Documentation ¶
Index ¶
Constants ¶
const ( LLAMA2_13B_CHAT_V1 = Llama2("meta.llama2-13b-chat-v1") LLAMA2_70B_CHAT_V1 = Llama2("meta.llama2-70b-chat-v1") )
See https://docs.aws.amazon.com/bedrock/latest/userguide/model-ids.html
const ( TITAN_TEXT_LITE_V1 = TitanText("amazon.titan-text-lite-v1") TITAN_TEXT_EXPRESS_V1 = TitanText("amazon.titan-text-express-v1") )
See https://docs.aws.amazon.com/bedrock/latest/userguide/model-ids.html
Variables ¶
This section is empty.
Functions ¶
This section is empty.
Types ¶
type Client ¶
type Client struct {
// contains filtered or unexported fields
}
Bedrock client
func New ¶
Creates AWS BedRock embeddings client.
By default `us-east-1` region is used, supply custom `aws.Config` to alter behavior.
The client is configurable using
WithConfig(cfg aws.Config) WithModel(model Model) WithQuotaTokensInReply(quota int)
func (*Client) ConsumedTokens ¶
Number of tokens consumed within the session
type Llama2 ¶
type Llama2 string
Meta Llama 2 Chat model
See * https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-meta.html * https://replicate.com/blog/how-to-prompt-llama
type Option ¶
type Option func(*Client)
Config option for the client
func WithQuotaTokensInReply ¶
Config tokens quota in reply
type TitanText ¶
type TitanText string
Amazon Titan Text model See https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-titan-text.html See https://docs.aws.amazon.com/bedrock/latest/userguide/prompt-templates-and-examples.html