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
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
|
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"id": "c1f56ae3-a056-4b31-bcab-27c2c97c00f1",
"metadata": {},
"outputs": [],
"source": [
"from pathlib import Path\n",
"\n",
"from importlib.util import find_spec\n",
"if find_spec(\"rag\") is None:\n",
" import sys\n",
" sys.path.append('..')\n",
"from rag.rag import RAG"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "6b5cb12e-df7e-4532-b78b-216e11ed6161",
"metadata": {},
"outputs": [],
"source": [
"path = Path(\"/home/aktersnurra/projects/library/quant/math/a-signal-processing-perspective-on-financial-engineering.pdf\")"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "b8382795-9610-4b24-80b7-31397b2faf90",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[32m2024-04-06 01:37:11.913\u001b[0m | \u001b[34m\u001b[1mDEBUG \u001b[0m | \u001b[36mrag.db.document\u001b[0m:\u001b[36m__configure\u001b[0m:\u001b[36m26\u001b[0m - \u001b[34m\u001b[1mCreating documents table if it does not exist...\u001b[0m\n",
"\u001b[32m2024-04-06 01:37:11.926\u001b[0m | \u001b[34m\u001b[1mDEBUG \u001b[0m | \u001b[36mrag.db.vector\u001b[0m:\u001b[36m__configure\u001b[0m:\u001b[36m36\u001b[0m - \u001b[34m\u001b[1mCollection knowledge-base already exists...\u001b[0m\n"
]
}
],
"source": [
"rag = RAG()"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "ac57e50d-1fc3-4fc9-90e5-5bdb97bd2f5e",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[32m2024-04-06 01:37:17.243\u001b[0m | \u001b[34m\u001b[1mDEBUG \u001b[0m | \u001b[36mrag.db.document\u001b[0m:\u001b[36madd_document\u001b[0m:\u001b[36m37\u001b[0m - \u001b[34m\u001b[1mInserting document hash into documents db...\u001b[0m\n",
"\u001b[32m2024-04-06 01:37:17.244\u001b[0m | \u001b[34m\u001b[1mDEBUG \u001b[0m | \u001b[36mrag.db.document\u001b[0m:\u001b[36m__hash\u001b[0m:\u001b[36m32\u001b[0m - \u001b[34m\u001b[1mGenerating sha256 hash for pdf document\u001b[0m\n",
"\u001b[32m2024-04-06 01:37:17.247\u001b[0m | \u001b[34m\u001b[1mDEBUG \u001b[0m | \u001b[36mrag.rag\u001b[0m:\u001b[36madd_pdf\u001b[0m:\u001b[36m31\u001b[0m - \u001b[34m\u001b[1mDocument already exists!\u001b[0m\n"
]
}
],
"source": [
"rag.add_pdf(path)"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "1c6b48d2-eb04-4a7c-8224-78aabfc7c887",
"metadata": {},
"outputs": [],
"source": [
"query = \"What is a factor model?\""
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "a95c8250-00b2-4cbc-a9c6-a76d14ef2da5",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[32m2024-04-06 01:37:17.265\u001b[0m | \u001b[34m\u001b[1mDEBUG \u001b[0m | \u001b[36mrag.llm.encoder\u001b[0m:\u001b[36mencode_query\u001b[0m:\u001b[36m33\u001b[0m - \u001b[34m\u001b[1mEncoding query: What is a factor model?\u001b[0m\n",
"\u001b[32m2024-04-06 01:37:17.858\u001b[0m | \u001b[34m\u001b[1mDEBUG \u001b[0m | \u001b[36mrag.db.vector\u001b[0m:\u001b[36msearch\u001b[0m:\u001b[36m51\u001b[0m - \u001b[34m\u001b[1mSearching for vectors...\u001b[0m\n",
"\u001b[32m2024-04-06 01:37:17.864\u001b[0m | \u001b[34m\u001b[1mDEBUG \u001b[0m | \u001b[36mrag.rag\u001b[0m:\u001b[36m__context\u001b[0m:\u001b[36m35\u001b[0m - \u001b[34m\u001b[1mGot 5 hits in the vector db with limit=5\u001b[0m\n",
"\u001b[32m2024-04-06 01:37:17.865\u001b[0m | \u001b[34m\u001b[1mDEBUG \u001b[0m | \u001b[36mrag.llm.generator\u001b[0m:\u001b[36mgenerate\u001b[0m:\u001b[36m32\u001b[0m - \u001b[34m\u001b[1mGenerating answer...\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'A factor model is a type of model used to explain the returns or movements of financial assets by decomposing them into two parts: systematic risk, which is driven by a small number of factors affecting many securities; and idiosyncratic risk, which is specific to individual stocks. The general factor model is rt = φ0 + h(ft) + wt, where rt denotes the return of an asset at time t, φ0 represents a constant vector, ft is a vector of factors responsible for most of the randomness in the market, and h is a function that summarizes how these low-dimensional factors affect higher-dimensional markets. The residual wt accounts for any remaining uncorrelated perturbations with only a marginal effect on returns.'"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"rag.rag(query, \"quant researcher\", limit=5)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "11ac0d46-8589-4700-abf7-7959afbf611c",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.8"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
|
