Skip to main content

Google Gemini API plugin for the cjm-transcription-plugin-system library - provides speech-to-text transcription with configurable model selection and parameter control.

Project description

cjm-transcription-plugin-gemini

Install

pip install cjm_transcription_plugin_gemini

Project Structure

nbs/
├── meta.ipynb   # Metadata introspection for the Gemini plugin used by cjm-ctl to generate the registration manifest.
└── plugin.ipynb # Plugin implementation for Google Gemini API transcription

Total: 2 notebooks across 1 directory

Module Dependencies

graph LR
    meta[meta<br/>Metadata]
    plugin[plugin<br/>Gemini Plugin]

    plugin --> meta

1 cross-module dependencies detected

CLI Reference

No CLI commands found in this project.

Module Overview

Detailed documentation for each module in the project:

Metadata (meta.ipynb)

Metadata introspection for the Gemini plugin used by cjm-ctl to generate the registration manifest.

Import

from cjm_transcription_plugin_gemini.meta import (
    get_plugin_metadata
)

Functions

def get_plugin_metadata() -> Dict[str, Any]: # Plugin metadata for manifest generation
    """Return metadata required to register this plugin with the PluginManager."""
    # Calculate default DB path relative to the environment
    base_path = os.path.dirname(os.path.dirname(sys.executable))
    data_dir = os.path.join(base_path, "data")
    db_path = os.path.join(data_dir, "gemini_transcriptions.db")
    
    # Ensure data directory exists
    os.makedirs(data_dir, exist_ok=True)

    return {
        "name": "cjm-transcription-plugin-gemini",
    "Return metadata required to register this plugin with the PluginManager."

Gemini Plugin (plugin.ipynb)

Plugin implementation for Google Gemini API transcription

Import

from cjm_transcription_plugin_gemini.plugin import (
    GeminiPluginConfig,
    GeminiPlugin
)

Functions

@patch
def _get_api_key(
    self:GeminiPlugin
) -> str:  # The API key string
    "Get API key from config or environment."
@patch
def _refresh_available_models(
    self:GeminiPlugin
) -> List[str]:  # List of available model names
    "Fetch and filter available models from Gemini API."
@patch
def _update_max_tokens_for_model(
    self:GeminiPlugin,
    model_name: str  # Model name to update tokens for
) -> None
    "Update max_output_tokens config based on the model's token limit."
@patch
def update_config(
    self:GeminiPlugin,
    config: Union[Dict[str, Any], GeminiPluginConfig]  # New configuration values
) -> None
    "Update plugin configuration, adjusting max_tokens if model changes."
@patch
def _prepare_audio(
    self:GeminiPlugin,
    audio: Union[AudioData, str, Path]  # Audio data object or path to audio file
) -> Tuple[Path, bool]:  # Tuple of (processed audio path, whether temp file was created)
    "Prepare audio file for upload."
@patch
def _upload_audio_file(
    self:GeminiPlugin,
    audio_path: Path  # Path to audio file to upload
) -> Any:  # Uploaded file object
    "Upload audio file to Gemini API."
@patch
def _delete_uploaded_file(
    self:GeminiPlugin,
    file_name: str  # Name of file to delete
) -> None
    "Delete an uploaded file from Gemini API."
@patch
def get_available_models(
    self:GeminiPlugin
) -> List[str]:  # List of available model names
    "Get list of available audio-capable models."
@patch
def get_model_info(
    self:GeminiPlugin,
    model_name: Optional[str] = None  # Model name to get info for, defaults to current model
) -> Dict[str, Any]:  # Dict with model information
    "Get information about a specific model including token limits."
@patch
def supports_streaming(
    self:GeminiPlugin
) -> bool:  # True if streaming is supported
    "Check if this plugin supports streaming transcription."
@patch
def execute_stream(
    self:GeminiPlugin,
    audio: Union[AudioData, str, Path],  # Audio data object or path to audio file
    **kwargs  # Additional arguments to override config
) -> Generator[str, None, TranscriptionResult]:  # Yields text chunks, returns final result
    "Stream transcription results chunk by chunk."

