clean rag training

Notebooks for GPT evaluation

Add second RAG notebook

Add a rag helper notebook

Add a pre rag prompt

Updated compare_result function to allow passing the cursor, also re-ran test_pretrained and test_rag with updated loss function

Tweaked compare_result to work with proper directory, updated rag python notebook prompt and vector stores to increase accuracy

Updating compare result function in src directory, fixing small issues in test_rag prompt, adding test_rag notebook

Fix bug on function evaluation

Add a source folder