Build a contextual chatbot application using Knowledge Bases for Amazon Bedrock AWS Machine Learning Blog

This lets DevOps teams use chat channels as the primary means of collaboration when monitoring events, analyzing incidents, and operating AWS workloads. One way to enable more contextual conversations is by linking the chatbot to internal knowledge bases and information systems. Integrating proprietary enterprise data from internal knowledge bases enables chatbots to contextualize their responses to each user’s individual needs and interests. The ability to intelligently incorporate information, understand natural language, and provide customized replies in a conversational flow allows chatbots to deliver real business value across diverse use cases. The IAM policies will be consistent across

chat channels that support commands in your AWS Chatbot service.

Customers can securely run AWS CLI commands to scale EC2 instances, run AWS Systems Manager runbooks, and change AWS Lambda concurrency limits. Customers can now monitor, operate, and troubleshoot AWS workloads from Slack channels without switching context between Slack and other AWS Management Tools. Additionally, you can configure channel permissions to match your security and compliance needs by modifying account-level settings, using predefined permission templates, and using guardrail policies. You can also run AWS CLI commands directly in chat channels using AWS Chatbot.

Learn About AWS

Running AWS commands from Slack using AWS Chatbot expands the toolkit your team uses to respond to operational events and interact with AWS. In this post, I walked you through some of the use cases where AWS Chatbot helped reduce the time to recovery while also increasing transparency within DevOps teams. To get started, first configure Slack notifications for CloudWatch Alarms for a Lambda function via AWS Chatbot. Then, make your function fail to trigger the CloudWatch Alarm to go into the alarm state. Finally, if you also want to receive notifications, such as CloudWatch Alarms or AWS Budgets, select SNS topics that those notifications are published to. You can either select a public channel from the dropdown list or paste the URL or ID of a private channel.

In this blog post, you’ll learn how to extend the solution so you can use AWS Chatbot to remediate the findings in your Slack channel. You’ll receive the findings from Security Hub and then run AWS CLI commands from your Slack channel to remediate the reported security findings. CloudWatch alarm notifications show buttons in chat client notifications to view logs related to the

alarm. There may be service charges for using this feature to query and show

logs. In November 2021, we announced the preview of this feature update to the AWS Chatbot. In addition to the preview feature set, we are introducing improvements that allow customers to specify multiple guardrail policies in a chat configuration, giving more control in securing channel permissions.

Congratulations, you have created a Lambda function, related roles, and policies successfully. The popular architecture pattern of Retrieval Augmented Generation (RAG) is often used to augment user query context and responses. RAG combines the capabilities of LLMs with the grounding in facts and real-world knowledge that comes from retrieving relevant texts and passages from corpus of data. These retrieved texts are then used to inform and ground the output, reducing hallucination and improving relevance. If you encounter issues when trying to receive notifications, click troubleshooting AWS Chatbot documentation. We would like to receive notifications on Slack channel when the CPU utilization of EC2 instances reaches the threshold of 70%.

Create an App on Slack

You can automate these solutions based on your specific requirements using AWS CloudFormation or AWS CLI or SDK. To create an AWS Support case from Slack, enter @aws support create-case and follow the AWS Chatbot prompts to provide it with all the required parameters. For example, to provide a subject enter @aws subject SUBJECT STRING. For example, if you enter @aws lambda get-function with no further arguments,

the Chatbot requests the function name.

If you find you are unable to run commands, you may need to switch your user role or contact your administrator to find out what actions are permissible. You can specify parameters with either a double hyphen (–option) or a single hyphen (-option). This allows you to use a mobile device to run commands without running into issues with the mobile device automatically converting a double hyphen to a long dash. When you pass the logical ID of this resource to the intrinsic Ref function, Ref returns the ARN of the configuration created.

The following table includes some sample questions and related knowledge base responses. The solution presented in this post is available in the following GitHub repo. For data ingestion, it handles creating, storing, managing, and updating text embeddings of document data in the vector database automatically. It splits the documents into manageable chunks for efficient retrieval. The chunks are then converted to embeddings and written to a vector index, while allowing you to see the source documents when answering a question.

He works with organizations ranging from large enterprises to early-stage startups on problems related to machine learning. His role involves helping these organizations architect scalable, secure, and cost-effective workloads on AWS. Outside of work, he enjoys hiking on East Bay trails, road biking, and watching (and playing) cricket. When you submit a prompt, the Streamlit app triggers the Lambda function, which invokes the Knowledge Bases RetrieveAndGenerate API to search and generate responses. Therefore, a managed solution that handles these undifferentiated tasks could streamline and accelerate the process of implementing and managing RAG applications.

