Class swarmauri_standard.dataconnectors.GoogleDriveDataConnector.GoogleDriveDataConnector

swarmauri_standard.dataconnectors.GoogleDriveDataConnector.GoogleDriveDataConnector

GoogleDriveDataConnector(credentials_path=None)

Bases: DataConnectorBase

Data connector for interacting with Google Drive files and converting them to Swarmauri documents.

Supports authentication, data fetching, and basic CRUD operations for Google Drive resources.

Initialize the Google Drive Data Connector.

:param credentials_path: Path to the Google OAuth2 credentials JSON file

Source code in swarmauri_standard/dataconnectors/GoogleDriveDataConnector.py

def __init__(self, credentials_path: str = None):
    """
    Initialize the Google Drive Data Connector.

    :param credentials_path: Path to the Google OAuth2 credentials JSON file
    """
    with open(credentials_path, "r") as cred_file:
        credentials = json.load(cred_file)

    self.client_id = credentials.get("client_id")
    self.client_secret = credentials.get("client_secret")
    self.redirect_uri = credentials.get("redirect_uri")

    # Tokens will be stored here
    self.access_token = None
    self.refresh_token = None

    self.authorization_code = None

    self.client = httpx.Client()

client_id instance-attribute

client_id = get('client_id')

client_secret instance-attribute

client_secret = get('client_secret')

redirect_uri instance-attribute

redirect_uri = get('redirect_uri')

access_token instance-attribute

access_token = None

refresh_token instance-attribute

refresh_token = None

authorization_code instance-attribute

authorization_code = None

client instance-attribute

client = Client()

type class-attribute instance-attribute

type = 'ComponentBase'

model_config class-attribute instance-attribute

model_config = ConfigDict(
    extra="allow", arbitrary_types_allowed=True
)

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='ComponentBase')

version class-attribute instance-attribute

version = '0.1.0'

generate_authorization_url

generate_authorization_url()

Generate the authorization URL for user consent

Source code in swarmauri_standard/dataconnectors/GoogleDriveDataConnector.py

def generate_authorization_url(self) -> str:
    """Generate the authorization URL for user consent"""
    params = {
        "client_id": self.client_id,
        "redirect_uri": self.redirect_uri,
        "response_type": "code",
        "scope": "https://www.googleapis.com/auth/drive",
        "access_type": "offline",  # This ensures we get a refresh token
    }
    return f"https://accounts.google.com/o/oauth2/v2/auth?{urlencode(params)}"

refresh_access_token

refresh_access_token()

Refresh the access token using the refresh token

Source code in swarmauri_standard/dataconnectors/GoogleDriveDataConnector.py

def refresh_access_token(self):
    """Refresh the access token using the refresh token"""
    if not self.refresh_token:
        raise ValueError("No refresh token available")

    token_url = "https://oauth2.googleapis.com/token"
    payload = {
        "client_id": self.client_id,
        "client_secret": self.client_secret,
        "refresh_token": self.refresh_token,
        "grant_type": "refresh_token",
    }

    response = self.client.post(token_url, data=payload)
    tokens = response.json()
    self.access_token = tokens["access_token"]

authenticate

authenticate()

Authenticate with Google Drive using OAuth2.

This method generates an authorization URL, prompts the user to visit the URL and enter the authorization code, and then exchanges the code for tokens.

Source code in swarmauri_standard/dataconnectors/GoogleDriveDataConnector.py

def authenticate(self):
    """
    Authenticate with Google Drive using OAuth2.

    This method generates an authorization URL, prompts the user to visit the URL
    and enter the authorization code, and then exchanges the code for tokens.
    """
    try:
        # Generate authorization URL
        auth_url = self.generate_authorization_url()
        print("Please visit the following URL to authenticate:")
        print(auth_url)

        # Prompt for authorization code
        while True:
            authorization_code = input("Enter the authorization code: ").strip()

            if not authorization_code:
                print("Authorization code cannot be empty. Please try again.")
                continue

            self.authorization_code = authorization_code

            try:
                self._exchange_code_for_tokens()
                logging.info("Successfully authenticated and obtained tokens")
                return
            except ValueError as e:
                print(f"Error exchanging authorization code: {e}")
                print("Please try again.")
                self.authorization_code = None

    except Exception as e:
        logging.error(f"Authentication failed: {e}")
        raise ValueError(f"Authentication failed: {e}")

fetch_data

fetch_data(query=None, **kwargs)

Fetch documents from Google Drive based on a query.

:param query: Search query for files (optional) :param kwargs: Additional parameters like mime_type, max_results :return: List of Swarmauri Documents

Source code in swarmauri_standard/dataconnectors/GoogleDriveDataConnector.py

def fetch_data(self, query: str = None, **kwargs) -> List[DocumentBase]:
    """
    Fetch documents from Google Drive based on a query.

