connect to and initialize pinecone vector database, then read text from a text (.txt) document, chunk it into 2000 tokens with a 200 token overlap before using text-embedding-ada-002 openai api to generate and embed the document in pinecone

# Initialize pinecone database
print('Initializing pinecone vector database')
pc = Pinecone()

# Connect to pinecone vector database
pc.connect()

# load the file
with open('on-writing-well.txt', 'r') as file:
  text = file.read()

# load text into 2000 token (200 token overlap) chunks
chunk = 2000
overlap = 200

# initialize pinecone vector database
pc.init_doc()

# for each chunk of text
for i in range(0, len(text) - chunk, chunk - overlap):
  # get the text
  chunk_text = text[i:i + chunk - overlap]
  # transform text to vector
  vector = text_to_vector(chunk_text)
  # add vector to database
  pc.insert(vector)