File size: 6,468 Bytes
16d905e
360d0c5
16d905e
 
 
 
 
 
 
 
 
 
360d0c5
16d905e
 
 
 
 
 
 
 
 
 
 
360d0c5
16d905e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
360d0c5
16d905e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
405b27f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
# Define the input options for the API
from typing import Annotated, Optional

from pydantic import BaseModel, Field

from docling.datamodel.base_models import InputFormat, OutputFormat
from docling.datamodel.pipeline_options import OcrEngine, PdfBackend, TableFormerMode
from docling_core.types.doc import ImageRefMode


class ConvertDocumentsOptions(BaseModel):
    from_formats: Annotated[
        list[InputFormat],
        Field(
            description=(
                "Input format(s) to convert from. String or list of strings. "
                f"Allowed values: {', '.join([v.value for v in InputFormat])}. "
                "Optional, defaults to all formats."
            ),
            examples=[[v.value for v in InputFormat]],
        ),
    ] = list(InputFormat)

    to_formats: Annotated[
        list[OutputFormat],
        Field(
            description=(
                "Output format(s) to convert to. String or list of strings. "
                f"Allowed values: {', '.join([v.value for v in OutputFormat])}. "
                "Optional, defaults to Markdown."
            ),
            examples=[[OutputFormat.MARKDOWN]],
        ),
    ] = [OutputFormat.MARKDOWN]

    image_export_mode: Annotated[
        ImageRefMode,
        Field(
            description=(
                "Image export mode for the document (in case of JSON,"
                " Markdown or HTML). "
                f"Allowed values: {', '.join([v.value for v in ImageRefMode])}. "
                "Optional, defaults to Embedded."
            ),
            examples=[ImageRefMode.EMBEDDED.value],
            # pattern="embedded|placeholder|referenced",
        ),
    ] = ImageRefMode.EMBEDDED

    do_ocr: Annotated[
        bool,
        Field(
            description=(
                "If enabled, the bitmap content will be processed using OCR. "
                "Boolean. Optional, defaults to true"
            ),
            # examples=[True],
        ),
    ] = True

    force_ocr: Annotated[
        bool,
        Field(
            description=(
                "If enabled, replace existing text with OCR-generated "
                "text over content. Boolean. Optional, defaults to false."
            ),
            # examples=[False],
        ),
    ] = False

    # TODO: use a restricted list based on what is installed on the system
    ocr_engine: Annotated[
        OcrEngine,
        Field(
            description=(
                "The OCR engine to use. String. "
                "Allowed values: easyocr, tesseract, rapidocr. "
                "Optional, defaults to easyocr."
            ),
            examples=[OcrEngine.EASYOCR],
        ),
    ] = OcrEngine.EASYOCR

    ocr_lang: Annotated[
        Optional[list[str]],
        Field(
            description=(
                "List of languages used by the OCR engine. "
                "Note that each OCR engine has "
                "different values for the language names. String or list of strings. "
                "Optional, defaults to empty."
            ),
            examples=[["fr", "de", "es", "en"]],
        ),
    ] = None

    pdf_backend: Annotated[
        PdfBackend,
        Field(
            description=(
                "The PDF backend to use. String. "
                f"Allowed values: {', '.join([v.value for v in PdfBackend])}. "
                f"Optional, defaults to {PdfBackend.DLPARSE_V2.value}."
            ),
            examples=[PdfBackend.DLPARSE_V2],
        ),
    ] = PdfBackend.DLPARSE_V2

    table_mode: Annotated[
        TableFormerMode,
        Field(
            TableFormerMode.FAST,
            description=(
                "Mode to use for table structure, String. "
                f"Allowed values: {', '.join([v.value for v in TableFormerMode])}. "
                "Optional, defaults to fast."
            ),
            examples=[TableFormerMode.FAST],
            # pattern="fast|accurate",
        ),
    ] = TableFormerMode.FAST

    abort_on_error: Annotated[
        bool,
        Field(
            description=(
                "Abort on error if enabled. Boolean. Optional, defaults to false."
            ),
            # examples=[False],
        ),
    ] = False

    return_as_file: Annotated[
        bool,
        Field(
            description=(
                "Return the output as a zip file "
                "(will happen anyway if multiple files are generated). "
                "Boolean. Optional, defaults to false."
            ),
            examples=[False],
        ),
    ] = False

    do_table_structure: Annotated[
        bool,
        Field(
            description=(
                "If enabled, the table structure will be extracted. "
                "Boolean. Optional, defaults to true."
            ),
            examples=[True],
        ),
    ] = True

    include_images: Annotated[
        bool,
        Field(
            description=(
                "If enabled, images will be extracted from the document. "
                "Boolean. Optional, defaults to true."
            ),
            examples=[True],
        ),
    ] = True

    images_scale: Annotated[
        float,
        Field(
            description="Scale factor for images. Float. Optional, defaults to 2.0.",
            examples=[2.0],
        ),
    ] = 2.0

    do_code_enrichment: Annotated[
        bool,
        Field(
            description=(
                "If enabled, perform OCR code enrichment. "
                "Boolean. Optional, defaults to false."
            ),
            examples=[False],
        ),
    ] = False

    do_formula_enrichment: Annotated[
        bool,
        Field(
            description=(
                "If enabled, perform formula OCR, return Latex code. "
                "Boolean. Optional, defaults to false."
            ),
            examples=[False],
        ),
    ] = False

    do_picture_classification: Annotated[
        bool,
        Field(
            description=(
                "If enabled, classify pictures in documents. "
                "Boolean. Optional, defaults to false."
            ),
            examples=[False],
        ),
    ] = False

    do_picture_description: Annotated[
        bool,
        Field(
            description=(
                "If enabled, describe pictures in documents. "
                "Boolean. Optional, defaults to false."
            ),
            examples=[False],
        ),
    ] = False