Juego de Mazmorra con IA

Módulo 3: Implementación de la API de historia

Precaución

Asegúrate de haber otorgado acceso al modelo Anthropic Claude 3.5 Sonnet v2 siguiendo los pasos descritos en esta guía.

La StoryApi consta de una única API generate_story que, dado un Game y una lista de Actions como contexto, generará una progresión de la historia. Esta API se implementará como una API de streaming en Python/FastAPI y además demostrará cómo se pueden realizar modificaciones al código generado para adaptarlo a su propósito.

Implementación de la API

Para crear nuestra API, primero necesitamos instalar algunas dependencias adicionales:

• boto3 se usará para llamar a Amazon Bedrock;
• uvicorn se usará para iniciar nuestra API en conjunto con el Lambda Web Adapter (LWA).
• copyfiles es una dependencia de npm que necesitaremos para soportar la copia multiplataforma de archivos al actualizar nuestra tarea bundle.

Para instalar estas dependencias, ejecuta los siguientes comandos:

pnpm

pnpm nx run dungeon_adventure.story_api:add --args boto3 uvicorn

yarn

yarn nx run dungeon_adventure.story_api:add --args boto3 uvicorn

npm

npx nx run dungeon_adventure.story_api:add --args boto3 uvicorn

bun

bunx nx run dungeon_adventure.story_api:add --args boto3 uvicorn

pnpm

pnpm add -Dw copyfiles

yarn

yarn add -D copyfiles

npm

npm install --legacy-peer-deps -D copyfiles

bun

bun install -D copyfiles

Ahora reemplazaremos el contenido de los siguientes archivos en packages/story_api/story_api:

main.py

import json

from boto3 import client
from fastapi.responses import PlainTextResponse, StreamingResponse
from pydantic import BaseModel

from .init import app, lambda_handler

handler = lambda_handler

bedrock = client('bedrock-runtime')

class Action(BaseModel):
    role: str
    content: str

class StoryRequest(BaseModel):
    genre: str
    playerName: str
    actions: list[Action]

async def bedrock_stream(request: StoryRequest):
    messages = [
        {"role": "user", "content": "Continue or create a new story..."}
    ]

    for action in request.actions:
        messages.append({"role": action.role, "content": action.content})

    response = bedrock.invoke_model_with_response_stream(
        modelId='anthropic.claude-3-sonnet-20240229-v1:0',
        body=json.dumps({
            "system":f"""
            You are running an AI text adventure game in the {request.genre} genre.
            Player: {request.playerName}. Return less than 200 characters of text.
            """,
            "messages": messages,
            "max_tokens": 1000,
            "temperature": 0.7,
            "anthropic_version": "bedrock-2023-05-31"
        })
    )

    stream = response.get('body')
    if stream:
        for event in stream:
            chunk = event.get('chunk')
            if chunk:
                message = json.loads(chunk.get("bytes").decode())
                if message['type'] == "content_block_delta":
                    yield message['delta']['text'] or ""
                elif message['type'] == "message_stop":
                    yield "\n"

@app.post("/story/generate",
          openapi_extra={'x-streaming': True},
          response_class=PlainTextResponse)
def generate_story(request: StoryRequest) -> str:
    return StreamingResponse(bedrock_stream(request), media_type="text/plain")

init.py

import os
import uuid
from collections.abc import Callable

from aws_lambda_powertools import Logger, Metrics, Tracer
from aws_lambda_powertools.metrics import MetricUnit
from fastapi import FastAPI, Request, Response
from fastapi.openapi.utils import get_openapi
from fastapi.responses import JSONResponse
from fastapi.routing import APIRoute
from mangum import Mangum
from pydantic import BaseModel
from starlette.middleware.exceptions import ExceptionMiddleware

os.environ["POWERTOOLS_METRICS_NAMESPACE"] = "StoryApi"
os.environ["POWERTOOLS_SERVICE_NAME"] = "StoryApi"

logger: Logger = Logger()
metrics: Metrics = Metrics()
tracer: Tracer = Tracer()

class InternalServerErrorDetails(BaseModel):
    detail: str

app = FastAPI(
    title="StoryApi",
    responses={
        500: {"model": InternalServerErrorDetails}
    }
)
lambda_handler = Mangum(app)

# Add tracing
lambda_handler.__name__ = "handler"  # tracer requires __name__ to be set
lambda_handler = tracer.capture_lambda_handler(lambda_handler)
# Add logging
lambda_handler = logger.inject_lambda_context(lambda_handler, clear_state=True)
# Add metrics last to properly flush metrics.
lambda_handler = metrics.log_metrics(lambda_handler, capture_cold_start_metric=True)

