components.pipeline

source

llm_pipeline

class llm_pipeline(
	llm_model: LLMModel
	temperature: float
	logger: Logger
	embeddings_path: str
	force_rebuild: bool
	embed_vocab: str[list]
	embedding_model: EmbeddingModelName
	embedding_search_kwargs: dict
)

This class is used to generate a pipeline for the model

Methods

__init__

def __init__(
	llm_model: LLMModel
	temperature: float
	logger: Logger
	embeddings_path: str
	force_rebuild: bool
	embed_vocab: str[list]
	embedding_model: EmbeddingModelName
	embedding_search_kwargs: dict
)

Initializes the llm_pipeline class

Parameters

llm_model: LLMModel The choice of LLM to run the pipeline

temperature: float The temperature the LLM uses for generation

logger: logging.Logger|None Logger for the pipeline

embeddings_path: str A path for the embeddings database. If one is not found, it will be built, which takes a long time. This is built from concepts fetched from the OMOP database.

force_rebuild: bool If true, the embeddings database will be rebuilt.

embed_vocab: List[str] A list of OMOP vocabulary_ids. If the embeddings database is built, these will be the vocabularies used in the OMOP query.

embedding_model: EmbeddingModel The model used to create embeddings.

embedding_search_kwargs: dict kwargs for vector search.

get_simple_assistant

def get_simple_assistant()

Get a simple assistant pipeline that connects a prompt with an LLM

Returns

Pipeline The pipeline for the assistant

get_rag_assistant

def get_rag_assistant()

Get an assistant that uses vector search to populate a prompt for an LLM

Returns

Pipeline The pipeline for the assistant