Logan M 8260 this is unrelated to the

Definitely! Although (in my opinion) open source models are still catching up to OpenAI, especially for more complicated tasks like predicting JSON and other more complex queries

Details on local Huggingface LLMs:
https://gpt-index.readthedocs.io/en/latest/how_to/customization/custom_llms.html#example-using-a-huggingface-llm

Implement any LLM:
https://gpt-index.readthedocs.io/en/latest/how_to/customization/custom_llms.html#example-using-a-custom-llm-model-advanced

Local embeddings from huggingface:
https://gpt-index.readthedocs.io/en/latest/how_to/customization/embeddings.html#custom-embeddings

You can also use any LLM / embedding integration from langchain, assuming you wrap it with our wrapper class (LLMPredictor(llm=llm) or LangchainEmbedding())