# Add exception middleware(s)
app.add_middleware(ExceptionMiddleware, handlers=app.exception_handlers)

@app.exception_handler(Exception)
async def unhandled_exception_handler(request, err):
    logger.exception("Unhandled exception")

    metrics.add_metric(name="Failure", unit=MetricUnit.Count, value=1)

    return JSONResponse(status_code=500,
                        content=InternalServerErrorDetails(
                            detail="Internal Server Error").model_dump())

@app.middleware("http")
async def metrics_handler(request: Request, call_next):
    metrics.add_dimension("route", f"{request.method} {request.url.path}")
    metrics.add_metric(name="RequestCount", unit=MetricUnit.Count, value=1)

    response = await call_next(request)

    if response.status_code == 200:
        metrics.add_metric(name="Success", unit=MetricUnit.Count, value=1)

    return response

# Add correlation id middleware
@app.middleware("http")
async def add_correlation_id(request: Request, call_next):
    # Get correlation id from X-Correlation-Id header
    corr_id = request.headers.get("x-correlation-id")
    if not corr_id and "aws.context" in request.scope:
        # If empty, use request id from aws context
        corr_id = request.scope["aws.context"].aws_request_id
    elif not corr_id:
        # If still empty, use uuid
        corr_id = uuid.uuid4().hex

    # Add correlation id to logs
    logger.set_correlation_id(corr_id)

    response = await call_next(request)

    # Return correlation header in response
    response.headers["X-Correlation-Id"] = corr_id
    return response

class LoggerRouteHandler(APIRoute):
    def get_route_handler(self) -> Callable:
        original_route_handler = super().get_route_handler()

        async def route_handler(request: Request) -> Response:
            # Add fastapi context to logs
            ctx = {
                "path": request.url.path,
                "route": self.path,
                "method": request.method,
            }
            logger.append_keys(fastapi=ctx)
            logger.info("Received request")

            return await original_route_handler(request)

        return route_handler

app.router.route_class = LoggerRouteHandler

def custom_openapi():
    if app.openapi_schema:
        return app.openapi_schema
    for route in app.routes:
        if isinstance(route, APIRoute):
            route.operation_id = route.name
    openapi_schema = get_openapi(
        title=app.title,
        version=app.version,
        openapi_version=app.openapi_version,
        description=app.description,
        routes=app.routes,
    )
    app.openapi_schema = openapi_schema
    return app.openapi_schema

app.openapi = custom_openapi

Nota

El cambio anterior en init.py simplemente elimina el middleware CORS para evitar conflictos con el manejo propio de cabeceras CORS de Lambda Function URL.

Analizando el código anterior:

• Usamos la configuración x-streaming para indicar que esta es una API de streaming cuando generemos nuestro SDK cliente. ¡Esto nos permitirá consumir esta API en modo streaming manteniendo la seguridad de tipos!
• Nuestra API simplemente devuelve un flujo de texto definido tanto por media_type="text/plain" como por response_class=PlainTextResponse

Nota

Cada vez que realices cambios en tu FastAPI, necesitarás reconstruir tu proyecto para ver esos cambios reflejados en el cliente generado en tu sitio web.

Haremos algunos cambios más a continuación antes de reconstruir.

Infraestructura

La infraestructura que configuramos anteriormente asume que todas las APIs tienen una API Gateway integrada con funciones Lambda. Para nuestra story_api no queremos usar API Gateway ya que no soporta respuestas en streaming. En su lugar, usaremos una Lambda Function URL configurada con response streaming.

Para soportar esto, primero actualizaremos nuestros constructos de CDK de la siguiente manera:

story-api.ts

import { Duration, Stack, CfnOutput } from 'aws-cdk-lib';
import { IGrantable, Grant } from 'aws-cdk-lib/aws-iam';
import {
  Runtime,
  Code,
  Tracing,
  LayerVersion,
  FunctionUrlAuthType,
  InvokeMode,
  Function,
} from 'aws-cdk-lib/aws-lambda';
import { Construct } from 'constructs';
import url from 'url';
import { RuntimeConfig } from '../../core/runtime-config.js';

export class StoryApi extends Construct {
  public readonly handler: Function;

  constructor(scope: Construct, id: string) {
    super(scope, id);

    this.handler = new Function(this, 'Handler', {
      runtime: Runtime.PYTHON_3_12,
      handler: 'run.sh',
      code: Code.fromAsset(
        url.fileURLToPath(
          new URL(
            '../../../../../../dist/packages/story_api/bundle',
            import.meta.url,
          ),
        ),
      ),
      timeout: Duration.seconds(30),
      tracing: Tracing.ACTIVE,
      environment: {
        AWS_CONNECTION_REUSE_ENABLED: '1',
      },
    });

