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
import gradio as gr
import git

git.Repo.clone_from("https://github.com/TheMITTech/shakespeare", "shakespeare")
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 chromadb.segment.impl.vector.local_hnsw import HnswParams
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)

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."
    ),
]

agent = initialize_agent(tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True)


def make_inference(query):
    return(agent.run(query))

if __name__ == "__main__":
    gr.Interface(
        make_inference,
        [
            gr.inputs.Textbox(lines=2, label="Query"),
        ],
        gr.outputs.Textbox(label="Response"),
        title="Shakespeare",
        description="Shakespeare is a tool that allows you to ask questions about Shakespeare.",
    ).launch()