Skip to content

Class swarmauri_ocr_pytesseract.PytesseractOCR.PytesseractOCR

swarmauri_ocr_pytesseract.PytesseractOCR.PytesseractOCR

PytesseractOCR(**data)

Bases: OCRBase

A model for performing OCR (Optical Character Recognition) using Pytesseract. It can process both local images and image bytes, returning extracted text. Requires Tesseract-OCR to be installed on the system.

Source code in swarmauri_ocr_pytesseract/PytesseractOCR.py
31
32
33
def __init__(self, **data):
    super().__init__(**data)
    pytesseract.pytesseract.tesseract_cmd = self.tesseract_cmd

tesseract_cmd class-attribute instance-attribute

tesseract_cmd = Field(
    default_factory=lambda: get(
        "TESSERACT_CMD",
        "/usr/bin/tesseract"
        if exists("/usr/bin/tesseract")
        else None,
    )
)

type class-attribute instance-attribute

type = 'PytesseractOCR'

language class-attribute instance-attribute

language = Field(default='eng')

config class-attribute instance-attribute

config = Field(default='')

model_config class-attribute instance-attribute

model_config = ConfigDict(protected_namespaces=())

id class-attribute instance-attribute

id = Field(default_factory=generate_id)

members class-attribute instance-attribute

members = None

owners class-attribute instance-attribute

owners = None

host class-attribute instance-attribute

host = None

default_logger class-attribute

default_logger = None

logger class-attribute instance-attribute

logger = None

name class-attribute instance-attribute

name = None

resource class-attribute instance-attribute

resource = Field(default=OCR.value, frozen=True)

version class-attribute instance-attribute

version = '0.1.0'

allowed_models class-attribute instance-attribute

allowed_models = []

extract_text

extract_text(image, **kwargs)

Extracts text from an image.

PARAMETER DESCRIPTION
image

Can be a file path, bytes, or PIL Image

TYPE: Union[str, bytes, Image]

**kwargs

Additional arguments for OCR processing - language: OCR language (e.g., 'eng', 'fra', etc.) - config: Custom Tesseract configuration string

DEFAULT: {}

RETURNS DESCRIPTION
str

Extracted text as string

Source code in swarmauri_ocr_pytesseract/PytesseractOCR.py
62
63
64
65
66
67
68
69
70
71
72
73
74
75
def extract_text(self, image: Union[str, bytes, Image.Image], **kwargs) -> str:
    """
    Extracts text from an image.

    Args:
        image: Can be a file path, bytes, or PIL Image
        **kwargs: Additional arguments for OCR processing
                 - language: OCR language (e.g., 'eng', 'fra', etc.)
                 - config: Custom Tesseract configuration string

    Returns:
        Extracted text as string
    """
    return self._process_image(image, **kwargs)

aextract_text async

aextract_text(image, **kwargs)

Asynchronously extracts text from an image.

Source code in swarmauri_ocr_pytesseract/PytesseractOCR.py
77
78
79
80
81
82
83
84
async def aextract_text(
    self, image: Union[str, bytes, Image.Image], **kwargs
) -> str:
    """
    Asynchronously extracts text from an image.
    """
    loop = asyncio.get_event_loop()
    return await loop.run_in_executor(None, self.extract_text, image, **kwargs)

batch

batch(images, **kwargs)

Process multiple images in batch.

PARAMETER DESCRIPTION
images

List of images (file paths, bytes, or PIL Images)

TYPE: List[Union[str, bytes, Image]]

**kwargs

Additional arguments for OCR processing

DEFAULT: {}

RETURNS DESCRIPTION
List[str]

List of extracted texts

Source code in swarmauri_ocr_pytesseract/PytesseractOCR.py
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
def batch(
    self, images: List[Union[str, bytes, Image.Image]], **kwargs
) -> List[str]:
    """
    Process multiple images in batch.

    Args:
        images: List of images (file paths, bytes, or PIL Images)
        **kwargs: Additional arguments for OCR processing

    Returns:
        List of extracted texts
    """
    results = []
    for image in images:
        text = self.extract_text(image=image, **kwargs)
        results.append(text)
    return results

abatch async

abatch(images, max_concurrent=5, **kwargs)

Asynchronously process multiple images in batch.

