langchain_community.embeddings.bedrock
.BedrockEmbeddings¶
- class langchain_community.embeddings.bedrock.BedrockEmbeddings[source]¶
Bases:
BaseModel
,Embeddings
Deprecated since version 0.2.11: Use
langchain_aws.BedrockEmbeddings
instead.Bedrock embedding models.
To authenticate, the AWS client uses the following methods to automatically load credentials: https://boto3.amazonaws.com/v1/documentation/api/latest/guide/credentials.html
If a specific credential profile should be used, you must pass the name of the profile from the ~/.aws/credentials file that is to be used.
Make sure the credentials / roles used have the required policies to access the Bedrock service.
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 client: Any = None¶
Bedrock client.
- param credentials_profile_name: Optional[str] = None¶
The name of the profile in the ~/.aws/credentials or ~/.aws/config files, which has either access keys or role information specified. If not specified, the default credential profile or, if on an EC2 instance, credentials from IMDS will be used. See: https://boto3.amazonaws.com/v1/documentation/api/latest/guide/credentials.html
- param endpoint_url: Optional[str] = None¶
Needed if you don’t want to default to us-east-1 endpoint
- param model_id: str = 'amazon.titan-embed-text-v1'¶
Id of the model to call, e.g., amazon.titan-embed-text-v1, this is equivalent to the modelId property in the list-foundation-models api
- param model_kwargs: Optional[Dict] = None¶
Keyword arguments to pass to the model.
- param normalize: bool = False¶
Whether the embeddings should be normalized to unit vectors
- param region_name: Optional[str] = None¶
The aws region e.g., us-west-2. Fallsback to AWS_DEFAULT_REGION env variable or region specified in ~/.aws/config in case it is not provided here.
- async aembed_documents(texts: List[str]) List[List[float]] [source]¶
Asynchronous compute doc embeddings using a Bedrock model.
- Parameters
texts (List[str]) – The list of texts to embed
- Returns
List of embeddings, one for each text.
- Return type
List[List[float]]
- async aembed_query(text: str) List[float] [source]¶
Asynchronous compute query embeddings using a Bedrock model.
- Parameters
text (str) – The text to embed.
- Returns
Embeddings for the text.
- Return type
List[float]