src/rag_pipeline.py

from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.embeddings import HuggingFaceEmbeddings
from langchain.vectorstores import FAISS

def build_rag_pipeline(docs, embedding_model):
    splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50)
    chunks = splitter.split_documents(docs)
    embeddings = HuggingFaceEmbeddings(model_name=embedding_model)
    db = FAISS.from_documents(chunks, embeddings)
    return db.as_retriever()

def get_relevant_docs(retriever, query, k=4):
    return retriever.get_relevant_documents(query)[:k]