PARAMETER DESCRIPTION
images

List of images (file paths, bytes, or PIL Images)

TYPE: List[Union[str, bytes, Image]]

max_concurrent

Maximum number of concurrent operations

TYPE: int DEFAULT: 5

**kwargs

Additional arguments for OCR processing

DEFAULT: {}

RETURNS DESCRIPTION
List[str]

List of extracted texts

Source code in swarmauri_ocr_pytesseract/PytesseractOCR.py
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
async def abatch(
    self,
    images: List[Union[str, bytes, Image.Image]],
    max_concurrent: int = 5,
    **kwargs,
) -> List[str]:
    """
    Asynchronously process multiple images in batch.

    Args:
        images: List of images (file paths, bytes, or PIL Images)
        max_concurrent: Maximum number of concurrent operations
        **kwargs: Additional arguments for OCR processing

    Returns:
        List of extracted texts
    """
    semaphore = asyncio.Semaphore(max_concurrent)

    async def process_image(image):
        async with semaphore:
            return await self.aextract_text(image=image, **kwargs)

    tasks = [process_image(image) for image in images]
    return await asyncio.gather(*tasks)

get_supported_languages

get_supported_languages()

Returns a list of supported languages by executing 'tesseract --list-langs' command.

RETURNS DESCRIPTION
List[str]

List[str]: List of available language codes (e.g., ['eng', 'osd'])

RAISES DESCRIPTION
Exception

If the command execution fails or returns unexpected output

Source code in swarmauri_ocr_pytesseract/PytesseractOCR.py
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
def get_supported_languages(self) -> List[str]:
    """
    Returns a list of supported languages by executing 'tesseract --list-langs' command.

    Returns:
        List[str]: List of available language codes (e.g., ['eng', 'osd'])

    Raises:
        Exception: If the command execution fails or returns unexpected output
    """
    try:
        # Execute tesseract command to list languages
        import subprocess

        result = subprocess.run(
            [self.tesseract_cmd, "--list-langs"],
            capture_output=True,
            text=True,
            check=True,
        )

        # Parse the output
        output_lines = result.stdout.strip().split("\n")

        # Skip the first line which is the directory info
        # and filter out empty lines
        languages = [lang.strip() for lang in output_lines[1:] if lang.strip()]

        return languages

    except subprocess.CalledProcessError as e:
        raise Exception(f"Failed to get language list from Tesseract: {e.stderr}")
    except Exception as e:
        raise Exception(f"Error getting supported languages: {str(e)}")

register_model classmethod

register_model()

Decorator to register a base model in the unified registry.

RETURNS DESCRIPTION
Callable

A decorator function that registers the model class.

TYPE: Callable[[Type[BaseModel]], Type[BaseModel]]

Source code in swarmauri_base/DynamicBase.py
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
@classmethod
def register_model(cls) -> Callable[[Type[BaseModel]], Type[BaseModel]]:
    """
    Decorator to register a base model in the unified registry.

    Returns:
        Callable: A decorator function that registers the model class.
    """

    def decorator(model_cls: Type[BaseModel]):
        """Register ``model_cls`` as a base model."""
        model_name = model_cls.__name__
        if model_name in cls._registry:
            glogger.warning(
                "Model '%s' is already registered; skipping duplicate.", model_name
            )
            return model_cls

        cls._registry[model_name] = {"model_cls": model_cls, "subtypes": {}}
        glogger.debug("Registered base model '%s'.", model_name)
        DynamicBase._recreate_models()
        return model_cls

    return decorator

register_type classmethod

register_type(resource_type=None, type_name=None)

Decorator to register a subtype under one or more base models in the unified registry.

PARAMETER DESCRIPTION
resource_type

The base model(s) under which to register the subtype. If None, all direct base classes (except DynamicBase) are used.

TYPE: Optional[Union[Type[T], List[Type[T]]]] DEFAULT: None

type_name

An optional custom type name for the subtype.

TYPE: Optional[str] DEFAULT: None

RETURNS DESCRIPTION
Callable

A decorator function that registers the subtype.

TYPE: Callable[[Type[DynamicBase]], Type[DynamicBase]]

Source code in swarmauri_base/DynamicBase.py
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
@classmethod
def register_type(
    cls,
    resource_type: Optional[Union[Type[T], List[Type[T]]]] = None,
    type_name: Optional[str] = None,
) -> Callable[[Type["DynamicBase"]], Type["DynamicBase"]]:
    """
    Decorator to register a subtype under one or more base models in the unified registry.

