https://github.com/pedroh183/turbo-journey
A learning project implementing a RAG chatbot using LangChain, Google Gemini, and FAISS for efficient similarity search.
https://github.com/pedroh183/turbo-journey
Last synced: 4 months ago
JSON representation
A learning project implementing a RAG chatbot using LangChain, Google Gemini, and FAISS for efficient similarity search.
- Host: GitHub
- URL: https://github.com/pedroh183/turbo-journey
- Owner: PedroH183
- Created: 2025-04-21T23:34:49.000Z (6 months ago)
- Default Branch: main
- Last Pushed: 2025-04-22T00:13:55.000Z (6 months ago)
- Last Synced: 2025-05-09T01:49:42.088Z (5 months ago)
- Language: Python
- Homepage:
- Size: 47.9 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# RAG Chat with LangChain and Google Gemini
A learning project implementing a Retrieval-Augmented Generation (RAG) chatbot using LangChain, Google Gemini, and FAISS for efficient similarity search.
## Requirements
- Python >= 3.13
- Dependencies:
- langchain-google-genai
- faiss-cpu
- sentence-transformers
- python-dotenv
## Installation
```bash
git clone git@github.com:PedroH183/turbo-journey.git
cd turbo-journey
pip install -r requirements.txt
```
## How It Works
1. **Text Processing**: Documents are loaded and split into manageable chunks
2. **Embedding Generation**: Using Sentence Transformers (all-MiniLM-L6-v2)
3. **Vector Storage**: FAISS indexes embeddings for efficient similarity search
4. **Query Processing**: User questions are embedded and matched with relevant context
5. **Response Generation**: Google Gemini generates responses based on retrieved context
## Environment Variables
Create a `.env` file in the root directory with the following variables:
```env
LANGSMITH_ENDPOINT=""
LANGSMITH_API_KEY=""
LANGSMITH_PROJECT=""
GOOGLE_API_KEY=""
```
## Next features
1. Replace FAISS to Pinecone for index database
2. Add support for PDF
3. Create an interface using streamlit