To perform actions in your chat channels, you must first have the appropriate permissions. For more information about AWS Chatbot’s permissions, see Understanding permissions. The AWS managed ‘AdministratorAccess’ policy is applied as a default if this is not set. Click on the newly created API Gateway Trigger and a card below should appear with a link. Copy the link (API Endpoint) and let’s test our lambda function works by clicking the link.

With this feature, customers can now monitor, operate, and troubleshoot AWS workloads from Slack channels without switching context between Slack and other AWS Management Tools. Customers can securely run AWS CLI commands to perform common DevOps tasks, such as scaling EC2 instances, running Systems Manager runbooks, and changing Lambda concurrency limits. Additionally, service administrators can use policy guardrails as well as account-level and user-role permissions to meet their security and compliance needs. Channel members must select an IAM role to run commands for the channel configuration with user roles-based AWS Chatbot configuration permissions configured in Task 1.

The most important alerts from CloudWatch Alarms can be displayed as rich messages with graphs. Teams can set which AWS services send notifications where so developers aren’t bombarded with unnecessary information. All the services are successfully created and I can verify them through the AWS console. I also tried to configure the Slack client via the AWS console, and it does work that way. I receive notifications on my Slack channel, which is a positive outcome. However, I need to automate all of these tasks programmatically through the Python script.

Take API endpoint and add to events in slack

AWS recommends that you grant only the permissions required to perform a task for other users. For more information, see Apply least-privilege permissions in the AWS Identity and Access Management User Guide. To receive a notification when a Lambda function fails to execute, create a CloudWatch alarm, select AWS Lambda namespace, Errors as metric name and select the Lambda function to watch. You can configure AWS Chatbot for multiple AWS accounts in the same chat channel. When you work

with AWS Chatbot for the first time in that channel, it will ask you which account you want to use. For any AWS Chatbot role that creates AWS Support cases, you need to attach the AWS Support command permissions policy to the role.

You can send your comments to the AWS Chatbot team by typing @aws feedback  in your Slack channel. Gain near real-time visibility into anomalous spend with AWS Cost Anomaly Detection alert notifications in Microsoft Teams and Slack by using AWS Chatbot. All this happens securely from within the Slack channels you already use every day.

AWS Chatbot will show the first 30 log entries starting from the beginning of the alarm evaluation period. Once the function invocation completes, AWS Chatbot will show the output of the Invoke call. AWS Chatbot will execute the automation runbook and provide notification updates in the channel as the automation runbook progresses. In Slack, this powerful integration is designed to streamline ChatOps, making it easier for teams to manage just about every operational activity, whether it’s monitoring, system management or CI/CD workflows. Manish Chugh is a Principal Solutions Architect at AWS based in San Francisco, CA.

Now that we have initial set up ready, let’s discuss a few use cases where you can use the bot with other AWS services. The Support Command Permissions policy applies only to the

AWS Support service. You

can define your own policy with greater restrictions, using this policy as a template. Follow the prompts from AWS Chatbot to fill out the support case with its needed parameters.

When

you complete the case information entry, AWS Chatbot asks for confirmation. You can enter a complete AWS CLI command with all the parameters, or you can enter the command

without parameters and AWS Chatbot prompts you for missing parameters. By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy. The ARNs of the SNS topics that deliver notifications to AWS Chatbot. The way I stop this from happening is by checking the username or user_id of the request. This way it partially stops an infinite amount of requests being made.

You can retrieve diagnostic information, configure AWS resources, and run workflows. To run a command, AWS Chatbot checks that all required parameters are entered. If any are missing, AWS Chatbot prompts you for the required information. AWS Chatbot

then confirms if the command is permissible by checking the command against what is allowed by the configured IAM roles and the channel guardrail policies. For more information, see Running AWS CLI commands from chat channels and Understanding permissions.

• Manish Chugh is a Principal Solutions Architect at AWS based in San Francisco, CA.
• Failing to delete resources such as the S3 bucket, OpenSearch Serverless collection, and knowledge base will incur charges.
• To perform actions in your chat channels, you must first have the appropriate permissions.
• His role involves helping these organizations architect scalable, secure, and cost-effective workloads on AWS.
• Make sure to delete any resources that you do not plan to use in the future to avoid incurring costs.