Classes

@dataclass
class GeminiPluginConfig:
    "Configuration for Gemini transcription plugin."
    
    model: str = field(...)
    api_key: Optional[str] = field(...)
    prompt: str = field(...)
    temperature: float = field(...)
    top_p: float = field(...)
    max_output_tokens: int = field(...)
    seed: Optional[int] = field(...)
    response_mime_type: str = field(...)
    downsample_audio: bool = field(...)
    downsample_rate: int = field(...)
    downsample_channels: int = field(...)
    safety_settings: str = field(...)
    auto_refresh_models: bool = field(...)
    model_filter: List[str] = field(...)
    use_file_upload: bool = field(...)
    use_streaming: bool = field(...)
    delete_uploaded_files: bool = field(...)
class GeminiPlugin:
    def __init__(self):
        """Initialize the Gemini plugin with default configuration."""
        self.logger = logging.getLogger(f"{__name__}.{type(self).__name__}")
        self.config: GeminiPluginConfig = None
    "Google Gemini API transcription plugin."
    
    def __init__(self):
            """Initialize the Gemini plugin with default configuration."""
            self.logger = logging.getLogger(f"{__name__}.{type(self).__name__}")
            self.config: GeminiPluginConfig = None
        "Initialize the Gemini plugin with default configuration."
    
    def name(self) -> str: # Plugin name identifier
            """Return the plugin name identifier."""
            return "gemini"
        
        @property
        def version(self) -> str: # Plugin version string
        "Return the plugin name identifier."
    
    def version(self) -> str: # Plugin version string
            """Return the plugin version string."""
            return "1.0.0"
        
        @property
        def supported_formats(self) -> List[str]: # List of supported audio formats
        "Return the plugin version string."
    
    def supported_formats(self) -> List[str]: # List of supported audio formats
            """Return list of supported audio file formats."""
            return ["wav", "mp3", "aiff", "aac", "ogg", "flac"]
    
        def get_current_config(self) -> Dict[str, Any]: # Current configuration as dictionary
        "Return list of supported audio file formats."
    
    def get_current_config(self) -> Dict[str, Any]: # Current configuration as dictionary
            """Return current configuration state."""
            if not self.config
        "Return current configuration state."
    
    def get_config_schema(self) -> Dict[str, Any]: # JSON Schema for configuration
            """Return JSON Schema for UI generation."""
            return dataclass_to_jsonschema(GeminiPluginConfig)
    
        @staticmethod
        def get_config_dataclass() -> GeminiPluginConfig: # Configuration dataclass
        "Return JSON Schema for UI generation."
    
    def get_config_dataclass() -> GeminiPluginConfig: # Configuration dataclass
            """Return dataclass describing the plugin's configuration options."""
            return GeminiPluginConfig
        
        def initialize(
            self,
            config: Optional[Any] = None # Configuration dataclass, dict, or None
        ) -> None
        "Return dataclass describing the plugin's configuration options."
    
    def initialize(
            self,
            config: Optional[Any] = None # Configuration dataclass, dict, or None
        ) -> None
        "Initialize or re-configure the plugin (idempotent)."
    
    def execute(
            self,
            audio: Union[AudioData, str, Path], # Audio data object or path to audio file
            **kwargs # Additional arguments to override config
        ) -> TranscriptionResult: # Transcription result object
        "Transcribe audio using Gemini."
    
    def is_available(self) -> bool: # True if the Gemini API is available
            """Check if Gemini API is available."""
            return GEMINI_AVAILABLE
    
        def cleanup(
            self
        ) -> None
        "Check if Gemini API is available."
    
    def cleanup(
            self
        ) -> None
        "Clean up resources."

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

cjm_transcription_plugin_gemini-0.0.9.tar.gz (19.5 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

cjm_transcription_plugin_gemini-0.0.9-py3-none-any.whl (18.3 kB view details)

Uploaded Python 3

File details

Details for the file cjm_transcription_plugin_gemini-0.0.9.tar.gz.

File metadata

File hashes

Hashes for cjm_transcription_plugin_gemini-0.0.9.tar.gz
Algorithm Hash digest
SHA256 3fc02fb48e3c4f49e6750807c0a0974e2fa8bc0111f7adbb6f8325cb73d1dec6
MD5 13225d94afa087f8ba28add1805e70ca
BLAKE2b-256 6a5bed34378f0aea353363999b7d77d656eaabaa3b26b231ca6d3100214f834f

See more details on using hashes here.

File details

Details for the file cjm_transcription_plugin_gemini-0.0.9-py3-none-any.whl.

File metadata

File hashes

Hashes for cjm_transcription_plugin_gemini-0.0.9-py3-none-any.whl
Algorithm Hash digest
SHA256 68c3a06fa777763abe3f8e37d9be690280cc1d204c9785916e0cf3c69fdd6cbe
MD5 18a01f31fecfd99b21ceb48c4d57a2d4
BLAKE2b-256 5fc21935281e77139bfce29dc09024afbcea3eb5b9c49d148ab4606d0af41218

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page