Create Prompt
| bedrockagent_create_prompt | R Documentation |
Creates a prompt in your prompt library that you can add to a flow¶
Description¶
Creates a prompt in your prompt library that you can add to a flow. For more information, see Prompt management in Amazon Bedrock, Create a prompt using Prompt management and Prompt flows in Amazon Bedrock in the Amazon Bedrock User Guide.
Usage¶
bedrockagent_create_prompt(name, description, customerEncryptionKeyArn,
defaultVariant, variants, clientToken, tags)
Arguments¶
name |
[required] A name for the prompt. |
description |
A description for the prompt. |
customerEncryptionKeyArn |
The Amazon Resource Name (ARN) of the KMS key to encrypt the prompt. |
defaultVariant |
The name of the default variant for the prompt. This value must
match the |
variants |
A list of objects, each containing details about a variant of the prompt. |
clientToken |
A unique, case-sensitive identifier to ensure that the API request completes no more than one time. If this token matches a previous request, Amazon Bedrock ignores the request, but does not return an error. For more information, see Ensuring idempotency. |
tags |
Any tags that you want to attach to the prompt. For more information, see Tagging resources in Amazon Bedrock. |
Value¶
A list with the following syntax:
list(
name = "string",
description = "string",
customerEncryptionKeyArn = "string",
defaultVariant = "string",
variants = list(
list(
name = "string",
templateType = "TEXT"|"CHAT",
templateConfiguration = list(
text = list(
text = "string",
cachePoint = list(
type = "default"
),
inputVariables = list(
list(
name = "string"
)
)
),
chat = list(
messages = list(
list(
role = "user"|"assistant",
content = list(
list(
text = "string",
cachePoint = list(
type = "default"
)
)
)
)
),
system = list(
list(
text = "string",
cachePoint = list(
type = "default"
)
)
),
inputVariables = list(
list(
name = "string"
)
),
toolConfiguration = list(
tools = list(
list(
toolSpec = list(
name = "string",
description = "string",
inputSchema = list(
json = list()
),
strict = TRUE|FALSE
),
cachePoint = list(
type = "default"
)
)
),
toolChoice = list(
auto = list(),
any = list(),
tool = list(
name = "string"
)
)
)
)
),
modelId = "string",
inferenceConfiguration = list(
text = list(
temperature = 123.0,
topP = 123.0,
maxTokens = 123,
stopSequences = list(
"string"
)
)
),
metadata = list(
list(
key = "string",
value = "string"
)
),
additionalModelRequestFields = list(),
genAiResource = list(
agent = list(
agentIdentifier = "string"
)
)
)
),
id = "string",
arn = "string",
version = "string",
createdAt = as.POSIXct(
"2015-01-01"
),
updatedAt = as.POSIXct(
"2015-01-01"
)
)
Request syntax¶
svc$create_prompt(
name = "string",
description = "string",
customerEncryptionKeyArn = "string",
defaultVariant = "string",
variants = list(
list(
name = "string",
templateType = "TEXT"|"CHAT",
templateConfiguration = list(
text = list(
text = "string",
cachePoint = list(
type = "default"
),
inputVariables = list(
list(
name = "string"
)
)
),
chat = list(
messages = list(
list(
role = "user"|"assistant",
content = list(
list(
text = "string",
cachePoint = list(
type = "default"
)
)
)
)
),
system = list(
list(
text = "string",
cachePoint = list(
type = "default"
)
)
),
inputVariables = list(
list(
name = "string"
)
),
toolConfiguration = list(
tools = list(
list(
toolSpec = list(
name = "string",
description = "string",
inputSchema = list(
json = list()
),
strict = TRUE|FALSE
),
cachePoint = list(
type = "default"
)
)
),
toolChoice = list(
auto = list(),
any = list(),
tool = list(
name = "string"
)
)
)
)
),
modelId = "string",
inferenceConfiguration = list(
text = list(
temperature = 123.0,
topP = 123.0,
maxTokens = 123,
stopSequences = list(
"string"
)
)
),
metadata = list(
list(
key = "string",
value = "string"
)
),
additionalModelRequestFields = list(),
genAiResource = list(
agent = list(
agentIdentifier = "string"
)
)
)
),
clientToken = "string",
tags = list(
"string"
)
)