Utils

Defines utilities for gllm_inference.

get_basic_auth_headers(username, password)

Generates the headers required for Basic Authentication.

This method creates a header dictionary using Basic Authentication scheme. It encodes the username and password constants into Base64 format and prepares them for HTTP header authentication.

Returns:

Type	Description
dict[str, str] | None	dict[str, str] | None: A dictionary containing the 'Authorization' header with Base64 encoded credentials. Returns None if both username and password are empty strings.

get_mime_type(content)

Determines the MIME type of the provided content.

This method determines the MIME type of the provided content by using the magic library.

Parameters:

Name	Type	Description	Default
content	bytes	The content to determine the MIME type.	required

Returns:

Name	Type	Description
str	str	The MIME type of the content.

get_prompt_keys(template)

Extracts keys from a template string based on a regex pattern.

This function searches the template for placeholders enclosed in single curly braces {} and ignores any placeholders within double curly braces {{}}. It returns a set of the unique keys found.

Parameters:

Name	Type	Description	Default
template	str	The template string containing placeholders.	required

Returns:

Type	Description
set[str]	set[str]: A set of keys extracted from the template.

invoke_google_multimodal_lm(client, messages, hyperparameters, event_emitter) async

Invokes the Google multimodal language model with the provided prompt and hyperparameters.

This method processes the prompt using the input prompt and hyperparameters. It handles both standard and streaming invocation. Streaming mode is enabled if an event emitter is provided.

Parameters:

Name	Type	Description	Default
client	Any	The Google client instance. This could either be: 1. A google.generativeai.GenerativeModel instance. 2. A vertexai.generative_models.GenerativeModel instance.	required
messages	list[dict[str, Any]]	The input messages to be sent to the model.	required
hyperparameters	dict[str, Any]	A dictionary of hyperparameters for the model.	required
event_emitter	EventEmitter | None	The event emitter for streaming tokens. If provided, streaming invocation is enabled. Defaults to None.	required

Returns:

Name	Type	Description
str	str	The generated response from the model.

is_local_file_path(content, valid_extensions)

Checks if the content is a local file path.

This method checks if the content is a local file path by verifying that the content: 1. Is a string. 2. Is a valid existing file path. 3. Has a valid extension defined in the valid_extensions set.

Parameters:

Name	Type	Description	Default
content	Any	The content to check.	required
valid_extensions	set[str]	The set of valid extensions.	required

Returns:

Name	Type	Description
bool	bool	True if the content is a local file path with a valid extension, False otherwise.

is_remote_file_path(content, valid_extensions)

Checks if the content is a remote file path.

This method checks if the content is a remote file path by verifying that the content: 1. Is a string. 2. Is a URL with a valid scheme of http or https. 3. Has a valid extension defined in the valid_extensions set.

Parameters:

Name	Type	Description	Default
content	Any	The content to check.	required
valid_extensions	set[str]	The set of valid extensions.	required

Returns:

Name	Type	Description
bool	bool	True if the content is a remote file path with a valid extension, False otherwise.

is_valid_extension(content, valid_extensions)

Checks if the content has a valid extension.

Parameters:

Name	Type	Description	Default
content	str	The content to check.	required
valid_extensions	set[str]	The set of valid extensions.	required

Returns:

Name	Type	Description
bool	bool	True if the content has a valid extension, False otherwise.

load_google_vertexai_project_id(credentials_path)

Loads the Google Vertex AI project ID from the credentials file.

Parameters:

Name	Type	Description	Default
credentials_path	str	The path to the credentials file.	required

Returns:

Name	Type	Description
str	str	The Google Vertex AI project ID.

load_langchain_model(model_class_path, model_name, model_kwargs)

Loads the LangChain's model instance.

Parameters:

Name	Type	Description	Default
model_class_path	str	The path to the LangChain's class, e.g. "langchain_openai.ChatOpenAI".	required
model_name	str	The model name.	required
model_kwargs	dict[str, Any]	The additional keyword arguments.	required

Returns:

Type	Description
BaseChatModel | Embeddings	BaseChatModel | Embeddings: The LangChain's model instance.

parse_model_data(model)

Parses the model data from LangChain's BaseChatModel or Embeddings instance.

Parameters:

Name	Type	Description	Default
model	BaseChatModel | Embeddings	The LangChain's BaseChatModel or Embeddings instance.	required

Returns:

Type	Description
dict[str, str]	dict[str, str]: The dictionary containing the model name and path.

Raises:

Type	Description
ValueError	If the model name is not found in the model data.

preprocess_tei_input(texts, prefix)

Preprocesses TEI input texts by replacing newline characters with spaces and adding the prefix to the text.

Parameters:

Name	Type	Description	Default
texts	list[str]	The list of texts to preprocess.	required
prefix	str	The prefix to add to the text.	required

Returns:

Type	Description
list[str]	list[str]: The list of preprocessed texts.

validate_prompt_builder_kwargs(prompt_key_set, ignore_extra_keys=False, **kwargs)

Validates that the provided kwargs match the expected prompt keys exactly.

This helper function checks if the provided kwargs contain all and only the keys required by the prompt templates. If any required key is missing or there are extra keys, it raises a ValueError.

Parameters:

Name	Type	Description	Default
prompt_key_set	set[str]	The set of required prompt keys.	required
ignore_extra_keys	bool	Whether to ignore extra keys. Defaults to False.	False
**kwargs	Any	The keyword arguments to be validated against the required prompt keys.	{}

Raises:

Type	Description
ValueError	If any required key is missing from or any extra key is present in the kwargs.

validate_string_enum(enum_type, value)

Validates that the provided value is a valid string enum value.

Parameters:

Name	Type	Description	Default
enum_type	type[StrEnum]	The type of the string enum.	required
value	str	The value to validate.	required

Raises:

Type	Description
ValueError	If the provided value is not a valid string enum value.