morpheus_llm.llm.nodes.rag_node.RAGNode

Bases: morpheus_llm._lib.llm.LLMNode

Performs Retrieval Augmented Generation (RAG).

Parameters

promptstr

The prompt template string to populate with input values.

template_formatstr, optional default=”jinja”

The format of the template string. Must be one of: f-string, jinja.

vdb_serviceVectorDBResourceService

The VectorDB service to use for retrieval.

embeddingCallable[[list[str]], Coroutine[Any, Any, list[list[float]]]], optional

An asynchronous function to use to determine the embeddings to search the vdb_service for. If None, upstream nodes must provide the embeddings.

llm_clientLLMClient

The LLM client to use for generation.

Methods

add_node(self: morpheus_llm._lib.llm.LLMNode, name: str, *, inputs: object = None, node: morpheus_llm._lib.llm.LLMNodeBase, is_output: bool = False) → morpheus_llm._lib.llm.LLMNodeRunner

Add an LLMNode to the current node.

Parameters

namestr

The name of the node to add

inputslist[tuple[str, str]], optional

List of input mappings to use for the node, in the form of [(external_name, internal_name), ...] If unspecified the node’s input_names will be used.

nodeLLMNodeBase

The node to add

is_outputbool, optional

Indicates if the node is an output node, by default False

execute(self: morpheus_llm._lib.llm.LLMNodeBase, context: morpheus_llm._lib.llm.LLMContext) → Awaitable[morpheus_llm._lib.llm.LLMContext]

Execute the current node with the given context instance.

All inputs for the given node should be fetched from the context, typically by calling either context.get_inputs to fetch all inputs as a dict, or context.get_input to fetch a specific input.

Similarly the output of the node is written to the context using context.set_output.

Parameters

contextmorpheus._lib.llm.LLMContext

Context instance to use for the execution

get_input_names(self: morpheus_llm._lib.llm.LLMNodeBase) → List[str]

Get the input names for the node.

Returns

list[str]

The input names for the node