Run Prompt management code samples

Note

Prompt management is in preview and is subject to change.

To try out some code samples for Prompt management, select the tab corresponding to your method of choice and follow the steps. The following code samples assume that you've set up your credentials to use the AWS API. If you haven't, refer to Getting started with the AWS API.

Python

Run the following code snippet to load the AWS SDK for Python (Boto3), create a client, and create a prompt that creates a music playlist using two variables (genre and number) by making a CreatePrompt Agents for Amazon Bedrock build-time endpoint:


# Create a prompt in Prompt management
import boto3

# Create an Agents for Amazon Bedrock client
client = boto3.client(service_name="bedrock-agent")

# Create the prompt
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}}."
                }
            }
      }
    ]
)

Run the following code snippet to see the prompt that you just created (alongside any other prompts in your account) to make a ListPrompts Agents for Amazon Bedrock build-time endpoint:
```
# List prompts that you've created
client.list_prompts()
```
You should see the ID of the prompt you created in the id field in the object in the promptSummaries field. In the following examples, we use PROMPT12345 as a placeholder for the prompt ID. Run the following code snippet using the ID of the prompt that you just created to show information for just that prompt to make a GetPrompt Agents for Amazon Bedrock build-time endpoint:
```
# Get information about the prompt that you created
client.get_prompt(promptIdentifier="PROMPT12345")
```
Create a version of the prompt by running the following code snippet to make a CreatePromptVersion Agents for Amazon Bedrock build-time endpoint:
```
# Create a version of the prompt that you created
client.create_prompt_version(promptIdentifier="PROMPT12345")
```
View information about the prompt version that you just created, alongside information about the draft version, by running the following code snippet to make a ListPrompts Agents for Amazon Bedrock build-time endpoint:
```
# List versions of the prompt that you just created
client.list_prompts(promptIdentifier="PROMPT12345")
```
View information for the prompt version that you just created by running the following code snippet to make a GetPrompt Agents for Amazon Bedrock build-time endpoint:
```
# Get information about the prompt version that you created
client.get_prompt(
    promptIdentifier="PROMPT12345", 
    promptVersion="1"
)
```

Test the prompt by adding it to a prompt flow by following the steps at Run Prompt flows code samples. In the first step when you create the flow, run the following code snippet instead to use the prompt that you created instead of defining an inline prompt in the flow (replace the ARN of the prompt version in the promptARN field with the ARN of the version of the prompt that you created):


# Import Python SDK and create client
import boto3

client = boto3.client(service_name='bedrock-agent')

# 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": "arn:aws:bedrock:<replaceable>us-east-1</replaceable>:<replaceable>123456789012<replaceable>:prompt/PROMPT1234:1"
                }
            }
        }
    },
    "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="arn:aws:iam::<replaceable>123456789012</replaceable>:role/<replaceable>MyPromptFlowsRole</replaceable>",
    definition={
        "nodes": [input_node, prompt_node, output_node],
        "connections": connections
    }
)

Delete the prompt version that you just created by running the following code snippet to make a DeletePrompt Agents for Amazon Bedrock build-time endpoint:
```
# Delete the prompt version that you created
client.delete_prompt(
    promptIdentifier="PROMPT12345", 
    promptVersion="1"
)
```
Fully delete the prompt that you just created by running the following code snippet to make a DeletePrompt Agents for Amazon Bedrock build-time endpoint:
```
# Delete the prompt that you created
client.delete_prompt(
    promptIdentifier="PROMPT12345"
)
```

Warning Javascript is disabled or is unavailable in your browser.

To use the Amazon Web Services Documentation, Javascript must be enabled. Please refer to your browser's Help pages for instructions.

Document Conventions

Deploy a prompt (versioning)

Guardrails for Amazon Bedrock