app.py

import os
from langchain.chains import RetrievalQA
from langchain.llms import OpenAI
from langchain.document_loaders import PyPDFLoader
from langchain.indexes import VectorstoreIndexCreator
from langchain.text_splitter import CharacterTextSplitter
from langchain.embeddings import OpenAIEmbeddings
from langchain.vectorstores import Chroma
import gradio as gr
import tempfile


def qa(file, openaikey, query, chain_type, k):
    os.environ["OPENAI_API_KEY"] = openaikey

    # load document
    loader = PyPDFLoader(file.name)
    documents = loader.load()
    # split the documents into chunks
    text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
    texts = text_splitter.split_documents(documents)
    # select which embeddings we want to use
    embeddings = OpenAIEmbeddings()
    # create the vectorestore to use as the index
    db = Chroma.from_documents(texts, embeddings)
    # expose this index in a retriever interface
    retriever = db.as_retriever(
        search_type="similarity", search_kwargs={"k": k})
    # create a chain to answer questions
    qa = RetrievalQA.from_chain_type(
        llm=OpenAI(), chain_type=chain_type, retriever=retriever, return_source_documents=True)
    result = qa({"query": query})
    print(result['result'])
    return result["result"]


iface = gr.Interface(
    fn=qa, 
    inputs=[
        gr.inputs.File(label="Upload PDF"),
        gr.inputs.Textbox(label="OpenAI API Key"),
        gr.inputs.Textbox(label="Your question"),
        gr.inputs.Dropdown(choices=['stuff', 'map_reduce', "refine", "map_rerank"], label="Chain type"),
        gr.inputs.Slider(minimum=1, maximum=5, default=2, label="Number of relevant chunks"),
    ], 
    outputs="text",
    title="Question Answering with your PDF file",
    description="Upload a PDF file, enter OpenAI API key, type a question and get your answer."
)

iface.launch()