langchain.embeddings.embaas.EmbaasEmbeddings

class langchain.embeddings.embaas.EmbaasEmbeddings(*, model: str = 'e5-large-v2', instruction: Optional[str] = None, api_url: str = 'https://api.embaas.io/v1/embeddings/', embaas_api_key: Optional[str] = None)

Bases: BaseModel, Embeddings

Embaas’s embedding service.

To use, you should have the environment variable EMBAAS_API_KEY set with your API key, or pass it as a named parameter to the constructor.

Example

# Initialise with default model and instruction
from langchain.embeddings import EmbaasEmbeddings
emb = EmbaasEmbeddings()

# Initialise with custom model and instruction
from langchain.embeddings import EmbaasEmbeddings
emb_model = "instructor-large"
emb_inst = "Represent the Wikipedia document for retrieval"
emb = EmbaasEmbeddings(
    model=emb_model,
    instruction=emb_inst
)

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 api_url: str = 'https://api.embaas.io/v1/embeddings/'

The URL for the embaas embeddings API.

param embaas_api_key: Optional[str] = None

param instruction: Optional[str] = None

Instruction used for domain-specific embeddings.

param model: str = 'e5-large-v2'

The model used for embeddings.

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

Get embeddings for a list of texts.

Parameters

texts – The list of texts to get embeddings for.

Returns

List of embeddings, one for each text.

embed_query(text: str) → List[float]

Get embeddings for a single text.

Parameters

text – The text to get embeddings for.

Returns

List of embeddings.

validator validate_environment  »  all fields

Validate that api key and python package exists in environment.

model Config

Bases: object

Configuration for this pydantic object.

extra = 'forbid'

Examples using EmbaasEmbeddings

• Embaas