Skip to content

About

Hybrid RAG-based Conversational Tourism Recommender System (C-TRS)

Resources

Stars

3 stars

Watchers

0 watching

Forks

Latest commit

 

History

3 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 
 
 

Repository files navigation

Hybrid RAG-based Conversational Tourism Recommender System (C-TRS)

Pipeline

Pipeline

Prerequisites

Dataset

Follow these steps to download the dataset used for SFI computation and vector database creation:

  • European City Data:
    1. Download european-city-data dataset
    2. Save under backend/european-city-data directory
  • Tripadvisor Data:
    1. Download european-city-tripadvisor-data dataset
    2. Save under backend/european-city-data/data-sources/tripadvisor directory

Configuration

The system has several configuration options that can be set via the config.ini file in the backend directory.

  • Note: For sections "retrieval" and "indexing" certain configurations are pre-configured in the backend and don't require manual adjustment.

Section [server]

Configure the IP address and port for hosting the FastAPI server.

Section [user_intents_classification], [extractor], [constraints_updater], [generation]

Configure the necessary parameters for tasks that use pre-trained LLMs.

Section [retrieval]

Configure the retriever, reranking, and context limit.

Section [logging]

Configure the file path used for saving the logs.

Environment Variables

Set the following environment variables in backend/.env. VertexAI authentication additionally requires a JSON file with the credentials under the path backend/.config/gcp_default_credentials.json.

Variable Description
DATA_REPO Path of the repository or file where the data is stored
HF_TOKEN Hugging Face API Token
OPENAI_API_KEY OpenAI API Key
VERTEXAI_PROJECTID Vertex AI Project ID
RAGAS_APP_TOKEN RAGAS API token for uploading/visualizing evaluation results

Pandoc (required only for vector DB creation)

Install Pandoc for Wikitext to Markdown conversion.

MacOS (Homebrew)

brew install pandoc

Linux (apt)

sudo apt-get install pandoc

Installation Steps

cd backend
python3.12 -m venv venv
source venv/bin/activate
pip install -r requirements.txt
python3 src/vectordb/create_db.py
python3 server.py

Credits

This project incorporates inspired/modified code from:

About

Hybrid RAG-based Conversational Tourism Recommender System (C-TRS)

Resources

Stars

3 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages