LangChain RAG project
What is RAG?
RAG is a technique for augmenting LLM knowledge with additional, often private or real-time, data.
Large Language Models (LLMs) have knowledge up to a certain training date and can reason on various topics. To handle private or newer data, they need Retrieval Augmented Generation (RAG) to integrate specific, updated information into their prompts.
So far, RAG applications are the most helpful outcome of the AI revolution.
Tech Stack
LangChain is a framework designed to simplify the creation of applications using large language models.
OpenAI LLM
Chroma vector database
Setup Instructions
Update .env file
Update the .env file with your OPENAI_KEY
Setup a virtual environment
python3 -m venv envLoad virtual environment (Mac)
source env/bin/activateInstall dependencies
pip3 install -r requirements.txtRun WEB RAG to get answers from a URL
python3 web_rag.pyRun TXT RAG to get answers from a TEXT FILE
python3 txt_rag.py0 likes · 9 views · Jan 27, 2024
Contribute to FreakWolf/LangChain-RAG development by creating an account on GitHub.
