Skip to content

Summary objects

Wordcab API Summary object.

BaseSummary dataclass

Summary object.

Source code in src/wordcab/core_objects/summary.py 
 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
@dataclass
class BaseSummary:
    """Summary object."""

    job_status: str
    summary_id: str
    display_name: Optional[str] = field(default=None)
    job_name: Optional[str] = field(default=None)
    process_time: Optional[str] = field(default=None)
    speaker_map: Optional[Dict[str, str]] = field(default=None)
    source: Optional[str] = field(default=None)
    source_lang: Optional[str] = field(default=None)
    summary_type: Optional[str] = field(default=None)
    summary: Optional[Dict[str, Any]] = field(default=None)
    target_lang: Optional[str] = field(default=None)
    transcript_id: Optional[str] = field(default=None)
    time_started: Optional[str] = field(default=None)
    time_completed: Optional[str] = field(default=None)

    def __post_init__(self) -> None:
        """Post init."""
        if self.summary_type:
            if self.summary_type not in SUMMARY_TYPES:
                raise ValueError(
                    f"Summary type must be one of {SUMMARY_TYPES}, not"
                    f" {self.summary_type}"
                )

        if self.time_started and self.time_completed:
            if self.time_started == self.time_completed:
                raise ValueError("time_started and time_completed must be different")

    def get_summaries(self) -> Dict[str, List[Union[str, List[str]]]]:
        """
        Get the summaries as a dictionary with the summary length as key and the summaries as values.

        Returns
        -------
        Dict[str, List[Union[str, List[str]]]]
            The summaries as a dictionnary with the summary length as key and the summaries as values.
            If the summary type is brief, the summaries are returned as a list of list of str,
            otherwise they are returned as a list of str.
        """
        if self.summary is None:
            return {}

        summaries: Dict[str, Any] = {}

        for summary_len in self.summary:
            summaries_list = [
                s.summary for s in self.summary[summary_len]["structured_summary"]
            ]

            if self.summary_type == "brief":
                summaries_list = [
                    [s["title"], s["brief_summary"]] for s in summaries_list
                ]

            summaries[summary_len] = summaries_list

        return summaries

    def get_formatted_summaries(
        self, add_context: Optional[bool] = False
    ) -> Dict[str, str]:
        """Format the summaries in an human readable format.

        Return the summaries as a dictionary in an human readable format with the summary length as key
        and the summaries as values.

        Parameters
        ----------
        add_context : bool, optional
            If True, add the context items to the summary, by default False.

        Returns
        -------
        Dict[str, str]
            The summaries as a dictionary with the summary length as key and the summaries as values formatted
            in an human readable format.
        """
        if self.summary is None:
            return {}

        summaries: Dict[str, Any] = {}

        if self.summary is None:
            raise ValueError("No summary available.")

        if self.summary_type is None:
            raise ValueError("No summary type found.")

        for summary_len in self.summary:
            summaries[summary_len] = _format_summary(
                self.summary[summary_len]["structured_summary"],
                self.summary_type,
                summary_len,
                add_context,
            )

        return summaries

__post_init__()

Post init.

Source code in src/wordcab/core_objects/summary.py 
70
71
72
73
74
75
76
77
78
79
80
81
def __post_init__(self) -> None:
    """Post init."""
    if self.summary_type:
        if self.summary_type not in SUMMARY_TYPES:
            raise ValueError(
                f"Summary type must be one of {SUMMARY_TYPES}, not"
                f" {self.summary_type}"
            )

    if self.time_started and self.time_completed:
        if self.time_started == self.time_completed:
            raise ValueError("time_started and time_completed must be different")

get_formatted_summaries(add_context=False)

Format the summaries in an human readable format.

Return the summaries as a dictionary in an human readable format with the summary length as key and the summaries as values.

Parameters:

Name Type Description Default
add_context bool

If True, add the context items to the summary, by default False.

