Script to create the vector database

[jjiang85]

This is a PR for #8 with a script that (theoretically) creates a Chroma vector database using LangChain and HuggingFace embeddings. It's not yet complete (and maybe will never be) but the idea is that the script will:

1. Read in data from the terms to cui and cui to definitions dictionaries and put them into LangChain Documents
2. Create embeddings of those definitions
3. Store those embeddings in a Chroma vector db (possibly to disk for later load) for later retrieval
   It's not complete and runs into issues when attempting to run on Windows. I've tested each piece of the code in Colab and it seems to work, there's just some local environment issues.

Python version >= 3.11 is required for langchain and its associated libraries
You'll want to run pip --upgrade langchain langchain_chroma langchain_community langchain_core sentence_transformers before running the script