indexes.py

import tempfile
import os
from langchain.document_loaders import PyPDFLoader
from langchain.embeddings.openai import OpenAIEmbeddings
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.document_loaders import DirectoryLoader, TextLoader
from langchain.vectorstores import Pinecone
from PyPDF2 import PdfReader
import pinecone

from config import config

def create_indexes(file: tempfile, pinecone_api_key: str, pinecone_environment: str, pinecone_index_name: str, openai_api_key: str) -> str:
    try:
        file_path = file.name
        reader = PyPDFLoader(file_path)
        documents = reader.load_and_split()
        embeddings = OpenAIEmbeddings(
            openai_api_key=openai_api_key
        )
        pinecone.init(
            api_key=pinecone_api_key,
            environment=pinecone_environment
        )
        indexes_list = pinecone.list_indexes()
        if pinecone_index_name not in indexes_list:
            pinecone.create_index(
                name=pinecone_index_name,
                dimension=1536
            )
        Pinecone.from_documents(
            documents=documents,
            embedding=embeddings,
            index_name=pinecone_index_name
        )
        return 'Document uploaded and index created successfully. You can chat now.'
    except Exception as e:
        return e

def clear_indexes(pinecone_api_key: str, pinecone_environment: str, pinecone_index_name: str) -> str:
    try:
        pinecone.init(
            api_key=pinecone_api_key,
            environment=pinecone_environment
        )
        indexes_list = pinecone.list_indexes()
        if pinecone_index_name in indexes_list:
            pinecone.delete_index(name=pinecone_index_name)
        return 'Indexes cleared.', None
    except Exception as e:
        return e, None