本文為英文版的機器翻譯版本，如內容有任何歧義或不一致之處，概以英文版為準。
# 執行提示管理程式碼範例
若要嘗試提示管理的一些程式碼範例，請選擇您偏好方法的索引標籤，然後遵循下列步驟：下列程式碼範例假設您已設定登入資料以使用 AWS API。如果您還沒有執行此操作，請參閱[開始使用 API](getting-started-api.md)。
------
#### [ Python ]
1. 執行下列程式碼片段以載入 適用於 Python (Boto3) 的 AWS SDK、建立用戶端，並建立提示，透過建立適用於 Amazon Bedrock 建置時間端點的 [CreatePrompt](https://docs.aws.amazon.com/bedrock/latest/APIReference/API_agent_CreatePrompt.html) 代理程式，使用兩個變數 (`genre` 和 `number`) 建立音樂播放清單： [https://docs.aws.amazon.com/general/latest/gr/bedrock.html#bra-bt](https://docs.aws.amazon.com/general/latest/gr/bedrock.html#bra-bt)
```
# Create a prompt in Prompt management
import boto3
# Create an Amazon Bedrock Agents client
client = boto3.client(service_name="bedrock-agent")
# Create the prompt
response = client.create_prompt(
name="MakePlaylist",
description="My first prompt.",
variants=[
{
"name": "Variant1",
"modelId": "amazon.titan-text-express-v1",
"templateType": "TEXT",
"inferenceConfiguration": {
"text": {
"temperature": 0.8
}
},
"templateConfiguration": {
"text": {
"text": "Make me a {{{{genre}}}} playlist consisting of the following number of songs: {{{{number}}}}."
}
}
}
]
)
prompt_id = response.get("id")
```
1. 執行下列程式碼片段產生 [ListPrompts](https://docs.aws.amazon.com/bedrock/latest/APIReference/API_agent_ListPrompts.html) [Amazon Bedrock 代理人建置時期端點](https://docs.aws.amazon.com/general/latest/gr/bedrock.html#bra-bt)，以查看您剛建立的提示 (以及您帳戶中的任何其他提示)：
```
# List prompts that you've created
client.list_prompts()
```
1. 您應該會在 `promptSummaries` 欄位的物件中，看到您在 `id` 欄位中建立的提示 ID。執行下列程式碼片段，以透過產生 [GetPrompt](https://docs.aws.amazon.com/bedrock/latest/APIReference/API_agent_GetPrompt.html) [Amazon Bedrock 代理人建置時期端點](https://docs.aws.amazon.com/general/latest/gr/bedrock.html#bra-bt)，來顯示您所建立提示的資訊：
```
# Get information about the prompt that you created
client.get_prompt(promptIdentifier=prompt_id)
```
1. 透過執行下列程式碼片段產生 [CreatePromptVersion](https://docs.aws.amazon.com/bedrock/latest/APIReference/API_agent_CreatePromptVersion.html) [Amazon Bedrock 代理人建置時期端點](https://docs.aws.amazon.com/general/latest/gr/bedrock.html#bra-bt)，以建立提示的版本並取得其 ID：
```
# Create a version of the prompt that you created
response = client.create_prompt_version(promptIdentifier=prompt_id)
prompt_version = response.get("version")
prompt_version_arn = response.get("arn")
```
1. 透過執行下列程式碼片段產生 [ListPrompts](https://docs.aws.amazon.com/bedrock/latest/APIReference/API_agent_ListPrompts.html) [Amazon Bedrock 代理人建置時期端點](https://docs.aws.amazon.com/general/latest/gr/bedrock.html#bra-bt)，以檢視您剛建立的提示版本相關資訊，及草稿版本相關資訊：
```
# List versions of the prompt that you just created
client.list_prompts(promptIdentifier=prompt_id)
```
1. 透過執行下列程式碼片段產生 [GetPrompt](https://docs.aws.amazon.com/bedrock/latest/APIReference/API_agent_GetPrompt.html) [Amazon Bedrock 代理人建置時期端點](https://docs.aws.amazon.com/general/latest/gr/bedrock.html#bra-bt)，以檢視您剛建立的提示版本相關資訊：
```
# Get information about the prompt version that you created
client.get_prompt(
promptIdentifier=prompt_id,
promptVersion=prompt_version
)
```
1. 透過遵循 [執行 Amazon Bedrock 流程程式碼範例](flows-code-ex.md) 的步驟將提示新增至流程，來測試該提示。在第一個步驟中，當您建立流程時，以改為執行下列程式碼片段來使用您建立的提示，而不是在流程中定義內嵌提示 (將 `promptARN` 欄位中提示版本的 ARN 取代為您所建立提示版本的 ARN)：
```
# Import Python SDK and create client
import boto3
client = boto3.client(service_name='bedrock-agent')
FLOWS_SERVICE_ROLE = "arn:aws:iam::123456789012:role/MyPromptFlowsRole" # Flows service role that you created. For more information, see https://docs.aws.amazon.com/bedrock/latest/userguide/flows-permissions.html
PROMPT_ARN = prompt_version_arn # ARN of the prompt that you created, retrieved programatically during creation.
