Skip to content

Commit 00b5099

Browse files
sycaisycai
committed
docs: add an intro notebook for bbq AI functions
1 parent 8514200 commit 00b5099

File tree

1 file changed

+196
-0
lines changed

1 file changed

+196
-0
lines changed

‎notebooks/generative_ai/ai_functions.ipynb‎

Lines changed: 196 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,196 @@
1+
{
2+
"cells": [
3+
{
4+
"cell_type": "code",
5+
"execution_count": null,
6+
"id": "acd53f9d",
7+
"metadata": {},
8+
"outputs": [],
9+
"source": [
10+
"# Copyright 2025 Google LLC\n",
11+
"#\n",
12+
"# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
13+
"# you may not use this file except in compliance with the License.\n",
14+
"# You may obtain a copy of the License at\n",
15+
"#\n",
16+
"# https://www.apache.org/licenses/LICENSE-2.0\n",
17+
"#\n",
18+
"# Unless required by applicable law or agreed to in writing, software\n",
19+
"# distributed under the License is distributed on an \"AS IS\" BASIS,\n",
20+
"# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n",
21+
"# See the License for the specific language governing permissions and\n",
22+
"# limitations under the License."
23+
]
24+
},
25+
{
26+
"cell_type": "markdown",
27+
"id": "e75ce682",
28+
"metadata": {},
29+
"source": [
30+
"# BigQuery DataFrames (BigFrames) AI Functions\n",
31+
"\n",
32+
"<table align=\"left\">\n",
33+
"\n",
34+
" <td>\n",
35+
" <a href=\"https://colab.research.google.com/github/googleapis/python-bigquery-dataframes/blob/main/notebooks/generative_ai/ai_functions.ipynb\">\n",
36+
" <img src=\"https://raw.githubusercontent.com/googleapis/python-bigquery-dataframes/refs/heads/main/third_party/logo/colab-logo.png\" alt=\"Colab logo\"> Run in Colab\n",
37+
" </a>\n",
38+
" </td>\n",
39+
" <td>\n",
40+
" <a href=\"https://github.com/googleapis/python-bigquery-dataframes/blob/main/notebooks/generative_ai/ai_functions.ipynb\">\n",
41+
" <img src=\"https://raw.githubusercontent.com/googleapis/python-bigquery-dataframes/refs/heads/main/third_party/logo/github-logo.png\" width=\"32\" alt=\"GitHub logo\">\n",
42+
" View on GitHub\n",
43+
" </a>\n",
44+
" </td>\n",
45+
" <td>\n",
46+
" <a href=\"https://console.cloud.google.com/bigquery/import?url=https://github.com/googleapis/python-bigquery-dataframes/blob/main/notebooks/generative_ai/ai_functions.ipynb\">\n",
47+
" <img src=\"https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcTW1gvOovVlbZAIZylUtf5Iu8-693qS1w5NJw&s\" alt=\"BQ logo\" width=\"35\">\n",
48+
" Open in BQ Studio\n",
49+
" </a>\n",
50+
" </td>\n",
51+
"</table>"
52+
]
53+
},
54+
{
55+
"cell_type": "markdown",
56+
"id": "aee05821",
57+
"metadata": {},
58+
"source": [
59+
"This notebooks provides examples on how to use BigFrames AI functions, which are offered under the `bigframes.bigquery` package. "
60+
]
61+
},
62+
{
63+
"cell_type": "markdown",
64+
"id": "1232f400",
65+
"metadata": {},
66+
"source": [
67+
"## Preparation\n",
68+
"\n",
69+
"First, set up your BigFrames environment"
70+
]
71+
},
72+
{
73+
"cell_type": "code",
74+
"execution_count": 3,
75+
"id": "c9f924aa",
76+
"metadata": {},
77+
"outputs": [],
78+
"source": [
79+
"import bigframes.pandas as bpd \n",
80+
"\n",
81+
"PROJECT_ID = \"bigframes-dev\" # Your project ID here\n",
82+
"\n",
83+
"bpd.options.bigquery.project = PROJECT_ID\n",
84+
"bpd.options.bigquery.ordering_mode = \"partial\"\n",
85+
"bpd.options.display.progress_bar = None"
86+
]
