# Multi-modal RAG-based LLM for Information Retrieval

In this project, we have set up a RAG (Retrieval-Augmented Generation) system with the following features:

1. **Custom PDF Input**: Upload and process PDF files.
2. **Multi-modal Interface**: Supports both images and text.
3. **Feedback Recording and Reusage**: Collects user feedback and reuses it for improving retrieval.
4. **Usage of Agents for Context Retrieval**: Uses agents to enhance context retrieval capabilities.

## Running the Project

### Using Docker

1. Clone the project repository.
2. To run the Docker image, execute the `docker_rag.sh` script:

   ```bash
   /bin/zsh ./docker_rag.sh