    Parameters:
        resource_type (Optional[Union[Type[T], List[Type[T]]]]):
            The base model(s) under which to register the subtype. If None, all direct base classes (except DynamicBase)
            are used.
        type_name (Optional[str]): An optional custom type name for the subtype.

    Returns:
        Callable: A decorator function that registers the subtype.
    """

    def decorator(subclass: Type["DynamicBase"]):
        """Register ``subclass`` as a subtype."""
        if resource_type is None:
            resource_types = [
                base for base in subclass.__bases__ if base is not cls
            ]
        elif not isinstance(resource_type, list):
            resource_types = [resource_type]
        else:
            resource_types = resource_type

        for rt in resource_types:
            if not issubclass(subclass, rt):
                raise TypeError(
                    f"'{subclass.__name__}' must be a subclass of '{rt.__name__}'."
                )
            final_type_name = type_name or getattr(
                subclass, "_type", subclass.__name__
            )
            base_model_name = rt.__name__

            if base_model_name not in cls._registry:
                cls._registry[base_model_name] = {"model_cls": rt, "subtypes": {}}
                glogger.debug(
                    "Created new registry entry for base model '%s'.",
                    base_model_name,
                )

            subtypes_dict = cls._registry[base_model_name]["subtypes"]
            if final_type_name in subtypes_dict:
                glogger.warning(
                    "Type '%s' already exists under '%s'; skipping duplicate.",
                    final_type_name,
                    base_model_name,
                )
                continue

            subtypes_dict[final_type_name] = subclass
            glogger.debug(
                "Registered '%s' as '%s' under '%s'.",
                subclass.__name__,
                final_type_name,
                base_model_name,
            )

        DynamicBase._recreate_models()
        return subclass

    return decorator

model_validate_toml classmethod

model_validate_toml(toml_data)

Validate a model from a TOML string.

Source code in swarmauri_base/TomlMixin.py
12
13
14
15
16
17
18
19
20
21
22
23
24
@classmethod
def model_validate_toml(cls, toml_data: str):
    """Validate a model from a TOML string."""
    try:
        # Parse TOML into a Python dictionary
        toml_content = tomllib.loads(toml_data)

        # Convert the dictionary to JSON and validate using Pydantic
        return cls.model_validate_json(json.dumps(toml_content))
    except tomllib.TOMLDecodeError as e:
        raise ValueError(f"Invalid TOML data: {e}")
    except ValidationError as e:
        raise ValueError(f"Validation failed: {e}")

model_dump_toml

model_dump_toml(
    fields_to_exclude=None, api_key_placeholder=None
)

Return a TOML representation of the model.

Source code in swarmauri_base/TomlMixin.py
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
def model_dump_toml(self, fields_to_exclude=None, api_key_placeholder=None):
    """Return a TOML representation of the model."""
    if fields_to_exclude is None:
        fields_to_exclude = []

    # Load the JSON string into a Python dictionary
    json_data = json.loads(self.model_dump_json())

    # Function to recursively remove specific keys and handle api_key placeholders
    def process_fields(data, fields_to_exclude):
        """Recursively filter fields and apply placeholders."""
        if isinstance(data, dict):
            return {
                key: (
                    api_key_placeholder
                    if key == "api_key" and api_key_placeholder is not None
                    else process_fields(value, fields_to_exclude)
                )
                for key, value in data.items()
                if key not in fields_to_exclude
            }
        elif isinstance(data, list):
            return [process_fields(item, fields_to_exclude) for item in data]
        else:
            return data

    # Filter the JSON data
    filtered_data = process_fields(json_data, fields_to_exclude)

    # Convert the filtered data into TOML
    return toml.dumps(filtered_data)

model_validate_yaml classmethod

model_validate_yaml(yaml_data)

Validate a model from a YAML string.

