class langchain_community.embeddings.deepinfra.DeepInfraEmbeddings[source]

Bases: BaseModel, Embeddings

Deep Infra’s embedding inference service.

To use, you should have the environment variable DEEPINFRA_API_TOKEN set with your API token, or pass it as a named parameter to the constructor. There are multiple embeddings models available, see


from langchain_community.embeddings import DeepInfraEmbeddings
deepinfra_emb = DeepInfraEmbeddings(
r1 = deepinfra_emb.embed_documents(
        "Alpha is the first letter of Greek alphabet",
        "Beta is the second letter of Greek alphabet",
r2 = deepinfra_emb.embed_query(
    "What is the second letter of Greek alphabet"

Create a new model by parsing and validating input data from keyword arguments.

Raises ValidationError if the input data cannot be parsed to form a valid model.

param batch_size: int = 1024

Batch size for embedding requests.

param deepinfra_api_token: Optional[str] = None

API token for Deep Infra. If not provided, the token is fetched from the environment variable ‘DEEPINFRA_API_TOKEN’.

param embed_instruction: str = 'passage: '

Instruction used to embed documents.

param model_id: str = 'sentence-transformers/clip-ViT-B-32'

Embeddings model to use.

param model_kwargs: Optional[dict] = None

Other model keyword args

param normalize: bool = False

whether to normalize the computed embeddings

param query_instruction: str = 'query: '

Instruction used to embed the query.

async aembed_documents(texts: List[str]) List[List[float]]

Asynchronous Embed search docs.


texts (List[str]) –

Return type


async aembed_query(text: str) List[float]

Asynchronous Embed query text.


text (str) –

Return type


embed_documents(texts: List[str]) List[List[float]][source]

Embed documents using a Deep Infra deployed embedding model. For larger batches, the input list of texts is chunked into smaller batches to avoid exceeding the maximum request size.


texts (List[str]) – The list of texts to embed.


List of embeddings, one for each text.

Return type


embed_query(text: str) List[float][source]

Embed a query using a Deep Infra deployed embedding model.


text (str) – The text to embed.


Embeddings for the text.

Return type


Examples using DeepInfraEmbeddings