Tutorial: Using AWS Chatbot to run an AWS Lambda function remotely AWS Chatbot

If you see a spike in traffic to a specific URL, you should investigate whether your application is working properly. The sample of requests contains up to 100 requests that matched the criteria for a rule in the web ACL and another 100 requests for requests that didn’t match rules and thus had the default action for the web ACL applied. The requests in the sample come from the protected resources that have received requests for your content in the previous three hours. Using this integration, you can navigate back and forth between the dashboard and CloudWatch; for example, you can get a more granular metric overview by viewing the dashboard in CloudWatch. You can also add existing CloudWatch widgets and metrics to the traffic overview dashboard, bringing your tried-and-tested visibility structure into the dashboard.

AWS Chatbot gives users access to an intelligent interactive agent that they can use to interact with and monitor their AWS resources, wherever they are in their favourite chat rooms. This means that developers don’t need to spend as much time jumping between apps throughout their workday. In this post, I walked through the process of building an AWS Well-Architected chatbot using the OpenAI GPT model and Streamlit. We started by collecting data from the AWS Well-Architected Framework using Python, and then used the OpenAI API to generate responses to user input.

aws-samples/aws-genai-llm-chatbot

The integration of retrieval and generation also requires additional engineering effort and computational resources. 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. In this post, you learned how to use the dashboard to help secure your web application. Additionally, you learned how to observe traffic from bots and follow up with actions related to them according to the needs of your application. I developed the chat interface using my go-to tool for building web applications with Python, Streamlit.

Banjo is a Senior Developer Advocate at AWS, where he helps builders get excited about using AWS. Banjo is passionate about operationalizing data and has started a podcast, a meetup, and open-source projects around utilizing data. When not building the next big thing, Banjo likes to relax by playing video games, especially JRPGs, and exploring events happening around him. If you’re interested in building your own ChatGPT powered applications, I hope this post has provided you with some helpful tips and guidance. Q draws on its connections, integrations and data, including business-specific data, to come up with responses along with citations. If you have an existing AWS administrator user, you can access the AWS Chatbot console with no additional permissions.

He loves coffee and any discussion of any topics from microservices to AI / ML. With AWS WAF Bot Control, you can monitor, block, or rate limit bots such as scrapers, scanners, crawlers, status monitors, and search engines. If you use the targeted inspection level of the rule group, you can also challenge bots that don’t self-identify, making it harder and more expensive for malicious bots to operate against your website. The following figure shows the actions taken by rules in a web ACL and which rule matched the most.

AWS Chatbot: Bring AWS into your Slack channel

If you’re interested in how this project started, I encourage you to check out my previous post. Quickly establish integrations and security permissions between AWS resources and chat channels to receive preselected or event-driven notifications in aws chatbot real time. Notifications or alerts about a deviation from expected traffic patterns provide you a signal to explore the event. During your exploration, you can use the dashboard to understand the broader context and not just the event in isolation.

The solution presented in this post is available in the following GitHub repo. Afterwards, the user prompt is the query, such as “How can I design resilient workloads?”. Crafting these prompts is an art that many are still figuring out, but a rule of thumb is the more detailed the prompt, the better the desired outcome. This OpenAI Notebook provides a full end-to-end example of creating text embeddings. Small distances suggest high relatedness and large distances suggest low relatedness. Next, I created text embeddings for each of the pages using

OpenAI’s embeddings API.

For example, within a Bot Control rule group, it’s possible for a request without a valid token to exit the rule group evaluation and continue to be evaluated by the web ACL. To block requests that are missing their token or for which the token is rejected, you can add a rule to run immediately after the managed rule group to capture and block requests that the rule group doesn’t handle for you. Using the Token status pane, illustrated in Figure 5, you can also monitor the volume of requests that acquire tokens and decide if you want to rate limit or block such requests. The following figure shows a disproportionately larger number of matches to a rule indicating that a particular vector is used against a protected web application. When something does require your attention, Slack plus AWS Chatbot helps you move work forward more efficiently.

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. To become trusted advisors, chatbots need to provide thoughtful, tailored responses.

In a Slack channel, you can receive a notification, retrieve diagnostic information, initiate workflows by invoking AWS Lambda functions, create AWS support cases or issue a command. Here is an example of why new models such as GPT-3 are better in such scenarios than older ones like FLAN-XXL. I asked a question about toxicity based on the following paragraph from the LLama paper. Manish Chugh is a Principal Solutions Architect at AWS based in San Francisco, CA.

Analyze the data regularly to help detect potential threats and make informed decisions about optimizing. Check whether unusual spikes in blocked requests correspond to spikes in traffic from a particular IP address, country, or user agent. The following figure shows a typical layout for the traffic overview dashboard. It categorizes inspected requests with a breakdown of each of the categories that display actionable insights, such as attack types, client device types, and countries. Using this information and comparing it with your expected traffic profile, you can decide whether to investigate further or block the traffic right away.

Therefore, a managed solution that handles these undifferentiated tasks could streamline and accelerate the process of implementing and managing RAG applications. 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’re familiar with the AWS Well-Architected Framework, you’ll know that it offers a set of best practices designed to help you achieve secure, high-performing, resilient, and efficient infrastructure for your applications.

