
+
"colab": {
|
1647 |
+
"base_uri": "https://localhost:8080/"
|
1648 |
+
},
|
1649 |
+
"id": "oIAO-saJCzYe",
|
1650 |
+
"outputId": "7756d876-a474-42c3-e1a6-a4c042b8fbab"
|
1651 |
+
},
|
1652 |
+
"execution_count": null,
|
1653 |
+
"outputs": [
|
1654 |
+
{
|
1655 |
+
"output_type": "stream",
|
1656 |
+
"name": "stdout",
|
1657 |
+
"text": [
|
1658 |
+
"Node ID\t cccc8c69-1648-469b-8a2a-ea7f003dbe27\n",
|
1659 |
+
"Title\t Fine-Tuning a Llama-2 7B Model for Python Code Generation\n",
|
1660 |
+
"Text\t New Llama-2 model In mid-July, Meta released its new family of pre-trained and finetuned models called Llama-2, with an open source and commercial character to facilitate its use and expansion. The base model was released with a chat version and sizes 7B, 13B, and 70B. Together with the models, the corresponding papers were published describing their characteristics and relevant points of the learning process, which provide very interesting information on the subject. For pre-training, 40% more tokens were used, reaching 2T, the context length was doubled and the grouped-query attention (GQA) technique was applied to speed up inference on the heavier 70B model. On the standard transformer architecture, RMSNorm normalization, SwiGLU activation, and rotatory positional embedding are used, the context length reaches 4096 tokens, and an Adam optimizer is applied with a cosine learning rate schedule, a weight decay of 0.1 and gradient clipping. The dataset for tuning For our tuning process, we will take a dataset containing about 18,000 examples where the model is asked to build a Python code that solves a given task. This is an extraction of the original dataset [2], where only the Python language examples are selected. Each row contains the description of the task to be solved, an example of data input to the task if applicable, and the generated code fragment that solves the task is provided [3]. Creating the prompt To carry out an instruction fine-tuning, we must transform each one of our data examples as if it were an instruction, outlining its main sections as follows: Output: Fine-tuning the model To carry out this stage, we have used the Google Colab environment, where we have developed a notebook that allows us to run the training in an interactive way and also a Python script to run the training in unattended mode. For the first test runs, a T4 instance with a high RAM capacity is enough, but when it comes to running the whole dataset and epochs, we have opted to use an A100 instance in order to speed up the training and ensure that its execution time is reasonable. In order to be able to\n",
|
1661 |
+
"Score\t 0.768167879324151\n",
|
1662 |
+
"-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_\n",
|
1663 |
+
"Node ID\t 2b138886-4ff7-4c96-9d01-ea883d4f34ed\n",
|
1664 |
+
"Title\t Fine-Tuning a Llama-2 7B Model for Python Code Generation\n",
|
1665 |
+
