Multimodal Prompt Builder
Modules concerning the prompt builders used in multimodal Gen AI applications.
WARNING: This module is deprecated. Please use gllm_inference.prompt_builder
instead.
This module will be removed in version 0.5.0.
MultimodalPromptBuilder(system_template='', user_template='')
A prompt builder that is compatible with multimodal language models.
Attributes:
Name | Type | Description |
---|---|---|
system_template |
str
|
The system prompt template. May contain placeholders enclosed in curly braces |
user_template |
str
|
The user prompt template. May contain placeholders enclosed in curly braces |
prompt_key_set |
set[str]
|
A set of expected keys that must be present in the prompt templates. |
WARNING: This module is deprecated. Please use gllm_inference.prompt_builder
instead.
This module will be removed in version 0.5.0.
Initializes a new instance of the MultimodalPromptBuilder class.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
system_template |
str
|
The system prompt template. May contain placeholders enclosed in curly
braces |
''
|
user_template |
str
|
The user prompt template. May contain placeholders enclosed in curly
braces |
''
|
Raises:
Type | Description |
---|---|
ValueError
|
If both |
format_as_message_list(history=None, system_multimodal_contents=None, user_multimodal_contents=None, **kwargs)
Formats the prompt templates as a list of message tuples (role, formatted list of contents).
This method processes each prompt template, replacing the placeholders in the template content with the
corresponding values from kwargs
. If a required key is missing from kwargs
, it raises a ValueError
. It
returns a list of tuples, where each tuple consists of a role and the corresponding formatted list of contents,
which may contain multimodal inputs.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
history |
list[tuple[PromptRole, list[Any]]] | None
|
The optional chat history to be included in the prompt. Defaults to None. |
None
|
system_multimodal_contents |
list[Any] | None
|
The optional multimodal contents for the system prompt. Defaults to None. |
None
|
user_multimodal_contents |
list[Any] | None
|
The optional multimodal contents for the user prompt. Defaults to None. |
None
|
**kwargs |
Any
|
A dictionary of placeholder values to be injected into the prompt templates. |
{}
|
Returns:
Type | Description |
---|---|
list[tuple[PromptRole, list[Any]]]
|
list[tuple[PromptRole, list[Any]]]: A list of tuples, each containing a role and the corresponding formatted list of contents, which may contain multimodal inputs. |
Raises:
Type | Description |
---|---|
ValueError
|
If a required key for the prompt template is missing from |