Then, run the @aws lambda list-functions

command, find the function name you need, and re-run the first command with the corrected option. Add more parameters for the initial command with @aws function-name

name. AWS Chatbot parses your commands and helps you complete the

correct syntax so it can run the complete AWS CLI command. This helps to ensure visibility and collaboration across the SecOps and DevOps teams and promotes the philosophy of DevSecOps.

Today, we are excited to announce the general availability (GA) of a feature that allows AWS Chatbot customers to manage AWS resources and remediate issues in AWS workloads from their Slack channels. AWS Chatbot customers can do this by running AWS CLI commands and AWS System Manager Automation Runbooks from Slack channels. Previously, AWS customers could only monitor AWS resources and retrieve diagnostic information using AWS Chatbot.

For existing roles, you will

need to attach the policy in the IAM console. I have a Python script that uses boto3 to interact with AWS services. I’m trying to integrate this script so that, once executed, it activates GuardDuty and creates a logic to forward high severity findings to a Slack channel. After you set up the Slack channel with required permissions, you integrate the ChatOps for AWS app with your channel by using the following steps. For detailed instructions about setting up AWS Chatbot and defining permissions, see Getting started with AWS Chatbot. For more information about setting boundaries on the permissions that can be allowed by the channel and user IAM roles, see Channel guardrails.

Not only does this speed up our development time, but it improves the overall development experience for the team.” — Kentaro Suzuki, Solution Architect – LIFULL Co., Ltd. If you would like to add AWS Chatbot access to an existing user or group, you can choose from allowed Chatbot actions in IAM. After you sign up for an AWS account, secure your AWS account root user, enable AWS IAM Identity Center, and create an administrative user so that you

don’t use the root user for everyday tasks. If you do not have an AWS account, complete the following steps to create one. You only pay for the underlying services that you use, in the same manner as if you were using them without AWS Chatbot. Make sure to delete any resources that you do not plan to use in the future to avoid incurring costs.

Managing these interdependent parts can introduce complexities in system development and deployment. The integration of retrieval and generation also requires additional engineering effort and computational resources. You can foun additiona information about ai customer service and artificial intelligence and NLP. Some open source libraries provide wrappers to reduce this overhead; however, changes to libraries can introduce errors and add additional overhead of versioning. Even with open source libraries, significant effort is required to write code, determine optimal chunk size, generate embeddings, and more.

Chances are this is due to the fact that AWS Chatbot is a global service that doesn’t accept any region. He is passionate about helping customers and partners in their cloud journeys. He is particularly passionate in Cloud Security, hybrid networking and migrations. To get the ID, open Slack, right click on the channel name in the left pane, then choose Copy Link.

You can set up CloudWatch Alarms in any region where you select a topic and use them to send notifications to AWS Chatbot. You can quickly access logs for Lambda invocations using the new AWS Chatbot action buttons on CloudWatch Alarm notifications in Slack. Collaborate, retrieve observability telemetry, and respond quickly to incidents, security findings, and other alerts for applications in your AWS environment.

The ARN of the IAM role that defines the permissions for AWS Chatbot. You will be presented with a page to name your bot and assign it to the workspace you want the app to belong to. Choose Show error logs to filter results to only log entries containing “error”, “exception”, or “fail”. When you have an operational event or want to check in on your application’s health, you can use AWS Chatbot to show details about CloudWatch Alarms in your account.

The task now is to return the “challenge” value in our lambda function. He started this blog in 2004 and has been writing posts just about non-stop ever since. When you finish providing required parameters, AWS Chatbot will ask you to confirm creation of the case.

In this post, I will show you AWS Chatbot configuration steps and share sample DevOps use cases to configure your AWS resources using AWS CLI commands from Slack channels. If you work on a DevOps team, you already know that monitoring systems and responding to events require major context switching. In the course of a day—or a single notification—teams might need to cycle among Slack, email, text messages, chat rooms, phone calls, video conversations and the AWS console.

In the top-right corner, select the Slack workspace to configure and choose Allow. Your Slack workspace installs the AWS Slack App, and the AWS account that you logged in with is now authorized to communicate with your Slack workspace. 81% of developers believe adopting new tools is critical to an organization’s success. As engineering and IT departments onboard new technology, they need automation to optimize these efforts. Type @aws describe cw alarms in us-west-1 to see all of the alarms in the US West Northern California region. AWS Chatbot will understand your input, map it to matching AWS CLI commands, and ask for a confirmation.

Then, AWS Chatbot will guide you with all of the required parameters. When prompted for the reserved-concurrent-executions parameter, type @aws 10 as the input value. The following example shows the sample interaction aws chatbot slack and the command output on the execution of the AWS CLI command. AWS Chatbot will also provide an option to refine the AWS CLI command results by prompting you to rerun the AWS CLI command with optional parameters.

