Implementation:Explodinggradients Ragas HaystackEmbeddingsWrapper Class

Knowledge Sources	Explodinggradients_Ragas
Domains	Embeddings, Haystack
Last Updated	2026-02-10 00:00 GMT

Overview

Wrapper class adapting Haystack text embedder components to the Ragas embedding interface with sync/async support.

Description

HaystackEmbeddingsWrapper adapts Haystack embedder components (AzureOpenAITextEmbedder, HuggingFaceAPITextEmbedder, OpenAITextEmbedder, SentenceTransformersTextEmbedder) to work within the Ragas embedding system by implementing the BaseRagasEmbeddings interface.

Usage

Use this wrapper when you have existing Haystack embedder components and want to use them with Ragas evaluation metrics.

Code Reference

Source Location

• Repository: Explodinggradients_Ragas
• File: src/ragas/embeddings/haystack_wrapper.py
• Lines: 25-151

Signature

class HaystackEmbeddingsWrapper(BaseRagasEmbeddings):
    def __init__(
        self,
        embedder: Union[AzureOpenAITextEmbedder, HuggingFaceAPITextEmbedder, OpenAITextEmbedder, SentenceTransformersTextEmbedder],
        run_config: Optional[RunConfig] = None,
        cache: Optional[CacheInterface] = None,
    ) -> None:
        ...
    def embed_query(self, text: str) -> List[float]:
        ...
    def embed_documents(self, texts: List[str]) -> List[List[float]]:
        ...
    async def aembed_query(self, text: str) -> List[float]:
        ...
    async def aembed_documents(self, texts: List[str]) -> List[List[float]]:
        ...

Import

from ragas.embeddings.haystack_wrapper import HaystackEmbeddingsWrapper

I/O Contract

Inputs

Name	Type	Required	Description
embedder	Haystack TextEmbedder	Yes	Haystack embedder component
text	str	Yes	Text to embed

Outputs

Name	Type	Description
embed_query returns	List[float]	Embedding vector
embed_documents returns	List[List[float]]	Batch embedding vectors

Usage Examples

from haystack.components.embedders import OpenAITextEmbedder
from ragas.embeddings.haystack_wrapper import HaystackEmbeddingsWrapper

haystack_embedder = OpenAITextEmbedder(model="text-embedding-3-small")
ragas_embeddings = HaystackEmbeddingsWrapper(embedder=haystack_embedder)
vector = ragas_embeddings.embed_query("What is AI?")