app.py

from langchain.embeddings.openai import OpenAIEmbeddings
from langchain.vectorstores import Chroma
from langchain.text_splitter import CharacterTextSplitter
from langchain.chains.question_answering import load_qa_chain
from langchain.llms import OpenAI
import os
from glob import glob
import shutil


files = glob("./shakespeare/**/*.html")

os.mkdir('./data')
destination_folder = './data/'

for html_file in files:
  shutil.move(html_file, destination_folder + html_file.split("/")[-1])



from langchain.document_loaders import BSHTMLLoader, DirectoryLoader

bshtml_dir_loader = DirectoryLoader('./data/', loader_cls=BSHTMLLoader)

data = bshtml_dir_loader.load()


from langchain.text_splitter import RecursiveCharacterTextSplitter

text_splitter = RecursiveCharacterTextSplitter(
    chunk_size = 1000,
    chunk_overlap  = 20,
    length_function = len,
)

documents = text_splitter.split_documents(data)


from langchain.embeddings.openai import OpenAIEmbeddings

embeddings = OpenAIEmbeddings()



from langchain.vectorstores import Chroma

persist_directory = "vector_db"

vectordb = Chroma.from_documents(documents=documents, embedding=embeddings, persist_directory=persist_directory)


vectordb.persist()
vectordb = None

vectordb = Chroma(persist_directory=persist_directory, embedding_function=embeddings)

from langchain.chat_models import ChatOpenAI

llm = ChatOpenAI(temperature=0, model="gpt-4")

doc_retriever = vectordb.as_retriever()

from langchain.chains import RetrievalQA

shakespeare_qa = RetrievalQA.from_chain_type(llm=llm, chain_type="stuff", retriever=doc_retriever)



#chain = load_qa_chain(OpenAI(temperature=0), chain_type="stuff")

def make_inference(query):
    docs = shakespeare_qa.get_relevant_documents(query)
    return(chain.run(input_documents=docs, question=query))

if __name__ == "__main__":
    # make a gradio interface
    import gradio as gr

    gr.Interface(
        make_inference,
        [
            gr.inputs.Textbox(lines=2, label="Query"),
        ],
        gr.outputs.Textbox(label="Response"),
        title="🗣️TalkToMyDoc📄",
        description="🗣️TalkToMyDoc📄 is a tool that allows you to ask questions about a document. In this case - Hitch Hitchhiker's Guide to the Galaxy.",
    ).launch()