aws-samples / langchain-agents

MIT License
39 stars 6 forks source link

Lex issue : Create a next generation chat assistant with Amazon Bedrock, Amazon Connect, Amazon Lex, LangChain, and WhatsApp #13

Open redopal51 opened 2 weeks ago

redopal51 commented 2 weeks ago

https://aws.amazon.com/blogs/machine-learning/create-a-next-generation-chat-assistant-with-amazon-bedrock-amazon-connect-amazon-lex-langchain-and-whatsapp/

Solution deployment We’ve provided pre-built AWS CloudFormation templates that deploy everything you need in your AWS account.

Sign in to the AWS console if you aren’t already. Choose the following Launch Stack button to open the CloudFormation console and create a new stack. Enter the following parameters: StackName: Name your Stack, for example, WhatsAppAIStack LangchainAPIKey: The API key generated through LangChain Region Deploy button Template URL – use to upgrade existing stack to a new release AWS CDK stack to customize as needed N. Virginia (us-east-1) Launch Stack button YML GitHub Check the box to acknowledge that you are creating AWS Identity and Access Management (IAM) resources and choose Create Stack. Wait for the stack creation to be complete in approximately 10 minutes, which will create the following: LangChain agent Amazon Lex bot Amazon Bedrock Knowledge Base The vector store (Amazon OpenSearch Serverless) Lambdas (for data ingestion and providers) Data source (Amazon S3) DynamoDB Parameter Store for the LangChain API key IAM roles and permissions Upload files to the data source (Amazon S3) created for WhatsApp. As soon as you upload a file, the data source will synchronize automatically. To test the agent, on the Amazon Lex console, select the most recently created assistant. Choose English, choose Test, and send it a message.

Lex returns : Intent FallbackIntent is fulfilled

KBB99 commented 2 weeks ago

Can you confirm that you've enabled Claude Haiku in Bedrock Model Access? If you are still having issues then please open the LexBedrockMessageProcessor Lambda logs and let us know the error.