hf.py

from dotenv import load_dotenv
load_dotenv();

from langchain_community.document_loaders import WebBaseLoader
from langchain.text_splitter import RecursiveCharacterTextSplitter


#LOAD AND SPLIT DATA
data = WebBaseLoader("https://rise.mmu.ac.uk/what-is-rise/").load()
text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=150)
docs = text_splitter.split_documents(data)

#CREATE EMBEDDINGS AND PUSH TO VECTORSTORE
from langchain_community.embeddings import HuggingFaceEmbeddings
from langchain_community.vectorstores import FAISS
embeddings = HuggingFaceEmbeddings()
db = FAISS.from_documents(docs, embeddings)
db.save_local("_rise_faq_db");


#DO A QUESTION
from langchain_community.llms import HuggingFaceHub
from langchain.chains import LLMChain
from langchain.prompts import PromptTemplate

question = "Who won the FIFA World Cup in the year 1994? "

template = """Question: {question}

Answer: Let's think step by step."""

prompt = PromptTemplate(template=template, input_variables=["question"])


repo_id = "google/flan-t5-xxl"
llm = HuggingFaceHub(
    repo_id=repo_id, model_kwargs={"temperature": 0.5, "max_length": 64}
)

db = FAISS.load_local("_rise_product_db", embeddings)
from langchain.chains import RetrievalQA

# Use RetrievalQA chain for orchestration
qa = RetrievalQA.from_chain_type(llm=llm, chain_type="stuff", retriever=db.as_retriever())
result = qa.run(question)
#return {"response":result}