Building a GenAI Blog Generator with AWS Bedrock, Amazon S3, Lambda, API Gateway, and Postman

Creating a blog generator using AWS Bedrock, Amazon S3, AWS Lambda, API Gateway, and Postman combines the power of generative AI with serverless architecture. Follow this step-by-step guide to set up the system.

---

Step 1: Create the Lambda Function

Lambda Function Code

Below is the Python code for the Lambda function:

import boto3
import botocore.config
import json
from datetime import datetime

def blog_generate_using_bedrock(blogtopic: str) -> str:
    prompt = f"""<s>[INST]Human: Write a 200 words blog on the topic {blogtopic}
    Assistant:[/INST]
    """

    body = {
        "prompt": prompt,
        "max_gen_len": 512,
        "temperature": 0.5,
        "top_p": 0.9
    }

    try:
        bedrock = boto3.client("bedrock-runtime", region_name="us-east-1",
                               config=botocore.config.Config(read_timeout=300, retries={'max_attempts': 3}))
        response = bedrock.invoke_model(body=json.dumps(body), modelId="meta.llama2-13b-chat-v1")

        response_content = response.get('body').read()
        response_data = json.loads(response_content)
        print(response_data)
        blog_details = response_data['generation']
        return blog_details
    except Exception as e:
        print(f"Error generating the blog:{e}")
        return ""

def save_blog_details_s3(s3_key, s3_bucket, generate_blog):
    s3 = boto3.client('s3')

    try:
        s3.put_object(Bucket=s3_bucket, Key=s3_key, Body=generate_blog)
        print("Blog saved to S3")
    except Exception as e:
        print(f"Error saving blog to S3: {e}")

def lambda_handler(event, context):
    event = json.loads(event['body'])
    blogtopic = event['blog_topic']

    generate_blog = blog_generate_using_bedrock(blogtopic=blogtopic)

    if generate_blog:
        current_time = datetime.now().strftime('%H%M%S')
        s3_key = f"blog-output/{current_time}.txt"
        s3_bucket = 'aws_bedrock_course1'
        save_blog_details_s3(s3_key, s3_bucket, generate_blog)
    else:
        print("No blog was generated")

    return {
        'statusCode': 200,
        'body': json.dumps('Blog generation completed')
    }

---

Step 2: Build the Code in VS Code

1. Set up a Conda Environment:

    conda create -p venv python==3.12
    conda activate ./venv
   

2. Create Project Files:

   • Create a new folder.

   • Inside the folder, create app.py and a requirements.txt file.

   • Copy the Lambda function code into app.py.

3. Install Dependencies:

   • Add boto3 and botocore to requirements.txt:

       boto3
       botocore
     

   • Install dependencies using:

       pip install -r requirements.txt
     

4. Deploy the Code to Lambda:

   • Paste the code into the AWS Lambda console.

   • Add a layer to the Lambda function with an updated boto3 library if needed.

---

Step 3: Set Up API Gateway

1. Create an HTTP API:

   • Open the API Gateway console.

   • Create a new HTTP API.

2. Add a POST Route:

   • Define a POST route (e.g., /generate-blog).

3. Attach Integration:

   • Connect the POST route to the Lambda function.

---

Step 4: Create an S3 Bucket

1. Open the S3 console and create a bucket (e.g., aws_bedrock_course1).

2. Ensure the bucket has appropriate permissions for the Lambda function to write to it.

---

Step 5: Test Using Postman

1. Open Postman and create a new POST request.

2. Enter the API Gateway URL in the request URL field.

3. Go to the Body tab and select raw with JSON format.

4. Add the following payload:

    {
        "blog_topic": "The future of AI in education"
    }
   

5. Send the request. Check the S3 bucket for the generated blog.

---

Common Errors and Solutions

1. Error: Insufficient Lambda Permissions:

   • Ensure the Lambda execution role has AdministratorAccess or at least permissions for S3 and Bedrock actions.

2. Error: Unable to Invoke Model:

   • Check if Bedrock is enabled in your AWS account and ensure the region matches (us-east-1 in this example).

3. Error Saving to S3:

   • Verify the S3 bucket exists and the Lambda function has s3:PutObject permissions.

---

With this setup, you can generate blogs using AWS Bedrock's AI capabilities, save them in S3, and test the workflow seamlessly through Postman!