Generative AI - Has Generative AI captured your imagination to the extent it has for me?
Generative AI is indeed fascinating! The advancements in foundation models have opened up incredible possibilities. Who would have imagined that technology would evolve to the point where you can generate content summaries from transcripts, have chatbots that can answer questions on any subject without requiring any coding on your part, or even create custom images based solely on your imagination by simply providing a prompt to a Generative AI service and foundation model? It's truly remarkable to witness the power and potential of Generative AI unfold.
In this article, I am going to show you how to build a serverless GenAI solution to create call center transcript summary via a Rest API, Lambda and AWS Bedrock service. I have posted a similar article before using Amazon Bedrock Invoke Model API however, as of May 2024, AWS has announced a new Bedrock Converse API and I have updated the API and Lambda function code to call the foundation model using this converse API.
Amazon Bedrock is a fully managed service and it integrate with multiple popular foundation models like Anthropic, AI21 Labs, Meta, Cohere, Stability AI and AWS their own model Titan foundation model.
Recently, Amazon announced support for the latest Anthropic model - Anthropic Claude 3 Haiku, the fastest model that allows the creation of near-instant generative AI applications. By integrating with Amazon Bedrock Converse API, it provides a powerful combination for building generative AI applications with little effort, enabling enterprises to serve business needs and customers with speed-to-market and faster software delivery in an agile manner.
Let's consider an example of how to create a REST API that integrates with Amazon Bedrock Converse API and Anthropic Claude 3 Haiku. This API takes a call center transcript containing interactions between a call center employee and a customer, and then summarizes it into simple text for further analysis and training purposes.
I am going to show the steps to build a serverless Generative AI solution to create call center transcript summary via a rest API, Lambda and AWS Bedrock service. I will use recently released Anthropic Haiku foundation model and will invoke it via Amazon Bedrock Converse API.
Let's review our use cases:
There is a transcript available for a case resolution and conversation between customer and support/call center team member.
A call summary needs to be created based on this resolution/conversation transcript.
An automated solution is required to create call summary.
An automated solution will provide a repeatable way to create these call summary notes.
Increase in productivity as team members usually work on documenting these notes can focus on other tasks.
There is a transcript available for a case resolution and conversation between customer and support/call center team member.
A call summary needs to be created based on this resolution/conversation transcript.
An automated solution is required to create call summary.
An automated solution will provide a repeatable way to create these call summary notes.
Increase in productivity as team members usually work on documenting these notes can focus on other tasks.
I am generating my lambda function using AWS SAM, however similar can be created using AWS Console. I like to use AWS SAM wherever possible as it provides me the flexibility to test the function without first deploying to AWS cloud.
Here is the architecture diagram for our use case.
Bedrock Converse API
Let's see the steps to create this automated Generative AI solution for all center transcript summary.
Review Bedrock Service
Amazon Bedrock is fully managed service that offers choice of many foundation models like Anthropic Claude, AI21 Jurassic-2 , Stability AI, Amazon Titan and others.
Since Bedrock is another serverless offering from amazon, it allows integrating with popular FMs and also allows to privately customize FMs with your own data using the AWS tools without having to manage any infrastructure.
Why Bedrock Converse API?
You might be wondering why there's a need for another API when Bedrock already supports invoking models for large language models (LLMs). The challenge that the Converse API aims to address is the varying parameters required to invoke different LLMs. It offers a consistent API that can call underlying Amazon Bedrock foundation models without requiring changes in your code. For example, your code can call Anthropic Haiku, Anthropic Sonnet, or Amazon Titan just by changing the model ID without needing any other modifications!
While the API specification provides a standardized set of inference parameters, it also allows for the inclusion of unique parameters when needed.
As of May 2024, the newly introduced Converse API does not support embedding or image generation models.
Request Model Access
Before model can be used, you need to request the access to the model.
model access
Model Access2
For Amazon Models, typically it takes few mins to get access.
For Anthropic Haiku, it may take few hours to get access.
Temperature, Top P, Max Token Count
Let's review few key terms before we use the parameters for the model.
Temperature - A value of 0 indicate less random generation, a value of 1 means more random generation.