"Text\t weights As we mention, we have trained \"modification weights\" on the base model, our final model requires merging the pretrained model and the adapters in a single model. You can find and download the model in my Hugging Face account edumunozsala/llama-27b-int4-python-code-20k. Give it a try! Inferencing or generating Python code And finally, we will show you how you can download the model from the Hugging Face Hub and call the model to generate an accurate result: Thanks to Maxime Labonne for an excellent article [9] and Philipp Schmid who provides an inspiring code [8]. Their articles are a must-read for everyone interested in Llama 2 and model fine-tuning. And it is all I have to mention, I hope you find useful this article and claps are welcome!! You can Follow me and Subscribe to my articles, or even connect to me via Linkedin. The code is available in my Github Repository. References [1] Llama-2 paper [2] Link to the original dataset in the Huggingface hub [3] Link to the used dataset in the Huggingface hub [4] Fine-tuning a GPT - LoRA by Chris Kuo/Dr. Dataman [5] Edward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, & Weizhu Chen. (2021). LoRA: Low-Rank Adaptation of Large Language Models. arXiv:2106.09685 [6]. QLoRa: Efficient Finetuning of QuantizedLLMs [7] Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning [8] Extended Guide: Instruction-tune Llama 2 by Philipp Schmid. [9] Fine-Tune Your Own Llama 2 Model in a Colab Notebook by Maxime Labonne [10]. My Github Repository\n",
|
1666 |
+
"Score\t 0.7586440479430622\n",
|
1667 |
+
"-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_\n"
|
1668 |
+
]
|
1669 |
+
}
|
1670 |
+
]
|
1671 |
+
},
|
1672 |
+
{
|
1673 |
+
"cell_type": "markdown",
|
1674 |
+
"source": [
|
1675 |
+
"# No Metadata"
|
1676 |
+
],
|
1677 |
+
"metadata": {
|
1678 |
+
"id": "wvOhbZvl95di"
|
1679 |
+
}
|
1680 |
+
},
|
1681 |
+
{
|
1682 |
+
"cell_type": "code",
|
1683 |
+
"source": [
|
1684 |
+
"from llama_index import Document\n",
|
1685 |
+
"\n",
|
1686 |
+
"# Convert the chunks to Document objects so the LlamaIndex framework can process them.\n",
|
1687 |
+
"documents = [Document(text=row[1]) for row in rows]"
|
1688 |
+
],
|
1689 |
+
"metadata": {
|
1690 |
+
"id": "y5w5ZPbR97iK"
|
1691 |
+
},
|
1692 |
+
"execution_count": null,
|
1693 |
+
"outputs": []
|
1694 |
+
},
|
1695 |
+
{
|
1696 |
+
"cell_type": "code",
|
1697 |
+
"source": [
|
1698 |
+
"from llama_index.text_splitter import TokenTextSplitter\n",
|
1699 |
+
"\n",
|
1700 |
+
"text_splitter = TokenTextSplitter(\n",
|
1701 |
+
" separator=\" \", chunk_size=512, chunk_overlap=128\n",
|
1702 |
+
")"
|
1703 |
+
],
|
1704 |
+
"metadata": {
|
1705 |
+
"id": "WzF8LYgH9-o0"
|
1706 |
+
},
|
1707 |
+
"execution_count": null,
|
1708 |
+
"outputs": []
|
1709 |
+
},
|
1710 |
+
{
|
1711 |
+
"cell_type": "code",
|
1712 |
+
"source": [
|
1713 |
+
"from llama_index.extractors import (\n",
|
1714 |
+
" SummaryExtractor,\n",
|
1715 |
+
" QuestionsAnsweredExtractor,\n",
|
1716 |
+
" KeywordExtractor,\n",
|
1717 |
+
")\n",
|
1718 |
+
"from llama_index.embeddings import OpenAIEmbedding\n",
|
1719 |
+
"from llama_index.ingestion import IngestionPipeline\n",
|
1720 |
+
"\n",
|
1721 |
+
"pipeline = IngestionPipeline(\n",
|
1722 |
+
" transformations=[\n",
|
1723 |
+
" text_splitter\n",
|
1724 |
+
" ]\n",
|
1725 |
+
")\n",
|
1726 |
+
"\n",
|
1727 |
+
"nodes = pipeline.run(documents=documents, show_progress=True)"
|
1728 |
+
],
|
1729 |
+
"metadata": {
|
1730 |
+
"colab": {
|
1731 |
+
"base_uri": "https://localhost:8080/",
|
1732 |
+
"height": 299,
|
1733 |
+
"referenced_widgets": [
|
1734 |
+
"685e146910634868b154ba03885d8b4c",
