app.py

from dotenv import load_dotenv
import os
from PyPDF2 import PdfReader
import docx
from langchain.text_splitter import CharacterTextSplitter
from langchain.embeddings.openai import OpenAIEmbeddings
from langchain.vectorstores import FAISS
from langchain.chains.question_answering import load_qa_chain
from langchain_openai import OpenAI
from langchain.callbacks import get_openai_callback
import gradio as gr
from aiohttp import web

load_dotenv()

os.environ["OPENAI_API_KEY"] = "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"


def read_txt(file_path):
    with open(file_path, "r") as file:
        text = file.read()
    return text

def read_documents_from_directory(directory):
    combined_text = ""
    for filename in os.listdir(directory):
        file_path = os.path.join(directory, filename)
        if filename.endswith(".pdf"):
            combined_text += read_pdf(file_path)
        elif filename.endswith(".docx"):
            combined_text += read_word(file_path)
        elif filename.endswith(".txt"):
            combined_text += read_txt(file_path)
    return combined_text

text_file_path = '/content/lawsofpower.txt'
user_query = read_txt(text_file_path)

char_text_splitter = CharacterTextSplitter(separator="\n", chunk_size=1000,
                                           chunk_overlap=200, length_function=len)

text_chunks = char_text_splitter.split_text(user_query)

embeddings = OpenAIEmbeddings()
docsearch = FAISS.from_texts(text_chunks, embeddings)

llm = OpenAI()
chain = load_qa_chain(llm, chain_type="stuff")

async def chatbot_interface(request):
    data = await request.post()
    input_text = data.get("input_text", "")
    
    docs = docsearch.similarity_search(input_text)
    response = chain.run(input_documents=docs, question=input_text)
    
    return web.Response(text=response)

app = web.Application()
app.router.add_post('/chatbot', chatbot_interface)

if __name__ == "__main__":
    web.run_app(app, port=os.getenv("PORT", 8080))