Top P - If value is less than 1, it will have less probable set of tokens.
Max Token Count - This indicate Max numbers of tokens to generate. Responses are not guaranteed to fill up to the maximum desired length. Tokens are factor in the overall cost hence it is worthwhile to pay attention to max tokens you want to use.
Among a few others, these are some key parameters that need to be passed when invoking the Amazon Bedrock API along with the prompt to get the desired response.
Create a SAM template
I will create a SAM template for the lambda function that will contain the code to invoke Bedrock Converse API along with required parameters and a prompt. Lambda function can be created without the SAM template however, I prefer to use Infra as Code approach since that allow for easy recreation of cloud resources. Here is the SAM template for the lambda function.
SAM Template
Create a Lambda Function
The Lambda function serves as the core of this automated solution. It contains the code necessary to fulfill the business requirement of creating a summary of the call center transcript using the Amazon Bedrock Converse API. This Lambda function accepts a prompt, which is then forwarded to the Bedrock Converse API to generate a response using the Anthropic Haiku foundation model. Now, Let's look at the code behind it.
Lambda Code
Build function locally using AWS SAM
Next build and validate function using AWS SAM before deploying the lambda function in AWS cloud. Few SAM commands used are:
SAM Build
SAM local invoke
SAM deploy
Bedrock Invoke Model Vs. Bedrock Converse API
Bedrock InvokeModel
Bedrock InvokeModel
Bedrock Converse API
Bedrock Converse API
Validate the GenAI Model response using a prompt
Prompt engineering is an essential component of any Generative AI solution. It is both art and science, as crafting an effective prompt is crucial for obtaining the desired response from the foundation model. Often, it requires multiple attempts and adjustments to the prompt to achieve the desired outcome from the Generative AI model.
Given that I'm deploying the solution to AWS API Gateway, I'll have an API endpoint post-deployment. I plan to utilize Postman for passing the prompt in the request and reviewing the response. Additionally, I can opt to post the response to an AWS S3 bucket for later review.
API Validation via Postman
I am using Postman to pass transcript file for the prompt.
This transcript file has a conversation between call center employee (John) and customer (Girish) about a request to reset the password due to the locked account.
John: Hello, thank you for calling technical support. My name is John and I will be your technical support representative. Can I have your account number, please?
Girish: Yes, my account number is {ACCOUNT_NUMBER-1}.
John: Thank you. I see that you have locked your account due to multiple failed attempts to enter your password. To reset your password, I will need to ask you a few security questions. Can you please provide me with the answers to your security questions?
Girish: Sure, my security questions are: What is your favorite color? and What is your favorite food?
John: Great, thank you. I will now reset your password and send you an email with instructions on how to log in to your account. Please check your email in a few minutes.
Girish: Thank you so much for your help.
John: You're welcome. Is there anything else I can assist you with today?
Girish: No, that's all for now. Thank you again for your help.
John: You're welcome. Have a great day!
Review the response returned by Generative AI Foundation Model
Haiku Response
The above response is generated using Anthropic Haiku LLM, however since one of the strengths of Bedrock Converse API is to support multiple LLMs without requiring much change in the code, let's see below responses returned by Anthropic Sonnet and Amazon Titan by just passing a different model id to the Lambda function.
Response using Anthropic Sonnet
Sonnet Response Response using Amazon Titan
Titan Response
With these steps, a serverless GenAI solution to create call center transcript summary via a Rest API, Lambda and AWS Bedrock Converse API has been successfully completed. Python/Boto3 were used to invoke the Bedrock API with Anthropic Haiku.
As was demonstrated, with Converse API, a consistent approach to invoke the API allows changing the underlying foundation model a much less code intensive effort and we were able to get the responses by different models just by updating the model id via environment variable without requiring any code change!
As GenAI solutions continue to evolve, they are set to reshape traditional workflows and drive tangible benefits across industries. This workshop serves as a compelling example of the transformative power of AI technologies in addressing real-world challenges and unlocking new opportunities for innovation.
Thanks for reading!
Click here to get to YouTube video for this solution.
