Document institutional knowledge from voice inputs by using Amazon Bedrock and Amazon Transcribe - AWS Prescriptive Guidance
SummaryPrerequisites and limitationsArchitectureToolsBest practicesEpicsRelated resources

Document institutional knowledge from voice inputs by using Amazon Bedrock and Amazon Transcribe

Created by Praveen Kumar Jeyarajan (AWS), Jundong Qiao (AWS), Megan Wu (AWS), and Rajiv Upadhyay (AWS)

Summary

Capturing institutional knowledge is paramount for ensuring organizational success and resilience. Institutional knowledge represents the collective wisdom, insights, and experiences accumulated by employees over time, often tacit in nature and passed down informally. This wealth of information encompasses unique approaches, best practices, and solutions to intricate problems that might not be documented elsewhere. By formalizing and documenting this knowledge, companies can preserve institutional memory, foster innovation, enhance decision-making processes, and accelerate learning curves for new employees. Additionally, it promotes collaboration, empowers individuals, and cultivates a culture of continuous improvement. Ultimately, harnessing institutional knowledge helps companies use their most valuable asset—the collective intelligence of their workforce—to navigate challenges, drive growth, and maintain competitive advantage in dynamic business environments.

This pattern explains how to capture institutional knowledge through voice recordings from senior employees. It uses Amazon Transcribe and Amazon Bedrock for systematic documentation and verification. By documenting this informal knowledge, you can preserve it and share it with subsequent cohorts of employees. This endeavor supports operational excellence and improves the effectiveness of training programs through the incorporation of practical knowledge acquired through direct experience.

Prerequisites and limitations

Prerequisites

  • An active AWS account

  • Docker, installed

  • AWS Cloud Development Kit (AWS CDK) version 2.114.1 or later, installed and bootstrapped to the us-east-1 or us-west-2 AWS Regions

  • AWS CDK Toolkit version 2.114.1 or later, installed

  • AWS Command Line Interface (AWS CLI), installed and configured

  • Python version 3.12 or later, installed

  • Permissions to create Amazon Transcribe, Amazon Bedrock, Amazon Simple Storage Service (Amazon S3), and AWS Lambda resources

Limitations

  • This solution is deployed to a single AWS account.

  • This solution can be deployed only in AWS Regions where Amazon Bedrock and Amazon Transcribe are available. For information about availability, see the documentation for Amazon Bedrock and Amazon Transcribe.

  • The audio files must be in a format that Amazon Transcribe supports. For a list of supported formats, see Media formats in the Transcribe documentation.

Product versions

  • AWS SDK for Python (Boto3) version 1.34.57 or later

  • LangChain version 0.1.12 or later

Architecture

The architecture represents a serverless workflow on AWS. AWS Step Functions orchestrates Lambda functions for audio processing, text analysis, and document generation. The following diagram shows the Step Functions workflow, also known as a state machine.

Architecture diagram of Step Functions state machine generating a document

Each step in the state machine is handled by a distinct Lambda function. The following are the steps in the document generation process:

  1. The preprocess Lambda function validates the input passed to Step Functions and lists all of the audio files present in the provided Amazon S3 URI folder path. Downstream Lambda functions in the workflow use the file list to validate, summarize, and generate the document.

  2. The transcribe Lambda function uses Amazon Transcribe to convert audio files into text transcripts. This Lambda function is responsible for initiating the transcription process and accurately transforming speech into text, which is then stored for subsequent processing.

  3. The validate Lambda function analyzes the text transcripts, determining the relevance of the responses to the initial questions. By using a large language model (LLM) through Amazon Bedrock, it identifies and separates on-topic answers from off-topic responses.

  4. The summarize Lambda function uses Amazon Bedrock to generate a coherent and concise summary of the on-topic answers.

  5. The generate Lambda function assembles the summaries into a well-structured document. It can format the document according to predefined templates and include any additional necessary content or data.

  6. If any of the Lambda functions fail, you receive an email notification through Amazon Simple Notification Service (Amazon SNS).

Throughout this process, AWS Step Functions makes sure that each Lambda function is initiated in the correct sequence. This state machine has the capacity for parallel processing to enhance efficiency. An Amazon S3 bucket acts as the central storage repository, supporting the workflow by managing the various media and document formats involved.

Tools

AWS services

  • Amazon Bedrock is a fully managed service that makes high-performing foundation models (FMs) from leading AI startups and Amazon available for your use through a unified API.

  • AWS Lambda is a compute service that helps you run code without needing to provision or manage servers. It runs your code only when needed and scales automatically, so you pay only for the compute time that you use.

  • Amazon Simple Notification Service (Amazon SNS) helps you coordinate and manage the exchange of messages between publishers and clients, including web servers and email addresses.

  • Amazon Simple Storage Service (Amazon S3) is a cloud-based object storage service that helps you store, protect, and retrieve any amount of data.

  • AWS Step Functions is a serverless orchestration service that helps you combine AWS Lambda functions and other AWS services to build business-critical applications.  

  • Amazon Transcribe is an automatic speech recognition service that uses machine learning models to convert audio to text.

Other tools

  • LangChain is a framework for developing applications that are powered by large language models (LLMs).

