langchain.embeddings.cohere.CohereEmbeddings¶
- class langchain.embeddings.cohere.CohereEmbeddings(*, client: Any = None, async_client: Any = None, model: str = 'embed-english-v2.0', truncate: Optional[str] = None, cohere_api_key: Optional[str] = None)[source]¶
Bases:
BaseModel,EmbeddingsCohere embedding models.
To use, you should have the
coherepython package installed, and the environment variableCOHERE_API_KEYset with your API key or pass it as a named parameter to the constructor.Example
from langchain.embeddings import CohereEmbeddings cohere = CohereEmbeddings( model="embed-english-light-v2.0", cohere_api_key="my-api-key" )
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 async_client: Any = None¶
Cohere async client.
- param client: Any = None¶
Cohere client.
- param cohere_api_key: Optional[str] = None¶
- param model: str = 'embed-english-v2.0'¶
Model name to use.
- param truncate: Optional[str] = None¶
Truncate embeddings that are too long from start or end (“NONE”|”START”|”END”)
- async aembed_documents(texts: List[str]) List[List[float]][source]¶
Async call out to Cohere’s embedding endpoint.
- Parameters
texts – The list of texts to embed.
- Returns
List of embeddings, one for each text.
- async aembed_query(text: str) List[float][source]¶
Async call out to Cohere’s embedding endpoint.
- Parameters
text – The text to embed.
- Returns
Embeddings for the text.
- embed_documents(texts: List[str]) List[List[float]][source]¶
Call out to Cohere’s embedding endpoint.
- Parameters
texts – The list of texts to embed.
- Returns
List of embeddings, one for each text.
- embed_query(text: str) List[float][source]¶
Call out to Cohere’s embedding endpoint.
- Parameters
text – The text to embed.
- Returns
Embeddings for the text.