Implementation:Explodinggradients Ragas LiteLLMEmbeddings Class

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

Overview

Universal embedding interface using LiteLLM to support 100+ embedding models with intelligent batching and provider-specific optimizations.

Description

LiteLLMEmbeddings extends BaseRagasEmbedding to provide text embeddings via the LiteLLM library, which acts as a universal proxy supporting OpenAI, Azure, Cohere, HuggingFace, and 100+ other providers through a single API.

Usage

Use this provider when you need a single interface to switch between multiple embedding providers without code changes.

Code Reference

Source Location

• Repository: Explodinggradients_Ragas
• File: src/ragas/embeddings/litellm_provider.py
• Lines: 11-143

Signature

class LiteLLMEmbeddings(BaseRagasEmbedding):
    PROVIDER_NAME = "litellm"

    def __init__(
        self,
        model: str,
        api_key: Optional[str] = None,
        api_base: Optional[str] = None,
        api_version: Optional[str] = None,
        timeout: int = 600,
        max_retries: int = 3,
        batch_size: Optional[int] = None,
        cache: Optional[CacheInterface] = None,
        **litellm_params: Any,
    ) -> None:
        ...

Import

from ragas.embeddings.litellm_provider import LiteLLMEmbeddings

I/O Contract

Inputs

Name	Type	Required	Description
model	str	Yes	Model identifier (e.g., "openai/text-embedding-3-small")
api_key	Optional[str]	No	Provider API key
timeout	int	No	Request timeout in seconds (default 600)
batch_size	Optional[int]	No	Override automatic batch size

Outputs

Name	Type	Description
embed_text returns	List[float]	Embedding vector
embed_texts returns	List[List[float]]	Batch embedding vectors

Usage Examples

from ragas.embeddings.litellm_provider import LiteLLMEmbeddings

# Use with any provider via LiteLLM
embeddings = LiteLLMEmbeddings(model="openai/text-embedding-3-small")
vector = embeddings.embed_text("What is AI?")

# Use with Azure
azure_embeddings = LiteLLMEmbeddings(
    model="azure/my-deployment",
    api_base="https://my-resource.openai.azure.com",
    api_key="...",
)