Reference formatter

Defines a base class for reference formatters used in Gen AI applications.

BaseReferenceFormatter(stringify=True, format_references_func=None, format_chunk_func=None, format_chunk_metadata_map=None, streamable=True)

Bases: Component, ABC

An abstract base class for the reference formatters used in Gen AI applications.

The BaseReferenceFormatter class provides a framework for formatting references based on the synthesized response and retrieved chunks. It first retrieves the relevant chunks based on the synthesized response, then formats the references as a string or a list of chunks depending on the stringify attribute. Subclasses must implement the _get_relevant_chunks method to retrieve the relevant chunks.

Attributes:

Name	Type	Description
stringify	bool	Whether to format the references as a string. If False, the references will be returned as a list of chunks.
format_references_func	Callable[[list[str]], str]	A function that formats a list of formatted chunks as a string of references.
format_chunk_func	Callable[[Chunk], str]	A function that formats a chunk as a reference.
streamable	bool	A flag to indicate whether the formatted references will be streamed if an event emitter is provided.

Initializes a new instance of the BaseReferenceFormatter class.

Parameters:

Name	Type	Description	Default
stringify	bool	Whether to format the references as a string. If False, the references will be returned as a list of chunks. Defaults to True.	True
format_references_func	Callable[[list[str]], str] | None	A function that formats a list of formatted chunks as a string of references. Defaults to None, in which case format_references_as_string will be used.	None
format_chunk_func	Callable[[Chunk], str] | None	A function that formats a chunk as a reference. Defaults to None, in which case format_chunk_as_string will be used.	None
format_chunk_metadata_map	dict[str, str] | None	A dictionary mapping the metadata keys needed by the format_chunk_func to the actual chunk metadata keys. The keys in the dictionary must match the metadata keys needed by the format_chunk_func. Defaults to None, in which case DEFAULT_FORMAT_CHUNK_METADATA_MAP will be used.	None
streamable	bool	A flag to indicate whether the formatted references will be streamed if an event emitter is provided. Defaults to True.	True

format_reference(response, chunks, event_emitter=None) async

Formats references based on the synthesized response and retrieved chunks.

Parameters:

Name	Type	Description	Default
response	str	The synthesized response.	required
chunks	list[Chunk]	A list of Chunk objects used to generate the references.	required
event_emitter	EventEmitter | None	The optional event emitter to stream the formatted reference. Defaults to None.	None

Returns:

Type	Description
str | list[Chunk]	str | list[Chunk]: The formatted references as a string or a list of chunks.

Raises:

Type	Description
ValueError	If response or chunks are missing or invalid.

format_chunk_as_string(metadata_map)

Creates a function that formats a chunk as a string of reference.

Parameters:

Name	Type	Description	Default
metadata_map	dict[str, str]	A dictionary mapping the metadata keys to the chunk metadata keys.	required

Returns:

Type	Description
Callable[[Chunk], str]	Callable[[Chunk], str]: A function that formats a chunk as a string of reference.

format_references_as_string(formatted_chunks)

Formats a list of formatted chunks as a string of references.

Parameters:

Name	Type	Description	Default
formatted_chunks	list[str]	A list of formatted chunks.	required

Returns:

Name	Type	Description
str	str	A string of references.