Practical examples of using Amazon Bedrock with real-world applications and use cases.
This repository demonstrates practical applications of Amazon Bedrock, focusing on real-world scenarios and integrations. It showcases how to combine generative AI with external data sources, vector databases, and APIs to create meaningful applications.
Each example is documented with detailed explanations and demonstrates best practices for building production-ready AI applications.
Before running these examples, you'll need:
- An AWS account with access to Amazon Bedrock
- AWS credentials configured (via AWS CLI or environment variables)
- Python 3.8 or later
- Basic understanding of generative AI concepts
The repository is organized by increasing complexity:
- Simple LLM invocation 01_simple_prompt.py
- Context-aware responses 02_system_prompt.py
- Maintaining conversation history 03_conversation_history.py
- Real-time data augmentation 01_basic_rag.py
- Vector store integration 02_rag_with_vector_store.py
- Connecting the AI to external functions 01_tool_use.py
- Clone this repository
- Install the required dependencies:
cd python
pip install -r requirements.txt- Navigate to your preferred language directory
- Configure your AWS credentials
- Run the examples
This repository is for educational purposes only. The code samples are designed to be:
- Easy to understand
- Ready to run
- Simple to modify
- Adaptable for your own projects
As an educational repository, it does not accept Pull Requests or Issues. For the latest information on Amazon Bedrock, please refer to the official documentation.
This project is licensed under the MIT License - see the LICENSE file for details.