Tip
πAPI publication / Admin dashboard feature released. See release for the detail.
Warning
The current version (v0.4.x
) has no compatibility with the previous version (~v0.3.0
) due to changes in the DynamoDB table schema. Please note that the UPDATE (i.e. cdk deploy
) FROM PREVIOUS VERSION TO v0.4.x
WILL DESTROY ALL OF THE EXISTING CONVERSATIONS.
This repository is a sample chatbot using the Anthropic company's LLM Claude, one of the foundational models provided by Amazon Bedrock for generative AI.
Not only text but also images are available with Anthropic's Claude 3. Currently we support Haiku
and Sonnet
.
Add your own instruction and give external knowledge as URL or files (a.k.a RAG). The bot can be shared among application users. The customized bot also can be published as stand-alone API (See the detail).
Analyze usage for each user / bot on administrator dashboard. detail
- English π¬
- ζ₯ζ¬θͺ π¬ (γγγ₯γ‘γ³γγ―γγ‘γ)
- νκ΅μ΄ π¬
- δΈζ π¬
- FranΓ§ais π¬
- Deutsch π¬
- In the us-east-1 region, open Bedrock Model access >
Manage model access
> CheckAnthropic / Claude 3 Haiku
,Anthropic / Claude 3 Sonnet
andCohere / Embed Multilingual
thenSave changes
.
- Open CloudShell at the region where you want to deploy
- Run deployment via following commands
git clone https://github.com/aws-samples/bedrock-claude-chat.git
cd bedrock-claude-chat
chmod +x bin.sh
./bin.sh
- After about 30 minutes, you will get the following output, which you can access from your browser
Frontend URL: https://xxxxxxxxx.cloudfront.net
The sign-up screen will appear as shown above, where you can register your email and log in.
Important
This deployment method allows anyone with the URL to sign up. For production use, we strongly recommend adding IP address restrictions or disabling self-signup to mitigate security risks. To set up, Deploy using CDK for IP address restrictions or Disable self sign up.
It's an architecture built on AWS managed services, eliminating the need for infrastructure management. Utilizing Amazon Bedrock, there's no need to communicate with APIs outside of AWS. This enables deploying scalable, reliable, and secure applications.
- Amazon DynamoDB: NoSQL database for conversation history storage
- Amazon API Gateway + AWS Lambda: Backend API endpoint (AWS Lambda Web Adapter, FastAPI)
- Amazon CloudFront + S3: Frontend application delivery (React, Tailwind CSS)
- AWS WAF: IP address restriction
- Amazon Cognito: User authentication
- Amazon Bedrock: Managed service to utilize foundational models via APIs. Claude is used for chat response and Cohere for vector embedding
- Amazon EventBridge Pipes: Receiving event from DynamoDB stream and launching ECS task to embed external knowledge
- Amazon Elastic Container Service: Run crawling, parsing and embedding tasks. Cohere Multilingual is the model used for embedding.
- Amazon Aurora PostgreSQL: Scalable vector store with pgvector plugin
- Amazon Athena: Query service to analyze S3 bucket
Basic chat features
- Authentication (Sign-up, Sign-in)
- Creation, storage, and deletion of conversations
- Copying of chatbot replies
- Automatic subject suggestion for conversations
- Syntax highlighting for code
- Rendering of Markdown
- Streaming Response
- IP address restriction
- Edit message & re-send
- I18n
- Model switch
Customized bot features
- Customized bot creation
- Customized bot sharing
- Publish as stand-alone API
RAG features
- Web (html)
- Text data (txt, csv, markdown and etc)
- Microsoft office files (pptx, docx, xlsx)
- Youtube transcript
- Import from S3 bucket
- Import external existing Kendra / OpenSearch / KnowledgeBase
Admin features
- Tracking usage fees per bot
- List all published bot
Super-easy Deployment uses AWS CodeBuild to perform deployment by CDK internally. This section describes the procedure for deploying directly with CDK.