In addition to visibility into your web traffic, you can use the new dashboard to analyze patterns that could indicate potential threats or issues. By reviewing the dashboard’s graphs and metrics, you can spot unusual spikes or drops in traffic that deserve further investigation. If you have less than administrative permissions, ensure you have the aforementioned permissions to create a configuration.

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. In this guide, I’ve taken you through the process of building an AWS Well-Architected chatbot leveraging LangChain, the OpenAI GPT model, and Streamlit.

Using a chatbot in a call center application, your customers can perform tasks such as changing a password, requesting a balance on an account, or scheduling an appointment, without the need to speak to an agent. Chatbots maintain context and manage the dialogue, dynamically adjusting responses based on the conversation. To top it all off, thanks to an intuitive setup wizard, AWS Chatbot only takes a few minutes to configure in your workspace.

Text embeddings are vectors (lists) of floating-point numbers used to measure the relatedness of text strings. They are commonly used for various tasks such as search, clustering, recommendations, anomaly detection, diversity measurement, and classification. Once the embeddings were generated, I used the vector search library Faiss to create an index, enabling rapid text searching for each user query. Now, in this follow-up article, I’ll guide you through the process of building an enhanced version of the chatbot using the open-source library, LangChain. Selipsky underlined several times throughout the keynote that the answers Q gives — and the actions it takes — are fully controllable and filterable. Q will only return info a user’s authorized to see, and admins can restrict sensitive topics, having Q filter out inappropriate questions and answers where necessary.

But with a vast amount of information available, navigating the framework can be a daunting task. This code creates a simple interface with a text input for the user to enter their query, and a “Send” button to submit it. When the user clicks the “Send” button, the get_answer_from_chatgpt() function is called to get a response from the ChatGPT and the referenced documents. These data cleaning steps helped to refine the raw data and enhance the model’s overall performance, ultimately leading to more accurate and useful insights. Those bullet points were no doubt aimed at companies wary of adopting generative AI for liability and security reasons. Over a dozen companies have issued bans or restrictions on ChatGPT, expressing concerns about how data entered into the chatbot might be used and the risk of data leaks.

AWS Systems Manager Incident Manager

You can access default metrics such as the total number of requests, blocked requests, and common attacks blocked, or you can customize your dashboard with the metrics and visualizations that are most important to you. Cohesity has announced a Gen AI chatbot called Gaia that can search through a customer’s backups to find answers to conversational questions. A winning customer experience can be a significant differentiator for a business. Chatbots can be deployed into the channels that your customers and prospects are already engaged, like Facebook Messenger, so you can reach them in familiar environments to respond to their requests faster and meet their expectations.

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. Synthesizing the data from all those different sources isn’t just hard work; it’s inefficient. This is why I decided to develop a chatbot to answer questions related to the framework, offering developers quick, accurate responses complete with supporting document links.

Mistral AI, an AI company based in France, is on a mission to elevate publicly available models to state-of-the-art performance. They specialize in creating fast and secure large language models (LLMs) that can be used for various tasks, from chatbots to code generation. The AWS WAF traffic overview dashboard provides enhanced overall visibility into web traffic reaching resources that are protected with AWS WAF. In contrast, the CloudFront security dashboard brings AWS WAF visibility and controls directly to your CloudFront distribution.

If you would like to add AWS Chatbot access to an existing user or group, you can choose from allowed Chatbot actions in IAM. If you do not have an AWS account, complete the following steps to create one. 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.

You can easily combine multiple alarms together into alarm hierarchies that only trigger once,

when multiple alarms fire at the same time. When the dataset sync is complete, the status of the data source will change to the Ready state. Note that, if you add any additional documents in the S3 data folder, you need to re-sync the knowledge base.

• It categorizes inspected requests with a breakdown of each of the categories that display actionable insights, such as attack types, client device types, and countries.
• In this guide, I’ve taken you through the process of building an AWS Well-Architected chatbot leveraging LangChain, the OpenAI GPT model, and Streamlit.
• When the user clicks the “Send” button, the get_answer_from_chatgpt() function is called to get a response from the ChatGPT and the referenced documents.
• If you use the targeted inspection level of the rule group, you can also challenge bots that don’t self-identify, making it harder and more expensive for malicious bots to operate against your website.
• Banjo is passionate about operationalizing data and has started a podcast, a meetup, and open-source projects around utilizing data.

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. Failing to delete resources such as the S3 bucket, OpenSearch Serverless collection, and knowledge base will incur charges. The following table includes some sample questions and related knowledge base responses.

Tutorial: Using AWS Chatbot to run

The dataframe contains the text data, along with links to the corresponding ground truth information indicating how the chatbot responded. This allows for easy validation and verification of the chatbot’s accuracy and can aid in identifying areas for improvement. To use the API, you have to create a prompt that leverages a “system” persona, and then take input from the user. With text embeddings we can now do a Search of all the text based on an input query. We get a list of the documents that has text which is relevant to the query. Q can also troubleshoot things like network connectivity issues, analyzing network configurations to provide remediation steps.

