https://github.com/mu7annad0/2049search
RAG search engine combining Tavily API results with the Gemma2:9B model for accurate, source-backed answers.
https://github.com/mu7annad0/2049search
gemma-2b llms search-engine tavily
Last synced: 7 months ago
JSON representation
RAG search engine combining Tavily API results with the Gemma2:9B model for accurate, source-backed answers.
- Host: GitHub
- URL: https://github.com/mu7annad0/2049search
- Owner: Mu7annad0
- Created: 2024-12-09T19:04:35.000Z (10 months ago)
- Default Branch: main
- Last Pushed: 2025-01-12T23:10:44.000Z (9 months ago)
- Last Synced: 2025-01-13T00:20:29.849Z (9 months ago)
- Topics: gemma-2b, llms, search-engine, tavily
- Language: Python
- Homepage:
- Size: 20.5 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# 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
https://github.com/user-attachments/assets/356a6044-d84f-41ca-9c9d-5bdddaf7f71d
## Installation
1. Clone the Repository
```sh
git clone git@github.com:Mu7annad0/2049Search.git
cd 2049Search
```
2. Install the dependencies
```sh
pip install -r requirements.txt
```
3. Install Ollama
* https://ollama.com/
4. Download the model
```sh
ollama pull gemma2
```
5. Run the model
```sh
ollama serve
```
6. Sign-up in Tavily and get the API
* https://tavily.com/
7. Add your tavilyapi
```sh
export TAVILY_API_KEY=
```
8. Run the application
```sh
streamlit run src/app.py
```