Orbit.2049 Search Engine

Orbit.2049 is a simple Retrieval-Augmented Generation (RAG) search engine designed to provide detailed, accurate, and contextually enriched answers. It combines search results retrieved using the Tavily API with local processing powered by the Gemma2:9B language model, enhanced by vector embeddings and ChromaDB, to deliver comprehensive insights with reliable source citations.

Preview

WhatsApp.Video.Dec.13.2024.mp4

Installation

1. Clone the Repository

   git clone [email protected]:Mu7annad0/2049Search.git
   cd 2049Search

2. Install the dependencies

   pip install -r requirements.txt

3. Install Ollama

   • https://ollama.com/

4. Download the model

   ollama pull gemma2

5. Run the model

   ollama serve

6. Sign-up in Tavily and get the API

   • https://tavily.com/

7. Add your tavilyapi

    export TAVILY_API_KEY=<your tavily api>

8. Run the application

   streamlit run src/app.py