You can also run AWS CLI commands directly in chat channels using AWS Chatbot. You can retrieve diagnostic information, configure AWS resources, and run workflows. To run a command, AWS Chatbot checks that all required parameters are entered.

This makes it simpler to detect a trend in anomalies that could signify a security event or misconfigured rules. For example, if you normally get 2,000 requests per minute from a particular country, but suddenly see 10,000 requests per minute from it, you should investigate. The spike in requests alone might not be a clear indication of a threat, but if you see an additional indicator, such as an unexpected device type, this could be a strong reason for you to take follow-up action. Although the RAG architecture has many advantages, it involves multiple components, including a database, retrieval mechanism, prompt, and generative model. Managing these interdependent parts can introduce complexities in system development and deployment.

AWS Systems Manager Runbooks

You can foun additiona information about ai customer service and artificial intelligence and NLP. Onstage, Selipsky gave the example of an app that relies on high-performance video encoding and transcoding. Asked about the best EC2 instance for the app in question, Q would give a list taking into account performance and cost considerations, Selipsky said. 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. Read the FAQs to learn more about AWS Chatbot notifications and integrations. Run AWS Command Line Interface commands from Microsoft Teams and Slack channels to remediate your security findings. AWS WAF creates, updates, and encrypts tokens for clients that successfully respond to silent challenges and CAPTCHA puzzles.

Streamlit allows builders to easily create interactive web apps that provide instant feedback on user responses. From there, you can drill down into the web ACL metrics to see traffic trends and metrics for specific rules and rule groups. The dashboard displays metrics such as allowed requests, blocked requests, and more.

Parent composite alarms can have multiple triggering children however, the AWS Chatbot notification will only display a maximum of 3 of the total triggering metric children’s alarm states. For example,

if you have 10 total children alarms and 5 are currently triggered, the AWS Chatbot notification will display 3 of those 5. Composite alarms allow you to combine multiple alarms to reduce alarm noise and focus on

critical operational issues.

Gain near real-time visibility into anomalous spend with AWS Cost Anomaly Detection alert notifications in Microsoft Teams and Slack by using AWS Chatbot. Collaborate, retrieve observability telemetry, and respond quickly to incidents, security findings, and other alerts for applications in your AWS environment. Donnie Prakoso is a software engineer, self-proclaimed barista, and Principal Developer Advocate at AWS. With more than 17 years of experience in the technology industry, from telecommunications, banking to startups. He is now focusing on helping the developers to understand varieties of technology to transform their ideas into execution.

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. The RetrieveAndGenerate API manages the short-term memory and uses the chat history as long as the same sessionId is passed as an input in the successive calls.

When you submit a prompt, the Streamlit app triggers the Lambda function, which invokes the Knowledge Bases RetrieveAndGenerate API to search and generate responses. This enables you to focus on your core business applications and removes the undifferentiated heavy lifting. For data ingestion, it handles creating, storing, managing, and updating text embeddings of document data in the vector database automatically. 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. Once I compiled the list, I used the LangChain Selenium Document Loader to extract all the text from each page, dividing the text into chunks of 1000 characters. Breaking the text into 1000-character chunks simplifies handling large volumes of data and ensures that the text is in useful digestible segments for the model to process.

CloudWatch logging has a separate pricing model and if you have full logging enabled you will incur CloudWatch charges. You can customize the dashboards if you want to tailor the displayed data to the needs of your environment. Chatbots can combine the steps of complex processes to streamline and automate common and repetitive tasks through a few simple voice or text requests, reducing execution time and improving business efficiencies. Next, I generated text embeddings for each of the pages using the OpenAI’s embeddings API.

With minimal effort, developers will be able to receive notifications and execute commands, without losing track of critical team conversations. What’s more, AWS fully manages the entire integration, with a service that only takes a few minutes to set up. The chat interface was developed using Streamlit, a versatile tool for building interactive Python web applications. This code creates a simple interface with a text input for user queries and a “Submit” button to submit the query. When the “Submit” button is clicked, the query, along with the chat history, is sent to the LLM chain, which returns a response along with the referenced documents.

If you want the detailed visibility and analysis of patterns that could indicate potential threats or issues, then the AWS WAF traffic overview dashboard is the best fit. For many network security operators, protecting application uptime can be a time-consuming challenge of baselining network traffic, investigating suspicious senders, and determining how best to mitigate risks. Simplifying this process and understanding network security posture at all times is the goal of most IT organizations that are trying to scale their applications without also needing to scale their security operations center staff. To help you with this challenge, AWS WAF introduced traffic overview dashboards so that you can make informed decisions about your security posture when your application is protected by AWS WAF. If you work on a DevOps team, you already know that monitoring systems and responding to events require major context switching.

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. As a Senior Solutions Architect at AWS, Dmitriy supports AWS customers to use emerging technologies to generate business value. He’s a technology enthusiast who loves finding innovative solutions to complex challenges. He enjoys sharing his learnings on architecture and best practices in blog posts and whitepapers and at events.