Source code in swarmauri_base/YamlMixin.py
11
12
13
14
15
16
17
18
19
20
21
22
23
@classmethod
def model_validate_yaml(cls, yaml_data: str):
    """Validate a model from a YAML string."""
    try:
        # Parse YAML into a Python dictionary
        yaml_content = yaml.safe_load(yaml_data)

        # Convert the dictionary to JSON and validate using Pydantic
        return cls.model_validate_json(json.dumps(yaml_content))
    except yaml.YAMLError as e:
        raise ValueError(f"Invalid YAML data: {e}")
    except ValidationError as e:
        raise ValueError(f"Validation failed: {e}")

model_dump_yaml

model_dump_yaml(
    fields_to_exclude=None, api_key_placeholder=None
)

Return a YAML representation of the model.

Source code in swarmauri_base/YamlMixin.py
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
def model_dump_yaml(self, fields_to_exclude=None, api_key_placeholder=None):
    """Return a YAML representation of the model."""
    if fields_to_exclude is None:
        fields_to_exclude = []

    # Load the JSON string into a Python dictionary
    json_data = json.loads(self.model_dump_json())

    # Function to recursively remove specific keys and handle api_key placeholders
    def process_fields(data, fields_to_exclude):
        """Recursively filter fields and apply placeholders."""
        if isinstance(data, dict):
            return {
                key: (
                    api_key_placeholder
                    if key == "api_key" and api_key_placeholder is not None
                    else process_fields(value, fields_to_exclude)
                )
                for key, value in data.items()
                if key not in fields_to_exclude
            }
        elif isinstance(data, list):
            return [process_fields(item, fields_to_exclude) for item in data]
        else:
            return data

    # Filter the JSON data
    filtered_data = process_fields(json_data, fields_to_exclude)

    # Convert the filtered data into YAML using safe mode
    return yaml.safe_dump(filtered_data, default_flow_style=False)

model_post_init

model_post_init(logger=None)

Assign a logger instance after model initialization.

Source code in swarmauri_base/LoggerMixin.py
23
24
25
26
27
28
def model_post_init(self, logger: Optional[FullUnion[LoggerBase]] = None) -> None:
    """Assign a logger instance after model initialization."""

    # Directly assign the provided FullUnion[LoggerBase] or fallback to the
    # class-level default.
    self.logger = self.logger or logger or self.default_logger

add_allowed_model

add_allowed_model(model)

Add a new model to the list of allowed models.

RAISES DESCRIPTION
ValueError

If the model is already in the allowed models list.

Source code in swarmauri_base/ocrs/OCRBase.py
27
28
29
30
31
32
33
34
35
36
def add_allowed_model(self, model: str) -> None:
    """
    Add a new model to the list of allowed models.

    Raises:
        ValueError: If the model is already in the allowed models list.
    """
    if model in self.allowed_models:
        raise ValueError(f"Model '{model}' is already allowed.")
    self.allowed_models.append(model)

remove_allowed_model

remove_allowed_model(model)

Remove a model from the list of allowed models.

RAISES DESCRIPTION
ValueError

If the model is not in the allowed models list.

Source code in swarmauri_base/ocrs/OCRBase.py
38
39
40
41
42
43
44
45
46
47
def remove_allowed_model(self, model: str) -> None:
    """
    Remove a model from the list of allowed models.

    Raises:
        ValueError: If the model is not in the allowed models list.
    """
    if model not in self.allowed_models:
        raise ValueError(f"Model '{model}' is not in the allowed models list.")
    self.allowed_models.remove(model)

predict abstractmethod

predict(*args, **kwargs)
Source code in swarmauri_base/ocrs/OCRBase.py
49
50
51
@abstractmethod
def predict(self, *args, **kwargs):
    raise NotImplementedError("predict() not implemented in subclass yet.")

apredict abstractmethod async

apredict(*args, **kwargs)
Source code in swarmauri_base/ocrs/OCRBase.py
53
54
55
@abstractmethod
async def apredict(self, *args, **kwargs):
    raise NotImplementedError("apredict() not implemented in subclass yet.")

stream abstractmethod

stream(*args, **kwargs)
Source code in swarmauri_base/ocrs/OCRBase.py
57
58
59
@abstractmethod
def stream(self, *args, **kwargs):
    raise NotImplementedError("stream() not implemented in subclass yet.")

astream abstractmethod async

astream(*args, **kwargs)
Source code in swarmauri_base/ocrs/OCRBase.py
61
62
63
@abstractmethod
async def astream(self, *args, **kwargs):
    raise NotImplementedError("astream() not implemented in subclass yet.")