|
1735 |
+
"fefe61069a1a416cbb512e1f006c82b0",
|
1736 |
+
"3cac12c147134eb4b71561f17345712d",
|
1737 |
+
"810b0e9e274a433892f87040283b4db9",
|
1738 |
+
"11629aeef5a146e79869fded9f603d6d",
|
1739 |
+
"dfe6494357d040ac8d51d03069822e41",
|
1740 |
+
"190de89f93d048658ee4788ee4af4418",
|
1741 |
+
"835fd209022c4086b509bf42084243b2",
|
1742 |
+
"4b27da15dad34e839a4a02dab06d3e5a",
|
1743 |
+
"afa339155f4b4ffaa5fc70457b6b7a69",
|
1744 |
+
"e8d0668d65dd4743b25c1bc74e1d8057"
|
1745 |
+
]
|
1746 |
+
},
|
1747 |
+
"id": "hYGkf-Rf-DKd",
|
1748 |
+
"outputId": "a1117309-317c-42c0-9b66-8efe3af493f4"
|
1749 |
+
},
|
1750 |
+
"execution_count": null,
|
1751 |
+
"outputs": [
|
1752 |
+
{
|
1753 |
+
"output_type": "display_data",
|
1754 |
+
"data": {
|
1755 |
+
"text/plain": [
|
1756 |
+
"Parsing nodes: 0%| | 0/14 [00:00<?, ?it/s]"
|
1757 |
+
],
|
1758 |
+
"application/vnd.jupyter.widget-view+json": {
|
1759 |
+
"version_major": 2,
|
1760 |
+
"version_minor": 0,
|
1761 |
+
"model_id": "685e146910634868b154ba03885d8b4c"
|
1762 |
+
}
|
1763 |
+
},
|
1764 |
+
"metadata": {}
|
1765 |
+
},
|
1766 |
+
{
|
1767 |
+
"output_type": "stream",
|
1768 |
+
"name": "stdout",
|
1769 |
+
"text": [
|
1770 |
+
"510\n",
|
1771 |
+
"510\n",
|
1772 |
+
"510\n",
|
1773 |
+
"510\n",
|
1774 |
+
"510\n",
|
1775 |
+
"510\n",
|
1776 |
+
"510\n",
|
1777 |
+
"510\n",
|
1778 |
+
"510\n",
|
1779 |
+
"510\n",
|
1780 |
+
"510\n",
|
1781 |
+
"510\n",
|
1782 |
+
"510\n",
|
1783 |
+
"510\n"
|
1784 |
+
]
|
1785 |
+
}
|
1786 |
+
]
|
1787 |
+
},
|
1788 |
+
{
|
1789 |
+
"cell_type": "code",
|
1790 |
+
"source": [
|
1791 |
+
"from llama_index import ServiceContext\n",
|
1792 |
+
"\n",
|
1793 |
+
"index_no_metadata = VectorStoreIndex(\n",
|
1794 |
+
" nodes=nodes,\n",
|
1795 |
+
" service_context=ServiceContext.from_defaults(llm=OpenAI(model=\"gpt-3.5-turbo\")),\n",
|
1796 |
+
")"
|
1797 |
+
],
|
1798 |
+
"metadata": {
|
1799 |
+
"id": "2FR8rgOd-Jt2"
|
1800 |
+
},
|
1801 |
+
"execution_count": null,
|
1802 |
+
"outputs": []
|
1803 |
+
},
|
1804 |
+
{
|
1805 |
+
"cell_type": "code",
|
1806 |
+
"source": [
|
1807 |
+
"query_engine_no_metadata = index_no_metadata.as_query_engine()"
|
1808 |
+
],
|
1809 |
+
"metadata": {
|
1810 |
+
"id": "HfzZ7Xyx-mbX"
|
1811 |
+
},
|
1812 |
+
"execution_count": null,
|
1813 |
+
"outputs": []
|
1814 |
+
},
|
1815 |
+
{
|
1816 |
+
"cell_type": "code",
|
1817 |
+
"source": [
|
1818 |
+
"res = query_engine_no_metadata.query(\"How many parameters LLaMA2 model has?\")"
|
1819 |
+
],
|
1820 |
+
"metadata": {
|
1821 |
+
"id": "n8WQJFuLD4FW"
|
1822 |
+
},
|
1823 |
+
"execution_count": null,
|
1824 |
+
"outputs": []
|
1825 |
+
},
|
1826 |
+
{
|
1827 |
+
"cell_type": "code",
|
1828 |
+
"source": [
|
1829 |
+
"res.response"
|
1830 |
+
],
|
1831 |
+
"metadata": {
|
1832 |
+
"colab": {
|
1833 |
+
"base_uri": "https://localhost:8080/",
|
1834 |
+
"height": 35
|
1835 |
+
},
|
1836 |
+
"id": "uZw_S9gNGS17",
|
1837 |
+
"outputId": "b7ce3cd0-296d-400a-d12a-6b39dd2c008a"
|
1838 |
+
},
|
1839 |
+
"execution_count": null,
|
1840 |
+
"outputs": [
|
1841 |
+
{
|
1842 |
+
"output_type": "execute_result",
|
1843 |
+
"data": {
|
1844 |
+
"text/plain": [
|
1845 |
+
"'The context information does not provide any information about the number of parameters in the LLaMA2 model.'"
