`components.pipeline`

The Pipeline module provides functionality for creating different types of inference pipelines using the Haystack framework. It supports both simple LLM-based and Retrieval-Augmented Generation (RAG) pipelines for converting informal medication names to OMOP concepts.

source

`Generator`

This type is a wrapper for various Haystack generators. This may or may not include LlamaCppGenerator, depending on your configuration.

`llm_pipeline`

This class generates pipelines that connect LLMs with prompts and optionally vector search capabilities.

class LLMPipeline(
    llm_model: Generator,
    temperature: float,
    logger: Logger,
    embed_vocab: list[str] | None = None,
    standard_concept: bool = False,
    embedding_model: EmbeddingModelName = EmbeddingModelName.BGESMALL,
    top_k: int = 5
)

Parameters

Parameter	Type	Description
`llm_model`	`Generator`	An LLM generator
`temperature`	`float`	Controls the randomness of LLM output generation. Lower values (e.g., `0.0`) produce more deterministic output.
`logger`	`logging.Logger`	Logger instance for recording pipeline operations.
`inference_type`	`InferenceType`	The engine to use for inference, taken from pipeline options
`inference_url`	`str` or `None`	A URL to use for inference, if you’re using an external server. Defaults to the `ollama_url` from the environment
`embed_vocab`	`list[str] \| None`	Optional list of OMOP vocabulary IDs to filter RAG results (e.g., `["RxNorm", "SNOMED"]`).
`standard_concept`	`bool`	If `True`, restricts RAG results to standard concepts only.
`embedding_model`	`EmbeddingModelName`	The model used to create embeddings for vector search. Default is `BGESMALL`.
`top_k`	`int`	Number of top matching results to return from vector search for RAG. Default is `5`.

Methods

`get_simple_assistant`

Creates a basic pipeline that connects a prompt template with an LLM.

get_simple_assistant() -> Pipeline

Returns

Pipeline

A Haystack pipeline that takes informal medication names and uses an LLM to infer OMOP concepts.

`get_simple_assistant`

def get_simple_assistant() -> Pipeline

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() -> Pipeline

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

Returns

Pipeline

A Haystack pipeline that takes informal medication names and uses an LLM to infer OMOP concepts.

Properties

`llm_model`

Get or set the LLM model used by the pipeline.

Technical Details

Pipeline Architecture

The pipeline module uses Haystack’s component architecture to create flexible processing pipelines:

Simple Assistant Pipeline:
- Prompt Template → LLM → Result
RAG Assistant Pipeline:
- Query → Embedder → Retriever → Conditional Router →
  - If exact match (score > 0.95) → Return vector results
  - If no exact match → Embedder → Prompt template with vector results → LLM → Result

Environmental Variables

LOCAL_LLM: Path to local model weights if using locally-stored models

⚠️

When using the RAG pipeline, ensure you have built a vector database first.

Models Prompt