# Define each node
# The input node validates that the content of the InvokeFlow request is a JSON object.
input_node = {
"type": "Input",
"name": "FlowInput",
"outputs": [
{
"name": "document",
"type": "Object"
}
]
}
# This prompt node contains a prompt that you defined in Prompt management.
# It validates that the input is a JSON object that minimally contains the fields "genre" and "number", which it will map to the prompt variables.
# The output must be named "modelCompletion" and be of the type "String".
prompt_node = {
"type": "Prompt",
"name": "MakePlaylist",
"configuration": {
"prompt": {
"sourceConfiguration": {
"resource": {
"promptArn": ""
}
}
}
},
"inputs": [
{
"name": "genre",
"type": "String",
"expression": "$.data.genre"
},
{
"name": "number",
"type": "Number",
"expression": "$.data.number"
}
],
"outputs": [
{
"name": "modelCompletion",
"type": "String"
}
]
}
# The output node validates that the output from the last node is a string and returns it as is. The name must be "document".
output_node = {
"type": "Output",
"name": "FlowOutput",
"inputs": [
{
"name": "document",
"type": "String",
"expression": "$.data"
}
]
}
# Create connections between the nodes
connections = []
# First, create connections between the output of the flow input node and each input of the prompt node
for input in prompt_node["inputs"]:
connections.append(
{
"name": "_".join([input_node["name"], prompt_node["name"], input["name"]]),
"source": input_node["name"],
"target": prompt_node["name"],
"type": "Data",
"configuration": {
"data": {
"sourceOutput": input_node["outputs"][0]["name"],
"targetInput": input["name"]
}
}
}
)
# Then, create a connection between the output of the prompt node and the input of the flow output node
connections.append(
{
"name": "_".join([prompt_node["name"], output_node["name"]]),
"source": prompt_node["name"],
"target": output_node["name"],
"type": "Data",
"configuration": {
"data": {
"sourceOutput": prompt_node["outputs"][0]["name"],
"targetInput": output_node["inputs"][0]["name"]
}
}
}
)
# Create the flow from the nodes and connections
client.create_flow(
name="FlowCreatePlaylist",
description="A flow that creates a playlist given a genre and number of songs to include in the playlist.",
executionRoleArn=FLOWS_SERVICE_ROLE,
definition={
"nodes": [input_node, prompt_node, output_node],
"connections": connections
}
)
```
1. 透過執行下列程式碼片段產生 [DeletePrompt](https://docs.aws.amazon.com/bedrock/latest/APIReference/API_agent_DeletePrompt.html) [Amazon Bedrock 代理人建置時期端點](https://docs.aws.amazon.com/general/latest/gr/bedrock.html#bra-bt)，以刪除您剛建立的提示版本：
```
# Delete the prompt version that you created
client.delete_prompt(
promptIdentifier=prompt_id,
promptVersion=prompt_version
)
```
1. 透過執行下列程式碼片段產生 [DeletePrompt](https://docs.aws.amazon.com/bedrock/latest/APIReference/API_agent_DeletePrompt.html) [Amazon Bedrock 代理人建置時期端點](https://docs.aws.amazon.com/general/latest/gr/bedrock.html#bra-bt)，以完全刪除您剛建立的提示：
```
# Delete the prompt that you created
client.delete_prompt(
promptIdentifier=prompt_id
)
```
------
## 叫用受管提示
建立提示並建立版本後，您可以使用 [Converse](https://docs.aws.amazon.com/bedrock/latest/APIReference/API_runtime_Converse.html) API 叫用它以進行推論。將提示 ARN 指定為 `modelId`，並提供 `promptVariables` 欄位中任何提示變數的值。
```
import boto3, json
bedrock_runtime = boto3.client(service_name="bedrock-runtime", region_name="us-east-1")
# Use the prompt ARN (with version) as the modelId
prompt_arn = "arn:aws:bedrock:us-east-1:123456789012:prompt/PROMPT_ID:VERSION"
response = bedrock_runtime.converse(
modelId=prompt_arn,
promptVariables={
"genre": {"text": "jazz"},
"number": {"text": "5"}
}
)
# Print the response
print(response["output"]["message"]["content"][0]["text"])
```
**注意**
叫用受管提示時，您不需要指定 `messages`或 `system` 欄位，這些會在提示範本中定義。您只需為提示中定義的變數提供值。