Code repository

The code for this pattern is available in the GitHub genai-knowledge-capture repository.

The code repository contains the following files and folders:

  • assets folder – The static assets for the solution, such as the architecture diagram and the public dataset

  • code/lambdas folder – The Python code for all Lambda functions

    • code/lambdas/generate folder - The Python code that generates a document from the summarized data in the S3 bucket

    • code/lambdas/preprocess folder - The Python code that processes the inputs for the Step Functions state machine

    • code/lambdas/summarize folder - The Python code that summarizes the transcribed data by using Amazon Bedrock service

    • code/lambdas/transcribe folder - The Python code that converts speech data (audio file) into text by using Amazon Transcribe

    • code/lambdas/validate folder - The Python code that validates whether all answers pertain to the same topic

  • code/code_stack.py – The AWS CDK construct Python file that is used to create AWS resources

  • app.py – The AWS CDK app Python file that is used to deploy AWS resources in the target AWS account

  • requirements.txt – The list of all Python dependencies that must be installed for the AWS CDK

  • cdk.json – The input file to provide values that are required to create resources

Best practices

The code example provided is for proof-of-concept (PoC) or pilot purposes only. If you want to take the solution to production, use the following best practices:

Epics

TaskDescriptionSkills required

Export variables for the account and AWS Region.

To provide AWS credentials for the AWS CDK by using environment variables, run the following commands.

export CDK_DEFAULT_ACCOUNT=<12-digit AWS account number>
export CDK_DEFAULT_REGION=<Region>
AWS DevOps, DevOps engineer

Set up the AWS CLI named profile.

To set up the AWS CLI named profile for the account, follow the instructions in Configuration and credential file settings.

AWS DevOps, DevOps engineer
TaskDescriptionSkills required

Clone the repo to your local workstation.

To clone the genai-knowledge-capture repository, run the following command in your terminal.

git clone https://github.com/aws-samples/genai-knowledge-capture
AWS DevOps, DevOps engineer

(Optional) Replace the audio files.

To customize the sample application to incorporate your own data, do the following:

  1. Navigate to the assets/audio_samples folder in the cloned repository.

  2. Delete the folders containing the sample audio files.

  3. Create a folder for each topic you want to analyze.

  4. Transfer your audio files to their respective folders.

AWS DevOps, DevOps engineer

Set up the Python virtual environment.

To set up the Python virtual environment, run the following commands.

cd genai-knowledge-capture
python3 -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt
AWS DevOps, DevOps engineer

Synthesize the AWS CDK code.

To convert the code to an AWS CloudFormation stack configuration, run the following command.

cdk synth
AWS DevOps, DevOps engineer
TaskDescriptionSkills required

Provision foundation model access.

Enable access to the Anthropic Claude 3 Sonnet model for your AWS account. For instructions, see Add model access in the Bedrock documentation.

AWS DevOps

Deploy resources in the account.

To deploy resources in the AWS account by using the AWS CDK, do the following:

  1. (Optional) In the root of the cloned repository, in the app.py file, update the AWS CloudFormation stack name. The default stack name is genai-knowledge-capture-stack.

  2. To deploy resources, run the command cdk deploy.

    The cdk deploy command uses layer-3 constructs to create a set of Lambda functions, an S3 bucket, an Amazon SNS topic, and a Step Functions state machine. Audio files in the assets/audio_samples folder are copied into the S3 bucket during deployment.

  3. Sign in to the AWS Management Console, and then open the CloudFormation console at https://console.aws.amazon.com/cloudformation/.

  4. Confirm that the stack deployed successfully. For instructions, see Reviewing your stack on the AWS CloudFormation console.

AWS DevOps, DevOps engineer

Subscribe to the Amazon SNS topic.

To subscribe to the Amazon SNS topic for notification, do the following:

  1. In the CloudFormation console, in the navigate pane, choose Stacks.

  2. Choose the genai-knowledge-capture-stack stack.

  3. Choose the Outputs tab.

  4. Find the Amazon SNS topic name with the key SNSTopicName.

  5. Configure an email address to receive notifications by following the instructions in Subscribe an email address to an Amazon SNS topic.

General AWS
TaskDescriptionSkills required

Run the state machine.

  1. Open the Step Functions console.

  2. On the State machines page, choose genai-knowledge-capture-stack-state-machine.

  3. Choose Start execution.

  4. (Optional) In the Name box, enter a name for the execution.

  5. In the Input area, enter the following JSON object by replacing the placeholder text, where:

    • <Name> is what you want to name the document.

    • <S3 bucket name> is the name of the Amazon S3 bucket that contains the audio files.

    • <Folder path> is the directory that contains the audio files.

    {
  "documentName": "<Name>",
  "audioFileFolderUri": "s3://<S3 bucket name>/<Folder path>"
}

  6. Choose Start Execution.

  7. On the execution details page, review the results and wait for the execution to complete.

App developer, General AWS
TaskDescriptionSkills required

Remove the AWS resources.

After you test the solution, clean up the resources:

  1. Delete all objects from the S3 bucket, and then delete the bucket. For more information, see Deleting a bucket.

  2. From the cloned repository, run the command cdk destroy.

AWS DevOps, DevOps engineer

Related resources

AWS documentation

Other resources