src/pipelines/completePipeline.py

from src.components.loaders.websiteCrawler import WebsiteCrawler
from src.components.loaders.youtubeLoader import YoutubeTranscriptLoader
from src.components.loaders.pdfLoader import PdfLoader
from src.components.rag.RAG import Chain
from dotenv import load_dotenv

load_dotenv("secrets.env")

class Pipeline:
    def __init__(self):
        self.pdfLoader = PdfLoader()
        self.webCrawler = WebsiteCrawler()
        self.youtubeLoader = YoutubeTranscriptLoader()
        self.ragChain = Chain()
        
    def plainText(self, text: str):
        chain = self.ragChain.returnChain(text = text)
        return chain

    def searchablePdf(self, path: str):
        extractedText = self.pdfLoader.searchablePdf(pdfPath = path)
        chain = self.ragChain.returnChain(text = extractedText)
        return chain

    def scannablePdf(self, path: str):
        extractedText = self.pdfLoader.scannablePdf(pdfPath = path)
        chain = self.ragChain.returnChain(text = extractedText)
        return chain
    
    def webCrawl(self, urls: list[str]):
        extractedText = self.webCrawler.extractTextFromUrlList(urls = urls)
        chain = self.ragChain.returnChain(text = extractedText)
        return chain     
    
    def youtubeLinks(self, urls: list[str]):
        extractedText = self.youtubeLoader.getTranscripts(urls = urls)
        print(extractedText)
        chain = self.ragChain.returnChain(text = extractedText)
        return chain