Bedrock Chat

Abstract

1. Introduction

A multilingual generative AI platform powered by Amazon Bedrock. Supports chat, custom bots with knowledge (RAG), bot sharing via a bot store, and task automation using agents.

Add your own instruction and knowledge (a.k.a RAG. The bot can be shared among application users via bot store market place. The customized bot also can be published as stand-alone API (See the detail).

API Management, Mark bots as essential, Analyze usage for bots. detail

2. Objective

AWS-native chatbot using Bedrock

This project demonstrates how TypeScript, FastAPI, Python can be applied to a real-world AI & Machine Learning problem.

4. Technology Stack

5. System Requirements

General requirements for this technology stack — check the README for exact versions.

• Node.js (LTS) and npm / yarn / pnpm
• VS Code or any code editor
• Python 3.8 or later
• pip / virtualenv for dependencies
• VS Code, PyCharm or Jupyter Notebook
• Git (to clone the repository)

6. Installation & Setup

git clone https://github.com/aws-samples/bedrock-chat.git
cd bedrock-chat

1. In the us-east-1 region, open Bedrock Model access > Manage model access > Check all of models you wish to use and then Save changes.
2. Please have UNIX, Docker and a Node.js runtime environment.
3. Clone this repository
4. Install npm packages
5. If necessary, edit the following entries in cdk.json.
6. bedrockRegion: Region where Bedrock is available. NOTE: Bedrock does NOT support all regions for now.
7. allowedIpV4AddressRanges, allowedIpV6AddressRanges: Allowed IP Address range.
8. enableLambdaSnapStart: Defaults to true. Set to false if deploying to a region that doesn't support Lambda SnapStart for Python functions.

aws dynamodb execute-statement --statement "UPDATE \"$BotTableNameV3\" SET BedrockKnowledgeBase.type='shared' SET SyncStatus='QUEUED' WHERE PK='$UserID' AND SK='BOT#$BotID'"
# Execute for all target bots

aws stepfunctions start-execution --state-machine-arn $EmbeddingStateMachineArn

git clone https://github.com/aws-samples/bedrock-chat

cd bedrock-chat
cd cdk
npm ci

npx cdk bootstrap

Full setup instructions are in the project README.

7. Future Enhancements

Suggested extensions you can add to make this your own project.

• Deploy the model as a web app with Streamlit, Flask or FastAPI
• Compare against an additional model and report the metric difference
• Add explainability (SHAP / Grad-CAM)

8. Viva / Review Questions

Common questions examiners ask for projects in this domain.

1. What dataset does the project use and how was it pre-processed?
2. Which algorithm / model architecture is used and why was it chosen over alternatives?
3. How are training and testing data split, and how is overfitting avoided?
4. Which evaluation metrics (accuracy, precision, recall, F1) are reported and what do they mean here?
5. How would you deploy this model for real users?

9. Source Code & License

This project is developed by aws-samples and published on GitHub under the MIT No Attribution. Please follow the license terms and credit the original author when you use or modify this code.