train.py

from pathlib import Path

import openai
import pinecone
from llama_index import StorageContext, VectorStoreIndex, download_loader
from llama_index.vector_stores import PineconeVectorStore

from environments import PINECONE_API_KEY, PINECONE_INDEX, OPENAI_API_KEY

openai.api_key = OPENAI_API_KEY

print('Start Loading Data ...')

# PagedCSVReader = download_loader("PagedCSVReader")
# loader = PagedCSVReader(encoding="utf-8")
# documents = loader.load_data(file=Path('train-assets/training-target-simple.csv'))

PDFReader = download_loader("PDFReader")
loader = PDFReader()
documents = loader.load_data(file=Path('./train-assets/faq.pdf'))

pinecone.init(
    api_key=PINECONE_API_KEY,
    environment='gcp-starter'
)
pinecone_index = pinecone.Index(PINECONE_INDEX)
vector_store = PineconeVectorStore(pinecone_index=pinecone_index)
storage_context = StorageContext.from_defaults(vector_store=vector_store)
index = VectorStoreIndex.from_documents(documents, storage_context=storage_context)

print('Done!')