|
1846 |
+
],
|
1847 |
+
"application/vnd.google.colaboratory.intrinsic+json": {
|
1848 |
+
"type": "string"
|
1849 |
+
}
|
1850 |
+
},
|
1851 |
+
"metadata": {},
|
1852 |
+
"execution_count": 134
|
1853 |
+
}
|
1854 |
+
]
|
1855 |
+
},
|
1856 |
+
{
|
1857 |
+
"cell_type": "code",
|
1858 |
+
"source": [
|
1859 |
+
"for src in res.source_nodes:\n",
|
1860 |
+
" print( src )\n",
|
1861 |
+
" print(\"-_\"*20)"
|
1862 |
+
],
|
1863 |
+
"metadata": {
|
1864 |
+
"colab": {
|
1865 |
+
"base_uri": "https://localhost:8080/"
|
1866 |
+
},
|
1867 |
+
"id": "V6Rm7v8eD3xh",
|
1868 |
+
"outputId": "88ede9b3-c322-4968-f99d-b27e482ca050"
|
1869 |
+
},
|
1870 |
+
"execution_count": null,
|
1871 |
+
"outputs": [
|
1872 |
+
{
|
1873 |
+
"output_type": "stream",
|
1874 |
+
"name": "stdout",
|
1875 |
+
"text": [
|
1876 |
+
"Node ID: 895debf4-60ad-4156-8f52-cdddf03b1138\n",
|
1877 |
+
"Text: I. Llama 2: Revolutionizing Commercial Use Unlike its\n",
|
1878 |
+
"predecessor Llama 1, which was limited to research use, Llama 2\n",
|
1879 |
+
"represents a major advancement as an open-source commercial model.\n",
|
1880 |
+
"Businesses can now integrate Llama 2 into products to create AI-\n",
|
1881 |
+
"powered applications. Availability on Azure and AWS facilitates fine-\n",
|
1882 |
+
"tuning and adoption. However,...\n",
|
1883 |
+
"Score: 0.852\n",
|
1884 |
+
"\n",
|
1885 |
+
"-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_\n",
|
1886 |
+
"Node ID: a919ca6a-bdda-4d92-a7b2-ab4048cdc0d8\n",
|
1887 |
+
"Text: basis. The sharing of codes and weights allows other researchers\n",
|
1888 |
+
"to test new approaches in LLMs. The LLaMA models have a range of 7\n",
|
1889 |
+
"billion to 65 billion parameters. LLaMA-65B can be compared to\n",
|
1890 |
+
"DeepMind's Chinchilla and Google's PaLM. Publicly available unlabeled\n",
|
1891 |
+
"data was used to train these models, and training smaller foundational\n",
|
1892 |
+
"models requ...\n",
|
1893 |
+
"Score: 0.830\n",
|
1894 |
+
"\n",
|
1895 |
+
"-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_\n"
|
1896 |
+
]
|
1897 |
+
}
|
1898 |
+
]
|
1899 |
+
}
|
1900 |
+
]
|
1901 |
+
}
|