Embeddings for Large Language Models
This repository provides an implementation of embeddings using pre-trained embedding models. The goal is to enable Large Language Models (LLMs) to adapt to specific domains or projects without extensive fine-tuning.
- Generate embeddings from text data with OpenAI-compatible embeddings API and save as a file
- Extract data from embeddings based on query
- Incorporate embeddings into a chatbot for better contextual understanding
- Install Python 3.x (Tested with 3.9, 3.11)
- Clone the repository:
git clone https://github.com/NeuralWeights/RAG-LLM-Embeddings.git - Install dependencies:
pip install -r requirements.txt - Initialize embeddings:
python emb.py - Run the application:
python app.py
For a comprehensive tutorial on using this project, please refer to our Medium article: You Don't Need Fine-Tuning: Embeddings. Comprehensive Step-by-Step Guide
This project were made for demonstration purposes only and might receive no further updates, therefore we encourage you to fork it and contribute your own code.