Preparation

Make sure Llama is running as a server: in the terminal, type: Ollama serve
Use existing embedding models: "mxbai-embed-large" from OllamaEmbeddings (Note: couldn't get BedrockEmbeddings work from AWS)
Make sure running scripts in the correct virtual environment

Steps

To reset/add new PDF files, type in terminal: python populate_database.py --reset
To run the model, type in terminal: python query_data.py "What is positive thought disorder?"

Name		Name	Last commit message	Last commit date
Latest commit History 6 Commits
data		data
.gitignore		.gitignore
README.md		README.md
populate_database.py		populate_database.py
query_data.py		query_data.py
requirements.txt		requirements.txt
test_rag.py		test_rag.py