python-bigquery-dataframes/bigframes/operations/ai_ops.py at d29f83d71c3bb141e83ef3a5db7af68c212ec4d9 · googleapis/python-bigquery-dataframes · GitHub

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
# Copyright 2025 Google LLC
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

from __future__ import annotations

import dataclasses
from typing import ClassVar, Literal, Tuple

import pandas as pd
import pyarrow as pa

from bigframes import dtypes
from bigframes.operations import base_ops


@dataclasses.dataclass(frozen=True)
class AIGenerate(base_ops.NaryOp):
    name: ClassVar[str] = "ai_generate"

    prompt_context: Tuple[str | None, ...]
    connection_id: str
    endpoint: str | None
    request_type: Literal["dedicated", "shared", "unspecified"]
    model_params: str | None

    def output_type(self, *input_types: dtypes.ExpressionType) -> dtypes.ExpressionType:
        return pd.ArrowDtype(
            pa.struct(
                (
                    pa.field("result", pa.string()),
                    pa.field("full_response", dtypes.JSON_ARROW_TYPE),
                    pa.field("status", pa.string()),
                )
            )
        )


@dataclasses.dataclass(frozen=True)
class AIGenerateBool(base_ops.NaryOp):
    name: ClassVar[str] = "ai_generate_bool"

    prompt_context: Tuple[str | None, ...]
    connection_id: str
    endpoint: str | None
    request_type: Literal["dedicated", "shared", "unspecified"]
    model_params: str | None

    def output_type(self, *input_types: dtypes.ExpressionType) -> dtypes.ExpressionType:
        return pd.ArrowDtype(
            pa.struct(
                (
                    pa.field("result", pa.bool_()),
                    pa.field("full_response", dtypes.JSON_ARROW_TYPE),
                    pa.field("status", pa.string()),
                )
            )
        )


@dataclasses.dataclass(frozen=True)
class AIGenerateInt(base_ops.NaryOp):
    name: ClassVar[str] = "ai_generate_int"

    prompt_context: Tuple[str | None, ...]
    connection_id: str
    endpoint: str | None
    request_type: Literal["dedicated", "shared", "unspecified"]
    model_params: str | None

    def output_type(self, *input_types: dtypes.ExpressionType) -> dtypes.ExpressionType:
        return pd.ArrowDtype(
            pa.struct(
                (
                    pa.field("result", pa.int64()),
                    pa.field("full_response", dtypes.JSON_ARROW_TYPE),
                    pa.field("status", pa.string()),
                )
            )
        )


@dataclasses.dataclass(frozen=True)
class AIGenerateDouble(base_ops.NaryOp):
    name: ClassVar[str] = "ai_generate_double"

    prompt_context: Tuple[str | None, ...]
    connection_id: str
    endpoint: str | None
    request_type: Literal["dedicated", "shared", "unspecified"]
    model_params: str | None

    def output_type(self, *input_types: dtypes.ExpressionType) -> dtypes.ExpressionType:
        return pd.ArrowDtype(
            pa.struct(
                (
                    pa.field("result", pa.float64()),
                    pa.field("full_response", dtypes.JSON_ARROW_TYPE),
                    pa.field("status", pa.string()),
                )
            )
        )


@dataclasses.dataclass(frozen=True)
class AIIf(base_ops.NaryOp):
    name: ClassVar[str] = "ai_if"

    prompt_context: Tuple[str | None, ...]
    connection_id: str

    def output_type(self, *input_types: dtypes.ExpressionType) -> dtypes.ExpressionType:
        return dtypes.BOOL_DTYPE


@dataclasses.dataclass(frozen=True)
class AIScore(base_ops.NaryOp):
    name: ClassVar[str] = "ai_score"

    prompt_context: Tuple[str | None, ...]
    connection_id: str

    def output_type(self, *input_types: dtypes.ExpressionType) -> dtypes.ExpressionType:
        return dtypes.FLOAT_DTYPE