from PyPDF2 import PdfReader
from langchain.embeddings.openai import OpenAIEmbeddings
from langchain.text_splitter import CharacterTextSplitter
from langchain.vectorstores import FAISS
import os
OPENAI_API_KEY="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"
os.environ["OPENAI_API_KEY"] = OPENAI_API_KEY
pdfreader = PdfReader('csp.pdf')
from typing_extensions import Concatenate
# read text from pdf
raw_text = ''
for i, page in enumerate(pdfreader.pages):
    content = page.extract_text()
    if content:
        raw_text += content
raw_text
text_splitter = CharacterTextSplitter(
    separator = "\n",
    chunk_size = 800,
    chunk_overlap  = 200,
    length_function = len,
)
texts = text_splitter.split_text(raw_text)
len(texts)
embeddings = OpenAIEmbeddings()
document_search = FAISS.from_texts(texts, embeddings)
document_search
from langchain.chains.question_answering import load_qa_chain
from langchain.llms import OpenAI
chain = load_qa_chain(OpenAI(), chain_type="stuff")
import gradio as gr

# Define function to process user query
def process_query(query):
    # Perform similarity search to retrieve relevant documents
    docs = document_search.similarity_search(query)
    
    # Run question-answering process with retrieved documents and user query
    response = chain.run(input_documents=docs, question=query)
    
    # Return the response
    return response

# Define Gradio interface
iface = gr.Interface(
    fn=process_query,
    inputs="text",
    outputs="text",
    title="Woxsenite",
    description="Hi! How can I help you?"
)

# Launch the interface
iface.launch()