Skip to content

amazon_bedrock

__all__ = ['AmazonBedrockTitanEmbeddingDriver', 'AmazonBedrockCohereEmbeddingDriver'] module-attribute

AmazonBedrockCohereEmbeddingDriver

Bases: BaseEmbeddingDriver

Amazon Bedrock Cohere Embedding Driver.

Attributes:

Name Type Description
model str

Embedding model name. Defaults to DEFAULT_MODEL.

input_type str

Defaults to search_query. Prepends special tokens to differentiate each type from one another: search_document when you encode documents for embeddings that you store in a vector database. search_query when querying your vector DB to find relevant documents.

session Session

Optionally provide custom boto3.Session.

tokenizer BaseTokenizer

Optionally provide custom BedrockCohereTokenizer.

client BedrockClient

Optionally provide custom bedrock-runtime client.

Source code in griptape/drivers/embedding/amazon_bedrock_cohere_embedding_driver.py
@define
class AmazonBedrockCohereEmbeddingDriver(BaseEmbeddingDriver):
    """Amazon Bedrock Cohere Embedding Driver.

    Attributes:
        model: Embedding model name. Defaults to DEFAULT_MODEL.
        input_type: Defaults to `search_query`. Prepends special tokens to differentiate each type from one another:
            `search_document` when you encode documents for embeddings that you store in a vector database.
            `search_query` when querying your vector DB to find relevant documents.
        session: Optionally provide custom `boto3.Session`.
        tokenizer: Optionally provide custom `BedrockCohereTokenizer`.
        client: Optionally provide custom `bedrock-runtime` client.
    """

    DEFAULT_MODEL = "cohere.embed-english-v3"

    model: str = field(default=DEFAULT_MODEL, kw_only=True)
    input_type: str = field(default="search_query", kw_only=True)
    session: boto3.Session = field(default=Factory(lambda: import_optional_dependency("boto3").Session()), kw_only=True)
    tokenizer: BaseTokenizer = field(
        default=Factory(lambda self: AmazonBedrockTokenizer(model=self.model), takes_self=True),
        kw_only=True,
    )
    _client: BedrockClient = field(default=None, kw_only=True, alias="client", metadata={"serializable": False})

    @lazy_property()
    def client(self) -> BedrockClient:
        return self.session.client("bedrock-runtime")

    def try_embed_chunk(self, chunk: str) -> list[float]:
        payload = {"input_type": self.input_type, "texts": [chunk]}

        response = self.client.invoke_model(
            body=json.dumps(payload),
            modelId=self.model,
            accept="*/*",
            contentType="application/json",
        )
        response_body = json.loads(response.get("body").read())

        return response_body.get("embeddings")[0]

DEFAULT_MODEL = 'cohere.embed-english-v3' class-attribute instance-attribute

input_type: str = field(default='search_query', kw_only=True) class-attribute instance-attribute

model: str = field(default=DEFAULT_MODEL, kw_only=True) class-attribute instance-attribute

session: boto3.Session = field(default=Factory(lambda: import_optional_dependency('boto3').Session()), kw_only=True) class-attribute instance-attribute

tokenizer: BaseTokenizer = field(default=Factory(lambda self: AmazonBedrockTokenizer(model=self.model), takes_self=True), kw_only=True) class-attribute instance-attribute

client()

Source code in griptape/drivers/embedding/amazon_bedrock_cohere_embedding_driver.py
@lazy_property()
def client(self) -> BedrockClient:
    return self.session.client("bedrock-runtime")

try_embed_chunk(chunk)

Source code in griptape/drivers/embedding/amazon_bedrock_cohere_embedding_driver.py
def try_embed_chunk(self, chunk: str) -> list[float]:
    payload = {"input_type": self.input_type, "texts": [chunk]}

    response = self.client.invoke_model(
        body=json.dumps(payload),
        modelId=self.model,
        accept="*/*",
        contentType="application/json",
    )
    response_body = json.loads(response.get("body").read())

    return response_body.get("embeddings")[0]

AmazonBedrockTitanEmbeddingDriver

Bases: BaseEmbeddingDriver

Amazon Bedrock Titan Embedding Driver.

Attributes:

Name Type Description
model str

Embedding model name. Defaults to DEFAULT_MODEL.

tokenizer BaseTokenizer

Optionally provide custom BedrockTitanTokenizer.

session Session

Optionally provide custom boto3.Session.

client BedrockClient

Optionally provide custom bedrock-runtime client.

Source code in griptape/drivers/embedding/amazon_bedrock_titan_embedding_driver.py
@define
class AmazonBedrockTitanEmbeddingDriver(BaseEmbeddingDriver):
    """Amazon Bedrock Titan Embedding Driver.

    Attributes:
        model: Embedding model name. Defaults to DEFAULT_MODEL.
        tokenizer: Optionally provide custom `BedrockTitanTokenizer`.
        session: Optionally provide custom `boto3.Session`.
        client: Optionally provide custom `bedrock-runtime` client.
    """

    DEFAULT_MODEL = "amazon.titan-embed-text-v1"

    model: str = field(default=DEFAULT_MODEL, kw_only=True, metadata={"serializable": True})
    session: boto3.Session = field(default=Factory(lambda: import_optional_dependency("boto3").Session()), kw_only=True)
    tokenizer: BaseTokenizer = field(
        default=Factory(lambda self: AmazonBedrockTokenizer(model=self.model), takes_self=True),
        kw_only=True,
    )
    _client: BedrockClient = field(default=None, kw_only=True, alias="client", metadata={"serializable": False})

    @lazy_property()
    def client(self) -> BedrockClient:
        return self.session.client("bedrock-runtime")

    def try_embed_chunk(self, chunk: str) -> list[float]:
        payload = {"inputText": chunk}

        response = self.client.invoke_model(
            body=json.dumps(payload),
            modelId=self.model,
            accept="application/json",
            contentType="application/json",
        )
        response_body = json.loads(response.get("body").read())

        return response_body.get("embedding")

DEFAULT_MODEL = 'amazon.titan-embed-text-v1' class-attribute instance-attribute

model: str = field(default=DEFAULT_MODEL, kw_only=True, metadata={'serializable': True}) class-attribute instance-attribute

session: boto3.Session = field(default=Factory(lambda: import_optional_dependency('boto3').Session()), kw_only=True) class-attribute instance-attribute

tokenizer: BaseTokenizer = field(default=Factory(lambda self: AmazonBedrockTokenizer(model=self.model), takes_self=True), kw_only=True) class-attribute instance-attribute

client()

Source code in griptape/drivers/embedding/amazon_bedrock_titan_embedding_driver.py
@lazy_property()
def client(self) -> BedrockClient:
    return self.session.client("bedrock-runtime")

try_embed_chunk(chunk)

Source code in griptape/drivers/embedding/amazon_bedrock_titan_embedding_driver.py
def try_embed_chunk(self, chunk: str) -> list[float]:
    payload = {"inputText": chunk}

    response = self.client.invoke_model(
        body=json.dumps(payload),
        modelId=self.model,
        accept="application/json",
        contentType="application/json",
    )
    response_body = json.loads(response.get("body").read())

    return response_body.get("embedding")