feat: Pinecone Vector Database

[FinnConnor]

Added Pinecone vector database support. To setup (also in readme) set VECTOR_DB_TYPE=pinecone and PINECONE_API_KEY=<api key>

Tested with Pinecone, openai text-embedding-3-small

1. Embedding multiple text files
2. Getting all ids for multiple files
3. Deleting documents, ensuring not in database
4. Querying one file, ensuring relevant results to query
5. Getting documents according to id
6. Querying multiple documents, ensuring all documents are queried
7. Change back to Pgvector , to ensure still working

[FinnConnor]

IDs per vector assigned as (file_id)_# . Using a prefix file_id with numbering 0,1,2,.... Should not affect naming file_id able to include '_' in file_id such that read my_file_0