I was trying to follow this guid on RAG chatbot from pinecone – https://docs.pinecone.io/guides/get-started/build-a-rag-chatbot

Instead of using OpenAI I was using alternatives like SentenceTransformerEmbeddings for embeddings and LaMini Model instead of mentioned gpt3.5 turbo in the guide

When building the RetrievalQA chain I faced this error

ValidationError: 2 validation errors for LLMChain llm instance of Runnable expected (type=type_error.arbitrary_type; expected_arbitrary_type=Runnable) llm instance of Runnable expected (type=type_error.arbitrary_type; expected_arbitrary_type=Runnable)

This is my current code:
The error occurs on line -:
qa = RetrievalQA.from_chain_type

from langchain.chains import RetrievalQA  
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM 
from transformers import pipeline
import torch

checkpoint = "LaMini-Flan-T5-783M"
print(f"Checkpoint path: {checkpoint}")  # Add this line for debugging
tokenizer = AutoTokenizer.from_pretrained(checkpoint)
base_model = AutoModelForSeq2SeqLM.from_pretrained(
    checkpoint,
    
    torch_dtype=torch.float32
)

qa = RetrievalQA.from_chain_type(
    llm=base_model,
    chain_type="stuff",
    retriever=docsearch.as_retriever()
)

For reference

docsearch = PineconeVectorStore.from_documents(
    documents=pdf_text,
    index_name=index_name,
    embedding=embeddings, 
    namespace=namespace,
    
    
)

I have tried updating langchain but same issue