utils/rag_pipeline.py

from models.embedder import Embedder 
from documents.chunker import DocumentChunker 
 
class RAGPipeline: 
    def __init__(self): 
        self.embedder = Embedder() 
        self.chunker = DocumentChunker() 
 
    def add_documents(self, text): 
        chunks = self.chunker.chunk_text(text) 
        embeddings = self.embedder.embed(chunks) 
        for i, (chunk, embedding) in enumerate(zip(chunks, embeddings)): 
            self.embedder.collection.add( 
                documents=[chunk], 
                embeddings=[embedding], 
                ids=[str(i)] 
            )