    const stack = Stack.of(this);
    this.handler.addLayers(
      LayerVersion.fromLayerVersionArn(
        this,
        'LWALayer',
        `arn:aws:lambda:${stack.region}:753240598075:layer:LambdaAdapterLayerX86:24`,
      ),
    );
    this.handler.addEnvironment('PORT', '8000');
    this.handler.addEnvironment('AWS_LWA_INVOKE_MODE', 'response_stream');
    this.handler.addEnvironment('AWS_LAMBDA_EXEC_WRAPPER', '/opt/bootstrap');
    const functionUrl = this.handler.addFunctionUrl({
      authType: FunctionUrlAuthType.AWS_IAM,
      invokeMode: InvokeMode.RESPONSE_STREAM,
      cors: {
        allowedOrigins: ['*'],
        allowedHeaders: [
          'authorization',
          'content-type',
          'x-amz-content-sha256',
          'x-amz-date',
          'x-amz-security-token',
        ],
      },
    });

    new CfnOutput(this, 'StoryApiUrl', { value: functionUrl.url });

    // Register the API URL in runtime configuration for client discovery
    RuntimeConfig.ensure(this).config.apis = {
      ...RuntimeConfig.ensure(this).config.apis!,
      StoryApi: functionUrl.url,
    };
  }

  public grantInvokeAccess(grantee: IGrantable) {
    Grant.addToPrincipal({
      grantee,
      actions: ['lambda:InvokeFunctionUrl'],
      resourceArns: [this.handler.functionArn],
      conditions: {
        StringEquals: {
          'lambda:FunctionUrlAuthType': 'AWS_IAM',
        },
      },
    });
  }
}

application-stack.ts

stacks/application-stack.ts

import {
  GameApi,
  GameUI,
  StoryApi,
  UserIdentity,
} from ':dungeon-adventure/common-constructs';
import * as cdk from 'aws-cdk-lib';
import { Construct } from 'constructs';
import { ElectrodbDynamoTable } from '../constructs/electrodb-table.js';
import { PolicyStatement, Effect } from 'aws-cdk-lib/aws-iam';

export class ApplicationStack extends cdk.Stack {
  constructor(scope: Construct, id: string, props?: cdk.StackProps) {
    super(scope, id, props);

    // The code that defines your stack goes here
    const userIdentity = new UserIdentity(this, 'UserIdentity');

    const electroDbTable = new ElectrodbDynamoTable(this, 'ElectroDbTable');

    const gameApi = new GameApi(this, 'GameApi', {
      integrations: GameApi.defaultIntegrations(this)
        .withDefaultOptions({
          environment: {
            TABLE_NAME: electroDbTable.tableName,
          },
        })
        .build(),
    });

    // Grant read/write access to each procedure's lambda handler according to the permissions it requires
    // Grant read/write access to each handler depending on the permissions it requires
    electroDbTable.grantReadData(gameApi.integrations['actions.query'].handler);
    electroDbTable.grantReadData(gameApi.integrations['games.query'].handler);
    electroDbTable.grantReadWriteData(
      gameApi.integrations['actions.save'].handler,
    );
    electroDbTable.grantReadWriteData(
      gameApi.integrations['games.save'].handler,
    );

    const storyApi = new StoryApi(this, 'StoryApi', {
      integrations: StoryApi.defaultIntegrations(this).build(),
    });
    const storyApi = new StoryApi(this, 'StoryApi');
    storyApi.handler.addToRolePolicy(
      new PolicyStatement({
        effect: Effect.ALLOW,
        actions: ['bedrock:InvokeModelWithResponseStream'],
        resources: [
          'arn:aws:bedrock:*::foundation-model/anthropic.claude-3-sonnet-20240229-v1:0',
        ],
      }),
    );

    // grant our authenticated role access to invoke our APIs
    [storyApi, gameApi].forEach((api) =>
      api.grantInvokeAccess(userIdentity.identityPool.authenticatedRole),
    );

    // Ensure this is instantiated last so our runtime-config.json can be automatically configured
    new GameUI(this, 'GameUI');
  }
}

Ahora actualizaremos la story_api para soportar el despliegue con Lambda Web Adapter.

