kwargs is the combined input and model_kwargs

r""" Specify the API input type and output api_kwargs that will be used in _call and _acall methods. Convert the Component's standard

Get embedder based on configuration or parameters. Args: is_local_ollama: Legacy parameter for Ollama embedder use_google_emb

Count the number of tokens in a text string using tiktoken. Args: text (str): The text to count tokens for. embedder_type (s

Get the current embedder configuration based on DEEPWIKI_EMBEDDER_TYPE. Returns: dict: The embedder configuration with model_client

Get the current embedder type based on configuration. Returns: str: 'bedrock', 'ollama', 'google', or 'openai' (default)

Configure logging for the application with log rotation. Environment variables: LOG_LEVEL: Log level (default: INFO) LOG_FIL

Run a single test function.

Get configuration for the specified provider and model Parameters: provider (str): Model provider ('google', 'openai', 'openrouter',

Creates and returns the data transformation pipeline. Args: embedder_type (str, optional): The embedder type ('openai', 'google', 'o

Call Google AI embedding API. Args: api_kwargs: API parameters model_type: Should be ModelType.EMBEDDER

Encode image to base64 string. Args: image_path: Path to image file. Returns: Base64 encoded image string.

Convert inputs to Google AI API format. Args: input: Text input(s) to embed model_kwargs: Model parameters in

Generates the file path for a given wiki cache.

Check if the current embedder configuration uses GoogleEmbedderClient. Returns: bool: True if using GoogleEmbedderClient, False othe

Parse the embedding response to a EmbedderOutput.

Parse Google AI embedding response to EmbedderOutput format. Args: response: Google AI embedding response (EmbeddingDict

Extract the provider from the model ID. Args: model_id: The model inference ID, e.g., "anthropic.claude-3-sonnet-20240229

Private helper method to prepare client configuration. Returns: tuple: (api_key, workspace_id, base_url) for cli

Prepare image content for API request. Args: image_source: Either a path to local image or a URL. detail: Image detai

Test a single embedder type.

Add a dialog turn to the conversation history. Args: user_query: The user's query assistant_response: The as

Convert inputs to API kwargs.

Retrieves the content of a file from a Git repository (GitHub or GitLab). Args: repo_type (str): Type of repository repo_url

Initialize the synchronous AWS Bedrock client.

Initialize the database manager with local storage

Check if the current embedder configuration uses BedrockClient. Returns: bool: True if using BedrockClient, False otherwise

Check if the current embedder configuration uses OllamaClient. Returns: bool: True if using OllamaClient, False otherwise

Parse the completion response to a GeneratorOutput.

Parse the response of the stream API.

Create a new database from the repository. Args: repo_type(str): Type of repository repo_url_or_path (str):

Prepare the retriever for a repository. Will load database from local storage if available. Args: repo_url_or_pa

Determine if a file should be processed based on inclusion/exclusion rules. Args: file_path (str): The file path to chec

Initialize the RAG component. Args: provider: Model provider to use (google, openai, openrouter, ollama) mod

Download and prepare all paths. Paths: ~/.adalflow/repos/{owner}_{repo_name} (for url, local path will be the same) ~

Extract the generated text from the response. Args: provider: The provider name, e.g., "anthropic" response:

Format the prompt according to the provider's requirements. Args: provider: The provider name, e.g., "anthropic"

Initialize the Google AI client with API key.

Validate embeddings and filter out documents with invalid or mismatched embedding sizes. Args: documents: List of docume

Async call to the Dashscope API.

Call the Dashscope API.

Batch call to DashScope embedder Args: input: List of input texts model_kwargs: Model parameters

Make a synchronous call to the AWS Bedrock API.

Check if required environment variables and dependencies are available.

Check if an Ollama model exists before attempting to use it. Args: model_name: Name of the model to check ollama_host: O

Downloads a Git repository (GitHub, GitLab, or Bitbucket) to a specified local path. Args: repo_type(str): Type of repository

Generate JSON export of wiki pages. Args: repo_url: The repository URL pages: List of wiki pages Returns: JSON

Generate Markdown export of wiki pages. Args: repo_url: The repository URL pages: List of wiki pages Returns: M

Retrieves the content of a file from a Bitbucket repository using the Bitbucket API. Args: repo_url (str): The URL of the Bitbucket

Retrieves the content of a file from a GitHub repository using the GitHub API. Supports both public GitHub (github.com) and GitHub Enterprise

Retrieves the content of a file from a GitLab repository (cloud or self-hosted). Args: repo_url (str): The GitLab repo URL (e.g., "h

Handle the streaming response.