Modern chatbots can serve as digital agents, providing a new avenue for delivering 24/7 customer service and support across many industries. Their popularity stems from the ability to respond to customer inquiries in real time and handle multiple queries simultaneously in different languages. Chatbots also offer valuable data-driven insights into customer behavior while scaling effortlessly as the user base grows; therefore, they present a cost-effective solution for engaging customers. Chatbots use the advanced natural language capabilities of large language models (LLMs) to respond to customer questions. However, chatbots that merely answer basic questions have limited utility.

Show CloudWatch Alarms in Slack

Today, we are announcing the public preview of a new feature that allows you to use AWS Chatbot to manage AWS resources and remediate issues in AWS workloads by running AWS CLI commands from Slack channels. Previously, you could only monitor AWS resources and retrieve diagnostic information using AWS Chatbot. Quickly establish integrations and security permissions between AWS resources and chat channels to receive preselected or event-driven notifications in real time. DevOps teams can receive real-time notifications that help them monitor their systems from within Slack. That means they can address situations before they become full-blown issues, whether it’s a budget deviation, a system overload or a security event.

To create an AWS Support case from Slack, type @aws support create-case and follow the AWS Chatbot prompts to provide it with all the required parameters. If you already use AWS Chatbot for sending notifications to Slack, you must create a new IAM role or update the existing one with additional permissions to be able to run commands. Today, we introduced a new feature that enables DevOps teams to run AWS commands and actions from Slack. You can retrieve diagnostic information, invoke AWS Lambda functions, and create support cases right from your Slack channels, so your team can collaborate and respond to events faster. AWS Chatbot supports commands using the already familiar AWS Command Line Interface syntax that you can use from Slack on desktop or mobile devices. DevOps teams widely use Slack channels as communication hubs where team members interact — both with one another and with the systems they operate.

In order to successfully test the configuration from the console, your role must also have permission to use the AWS KMS key. With AWS Chatbot, you can use chat rooms to monitor and respond to events in your AWS Cloud. You receive following notification on Slack channel when the specific Lambda fails to execute. To look up timeout and memory size parameters for a Lambda function.

AWS Chatbot is available free of charge and you only pay for the AWS resources you use, such as CloudWatch Log Insights that is used for querying logs. This guide will demonstrate just a few ways developers and IT professionals can improve their cloud-centric workflows by monitoring and managing their AWS environments from Slack. AWS Chatbot doesn’t currently support service endpoints and there are no adjustable quotas. For more information about AWS Chatbot AWS Region availability and quotas,

see AWS Chatbot endpoints and quotas. AWS Chatbot supports using all supported AWS services in the

Regions where they are available. Abhijit Barde is the Principal Product Manager for AWS Chatbot, where he focuses on making it easy for all AWS users to discover, monitor, and interact with AWS resources using conversational interfaces.

Synthesizing the data from all those different sources isn’t just hard work; it’s inefficient. Failing to delete resources such as the S3 bucket, OpenSearch Serverless collection, and knowledge base will incur charges. To change the default account in the channel, enter @aws set default-account

and select the account from the list. If you have existing chat channels using the AWS Chatbot, you can reconfigure them in a few steps

to support the AWS CLI.

To become trusted advisors, chatbots need to provide thoughtful, tailored responses. You can run commands using AWS CLI syntax directly in chat channels. AWS Chatbot enables you to retrieve diagnostic information, configure AWS resources, and run workflows.

For more information , see Running AWS CLI commands from Slack channels. In this post, I walked you through the steps to set up an AWS Chatbot configuration and securely run AWS CLI commands to configure AWS resources from Slack. Run AWS Command Line Interface commands from Microsoft Teams and Slack channels to remediate your security findings. To top it all off, thanks to an intuitive setup wizard, AWS Chatbot only takes a few minutes to configure in your workspace.

To choose or switch a user role at any time, type @aws switch-roles in the Slack channel. Select the configured AWS account link and navigate to the console to choose an IAM role. DevOps and engineering teams are increasingly moving their operations, system management, and CI/CD workflows to chat applications to streamline activities in chat channels and improve team collaboration. AWS customers have used the AWS Chatbot to monitor and retrieve diagnostic information. After receiving the information in the Slack channel, AWS customers had to switch to the AWS Console or AWS Command Line Interface (CLI) to remediate the incidents and configure their AWS environments. With this feature, customers can manage AWS resources directly from their Slack channels.