- Please have UNIX, Docker and a Node.js runtime environment. If not, you can also use Cloud9
Important
If there is insufficient storage space in the local environment during deployment, CDK bootstrapping may result in an error. If you are running in Cloud9 etc., we recommend expanding the volume size of the instance before deploying.
- Clone this repository
git clone https://github.com/aws-samples/bedrock-claude-chat
- Install npm packages
cd bedrock-claude-chat
cd cdk
npm ci
- Install AWS CDK
npm i -g aws-cdk
- Before deploying the CDK, you will need to work with Bootstrap once for the region you are deploying to. In this example, we will deploy to the us-east-1 region. Please replace your account id into
<account id>
.
cdk bootstrap aws://<account id>/us-east-1
-
If necessary, edit the following entries in cdk.json if necessary.
bedrockRegion
: Region where Bedrock is available. NOTE: Bedrock does NOT support all regions for now.allowedIpV4AddressRanges
,allowedIpV6AddressRanges
: Allowed IP Address range.
-
Deploy this sample project
cdk deploy --require-approval never --all
- You will get output similar to the following. The URL of the web app will be output in
BedrockChatStack.FrontendURL
, so please access it from your browser.
β
BedrockChatStack
β¨ Deployment time: 78.57s
Outputs:
BedrockChatStack.AuthUserPoolClientIdXXXXX = xxxxxxx
BedrockChatStack.AuthUserPoolIdXXXXXX = ap-northeast-1_XXXX
BedrockChatStack.BackendApiBackendApiUrlXXXXX = https://xxxxx.execute-api.ap-northeast-1.amazonaws.com
BedrockChatStack.FrontendURL = https://xxxxx.cloudfront.net
Edit config.py and run cdk deploy
.
# See: https://docs.anthropic.com/claude/reference/complete_post
GENERATION_CONFIG = {
"max_tokens": 2000,
"top_k": 250,
"top_p": 0.999,
"temperature": 0.6,
"stop_sequences": ["Human: ", "Assistant: "],
}
EMBEDDING_CONFIG = {
"model_id": "cohere.embed-multilingual-v3",
"chunk_size": 1000,
"chunk_overlap": 200,
}
If using cli and CDK, please cdk destroy
. If not, access CloudFormation and then delete BedrockChatStack
and FrontendWafStack
manually. Please note that FrontendWafStack
is in us-east-1
region.
By setting cdk.json in the following CRON format, you can stop and restart Aurora Serverless resources created by the VectorStore construct. Applying this setting can reduce operating costs. By default, Aurora Serverless is always running. *It will be executed in UTC time
...
"rdbSchedules": {
"stop": {
"minute": "50",
"hour": "10",
"day": "*",
"month": "*",
"year": "*"
},
"start": {
"minute": "40",
"hour": "2",
"day": "*",
"month": "*",
"year": "*"
}
}
This asset automatically detects the language using i18next-browser-languageDetector. You can switch languages from the application menu. Alternatively, you can use Query String to set the language as shown below.
https://example.com?lng=ja
This sample has self sign up enabled by default. To disable self sign up, open auth.ts and switch selfSignUpEnabled
as false
, then re-deploy.
const userPool = new UserPool(this, "UserPool", {
passwordPolicy: {
requireUppercase: true,
requireSymbols: true,
requireDigits: true,
minLength: 8,
},
// true -> false
selfSignUpEnabled: false,
signInAliases: {
username: false,
email: true,
},
});
This sample supports external identity provider. Currently we support Google and custom OIDC provider.
Open cdk.json
and set dbEncryption
to true
. Default value is false
.
Warning
If already deployed with false
, setting to true
and re-deployment will replace existing cluster, which deletes all of vector items.
See LOCAL DEVELOPMENT.
Thank you for considering contributing to this repository! We welcome bug fixes, language translations (i18n), feature enhancements, and other improvements.
For feature enhancements and other improvements, before creating a Pull Request, we would greatly appreciate it if you could create a Feature Request Issue to discuss the implementation approach and details. For bug fixes and language translations (i18n), proceed with creating a Pull Request directly.
Please also take a look at the following guidelines before contributing:
See here.
This library is licensed under the MIT-0 License. See the LICENSE file.