    :param query: Search query for files (optional)
    :param kwargs: Additional parameters like mime_type, max_results
    :return: List of Swarmauri Documents
    """
    if not self.access_token:
        raise ValueError("Not authenticated. Call authenticate() first.")

    try:
        # Prepare request parameters
        query_str = query or ""
        mime_type = kwargs.get("mime_type", "application/vnd.google-apps.document")
        max_results = kwargs.get("max_results", 100)

        # Construct request headers and parameters
        headers = {
            "Authorization": f"Bearer {self.access_token}",
            "Accept": "application/json",
        }

        params = {
            "q": f"mimeType='{mime_type}' and name contains '{query_str}'",
            "pageSize": max_results,
            "fields": "files(id,name,mimeType)",
        }

        # Make request to Google Drive API
        response = self.client.get(
            "https://www.googleapis.com/drive/v3/files",
            headers=headers,
            params=params,
        )
        response.raise_for_status()

        files = response.json().get("files", [])

        # Convert Google Drive files to Swarmauri Documents
        documents = []
        for file in files:
            content = self._get_file_content(file["id"])
            document = DocumentBase(
                content=content,
                metadata={
                    "id": file["id"],
                    "name": file["name"],
                    "mime_type": file["mimeType"],
                },
            )
            documents.append(document)

        return documents

    except httpx.HTTPError as error:
        raise ValueError(f"Error fetching Google Drive files: {error}")

insert_data

insert_data(data, **kwargs)

Insert a new file into Google Drive.

:param data: Content of the file to be inserted :param kwargs: Additional metadata like filename, mime_type :return: ID of the inserted file

Source code in swarmauri_standard/dataconnectors/GoogleDriveDataConnector.py

def insert_data(self, data, **kwargs):
    """
    Insert a new file into Google Drive.

    :param data: Content of the file to be inserted
    :param kwargs: Additional metadata like filename, mime_type
    :return: ID of the inserted file
    """
    if not self.access_token:
        raise ValueError("Not authenticated. Call authenticate() first.")

    try:
        headers = {
            "Authorization": f"Bearer {self.access_token}",
            "Content-Type": "application/json",
        }

        # Prepare file metadata
        file_metadata = {
            "name": kwargs.get("filename", "Untitled Document"),
            "mimeType": kwargs.get(
                "mime_type", "application/vnd.google-apps.document"
            ),
        }

        # Prepare file content (base64 encoded)
        media_content = base64.b64encode(data.encode("utf-8")).decode("utf-8")

        # Construct payload
        payload = {
            "metadata": file_metadata,
            "media": {"mimeType": "text/plain", "body": media_content},
        }

        # Make request to create file
        response = self.client.post(
            "https://www.googleapis.com/upload/drive/v3/files",
            headers=headers,
            json=payload,
        )
        response.raise_for_status()

        return response.json().get("id")

    except httpx.HTTPError as error:
        raise ValueError(f"Error inserting file: {error}")

update_data

update_data(identifier, data, **kwargs)

Update an existing Google Drive file.

:param identifier: File ID to update :param data: New content for the file :param kwargs: Additional update parameters

Source code in swarmauri_standard/dataconnectors/GoogleDriveDataConnector.py

def update_data(self, identifier, data, **kwargs):
    """
    Update an existing Google Drive file.

    :param identifier: File ID to update
    :param data: New content for the file
    :param kwargs: Additional update parameters
    """
    if not self.access_token:
        raise ValueError("Not authenticated. Call authenticate() first.")

    try:
        headers = {
            "Authorization": f"Bearer {self.access_token}",
            "Content-Type": "application/json",
        }

        # Prepare file content (base64 encoded)
        media_content = base64.b64encode(data.encode("utf-8")).decode("utf-8")

        # Construct payload
        payload = {"media": {"mimeType": "text/plain", "body": media_content}}

        # Make request to update file
        response = self.client.patch(
            f"https://www.googleapis.com/upload/drive/v3/files/{identifier}",
            headers=headers,
            json=payload,
        )
        response.raise_for_status()

    except httpx.HTTPError as error:
        raise ValueError(f"Error updating file: {error}")

delete_data

delete_data(identifier, **kwargs)

Delete a file from Google Drive.

:param identifier: File ID to delete

Source code in swarmauri_standard/dataconnectors/GoogleDriveDataConnector.py

def delete_data(self, identifier, **kwargs):
    """
    Delete a file from Google Drive.

    :param identifier: File ID to delete
    """
    if not self.access_token:
        raise ValueError("Not authenticated. Call authenticate() first.")

    try:
        headers = {"Authorization": f"Bearer {self.access_token}"}

        response = self.client.delete(
            f"https://www.googleapis.com/drive/v3/files/{identifier}",
            headers=headers,
        )
        response.raise_for_status()

    except httpx.HTTPError as error:
        raise ValueError(f"Error deleting file: {error}")

test_connection

test_connection(**kwargs)

Test the connection to Google Drive by listing files.

:return: Boolean indicating connection success

Source code in swarmauri_standard/dataconnectors/GoogleDriveDataConnector.py

def test_connection(self, **kwargs):
    """
    Test the connection to Google Drive by listing files.

    :return: Boolean indicating connection success
    """
    try:
        if not self.access_token:
            self.authenticate(**kwargs)

        # Prepare request headers
        headers = {
            "Authorization": f"Bearer {self.access_token}",
            "Accept": "application/json",
        }

        # List first 5 files to test connection
        params = {"pageSize": 5, "fields": "files(id,name)"}

        response = self.client.get(
            "https://www.googleapis.com/drive/v3/files",
            headers=headers,
            params=params,
        )
        response.raise_for_status()

        files = response.json().get("files", [])
        return len(files) > 0

    except Exception as e:
        print(f"Connection test failed: {e}")
        return False

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

@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

@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

@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

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

@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

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

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