This project focuses on fine-tuning large language models (LLMs) to improve embedding quality and text generation capabilities. The goal is to create models that better understand and generate text in these languages, which are underrepresented in current NLP research. This repository tries to build enterprise-grade Retrieval-Augmented Generation (RAG) system. The goal is to enhance the interaction between businesses and Language Models (LLMs) by automating and optimizing prompt engineering processes. Through services like Automatic Prompt Generation, Evaluation Data Generation, and Prompt Testing and Ranking, we aim to provide robust, efficient, and effective AI-driven solutions that cater to the evolving needs of modern enterprises. This project showcases how advanced prompt engineering can significantly improve the quality and relevance of outputs generated by LLMs, thereby driving better decision-making and user engagement in various business applications.The main focus lies in the following key services:
- Automatic Prompt Generation Service: This service streamlines the process of creating effective prompts, reducing the time and expertise required in crafting prompts manually.
- Automatic Evaluation Data Generation Service: Our system automates the generation of diverse test cases, ensuring comprehensive coverage and identifying potential issues. This saves significant time in the Quality Assurance (QA) process.
- Prompt Testing and Ranking Service: We evaluate and rank different prompts based on their effectiveness, helping users achieve the desired outcomes from LLMs. This ensures accurate and contextually relevant responses from chatbots and virtual assistants, improving user engagement and satisfaction.
To set up the project environment, follow these steps:
-
Clone the repository:
git clone https://github.com/Betfsh/Precision-RAG cd your-repo-name -
Create a virtual environment using Python 3.10:
python3.10 -m venv env source env/bin/activate # On Windows use `env\Scripts\activate`
-
Install the required dependencies:
pip install -r requirements.txt `` -
Setup environment variables on
.env:
(create .env file in the Titleroot directory)
#################
# Development env
#################
OPENAI_API_KEY=""
VECTORDB_MODEL="gpt-3.5-turbo"Bethelhem Mebratu
Pull requests are welcome. For major changes, please open an issue first to discuss what you would like to change.
MIT
I would like to thank 10 Academy for the support and resources provided to make this project possible. Special thanks to our mentors and the open-source community.