run.sh

#!/bin/bash

PATH=$PATH:$LAMBDA_TASK_ROOT/bin \
    PYTHONPATH=$PYTHONPATH:/opt/python:$LAMBDA_RUNTIME_DIR \
    exec python -m uvicorn --port=$PORT story_api.main:app

project.json

packages/story_api/project.json

{
  "name": "dungeon_adventure.story_api",
  ...
  "targets": {
    ...
    "bundle": {
      "cache": true,
      "executor": "nx:run-commands",
      "outputs": ["{workspaceRoot}/dist/packages/story_api/bundle"],
      "options": {
        "commands": [
          "uv export --frozen --no-dev --no-editable --project packages/story_api --package dungeon_adventure.story_api -o dist/packages/story_api/bundle/requirements.txt",
          "uv pip install -n --no-installer-metadata --no-compile-bytecode --python-platform x86_64-manylinux2014 --target dist/packages/story_api/bundle -r dist/packages/story_api/bundle/requirements.txt",
          "copyfiles -f packages/story_api/run.sh dist/packages/story_api/bundle"
        ],
        "parallel": false
      },
      "dependsOn": ["compile"]
    },
    ...
  }
}

Despliegue y pruebas

Primero, construyamos la base de código:

pnpm

pnpm nx run-many --target build --all

yarn

yarn nx run-many --target build --all

npm

npx nx run-many --target build --all

bun

bunx nx run-many --target build --all

Consejo

Si encuentras errores de linting, puedes ejecutar el siguiente comando para corregirlos automáticamente.

pnpm

pnpm nx run-many --target lint --configuration=fix --all

yarn

yarn nx run-many --target lint --configuration=fix --all

npm

npx nx run-many --target lint --configuration=fix --all

bun

bunx nx run-many --target lint --configuration=fix --all

Ahora puedes desplegar tu aplicación ejecutando el siguiente comando:

pnpm

pnpm nx run @dungeon-adventure/infra:deploy dungeon-adventure-infra-sandbox

yarn

yarn nx run @dungeon-adventure/infra:deploy dungeon-adventure-infra-sandbox

npm

npx nx run @dungeon-adventure/infra:deploy dungeon-adventure-infra-sandbox

bun

bunx nx run @dungeon-adventure/infra:deploy dungeon-adventure-infra-sandbox

Este despliegue tomará aproximadamente 2 minutos en completarse.

También puedes desplegar todos los stacks a la vez. Haz clic aquí para más detalles.

Una vez completado el despliegue, deberías ver algunas salidas similares a las siguientes (algunos valores han sido omitidos):

dungeon-adventure-infra-sandbox
dungeon-adventure-infra-sandbox: deploying... [2/2]

 ✅  dungeon-adventure-infra-sandbox

✨  Tiempo de despliegue: 354s

Outputs:
dungeon-adventure-infra-sandbox.ElectroDbTableTableNameXXX = dungeon-adventure-infra-sandbox-ElectroDbTableXXX-YYY
dungeon-adventure-infra-sandbox.GameApiEndpointXXX = https://xxx.execute-api.region.amazonaws.com/prod/
dungeon-adventure-infra-sandbox.GameUIDistributionDomainNameXXX = xxx.cloudfront.net
dungeon-adventure-infra-sandbox.StoryApiStoryApiUrlXXX = https://xxx.lambda-url.ap-southeast-2.on.aws/
dungeon-adventure-infra-sandbox.UserIdentityUserIdentityIdentityPoolIdXXX = region:xxx
dungeon-adventure-infra-sandbox.UserIdentityUserIdentityUserPoolIdXXX = region_xxx

Podemos probar nuestra API de dos maneras:

• Iniciando una instancia local del servidor FastAPI e invocando las APIs usando curl.
• Llamando a la API desplegada usando curl con Sigv4 directamente

Local

Inicia tu servidor FastAPI local ejecutando:

pnpm

pnpm nx run dungeon_adventure.story_api:serve

yarn

yarn nx run dungeon_adventure.story_api:serve

npm

npx nx run dungeon_adventure.story_api:serve

bun

bunx nx run dungeon_adventure.story_api:serve

Una vez que el servidor FastAPI esté en ejecución, llámalo con:

curl -N -X POST http://127.0.0.1:8000/story/generate \
  -d '{"genre":"superhero", "actions":[], "playerName":"UnnamedHero"}' \
  -H "Content-Type: application/json"

Desplegado

acurl ap-southeast-2 lambda -N -X POST \
  https://xxx.lambda-url.ap-southeast-2.on.aws/story/generate \
  -d '{"genre":"superhero", "actions":[], "playerName":"UnnamedHero"}' \
  -H "Content-Type: application/json"

Precaución

Usa el valor de salida dungeon-adventure-infra-sandbox.StoryApiStoryApiUrlXXX del despliegue CDK para reemplazar el marcador de posición de la URL y configura la región adecuadamente.

Si el comando se ejecuta correctamente, deberías ver una respuesta transmitida similar a:

UnnamedHero se alzó imponente, su capa ondeando al viento....

¡Felicidades! Has construido y desplegado tu primera API usando FastAPI. 🎉🎉🎉