Skip to content

With this WhatsApp app, you can chat in any language with a Large language models (LLM) on Amazon Bedrock. Send voice notes and receive transcriptions. By making a minor change in the code, you can also send the transcription to the model.

License

Notifications You must be signed in to change notification settings

build-on-aws/building-gen-ai-whatsapp-assistant-with-amazon-bedrock-and-python

AWS Generative AI WhatsApp Assistant Samples

This repository provides sample implementations using AWS AWS Cloud Development Kit (CDK) Python for building WhatsApp AI assistants using AWS services and Amazon Bedrock.

Here is a list of available samples:

Use Case Description Key Features AWS Services Languages
AWS Generative AI WhatsApp Assistant Samples Build an AI assistant with multi-language support and voice processing
  • Multi-language conversations with Claude 3.5
  • Voice note transcription and processing
  • Text message handling with Langchain
  • Implements conversation memory and session handling through Amazon DynamoDB, allowing for context retention and history tracking across interactions
Multilanguage
Processing WhatsApp Multimedia with Amazon Bedrock Agents: Images, Video, and Documents Create an advanced assistant for multimedia content analysis
  • A WhatsApp assistant that processes multimedia content (images, video, audio, documents) using Amazon Nova Model and Amazon Bedrock Agents to maintains conversation context.
  • Document information extraction
  • Audio transcription with context
  • Includes conversation memory management, session handling, and the ability to process different media types while maintaining context throughout interaction.
  • Amazon Transcribe
Multilanguage

🇻🇪🇨🇱 ¡Gracias!

Best,

Eli


Security

See CONTRIBUTING for more information.

License

This library is licensed under the MIT-0 License. See the LICENSE file.

About

With this WhatsApp app, you can chat in any language with a Large language models (LLM) on Amazon Bedrock. Send voice notes and receive transcriptions. By making a minor change in the code, you can also send the transcription to the model.

Topics

Resources

License

Code of conduct

Security policy

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published