 False

Returns:

Type Description
Dict[str, str]

The summaries as a dictionary with the summary length as key and the summaries as values formatted in an human readable format.
Source code in src/wordcab/core_objects/summary.py 
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
def get_formatted_summaries(
    self, add_context: Optional[bool] = False
) -> Dict[str, str]:
    """Format the summaries in an human readable format.

    Return the summaries as a dictionary in an human readable format with the summary length as key
    and the summaries as values.

    Parameters
    ----------
    add_context : bool, optional
        If True, add the context items to the summary, by default False.

    Returns
    -------
    Dict[str, str]
        The summaries as a dictionary with the summary length as key and the summaries as values formatted
        in an human readable format.
    """
    if self.summary is None:
        return {}

    summaries: Dict[str, Any] = {}

    if self.summary is None:
        raise ValueError("No summary available.")

    if self.summary_type is None:
        raise ValueError("No summary type found.")

    for summary_len in self.summary:
        summaries[summary_len] = _format_summary(
            self.summary[summary_len]["structured_summary"],
            self.summary_type,
            summary_len,
            add_context,
        )

    return summaries

get_summaries()

Get the summaries as a dictionary with the summary length as key and the summaries as values.

Returns:

Type Description
Dict[str, List[Union[str, List[str]]]]

The summaries as a dictionnary with the summary length as key and the summaries as values. If the summary type is brief, the summaries are returned as a list of list of str, otherwise they are returned as a list of str.
Source code in src/wordcab/core_objects/summary.py 
 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
def get_summaries(self) -> Dict[str, List[Union[str, List[str]]]]:
    """
    Get the summaries as a dictionary with the summary length as key and the summaries as values.

    Returns
    -------
    Dict[str, List[Union[str, List[str]]]]
        The summaries as a dictionnary with the summary length as key and the summaries as values.
        If the summary type is brief, the summaries are returned as a list of list of str,
        otherwise they are returned as a list of str.
    """
    if self.summary is None:
        return {}

    summaries: Dict[str, Any] = {}

    for summary_len in self.summary:
        summaries_list = [
            s.summary for s in self.summary[summary_len]["structured_summary"]
        ]

        if self.summary_type == "brief":
            summaries_list = [
                [s["title"], s["brief_summary"]] for s in summaries_list
            ]

        summaries[summary_len] = summaries_list

    return summaries

ListSummaries dataclass

List summaries object.

Source code in src/wordcab/core_objects/summary.py 
154
155
156
157
158
159
160
@dataclass
class ListSummaries:
    """List summaries object."""

    page_count: int
    next_page: str
    results: List[BaseSummary]

StructuredSummary dataclass

Structured summary object.

Source code in src/wordcab/core_objects/summary.py 
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
@dataclass
class StructuredSummary:
    """Structured summary object."""

    summary: Union[str, Dict[str, str]]
    context: Optional[
        Dict[str, Union[str, List[str], Dict[str, Union[str, List[str]]]]]
    ] = field(default=None)
    summary_html: Optional[Union[str, Dict[str, str]]] = field(default=None)
    end: Optional[str] = field(default=None)
    end_index: Optional[int] = field(default=None)
    start: Optional[str] = field(default=None)
    start_index: Optional[int] = field(default=None)
    timestamp_end: Optional[int] = field(default=None)
    timestamp_start: Optional[int] = field(default=None)
    transcript_segment: Optional[List[Dict[str, Union[str, int]]]] = field(default=None)

    def __repr__(self) -> str:
        """Return a string representation of the object without the None values."""
        return (
            f"{self.__class__.__name__}({', '.join(f'{k}={v!r}' for k, v in self.__dict__.items() if v is not None)})"
        )

__repr__()

Return a string representation of the object without the None values.

Source code in src/wordcab/core_objects/summary.py 
44
45
46
47
48
def __repr__(self) -> str:
    """Return a string representation of the object without the None values."""
    return (
        f"{self.__class__.__name__}({', '.join(f'{k}={v!r}' for k, v in self.__dict__.items() if v is not None)})"
    )
Last update: 2023-09-25
Created: 2023-09-25