87+
},
88+
{
89+
"cell_type": "markdown",
90+
"id": "e2188773",
91+
"metadata": {},
92+
"source": [
93+
"## ai.generate\n",
94+
"\n",
95+
"The `ai.generate` function lets you analyze any combination of text and unstructured data from BigQuery. You can mix BigFrames/Pandas series with string literals as your prompt in the form of a tuple. Here is an example:"
96+
]
97+
},
98+
{
99+
"cell_type": "code",
100+
"execution_count": 5,
101+
"id": "471a47fe",
102+
"metadata": {},
103+
"outputs": [
104+
{
105+
"data": {
106+
"text/plain": [
107+
"0 {'result': 'Salad\\n', 'full_response': '{\"cand...\n",
108+
"1 {'result': 'Hotdog\\n', 'full_response': '{\"can...\n",
109+
"dtype: struct<result: string, full_response: extension<dbjson<JSONArrowType>>, status: string>[pyarrow]"
110+
]
111+
},
112+
"execution_count": 5,
113+
"metadata": {},
114+
"output_type": "execute_result"
115+
}
116+
],
117+
"source": [
118+
"import bigframes.bigquery as bbq\n",
119+
"\n",
120+
"ingredients1 = bpd.Series([\"Lettuce\", \"Sausage\"])\n",
121+
"ingredients2 = bpd.Series([\"Cucumber\", \"Long Bread\"])\n",
122+
"\n",
123+
"prompt = (\"What's the food made from \", ingredients1, \" and \", ingredients2, \" One word only\")\n",
124+
"bbq.ai.generate(prompt)"
125+
]
126+
},
127+
{
128+
"cell_type": "markdown",
129+
"id": "03953835",
130+
"metadata": {},
131+
"source": [
132+
"The function returns a series of structs. The `'result'` field holds the answer, while more metadata can be found in the `'full_response'` field. The `'status'` field tells you whether LLM made a successful response for that specific row. "
133+
]
134+
},
135+
{
136+
"cell_type": "markdown",
137+
"id": "b606c51f",
138+
"metadata": {},
139+
"source": [
140+
"You can also include additional model parameters into your function call, as long as they satisfy the structure of `generateContent` [request body format](https://cloud.google.com/vertex-ai/docs/reference/rest/v1/projects.locations.endpoints/generateContent#request-body) For example:"
141+
]
142+
},
143+
{
144+
"cell_type": "code",
145+
"execution_count": null,
146+
"id": "4a3229a8",
147+
"metadata": {},
148+
"outputs": [
149+
{
150+
"data": {
151+
"text/plain": [
152+
"1 The food made from sausage and long bread is m...\n",
153+
"0 Lettuce and cucumber are commonly used togethe...\n",
154+
"Name: result, dtype: string"
155+
]
156+
},
157+
"execution_count": 7,
158+
"metadata": {},
159+
"output_type": "execute_result"
160+
}
161+
],
162+
"source": [
163+
"model_params = {\n",
164+
" \"generationConfig\": {\"maxOutputTokens\": 1}\n",
165+
"}\n",
166+
"\n",
167+
"ingredients1 = bpd.Series([\"Lettuce\", \"Sausage\"])\n",
168+
"ingredients2 = bpd.Series([\"Cucumber\", \"Long Bread\"])\n",
169+
"\n",
170+
"prompt = (\"What's the food made from \", ingredients1, \" and \", ingredients2)\n",
171+
"bbq.ai.generate(prompt).struct.field(\"result\")"
172+
]
173+
}
174+
],
175+
"metadata": {
176+
"kernelspec": {
177+
"display_name": "venv (3.10.17)",
178+
"language": "python",
179+
"name": "python3"
180+
},
181+
"language_info": {
182+
"codemirror_mode": {
183+
"name": "ipython",
184+
"version": 3
185+
},
186+
"file_extension": ".py",
187+
"mimetype": "text/x-python",
188+
"name": "python",
189+
"nbconvert_exporter": "python",
190+
"pygments_lexer": "ipython3",
191+
"version": "3.10.17"
192+
}
193+
},
194+
"nbformat": 4,
195+
"nbformat_minor": 5
196+
}

0 commit comments

Comments
 (0)