This is an API that uses LangChain, Bedrock, and Postgres pgvector to provide Retrieval Augmented Generation (RAG) functionality. This project has two main endpoints: one for uploading files to the RAG system and another for interacting with the Claude3 model through AWS Bedrock.
- Node.js (version 20 or higher)
- npm (version 10 or higher)
- Docker (optional)
git clone https://github.com/your-username/express-bedrock-rag.git
cd express-bedrock-rag
Copy the example file and make sure to modify the .env file with your specific configurations afterward.
cp .env.example .env
npm install
npm start
You can run the project using Docker Compose. Ensure Docker and Docker Compose are installed on your machine.
docker-compose up --build
Alternatively, you can use Docker directly with the included Dockerfile.
docker build -t express-bedrock-rag .
docker run -p 3000:3000 express-bedrock-rag
npm start
: Starts the server.npm run dev
: Starts a server with nodemon.npm test
: Runs the tests.
Contributions are welcome! Feel free to open issues and pull requests.
This project is licensed under the MIT License.