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

import subprocess
subprocess.run(["git", "clone", "https://github.com/TheMITTech/shakespeare"], check=True)

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


import shutil
import os
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
from bs4 import BeautifulSoup
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)

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()

chain = load_qa_chain(OpenAI(temperature=0), chain_type="stuff")
from langchain.chains import RetrievalQA
shakespeare_qa = RetrievalQA.from_chain_type(llm=llm, chain_type="stuff", retriever=doc_retriever)

from langchain.utilities import SerpAPIWrapper
search = SerpAPIWrapper()

from langchain.agents import initialize_agent, Tool
from langchain.agents import AgentType
from langchain.tools import BaseTool
from langchain.llms import OpenAI
from langchain import LLMMathChain, SerpAPIWrapper

tools = [
    Tool(
        name = "Shakespeare QA System",
        func=shakespeare_qa.run,
        description="useful for when you need to answer questions about Shakespeare's works. Input should be a fully formed question."
    ),
    Tool(
        name = "SERP API Search",
        func=search.run,
        description="useful for when you need to answer questions about ruff (a python linter). Input should be a fully formed question."
    ),
]

from langchain.memory import ConversationBufferMemory, ReadOnlySharedMemory
memory = ConversationBufferMemory(memory_key="chat_history")
readonlymemory = ReadOnlySharedMemory(memory=memory)

from langchain.agents import ZeroShotAgent, Tool, AgentExecutor

prefix = """Have a conversation with a human, answering the following questions as best you can. You have access to the following tools:"""
suffix = """Begin!"

{chat_history}
Question: {input}
{agent_scratchpad}"""

prompt = ZeroShotAgent.create_prompt(
    tools, 
    prefix=prefix, 
    suffix=suffix, 
    input_variables=["input", "chat_history", "agent_scratchpad"]
)


from langchain import OpenAI, LLMChain, PromptTemplate
llm_chain = LLMChain(llm=llm, prompt=prompt)
agent = ZeroShotAgent(llm_chain=llm_chain, tools=tools, verbose=True)
agent_chain = AgentExecutor.from_agent_and_tools(agent=agent, tools=tools, verbose=True, memory=memory)

def make_inference(query):
    return(agent_chain.run(input=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="🗣️QuestionMyDoc-OpenAI📄",
        description="🗣️QuestionMyDoc-OpenAI📄 is a tool that allows you to ask questions about a document. In this case - Shakespears.",
    ).launch()