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
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
|
{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# hide\n",
"%load_ext autoreload\n",
"%autoreload 2"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Vespa - Application Package\n",
"\n",
"> Python API to create, modify and deploy application packages"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Our goal is to create, modify and deploy simple application packages using our python API. This enables us to run data analysis experiments that are fully integrated with Vespa. As an example, we want to create the application package we used in our [text search tutorial](https://docs.vespa.ai/documentation/tutorials/text-search.html). "
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Application spec"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Our goal in this section is to create the following `msmarco` schema using our python API."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"```\n",
"schema msmarco {\n",
" document msmarco {\n",
" field id type string {\n",
" indexing: attribute | summary\n",
" }\n",
" field title type string {\n",
" indexing: index | summary\n",
" index: enable-bm25\n",
" }\n",
" field body type string {\n",
" indexing: index | summary\n",
" index: enable-bm25\n",
" }\n",
" }\n",
"\n",
" fieldset default {\n",
" fields: title, body\n",
" }\n",
"\n",
" rank-profile default {\n",
" first-phase {\n",
" expression: nativeRank(title, body)\n",
" }\n",
" }\n",
"\n",
" rank-profile bm25 inherits default {\n",
" first-phase {\n",
" expression: bm25(title) + bm25(body)\n",
" }\n",
" }\n",
"\n",
"}\n",
"```"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Schema API"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from vespa.package import Document, Field, Schema, FieldSet, RankProfile, ApplicationPackage\n",
"\n",
"document = Document(\n",
" fields=[\n",
" Field(name = \"id\", type = \"string\", indexing = [\"attribute\", \"summary\"]),\n",
" Field(name = \"title\", type = \"string\", indexing = [\"index\", \"summary\"], index = \"enable-bm25\"),\n",
" Field(name = \"body\", type = \"string\", indexing = [\"index\", \"summary\"], index = \"enable-bm25\") \n",
" ]\n",
")\n",
"\n",
"msmarco_schema = Schema(\n",
" name = \"msmarco\", \n",
" document = document, \n",
" fieldsets = [FieldSet(name = \"default\", fields = [\"title\", \"body\"])],\n",
" rank_profiles = [RankProfile(name = \"default\", first_phase = \"nativeRank(title, body)\")]\n",
")\n",
"\n",
"app_package = ApplicationPackage(name = \"msmarco\", schema=msmarco_schema)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Deploy it locally"
]
},
{
"cell_type": "raw",
"metadata": {},
"source": [
"from vespa.package import VespaDocker\n",
"\n",
"vespa_docker = VespaDocker(application_package=app_package)\n",
"vespa_docker.deploy(disk_folder=\"/Users/username/sample_application\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Change the application package and redeploy"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"We can add a new rank profile and redeploy our application"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"app_package.schema.add_rank_profile(\n",
" RankProfile(name = \"bm25\", inherits = \"default\", first_phase = \"bm25(title) + bm25(body)\")\n",
")"
]
},
{
"cell_type": "raw",
"metadata": {},
"source": [
"vespa_docker.deploy(disk_folder=\"/Users/username/sample_application\")"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "vespa",
"language": "python",
"name": "vespa"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
|
